system

Abstract

We provide the system. [Solution] Means for collecting learner activity data, A means for analyzing the aforementioned activity data to generate an individualized learning plan suitable for the learner, A means of delivering learning content based on the generated individual learning plan, A means of collecting learner feedback and dynamically adjusting the learning plan, A means of visualizing and providing learning progress to learners, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern educational settings, there is a problem that it is difficult to achieve individual optimization according to the learning ability and interests of each learner. Also, due to an overabundance of information, it is difficult to select appropriate teaching materials, and it is difficult for learners to grasp their own progress, leading to problems such as a decline in learning motivation and an expansion of the learning gap. The present invention aims to solve these problems and provide optimal education for all learners.

Means for Solving the Problems

[0005] This invention provides a system for collecting and analyzing learner activity data and generating individualized learning plans. Specifically, it includes means for collecting data such as learners' answer history, viewing patterns, and interests, and generates individualized learning plans based on this data. Furthermore, it delivers learning content based on the learning plan, collects feedback from learners, and dynamically adjusts the learning plan to optimize it in real time. In addition, it provides learners with means for visually representing their learning progress, enabling them to understand their own progress. In this way, by providing learners with an optimized learning experience, it is possible to improve their motivation to learn and reduce learning disparities.

[0006] "Activity data" refers to information related to the actions and behaviors that learners perform within the educational platform, and specifically includes answer history, viewing patterns, and interests.

[0007] An "individualized learning plan" is a customized learning plan and schedule that takes into account each learner's abilities and interests, and learning content is provided based on that plan.

[0008] "Generating means" refers to a method and apparatus for automatically creating a learning plan optimized for the learner based on collected activity data.

[0009] "Means of distribution" refers to the mechanism and method for transmitting learning content to the learner's device according to the generated individual learning plan.

[0010] "Feedback" refers to the process of providing learners with information such as their impressions, answers, and experiences gained through learning activities.

[0011] "Dynamic adjustment methods" refer to methods of adaptively changing learning plans and provided content in response to feedback from learners.

[0012] "Learning progress" refers to the results and level of proficiency achieved by learners through learning activities, and is meant to be visually represented to allow for objective understanding.

[0013] "Methods of visualization" refer to methods of converting learning progress information into visual formats such as graphs and charts, and providing them to learners in an easy-to-understand manner. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

[0019] In the following embodiments, a numbered 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.

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention is a system for providing optimized education tailored to the characteristics of learners. The system is primarily built around three components: a server, a terminal, and a user, each playing the following roles.

[0036] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests. By analyzing this data, the server evaluates the learner's aptitude and proficiency. Generative AI models are used for the analysis, enabling advanced data analysis.

[0037] Based on the analysis results, the server automatically generates an optimized, personalized learning plan for each user. This plan includes selecting content suitable for the learner, adjusting the difficulty level according to their progress, and even recommending learning paths. For example, a learner aiming to improve their English skills will be provided with a curriculum that balances listening and speaking.

[0038] The generated individual learning plan is delivered to the device by the server. The device then presents interactive learning content to the user according to this learning plan. Through their device, users engage in various learning activities, such as watching videos, answering questions, and practicing simulations. This makes learning more proactive and effective.

[0039] The device then collects user feedback and sends it to the server. This feedback includes the user's answers and reactions to the learning content. The server uses this feedback to dynamically adjust the learning plan using a generative AI model. For example, if a large number of incorrect answers occur on a particular topic, additional materials to reinforce that topic will be incorporated into the plan.

[0040] As a final step, the server visualizes the user's learning progress. This visualization uses graphs and charts to show the progress, allowing the user to check their current level of achievement. This makes it easy for users to understand the effectiveness of their learning, improve their motivation, and identify areas for improvement.

[0041] In this way, the present invention provides learners with an individually optimized learning experience, realizing a system that improves learning efficiency and the quality of education.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user logs into the learning portal using an iPad®. Upon login, a request is sent from the device to the server to access the user's past learning data.

[0045] Step 2:

[0046] The server retrieves the user's past learning activity data from the database. This data includes answer history, viewing history, and tag information that reflects the user's interests.

[0047] Step 3:

[0048] The server inputs activity data into a generating AI model and begins analyzing the data. The model then analyzes the user's strengths, weaknesses, and learning tendencies in detail.

[0049] Step 4:

[0050] The generating AI model creates an optimal, personalized learning plan for the user based on the analysis results. This plan includes recommended learning materials, learning order, and learning goals.

[0051] Step 5:

[0052] The server sends the generated individual learning plan to the device. The device then prepares to provide the user with appropriate learning content according to the plan.

[0053] Step 6:

[0054] Users learn using the provided learning content. This includes watching videos, practicing problems, and experiencing simulations.

[0055] Step 7:

[0056] The device continuously records the user's learning activity data, including the user's answer results, viewing time, and operation history.

[0057] Step 8:

[0058] The device sends the recorded feedback data to the server. This feedback is important data that indicates the level of understanding and response to the learned material.

[0059] Step 9:

[0060] The server analyzes the feedback received and dynamically adjusts the learning plan. This includes revising the plan and recommending new content.

[0061] Step 10:

[0062] The server sends the adjusted learning plan back to the device. Based on the updated plan, the device presents the learner with the next learning step.

[0063] Step 11:

[0064] The server ultimately visualizes the user's learning progress using graphs and charts and displays them on the device. Users can check their own progress and feel the effectiveness of their learning.

[0065] (Example 1)

[0066] 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."

[0067] Traditional teaching methods make it difficult to provide optimal education tailored to the individual characteristics and proficiency levels of each learner. This results in learners being unable to learn effectively at their own pace, hindering improvements in the quality of education. Furthermore, insufficient tracking of learning progress makes it difficult for learners to perceive their own growth, which is another challenge.

[0068] 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.

[0069] In this invention, the server includes means for collecting learner activity information, means for using a generative artificial intelligence model to analyze the activity information and generate an individualized education plan suitable for the learner, and means for delivering educational content based on the generated individualized education plan. This makes it possible to provide effective individualized education tailored to the characteristics of each learner and to accurately grasp their learning progress.

[0070] "Learner activity information" refers to data generated when learners engage in educational activities, including answer history, viewing patterns, interests, and other relevant information.

[0071] A "generative artificial intelligence model" is a model that utilizes advanced artificial intelligence technology to analyze learner activity information and generate appropriate educational plans.

[0072] An "individualized education plan" is a plan designed to provide educational content optimized for each learner's individual characteristics and proficiency level.

[0073] "Educational content" refers to the materials and teaching methods that learners actually use to study, and includes information such as videos, textbooks, and practice problems.

[0074] A "server" is a computer system that plays a central role in a learning system, managing data collection, analysis, creation of educational plans, and distribution of educational content.

[0075] "Visual presentation" refers to a method of displaying information using images and diagrams to effectively communicate progress and results to learners.

[0076] This invention is a system that provides personalized education optimized for each learner. The system mainly consists of three elements: a server, a terminal, and a user, each playing a specific role.

[0077] The server first collects learner activity information. This information includes data such as the learner's answer history, viewing patterns, and interests. To collect this data, the server has functions to manage user behavior on the online learning platform.

[0078] The collected data is analyzed on the server using a generated artificial intelligence model. A machine learning algorithm is a possible AI model used to evaluate the learner's proficiency and interests. During program execution, prompts such as "Identify the user's weak areas based on past answer history" can be used.

[0079] Based on the analysis results, the server generates an individualized learning plan. This plan is tailored to the learner's characteristics and includes details such as, "This user needs intermediate-level listening skills, so we will focus on delivering listening materials next week."

[0080] The generated educational plan is delivered from the server to the terminal. The terminal has the functionality to interactively present various educational content to the user, such as videos, text, and practice problems. This allows the user to learn at their own pace.

[0081] The device also collects feedback information on the user's answers and activities. Sending this information to the server allows for dynamic adjustments to the educational plan. For example, a prompt such as, "Provide additional practice exercises on topics the user is struggling with," can be used to determine specific strategies.

[0082] Furthermore, the server visually presents and provides the user with learning progress. At this stage, the data is visualized as graphs and charts, designed so that the user can understand their progress at a glance.

[0083] In this way, the system can provide learners with an individually optimized learning experience, thereby improving the quality of education.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server collects user activity information. It receives, as input, data such as user responses, viewing history, and interest-based data submitted via the user's device. Specifically, the server automatically logs this data and continuously updates it. As output, the collected activity information is used for analysis in the next step.

[0087] Step 2:

[0088] The server uses a generative artificial intelligence model to analyze the collected activity information. Data such as answer history and viewing patterns are supplied to the AI ​​model as input. Specifically, the prompt "Identify the user's weak areas based on past answer history" is input to the AI ​​model, and the user's learning tendencies are analyzed. As output, evaluation data regarding the user's aptitude and proficiency level is generated.

[0089] Step 3:

[0090] The server generates individualized learning plans based on the analyzed data. The evaluation data obtained in the previous step is used as input. Specifically, it utilizes a generative AI model to create plans such as, "For this user, please select learning materials to focus on next week to improve their listening skills." The output is an optimized individualized learning plan for each learner.

[0091] Step 4:

[0092] The server delivers the generated individualized learning plan to the terminal. The generated learning plan is provided as input. Specifically, the terminal prepares to interactively display learning materials (videos and practice problems) based on the learning plan. As output, the appropriate educational content is delivered to the user's terminal.

[0093] Step 5:

[0094] The device collects user feedback. It receives user responses and reactions to learning materials as input. Specifically, the device records correct / incorrect answer data and survey results after problem completion. The feedback data is sent to the server as output.

[0095] Step 6:

[0096] The server analyzes feedback from the terminal and dynamically adjusts the educational plan. Feedback data is supplied to the AI ​​model as input. Specifically, the model uses adjustment prompts such as, "Please provide additional practice exercises on topics the user is struggling with." An updated individualized educational plan is created as output.

[0097] Step 7:

[0098] The server visualizes and provides learning progress. As input, it aggregates and uses user learning result data. Specifically, it creates graphs and charts showing progress and displays them on the user's device in an easy-to-understand format. As output, it provides visual information to help the user understand their learning achievements and challenges.

[0099] (Application Example 1)

[0100] 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."

[0101] There is a need to efficiently provide educational content optimized based on the individual characteristics of learners and to realize a learning experience that matches the learner's level of understanding and progress. However, conventional systems have the challenge of not being able to quickly select appropriate content and dynamically adjust plans, making it difficult to provide an optimal educational experience for each learner.

[0102] 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.

[0103] In this invention, the server includes a device for collecting learner activity information, a device for analyzing the activity information to generate an individualized learning plan suitable for the learner, and a device for delivering educational content based on the generated individualized learning plan. This makes it possible to effectively provide individually optimized educational content according to the learner's characteristics and progress.

[0104] A "learner" refers to a user whose purpose is to acquire educational content and knowledge.

[0105] "Activity information" refers to a collection of information related to learning activities, including data such as learners' answer history, viewing behavior, and areas of interest.

[0106] An "individualized learning plan" is a plan of educational activities that is optimized and provided individually according to the learner's characteristics and progress.

[0107] "Educational content" refers to information that includes various learning resources provided to learners, such as textbooks, practice problems, and audiovisual content.

[0108] "Opinions" refer to feedback information that shows evaluations and reactions regarding learners' learning experiences.

[0109] "Learning progress" refers to the level of progress a learner has made through educational activities.

[0110] An "AI model" is a model that represents artificial intelligence technology used for data analysis and optimizing learning plans.

[0111] "Figures and tables" are graphical display formats used to visually represent data and information.

[0112] This invention includes a system that comprises a series of processes for collecting and analyzing learner activity information, generating individualized learning plans, and delivering educational content, in order to provide learners with an optimized educational experience. It is primarily composed of three components: a server, a terminal, and a user.

[0113] The server plays a crucial role in efficiently collecting learner activity information. This information includes learners' response history, viewing behavior, and areas of interest. This information is stored on the server and used for analysis. The server utilizes a generative AI model to analyze the activity information in an advanced manner, assessing learners' proficiency and interests, and automatically generating personalized learning plans. In this analysis process, the AI ​​model plays a central role in understanding data trends.

[0114] The generated individualized learning plan is delivered to the device. The device then presents the learner with interactive educational content based on this plan. Specifically, this includes playing video content, presenting practice problems, and providing simulations. This allows users to learn at their own pace and independently.

[0115] User feedback is sent to the server via the device. By receiving this feedback, the server dynamically adjusts the learning plan in real time. This process improves the quality of the educational experience, enabling a rapid response to learner needs. Learning progress is visualized using charts and graphs, allowing learners to intuitively understand their own progress.

[0116] For example, if a learner wishes to learn the basics of chemistry, the server can provide an optimized introductory chemistry course based on activity information it has collected. The content provided is automatically adjusted according to the learner's interests and level of understanding. For instance, based on a prompt such as, "Please provide a video that clearly explains the basics of chemistry," suitable materials will be suggested.

[0117] In this way, the interaction between the server, terminal, and user makes it possible to provide an optimized educational experience for each individual learner.

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server collects learner activity information. Its inputs include learner response history, viewing behavior, and interest data. Its output is stored in a centrally managed database. Specifically, it uses an API to periodically retrieve data from the device, organize it, and store it.

[0121] Step 2:

[0122] The server analyzes activity information using a generative AI model. The activity data collected in Step 1 is used as input. The analysis evaluates the learner's proficiency level and areas of interest. As output, an individualized learning plan is generated for each learner. Specifically, the AI ​​model is given analysis instructions using prompts, and the basic structure of the learning plan is created based on the results.

[0123] Step 3:

[0124] The generated individual learning plan is delivered from the server to the terminal. The learning plan generated in step 2 is used as input. The educational content based on this plan is displayed on the terminal as output. Specifically, the learning plan data is sent to the terminal using network communication, and the terminal interprets it and displays it in the user interface.

[0125] Step 4:

[0126] The device presents interactive educational content to the user. It uses learning plan data delivered from a server as input. The output is educational content displayed on the user's device. Specific actions include controlling video playback, presenting interactive exercises, and providing a feedback screen.

[0127] Step 5:

[0128] Users provide feedback on their learning through a device. Input includes their answers and reactions to their learning experience. Output is the transmission of this feedback information to the server. Specific actions include filling out survey forms and selecting answers.

[0129] Step 6:

[0130] The server dynamically adjusts the learning plan based on the feedback information. It uses the feedback data received in step 5 as input. A new learning plan is generated as output. Specifically, it analyzes the feedback and uses an AI model to adjust the learning plan. For example, it might incorporate additional practice questions for topics where the user frequently makes mistakes.

[0131] Step 7:

[0132] The server generates materials that visualize the learner's learning progress. It takes learning progress data as input and creates progress reports for learners in chart and graph format as output. Specifically, it uses data visualization tools to format the data so that learners can check their own progress.

[0133] 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.

[0134] This invention is a system for providing optimized education tailored to the characteristics and emotional state of learners. The system consists of four components: a server, a terminal, a user, and an emotion engine, each playing the following roles.

[0135] The server first collects learner activity data. This data includes the user's answer history, viewing patterns, interests, etc., and records the learner's behavior and progress in detail. The collected data is then analyzed by a generative AI model to generate a personalized learning plan suitable for the learner.

[0136] In addition, this system includes an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state through facial recognition and voice analysis. Furthermore, it also uses data from biosensors for emotion recognition, achieving highly accurate emotion analysis. The server incorporates this emotion data into the analysis results and generates an individualized learning plan that takes emotions into account. For example, if the emotion engine detects that the learner is lacking concentration, the server adjusts the learning plan, prioritizing the display of content that will interest the user or presenting tasks that can be completed in a short time.

[0137] The generated learning plan is delivered to the device and provided to the user. Based on the individual learning plan, the device provides the user with video viewing, problem solving, and interactive simulation experiences. During learning, the device continuously records the user's feedback and emotional changes and sends them to the server.

[0138] The server dynamically adjusts the learning plan based on the feedback and sentiment data it receives. For example, if a user's sentiment towards a particular piece of content is positive, it might add related learning materials for that content. Conversely, if a user is frustrated with a particular issue, it might provide supplementary information or explanations from different angles to delve deeper into that issue.

[0139] Ultimately, the server visualizes the user's learning progress and displays it on the terminal. This progress display uses graphs and charts, allowing users to see their own achievements and changes in their emotions. Through this feature, learners can objectively understand their learning status, which motivates them to continue learning.

[0140] Based on the above, the present invention provides a system that offers a learning experience individually optimized from both the behavioral and emotional perspectives of learners, aiming to realize efficient and effective education.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The user logs in and begins learning. When the user accesses the learning portal on their iPad, the device sends the user's identification information to the server. This is to associate past learning data with the current learning content.

[0144] Step 2:

[0145] The server retrieves the user's past activity data from the database based on the user's identification information sent from the terminal. This data includes answer history, viewing patterns, and existing learning tendencies.

[0146] Step 3:

[0147] The server analyzes past activity data and generates a personalized learning plan based on the user's learning needs. This analysis uses a generative AI model to identify the user's strengths and areas that need improvement.

[0148] Step 4:

[0149] The emotion engine is activated and captures the user's facial expressions and voice through the device. Furthermore, data such as pulse rate and skin reactions are acquired from wearable biosensors. This data is used to evaluate the user's emotional state.

[0150] Step 5:

[0151] The emotion engine analyzes the collected emotional data to identify the user's current emotional state. For example, if a user is feeling stressed, that information is sent to the server.

[0152] Step 6:

[0153] The server combines analysis results with emotional data to adapt individual learning plans to the user's emotions. The order of content and the materials presented are adjusted according to the user's emotional state.

[0154] Step 7:

[0155] A customized learning plan is sent to the device and displayed to the user. The user receives learning content such as videos, interactive exercises, and simulations.

[0156] Step 8:

[0157] The device continuously records the user's reactions and emotional changes during learning. This includes, for example, changes in facial expressions and answer results during the learning process.

[0158] Step 9:

[0159] The device sends feedback and sentiment data to the server. The server receives this data and analyzes it to incorporate it into the next learning plan.

[0160] Step 10:

[0161] The server visualizes learning progress data and sends visually represented graphs and charts to the user's device. Users can then check their learning achievements and emotional changes on a dashboard.

[0162] These steps enable a system where servers, terminals, users, and the emotion engine work together to provide a learning experience optimized for the learner.

[0163] (Example 2)

[0164] 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".

[0165] Traditional education systems often fail to adequately analyze learners' progress and activity data, making it difficult to provide individually optimized learning experiences. Furthermore, the lack of dynamic adjustments to learning plans that take learners' emotions into account can lead to decreased learning efficiency and motivation.

[0166] 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.

[0167] In this invention, the server includes means for collecting learner activity data, means for analyzing the data with a generative AI model to generate an individualized learning plan, and means for evaluating emotional states using facial recognition, voice analysis, and biosensors. This makes it possible to generate and provide an optimized individualized learning plan based on the individual characteristics and emotional states of each learner.

[0168] A "learner" refers to an individual who engages in learning activities using educational systems and materials.

[0169] "Activity data" refers to information about learners' behavior and performance, such as their answer history, viewing patterns, and interests.

[0170] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and generates a learning plan suitable for the learner.

[0171] An "individualized learning plan" refers to a learning curriculum and content optimized according to the learner's characteristics and progress.

[0172] "Emotional state" refers to the psychological and emotional state of a learner, assessed using information from their facial expressions, voice, and biosensors.

[0173] "Feedback" refers to reactions and comments on the learning experience provided by learners, and is used to improve the system.

[0174] "Learning progress" refers to information that indicates the degree to which a learner has progressed in learning and their level of understanding.

[0175] "Visual representation" refers to techniques that use graphs, charts, and other visual aids to present information in a way that can be understood by looking at it.

[0176] This invention is a system that provides education optimized according to the learner's characteristics and emotional state. The system mainly consists of four components: a server, a terminal, a user, and an emotion engine.

[0177] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests, allowing for a detailed understanding of the learner's behavior and progress. The collected data is analyzed by a generative AI model, which generates a personalized learning plan tailored to each learner. This AI model learns from large amounts of data and proposes learning plans quickly and accurately.

[0178] The emotion engine applies facial recognition and voice analysis technologies to assess the user's emotional state. Furthermore, it incorporates data from biosensors to enable more accurate emotion analysis. This allows the server to generate personalized learning plans that take the learner's emotions into account. For example, if a learner is lacking focus, the server adjusts the learning plan, providing content that engages the user and tasks that can be completed in a short amount of time.

[0179] The generated learning plan is provided to the user via the device. Based on the individual learning plan, the device provides the user with video viewing, problem-solving, and interactive simulation experiences. During learning, the device collects the user's reactions and feedback and sends the results to the server.

[0180] The server can dynamically rethink the learning plan based on feedback and sentiment data received from the device. If a user's sentiment towards a particular piece of content is positive, it will provide further related learning materials. Conversely, if a user is frustrated with a particular issue, it will provide supplementary information or explanations from different perspectives to help resolve that issue.

[0181] Ultimately, the server visualizes the learner's learning progress and displays it on the terminal. This visualization uses line graphs, bar graphs, and other methods, allowing users to check their achievements and changes in their emotions. This enables learners to objectively evaluate their learning status and motivates them to continue learning.

[0182] An example of a prompt statement is, "The user appears to have lost interest while learning calculus. What content or methods would you suggest to improve the user's engagement?" Using this prompt statement, the AI ​​model can suggest appropriate adjustments to the learning plan.

[0183] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0184] Step 1:

[0185] The server collects user activity data. Specifically, it retrieves digital information such as answer history, viewing patterns, and interests from various sensors and logs. This input data provides a detailed representation of the user's learning progress. The server organizes and stores this data, preparing it for the next analysis step.

[0186] Step 2:

[0187] The server analyzes the collected activity data using a generating AI model. By supplying the activity data obtained as input to the AI ​​model, the model extracts learner tendencies and learning progress from the data. As output, a personalized learning plan tailored to the learner's characteristics is generated. Specifically, the learning plan is customized based on information about which areas the learner is particularly strong in or interested in.

[0188] Step 3:

[0189] The server evaluates the user's emotional state using an emotion engine. This emotion engine utilizes facial recognition and voice analysis technologies, and also uses data from biosensors as input for analysis. This quantifies the user's mental state and adds it to the server's analysis process. This output leads to the adjustment of a personalized learning plan that takes emotions into account.

[0190] Step 4:

[0191] The server integrates analyzed sentiment and activity data to generate a learning plan that takes emotions into account. Based on the results of the sentiment analysis, it selects prompts and content that will help the user learn more effectively and adjusts the learning plan accordingly. As an output, an optimized learning plan is established.

[0192] Step 5:

[0193] The device receives a personalized learning plan sent from the server. Based on this input data, the device builds a platform that provides user-appropriate video viewing, problem-solving, and interactive simulations. This output provides information that supports the user's specific learning actions on their device.

[0194] Step 6:

[0195] The device records user feedback and emotional changes during learning. Specifically, it collects logs such as which content the user is interested in and which problems they found difficult. This input data is sent to a server and used to adjust the next learning plan.

[0196] Step 7:

[0197] The server dynamically adjusts the learning plan based on the feedback and sentiment data received. It analyzes user reactions, adding relevant materials if there is a positive sentiment towards specific content, and providing supplementary materials if there is frustration. As an output, the deactivation plan, which will be applied to the next learning cycle, is updated.

[0198] Step 8:

[0199] The server visualizes the user's learning progress and displays it on the terminal. Based on the input data of the learning results, it outputs them in an easy-to-understand format as graphs and charts. This allows users to see at a glance what results their efforts are producing and helps them determine the direction of their future learning.

[0200] (Application Example 2)

[0201] 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".

[0202] In online learning and e-commerce, offering uniform content without considering the individual characteristics and emotions of users can decrease user satisfaction. In particular, in situations where users exhibit emotional reactions during the purchasing or learning process, a lack of appropriate feedback and suggestions can impair efficient decision-making and motivation to continue learning. Solving this problem is crucial.

[0203] 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.

[0204] In this invention, the server includes means for collecting user activity information, means for analyzing the activity information to generate an individualized learning plan, and means for distributing educational materials based on the generated individualized learning plan. This enables the analysis of the user's behavioral history and emotional state, and the recommendation of personalized content based on this analysis.

[0205] "Learner activity information" refers to information about learners' behavioral history, such as answering questions, watching videos, and showing interest in various topics.

[0206] An "individualized learning plan" is a plan that proposes the most suitable learning methods and content for each individual learner based on their activity information.

[0207] "Educational materials" is a general term for educational content such as textbooks and assignments provided to learners.

[0208] "Learner responses" refer to the feedback, emotions, and other reactions that learners show to educational materials.

[0209] "Visualization" is a technique that makes information easier to understand intuitively by displaying learning progress visually, such as in graphs or charts.

[0210] "User emotions" refers to the psychological state or reaction that a user exhibits in response to specific content or situations.

[0211] "Recommending relevant information" refers to the act of presenting more relevant products, services, or learning content based on the user's activity information and emotions.

[0212] In this embodiment of the invention, the program is primarily executed by a server and a terminal. The server collects user activity information and analyzes it using a generative AI model. This generates a personalized learning plan suitable for the user. Based on this personalized learning plan, the terminal delivers specific educational materials to the user.

[0213] Furthermore, this system incorporates an emotion engine that evaluates the user's emotional state using facial expression and speech data acquired through the user's device. This emotion data is sent to a server and reflected in individual learning strategies and content recommendations. For example, if a positive emotion is detected towards a product or service that the user has shown interest in, highly relevant products will be recommended, potentially increasing their purchase intent.

[0214] For example, if a user begins to lose focus while watching a particular educational video, the server detects this state through analysis by the emotion engine and provides new videos or interactive content to rekindle their interest. This allows the user to continue learning effectively.

[0215] The generative AI model plays a crucial role throughout these processes, generating prompts tailored to individual user needs based on insights gained from data analysis. An example of such a prompt might be: "The user has stayed on the product details page for 5 minutes and is showing positive emotions. Suggest related products or offers." This optimizes the user experience.

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The server retrieves user activity information. This information includes answer history, viewing patterns, and interests. The activity information is sent to the server and stored in a database. This serves as input data for subsequent analysis.

[0219] Step 2:

[0220] The server analyzes activity information collected using a generative AI model. This analysis generates an optimized individual learning strategy for each user. Pattern recognition and machine learning algorithms are used in the analysis, and the output determines the selection of learning materials and the learning order.

[0221] Step 3:

[0222] Based on the generated individual learning plan, the server delivers specific educational materials to the terminal. These materials are then presented to the user on the terminal, initiating interactive learning activities. The input is the learning plan, and the output is the display of learning materials to the user.

[0223] Step 4:

[0224] The device collects user response information. The emotion engine evaluates the user's feedback and emotional state during their learning activities and sends the results to the server. This response information is then used to adjust individual learning strategies.

[0225] Step 5:

[0226] The server dynamically adjusts the individual learning strategy based on the received response information. Specifically, it enhances content in areas where the user shows interest and adds supplementary information to areas where understanding is insufficient. The input is response information, and the updated learning strategy is delivered to the terminal as output.

[0227] Step 6:

[0228] The server and terminal work together to visualize learning progress, clearly showing the user their current learning status. Graphs and charts are used for this visualization, allowing users to track their progress. The input for the visualization is the learning data and its results, while the output is a visually displayed learning interface.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] This invention is a system for providing optimized education tailored to the characteristics of learners. The system is primarily built around three components: a server, a terminal, and a user, each playing the following roles.

[0246] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests. By analyzing this data, the server evaluates the learner's aptitude and proficiency. Generative AI models are used for the analysis, enabling advanced data analysis.

[0247] Based on the analysis results, the server automatically generates an optimized, personalized learning plan for each user. This plan includes selecting content suitable for the learner, adjusting the difficulty level according to their progress, and even recommending learning paths. For example, a learner aiming to improve their English skills will be provided with a curriculum that balances listening and speaking.

[0248] The generated individual learning plan is delivered to the device by the server. The device then presents interactive learning content to the user according to this learning plan. Through their device, users engage in various learning activities, such as watching videos, answering questions, and practicing simulations. This makes learning more proactive and effective.

[0249] The device then collects user feedback and sends it to the server. This feedback includes the user's answers and reactions to the learning content. The server uses this feedback to dynamically adjust the learning plan using a generative AI model. For example, if a large number of incorrect answers occur on a particular topic, additional materials to reinforce that topic will be incorporated into the plan.

[0250] As a final step, the server visualizes the user's learning progress. This visualization uses graphs and charts to show the progress, allowing the user to check their current level of achievement. This makes it easy for users to understand the effectiveness of their learning, improve their motivation, and identify areas for improvement.

[0251] In this way, the present invention provides learners with an individually optimized learning experience, realizing a system that improves learning efficiency and the quality of education.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The user logs into the learning portal using an iPad. Upon login, a request is sent from the device to the server to access the user's past learning data.

[0255] Step 2:

[0256] The server retrieves the user's past learning activity data from the database. This data includes answer history, viewing history, and tag information that reflects the user's interests.

[0257] Step 3:

[0258] The server inputs activity data into a generating AI model and begins analyzing the data. The model then analyzes the user's strengths, weaknesses, and learning tendencies in detail.

[0259] Step 4:

[0260] The generating AI model creates an optimal, personalized learning plan for the user based on the analysis results. This plan includes recommended learning materials, learning order, and learning goals.

[0261] Step 5:

[0262] The server sends the generated individual learning plan to the device. The device then prepares to provide the user with appropriate learning content according to the plan.

[0263] Step 6:

[0264] Users learn using the provided learning content. This includes watching videos, practicing problems, and experiencing simulations.

[0265] Step 7:

[0266] The device continuously records the user's learning activity data, including the user's answer results, viewing time, and operation history.

[0267] Step 8:

[0268] The device sends the recorded feedback data to the server. This feedback is important data that indicates the level of understanding and response to the learned material.

[0269] Step 9:

[0270] The server analyzes the feedback received and dynamically adjusts the learning plan. This includes revising the plan and recommending new content.

[0271] Step 10:

[0272] The server sends the adjusted learning plan back to the device. Based on the updated plan, the device presents the learner with the next learning step.

[0273] Step 11:

[0274] The server ultimately visualizes the user's learning progress using graphs and charts and displays them on the device. Users can check their own progress and feel the effectiveness of their learning.

[0275] (Example 1)

[0276] 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."

[0277] Traditional teaching methods make it difficult to provide optimal education tailored to the individual characteristics and proficiency levels of each learner. This results in learners being unable to learn effectively at their own pace, hindering improvements in the quality of education. Furthermore, insufficient tracking of learning progress makes it difficult for learners to perceive their own growth, which is another challenge.

[0278] 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.

[0279] In this invention, the server includes means for collecting the activity information of the learner, means for generating an individualized education plan suitable for the learner using an artificial intelligence model generated for analyzing the activity information, and means for delivering educational content based on the generated individualized education plan. Thereby, it becomes possible to provide effective individualized education according to the characteristics of each learner and accurately grasp the learning progress.

[0280] The "activity information of the learner" is data generated when the learner conducts educational activities, and includes information such as answer history, viewing patterns, interests, etc.

[0281] The "generated artificial intelligence model" is a model that utilizes advanced artificial intelligence technology used for analyzing the activity information of the learner and generating an appropriate education plan.

[0282] The "individualized education plan" is a plan for providing educational content optimized according to the characteristics and proficiency levels of each learner.

[0283] The "educational content" is teaching materials and guidance content for the learner to actually learn, and includes information such as videos, texts, exercise problems, etc.

[0284] The "server" is a computer system that plays a central role in the learning system and manages the collection, analysis, generation of education plans, and delivery of educational content.

[0285] [[ID=()]]

[0286] This invention is a system that provides individualized education optimized for each learner. The system is mainly composed of three elements: a server, a terminal, and a user, each of which plays a specific role.

[0287] <000090S> The server first collects learner activity information. This information includes data such as the learner's answer history, viewing patterns, and interests. To collect this data, the server has functions to manage user behavior on the online learning platform.

[0288] The collected data is analyzed on the server using a generated artificial intelligence model. A machine learning algorithm is a possible AI model used to evaluate the learner's proficiency and interests. During program execution, prompts such as "Identify the user's weak areas based on past answer history" can be used.

[0289] Based on the analysis results, the server generates an individualized learning plan. This plan is tailored to the learner's characteristics and includes details such as, "This user needs intermediate-level listening skills, so we will focus on delivering listening materials next week."

[0290] The generated educational plan is delivered from the server to the terminal. The terminal has the functionality to interactively present various educational content to the user, such as videos, text, and practice problems. This allows the user to learn at their own pace.

[0291] The device also collects feedback information on the user's answers and activities. Sending this information to the server allows for dynamic adjustments to the educational plan. For example, a prompt such as, "Provide additional practice exercises on topics the user is struggling with," can be used to determine specific strategies.

[0292] Furthermore, the server visually presents and provides the user with learning progress. At this stage, the data is visualized as graphs and charts, designed so that the user can understand their progress at a glance.

[0293] In this way, the system can provide learners with an individually optimized learning experience, thereby improving the quality of education.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The server collects user activity information. It receives, as input, data such as user responses, viewing history, and interest-based data submitted via the user's device. Specifically, the server automatically logs this data and continuously updates it. As output, the collected activity information is used for analysis in the next step.

[0297] Step 2:

[0298] The server uses a generative artificial intelligence model to analyze the collected activity information. Data such as answer history and viewing patterns are supplied to the AI ​​model as input. Specifically, the prompt "Identify the user's weak areas based on past answer history" is input to the AI ​​model, and the user's learning tendencies are analyzed. As output, evaluation data regarding the user's aptitude and proficiency level is generated.

[0299] Step 3:

[0300] The server generates individualized learning plans based on the analyzed data. The evaluation data obtained in the previous step is used as input. Specifically, it utilizes a generative AI model to create plans such as, "For this user, please select learning materials to focus on next week to improve their listening skills." The output is an optimized individualized learning plan for each learner.

[0301] Step 4:

[0302] The server distributes the generated individualized education plan to the terminal. As input, the generated education plan is provided. As a specific operation, the terminal prepares to interactively display teaching materials (videos and exercise questions) based on the education plan. As output, appropriate educational content is distributed to the user's terminal.

[0303] Step 5: [[ID=,6]]

[0304] The terminal collects the user's feedback. As input, it receives the user's answers and reactions to the teaching materials. As a specific operation, the terminal records the correct / incorrect data and questionnaire results after problem-solving. As output, the feedback data is sent to the server.

[0305] Step 6:

[0306] [[ID=1,6]]The server analyzes the feedback from the terminal and dynamically adjusts the education plan. As input, the feedback data is supplied to the AI model. As a specific operation, adjustment prompts such as "Please provide additional practice questions for the topics the user is struggling with." are used within the model. As output, an updated individualized education plan is created.

[0307] Step 7:

[0308] The server visualizes and provides the learning progress. As input, the user's learning result data is aggregated and used. As a specific operation, graphs and charts indicating the progress situation are created and displayed on the terminal in a form that is easy for the user to understand. As output, visual information for the user to grasp the learning achievements and issues is provided.

[0309] (Application Example 1)

[0310] 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".

[0311] There is a need to efficiently provide educational content optimized based on the individual characteristics of learners and to realize a learning experience that matches the learner's level of understanding and progress. However, conventional systems have the challenge of not being able to quickly select appropriate content and dynamically adjust plans, making it difficult to provide an optimal educational experience for each learner.

[0312] 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.

[0313] In this invention, the server includes a device for collecting learner activity information, a device for analyzing the activity information to generate an individualized learning plan suitable for the learner, and a device for delivering educational content based on the generated individualized learning plan. This makes it possible to effectively provide individually optimized educational content according to the learner's characteristics and progress.

[0314] A "learner" refers to a user whose purpose is to acquire educational content and knowledge.

[0315] "Activity information" refers to a collection of information related to learning activities, including data such as learners' answer history, viewing behavior, and areas of interest.

[0316] An "individualized learning plan" is a plan of educational activities that is optimized and provided individually according to the learner's characteristics and progress.

[0317] "Educational content" refers to information that includes various learning resources provided to learners, such as textbooks, practice problems, and audiovisual content.

[0318] "Opinions" refer to feedback information that shows evaluations and reactions regarding learners' learning experiences.

[0319] "Learning progress" refers to the level of progress a learner has made through educational activities.

[0320] An "AI model" is a model that represents artificial intelligence technology used for data analysis and optimizing learning plans.

[0321] "Figures and tables" are graphical display formats used to visually represent data and information.

[0322] This invention includes a system that comprises a series of processes for collecting and analyzing learner activity information, generating individualized learning plans, and delivering educational content, in order to provide learners with an optimized educational experience. It is primarily composed of three components: a server, a terminal, and a user.

[0323] The server plays a crucial role in efficiently collecting learner activity information. This information includes learners' response history, viewing behavior, and areas of interest. This information is stored on the server and used for analysis. The server utilizes a generative AI model to analyze the activity information in an advanced manner, assessing learners' proficiency and interests, and automatically generating personalized learning plans. In this analysis process, the AI ​​model plays a central role in understanding data trends.

[0324] The generated individualized learning plan is delivered to the device. The device then presents the learner with interactive educational content based on this plan. Specifically, this includes playing video content, presenting practice problems, and providing simulations. This allows users to learn at their own pace and independently.

[0325] User feedback is sent to the server via the device. By receiving this feedback, the server dynamically adjusts the learning plan in real time. This process improves the quality of the educational experience, enabling a rapid response to learner needs. Learning progress is visualized using charts and graphs, allowing learners to intuitively understand their own progress.

[0326] For example, if a learner wishes to learn the basics of chemistry, the server can provide an optimized introductory chemistry course based on activity information it has collected. The content provided is automatically adjusted according to the learner's interests and level of understanding. For instance, based on a prompt such as, "Please provide a video that clearly explains the basics of chemistry," suitable materials will be suggested.

[0327] In this way, the interaction between the server, terminal, and user makes it possible to provide an optimized educational experience for each individual learner.

[0328] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0329] Step 1:

[0330] The server collects learner activity information. Its inputs include learner response history, viewing behavior, and interest data. Its output is stored in a centrally managed database. Specifically, it uses an API to periodically retrieve data from the device, organize it, and store it.

[0331] Step 2:

[0332] The server analyzes activity information using a generative AI model. The activity data collected in Step 1 is used as input. The analysis evaluates the learner's proficiency level and areas of interest. As output, an individualized learning plan is generated for each learner. Specifically, the AI ​​model is given analysis instructions using prompts, and the basic structure of the learning plan is created based on the results.

[0333] Step 3:

[0334] The generated individual learning plan is delivered from the server to the terminal. The learning plan generated in step 2 is used as input. The educational content based on this plan is displayed on the terminal as output. Specifically, the learning plan data is sent to the terminal using network communication, and the terminal interprets it and displays it in the user interface.

[0335] Step 4:

[0336] The device presents interactive educational content to the user. It uses learning plan data delivered from a server as input. The output is educational content displayed on the user's device. Specific actions include controlling video playback, presenting interactive exercises, and providing a feedback screen.

[0337] Step 5:

[0338] Users provide feedback on their learning through a device. Input includes their answers and reactions to their learning experience. Output is the transmission of this feedback information to the server. Specific actions include filling out survey forms and selecting answers.

[0339] Step 6:

[0340] The server dynamically adjusts the learning plan based on the feedback information. It uses the feedback data received in step 5 as input. A new learning plan is generated as output. Specifically, it analyzes the feedback and uses an AI model to adjust the learning plan. For example, it might incorporate additional practice questions for topics where the user frequently makes mistakes.

[0341] Step 7:

[0342] The server generates materials that visualize the learner's learning progress. It takes learning progress data as input and creates progress reports for learners in chart and graph format as output. Specifically, it uses data visualization tools to format the data so that learners can check their own progress.

[0343] 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.

[0344] This invention is a system for providing optimized education tailored to the characteristics and emotional state of learners. The system consists of four components: a server, a terminal, a user, and an emotion engine, each playing the following roles.

[0345] The server first collects learner activity data. This data includes the user's answer history, viewing patterns, interests, etc., and records the learner's behavior and progress in detail. The collected data is then analyzed by a generative AI model to generate a personalized learning plan suitable for the learner.

[0346] In addition, this system includes an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state through facial recognition and voice analysis. Furthermore, it also uses data from biosensors for emotion recognition, achieving highly accurate emotion analysis. The server incorporates this emotion data into the analysis results and generates an individualized learning plan that takes emotions into account. For example, if the emotion engine detects that the learner is lacking concentration, the server adjusts the learning plan, prioritizing the display of content that will interest the user or presenting tasks that can be completed in a short time.

[0347] The generated learning plan is delivered to the device and provided to the user. Based on the individual learning plan, the device provides the user with video viewing, problem solving, and interactive simulation experiences. During learning, the device continuously records the user's feedback and emotional changes and sends them to the server.

[0348] The server dynamically adjusts the learning plan based on the feedback and sentiment data it receives. For example, if a user's sentiment towards a particular piece of content is positive, it might add related learning materials for that content. Conversely, if a user is frustrated with a particular issue, it might provide supplementary information or explanations from different angles to delve deeper into that issue.

[0349] Ultimately, the server visualizes the user's learning progress and displays it on the terminal. This progress display uses graphs and charts, allowing users to see their own achievements and changes in their emotions. Through this feature, learners can objectively understand their learning status, which motivates them to continue learning.

[0350] Based on the above, the present invention provides a system that offers a learning experience individually optimized from both the behavioral and emotional perspectives of learners, aiming to realize efficient and effective education.

[0351] The following describes the processing flow.

[0352] Step 1:

[0353] The user logs in and begins learning. When the user accesses the learning portal on their iPad, the device sends the user's identification information to the server. This is to associate past learning data with the current learning content.

[0354] Step 2:

[0355] The server retrieves the user's past activity data from the database based on the user's identification information sent from the terminal. This data includes answer history, viewing patterns, and existing learning tendencies.

[0356] Step 3:

[0357] The server analyzes past activity data and generates a personalized learning plan based on the user's learning needs. This analysis uses a generative AI model to identify the user's strengths and areas that need improvement.

[0358] Step 4:

[0359] The emotion engine is activated and captures the user's facial expressions and voice through the device. Furthermore, data such as pulse rate and skin reactions are acquired from wearable biosensors. This data is used to evaluate the user's emotional state.

[0360] Step 5:

[0361] The emotion engine analyzes the collected emotional data to identify the user's current emotional state. For example, if a user is feeling stressed, that information is sent to the server.

[0362] Step 6:

[0363] The server combines analysis results with emotional data to adapt individual learning plans to the user's emotions. The order of content and the materials presented are adjusted according to the user's emotional state.

[0364] Step 7:

[0365] A customized learning plan is sent to the device and displayed to the user. The user receives learning content such as videos, interactive exercises, and simulations.

[0366] Step 8:

[0367] The device continuously records the user's reactions and emotional changes during learning. This includes, for example, changes in facial expressions and answer results during the learning process.

[0368] Step 9:

[0369] The device sends feedback and sentiment data to the server. The server receives this data and analyzes it to incorporate it into the next learning plan.

[0370] Step 10:

[0371] The server visualizes learning progress data and sends visually represented graphs and charts to the user's device. Users can then check their learning achievements and emotional changes on a dashboard.

[0372] These steps enable a system where servers, terminals, users, and the emotion engine work together to provide a learning experience optimized for the learner.

[0373] (Example 2)

[0374] 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".

[0375] Traditional education systems often fail to adequately analyze learners' progress and activity data, making it difficult to provide individually optimized learning experiences. Furthermore, the lack of dynamic adjustments to learning plans that take learners' emotions into account can lead to decreased learning efficiency and motivation.

[0376] 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.

[0377] In this invention, the server includes means for collecting learner activity data, means for analyzing the data with a generative AI model to generate an individualized learning plan, and means for evaluating emotional states using facial recognition, voice analysis, and biosensors. This makes it possible to generate and provide an optimized individualized learning plan based on the individual characteristics and emotional states of each learner.

[0378] A "learner" refers to an individual who engages in learning activities using educational systems and materials.

[0379] "Activity data" refers to information about learners' behavior and performance, such as their answer history, viewing patterns, and interests.

[0380] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and generates a learning plan suitable for the learner.

[0381] An "individualized learning plan" refers to a learning curriculum and content optimized according to the learner's characteristics and progress.

[0382] "Emotional state" refers to the psychological and emotional state of a learner, assessed using information from their facial expressions, voice, and biosensors.

[0383] "Feedback" refers to reactions and comments on the learning experience provided by learners, and is used to improve the system.

[0384] "Learning progress" refers to information that indicates the degree to which a learner has progressed in learning and their level of understanding.

[0385] "Visual representation" refers to techniques that use graphs, charts, and other visual aids to present information in a way that can be understood by looking at it.

[0386] This invention is a system that provides education optimized according to the learner's characteristics and emotional state. The system mainly consists of four components: a server, a terminal, a user, and an emotion engine.

[0387] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests, allowing for a detailed understanding of the learner's behavior and progress. The collected data is analyzed by a generative AI model, which generates a personalized learning plan tailored to each learner. This AI model learns from large amounts of data and proposes learning plans quickly and accurately.

[0388] The emotion engine applies facial recognition and voice analysis technologies to assess the user's emotional state. Furthermore, it incorporates data from biosensors to enable more accurate emotion analysis. This allows the server to generate personalized learning plans that take the learner's emotions into account. For example, if a learner is lacking focus, the server adjusts the learning plan, providing content that engages the user and tasks that can be completed in a short amount of time.

[0389] The generated learning plan is provided to the user via the device. Based on the individual learning plan, the device provides the user with video viewing, problem-solving, and interactive simulation experiences. During learning, the device collects the user's reactions and feedback and sends the results to the server.

[0390] The server can dynamically rethink the learning plan based on feedback and sentiment data received from the device. If a user's sentiment towards a particular piece of content is positive, it will provide further related learning materials. Conversely, if a user is frustrated with a particular issue, it will provide supplementary information or explanations from different perspectives to help resolve that issue.

[0391] Ultimately, the server visualizes the learner's learning progress and displays it on the terminal. This visualization uses line graphs, bar graphs, and other methods, allowing users to check their achievements and changes in their emotions. This enables learners to objectively evaluate their learning status and motivates them to continue learning.

[0392] An example of a prompt statement is, "The user appears to have lost interest while learning calculus. What content or methods would you suggest to improve the user's engagement?" Using this prompt statement, the AI ​​model can suggest appropriate adjustments to the learning plan.

[0393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0394] Step 1:

[0395] The server collects user activity data. Specifically, it retrieves digital information such as answer history, viewing patterns, and interests from various sensors and logs. This input data provides a detailed representation of the user's learning progress. The server organizes and stores this data, preparing it for the next analysis step.

[0396] Step 2:

[0397] The server analyzes the collected activity data using a generating AI model. By supplying the activity data obtained as input to the AI ​​model, the model extracts learner tendencies and learning progress from the data. As output, a personalized learning plan tailored to the learner's characteristics is generated. Specifically, the learning plan is customized based on information about which areas the learner is particularly strong in or interested in.

[0398] Step 3:

[0399] The server evaluates the user's emotional state using an emotion engine. This emotion engine utilizes facial recognition and voice analysis technologies, and also uses data from biosensors as input for analysis. This quantifies the user's mental state and adds it to the server's analysis process. This output leads to the adjustment of a personalized learning plan that takes emotions into account.

[0400] Step 4:

[0401] The server integrates analyzed sentiment and activity data to generate a learning plan that takes emotions into account. Based on the results of the sentiment analysis, it selects prompts and content that will help the user learn more effectively and adjusts the learning plan accordingly. As an output, an optimized learning plan is established.

[0402] Step 5:

[0403] The device receives a personalized learning plan sent from the server. Based on this input data, the device builds a platform that provides user-appropriate video viewing, problem-solving, and interactive simulations. This output provides information that supports the user's specific learning actions on their device.

[0404] Step 6:

[0405] The device records user feedback and emotional changes during learning. Specifically, it collects logs such as which content the user is interested in and which problems they found difficult. This input data is sent to a server and used to adjust the next learning plan.

[0406] Step 7:

[0407] The server dynamically adjusts the learning plan based on the feedback and sentiment data received. It analyzes user reactions, adding relevant materials if there is a positive sentiment towards specific content, and providing supplementary materials if there is frustration. As an output, the deactivation plan, which will be applied to the next learning cycle, is updated.

[0408] Step 8:

[0409] The server visualizes the user's learning progress and displays it on the terminal. Based on the input data of the learning results, it outputs them in an easy-to-understand format as graphs and charts. This allows users to see at a glance what results their efforts are producing and helps them determine the direction of their future learning.

[0410] (Application Example 2)

[0411] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0412] In online learning and e-commerce, offering uniform content without considering the individual characteristics and emotions of users can decrease user satisfaction. In particular, in situations where users exhibit emotional reactions during the purchasing or learning process, a lack of appropriate feedback and suggestions can impair efficient decision-making and motivation to continue learning. Solving this problem is crucial.

[0413] 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.

[0414] In this invention, the server includes means for collecting user activity information, means for analyzing the activity information to generate an individualized learning plan, and means for distributing educational materials based on the generated individualized learning plan. This enables the analysis of the user's behavioral history and emotional state, and the recommendation of personalized content based on this analysis.

[0415] "Learner activity information" refers to information about learners' behavioral history, such as answering questions, watching videos, and showing interest in various topics.

[0416] An "individualized learning plan" is a plan that proposes the most suitable learning methods and content for each individual learner based on their activity information.

[0417] "Educational materials" is a general term for educational content such as textbooks and assignments provided to learners.

[0418] "Learner responses" refer to the feedback, emotions, and other reactions that learners show to educational materials.

[0419] "Visualization" is a technique that makes information easier to understand intuitively by displaying learning progress visually, such as in graphs or charts.

[0420] "User emotions" refers to the psychological state or reaction that a user exhibits in response to specific content or situations.

[0421] "Recommending relevant information" refers to the act of presenting more relevant products, services, or learning content based on the user's activity information and emotions.

[0422] In this embodiment of the invention, the program is primarily executed by a server and a terminal. The server collects user activity information and analyzes it using a generative AI model. This generates a personalized learning plan suitable for the user. Based on this personalized learning plan, the terminal delivers specific educational materials to the user.

[0423] Furthermore, this system incorporates an emotion engine that evaluates the user's emotional state using facial expression and speech data acquired through the user's device. This emotion data is sent to a server and reflected in individual learning strategies and content recommendations. For example, if a positive emotion is detected towards a product or service that the user has shown interest in, highly relevant products will be recommended, potentially increasing their purchase intent.

[0424] For example, if a user begins to lose focus while watching a particular educational video, the server detects this state through analysis by the emotion engine and provides new videos or interactive content to rekindle their interest. This allows the user to continue learning effectively.

[0425] The generative AI model plays a crucial role throughout these processes, generating prompts tailored to individual user needs based on insights gained from data analysis. An example of such a prompt might be: "The user has stayed on the product details page for 5 minutes and is showing positive emotions. Suggest related products or offers." This optimizes the user experience.

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The server retrieves user activity information. This information includes answer history, viewing patterns, and interests. The activity information is sent to the server and stored in a database. This serves as input data for subsequent analysis.

[0429] Step 2:

[0430] The server analyzes activity information collected using a generative AI model. This analysis generates an optimized individual learning strategy for each user. Pattern recognition and machine learning algorithms are used in the analysis, and the output determines the selection of learning materials and the learning order.

[0431] Step 3:

[0432] Based on the generated individual learning plan, the server delivers specific educational materials to the terminal. These materials are then presented to the user on the terminal, initiating interactive learning activities. The input is the learning plan, and the output is the display of learning materials to the user.

[0433] Step 4:

[0434] The device collects user response information. The emotion engine evaluates the user's feedback and emotional state during their learning activities and sends the results to the server. This response information is then used to adjust individual learning strategies.

[0435] Step 5:

[0436] The server dynamically adjusts the individual learning strategy based on the received response information. Specifically, it enhances content in areas where the user shows interest and adds supplementary information to areas where understanding is insufficient. The input is response information, and the updated learning strategy is delivered to the terminal as output.

[0437] Step 6:

[0438] The server and terminal work together to visualize learning progress, clearly showing the user their current learning status. Graphs and charts are used for this visualization, allowing users to track their progress. The input for the visualization is the learning data and its results, while the output is a visually displayed learning interface.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] [Third Embodiment]

[0443] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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".

[0455] This invention is a system for providing optimized education tailored to the characteristics of learners. The system is primarily built around three components: a server, a terminal, and a user, each playing the following roles.

[0456] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests. By analyzing this data, the server evaluates the learner's aptitude and proficiency. Generative AI models are used for the analysis, enabling advanced data analysis.

[0457] Based on the analysis results, the server automatically generates an optimized, personalized learning plan for each user. This plan includes selecting content suitable for the learner, adjusting the difficulty level according to their progress, and even recommending learning paths. For example, a learner aiming to improve their English skills will be provided with a curriculum that balances listening and speaking.

[0458] The generated individual learning plan is delivered to the device by the server. The device then presents interactive learning content to the user according to this learning plan. Through their device, users engage in various learning activities, such as watching videos, answering questions, and practicing simulations. This makes learning more proactive and effective.

[0459] The device then collects user feedback and sends it to the server. This feedback includes the user's answers and reactions to the learning content. The server uses this feedback to dynamically adjust the learning plan using a generative AI model. For example, if a large number of incorrect answers occur on a particular topic, additional materials to reinforce that topic will be incorporated into the plan.

[0460] As a final step, the server visualizes the user's learning progress. This visualization uses graphs and charts to show the progress, allowing the user to check their current level of achievement. This makes it easy for users to understand the effectiveness of their learning, improve their motivation, and identify areas for improvement.

[0461] In this way, the present invention provides learners with an individually optimized learning experience, realizing a system that improves learning efficiency and the quality of education.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The user logs into the learning portal using an iPad. Upon login, a request is sent from the device to the server to access the user's past learning data.

[0465] Step 2:

[0466] The server retrieves the user's past learning activity data from the database. This data includes answer history, viewing history, and tag information that reflects the user's interests.

[0467] Step 3:

[0468] The server inputs activity data into a generating AI model and begins analyzing the data. The model then analyzes the user's strengths, weaknesses, and learning tendencies in detail.

[0469] Step 4:

[0470] The generating AI model creates an optimal, personalized learning plan for the user based on the analysis results. This plan includes recommended learning materials, learning order, and learning goals.

[0471] Step 5:

[0472] The server sends the generated individual learning plan to the device. The device then prepares to provide the user with appropriate learning content according to the plan.

[0473] Step 6:

[0474] Users learn using the provided learning content. This includes watching videos, practicing problems, and experiencing simulations.

[0475] Step 7:

[0476] The device continuously records the user's learning activity data, including the user's answer results, viewing time, and operation history.

[0477] Step 8:

[0478] The device sends the recorded feedback data to the server. This feedback is important data that indicates the level of understanding and response to the learned material.

[0479] Step 9:

[0480] The server analyzes the feedback received and dynamically adjusts the learning plan. This includes revising the plan and recommending new content.

[0481] Step 10:

[0482] The server sends the adjusted learning plan back to the device. Based on the updated plan, the device presents the learner with the next learning step.

[0483] Step 11:

[0484] The server ultimately visualizes the user's learning progress using graphs and charts and displays them on the device. Users can check their own progress and feel the effectiveness of their learning.

[0485] (Example 1)

[0486] 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."

[0487] Traditional teaching methods make it difficult to provide optimal education tailored to the individual characteristics and proficiency levels of each learner. This results in learners being unable to learn effectively at their own pace, hindering improvements in the quality of education. Furthermore, insufficient tracking of learning progress makes it difficult for learners to perceive their own growth, which is another challenge.

[0488] 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.

[0489] In this invention, the server includes means for collecting learner activity information, means for using a generative artificial intelligence model to analyze the activity information and generate an individualized education plan suitable for the learner, and means for delivering educational content based on the generated individualized education plan. This makes it possible to provide effective individualized education tailored to the characteristics of each learner and to accurately grasp their learning progress.

[0490] "Learner activity information" refers to data generated when learners engage in educational activities, including answer history, viewing patterns, interests, and other relevant information.

[0491] A "generative artificial intelligence model" is a model that utilizes advanced artificial intelligence technology to analyze learner activity information and generate appropriate educational plans.

[0492] An "individualized education plan" is a plan designed to provide educational content optimized for each learner's individual characteristics and proficiency level.

[0493] "Educational content" refers to the materials and teaching methods that learners actually use to study, and includes information such as videos, textbooks, and practice problems.

[0494] A "server" is a computer system that plays a central role in a learning system, managing data collection, analysis, creation of educational plans, and distribution of educational content.

[0495] "Visual presentation" refers to a method of displaying information using images and diagrams to effectively communicate progress and results to learners.

[0496] This invention is a system that provides personalized education optimized for each learner. The system mainly consists of three elements: a server, a terminal, and a user, each playing a specific role.

[0497] The server first collects learner activity information. This information includes data such as the learner's answer history, viewing patterns, and interests. To collect this data, the server has functions to manage user behavior on the online learning platform.

[0498] The collected data is analyzed on the server using a generated artificial intelligence model. A machine learning algorithm is a possible AI model used to evaluate the learner's proficiency and interests. During program execution, prompts such as "Identify the user's weak areas based on past answer history" can be used.

[0499] Based on the analysis results, the server generates an individualized learning plan. This plan is tailored to the learner's characteristics and includes details such as, "This user needs intermediate-level listening skills, so we will focus on delivering listening materials next week."

[0500] The generated educational plan is delivered from the server to the terminal. The terminal has the functionality to interactively present various educational content to the user, such as videos, text, and practice problems. This allows the user to learn at their own pace.

[0501] The device also collects feedback information on the user's answers and activities. Sending this information to the server allows for dynamic adjustments to the educational plan. For example, a prompt such as, "Provide additional practice exercises on topics the user is struggling with," can be used to determine specific strategies.

[0502] Furthermore, the server visually presents and provides the user with learning progress. At this stage, the data is visualized as graphs and charts, designed so that the user can understand their progress at a glance.

[0503] In this way, the system can provide learners with an individually optimized learning experience, thereby improving the quality of education.

[0504] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0505] Step 1:

[0506] The server collects user activity information. It receives, as input, data such as user responses, viewing history, and interest-based data submitted via the user's device. Specifically, the server automatically logs this data and continuously updates it. As output, the collected activity information is used for analysis in the next step.

[0507] Step 2:

[0508] The server uses a generative artificial intelligence model to analyze the collected activity information. Data such as answer history and viewing patterns are supplied to the AI ​​model as input. Specifically, the prompt "Identify the user's weak areas based on past answer history" is input to the AI ​​model, and the user's learning tendencies are analyzed. As output, evaluation data regarding the user's aptitude and proficiency level is generated.

[0509] Step 3:

[0510] The server generates individualized learning plans based on the analyzed data. The evaluation data obtained in the previous step is used as input. Specifically, it utilizes a generative AI model to create plans such as, "For this user, please select learning materials to focus on next week to improve their listening skills." The output is an optimized individualized learning plan for each learner.

[0511] Step 4:

[0512] The server delivers the generated individualized learning plan to the terminal. The generated learning plan is provided as input. Specifically, the terminal prepares to interactively display learning materials (videos and practice problems) based on the learning plan. As output, the appropriate educational content is delivered to the user's terminal.

[0513] Step 5:

[0514] The device collects user feedback. It receives user responses and reactions to learning materials as input. Specifically, the device records correct / incorrect answer data and survey results after problem completion. The feedback data is sent to the server as output.

[0515] Step 6:

[0516] The server analyzes feedback from the terminal and dynamically adjusts the educational plan. Feedback data is supplied to the AI ​​model as input. Specifically, the model uses adjustment prompts such as, "Please provide additional practice exercises on topics the user is struggling with." An updated individualized educational plan is created as output.

[0517] Step 7:

[0518] The server visualizes and provides learning progress. As input, it aggregates and uses user learning result data. Specifically, it creates graphs and charts showing progress and displays them on the user's device in an easy-to-understand format. As output, it provides visual information to help the user understand their learning achievements and challenges.

[0519] (Application Example 1)

[0520] 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."

[0521] There is a need to efficiently provide educational content optimized based on the individual characteristics of learners and to realize a learning experience that matches the learner's level of understanding and progress. However, conventional systems have the challenge of not being able to quickly select appropriate content and dynamically adjust plans, making it difficult to provide an optimal educational experience for each learner.

[0522] 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.

[0523] In this invention, the server includes a device for collecting learner activity information, a device for analyzing the activity information to generate an individualized learning plan suitable for the learner, and a device for delivering educational content based on the generated individualized learning plan. This makes it possible to effectively provide individually optimized educational content according to the learner's characteristics and progress.

[0524] A "learner" refers to a user whose purpose is to acquire educational content and knowledge.

[0525] "Activity information" refers to a collection of information related to learning activities, including data such as learners' answer history, viewing behavior, and areas of interest.

[0526] An "individualized learning plan" is a plan of educational activities that is optimized and provided individually according to the learner's characteristics and progress.

[0527] "Educational content" refers to information that includes various learning resources provided to learners, such as textbooks, practice problems, and audiovisual content.

[0528] "Opinions" refer to feedback information that shows evaluations and reactions regarding learners' learning experiences.

[0529] "Learning progress" refers to the level of progress a learner has made through educational activities.

[0530] An "AI model" is a model that represents artificial intelligence technology used for data analysis and optimizing learning plans.

[0531] "Figures and tables" are graphical display formats used to visually represent data and information.

[0532] This invention includes a system that comprises a series of processes for collecting and analyzing learner activity information, generating individualized learning plans, and delivering educational content, in order to provide learners with an optimized educational experience. It is primarily composed of three components: a server, a terminal, and a user.

[0533] The server plays a crucial role in efficiently collecting learner activity information. This information includes learners' response history, viewing behavior, and areas of interest. This information is stored on the server and used for analysis. The server utilizes a generative AI model to analyze the activity information in an advanced manner, assessing learners' proficiency and interests, and automatically generating personalized learning plans. In this analysis process, the AI ​​model plays a central role in understanding data trends.

[0534] The generated individualized learning plan is delivered to the device. The device then presents the learner with interactive educational content based on this plan. Specifically, this includes playing video content, presenting practice problems, and providing simulations. This allows users to learn at their own pace and independently.

[0535] User feedback is sent to the server via the device. By receiving this feedback, the server dynamically adjusts the learning plan in real time. This process improves the quality of the educational experience, enabling a rapid response to learner needs. Learning progress is visualized using charts and graphs, allowing learners to intuitively understand their own progress.

[0536] For example, if a learner wishes to learn the basics of chemistry, the server can provide an optimized introductory chemistry course based on activity information it has collected. The content provided is automatically adjusted according to the learner's interests and level of understanding. For instance, based on a prompt such as, "Please provide a video that clearly explains the basics of chemistry," suitable materials will be suggested.

[0537] In this way, the interaction between the server, terminal, and user makes it possible to provide an optimized educational experience for each individual learner.

[0538] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0539] Step 1:

[0540] The server collects learner activity information. Its inputs include learner response history, viewing behavior, and interest data. Its output is stored in a centrally managed database. Specifically, it uses an API to periodically retrieve data from the device, organize it, and store it.

[0541] Step 2:

[0542] The server analyzes activity information using a generative AI model. The activity data collected in Step 1 is used as input. The analysis evaluates the learner's proficiency level and areas of interest. As output, an individualized learning plan is generated for each learner. Specifically, the AI ​​model is given analysis instructions using prompts, and the basic structure of the learning plan is created based on the results.

[0543] Step 3:

[0544] The generated individual learning plan is delivered from the server to the terminal. The learning plan generated in step 2 is used as input. The educational content based on this plan is displayed on the terminal as output. Specifically, the learning plan data is sent to the terminal using network communication, and the terminal interprets it and displays it in the user interface.

[0545] Step 4:

[0546] The device presents interactive educational content to the user. It uses learning plan data delivered from a server as input. The output is educational content displayed on the user's device. Specific actions include controlling video playback, presenting interactive exercises, and providing a feedback screen.

[0547] Step 5:

[0548] Users provide feedback on their learning through a device. Input includes their answers and reactions to their learning experience. Output is the transmission of this feedback information to the server. Specific actions include filling out survey forms and selecting answers.

[0549] Step 6:

[0550] The server dynamically adjusts the learning plan based on the feedback information. It uses the feedback data received in step 5 as input. A new learning plan is generated as output. Specifically, it analyzes the feedback and uses an AI model to adjust the learning plan. For example, it might incorporate additional practice questions for topics where the user frequently makes mistakes.

[0551] Step 7:

[0552] The server generates materials that visualize the learner's learning progress. It takes learning progress data as input and creates progress reports for learners in chart and graph format as output. Specifically, it uses data visualization tools to format the data so that learners can check their own progress.

[0553] 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.

[0554] This invention is a system for providing optimized education tailored to the characteristics and emotional state of learners. The system consists of four components: a server, a terminal, a user, and an emotion engine, each playing the following roles.

[0555] The server first collects learner activity data. This data includes the user's answer history, viewing patterns, interests, etc., and records the learner's behavior and progress in detail. The collected data is then analyzed by a generative AI model to generate a personalized learning plan suitable for the learner.

[0556] In addition, this system includes an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state through facial recognition and voice analysis. Furthermore, it also uses data from biosensors for emotion recognition, achieving highly accurate emotion analysis. The server incorporates this emotion data into the analysis results and generates an individualized learning plan that takes emotions into account. For example, if the emotion engine detects that the learner is lacking concentration, the server adjusts the learning plan, prioritizing the display of content that will interest the user or presenting tasks that can be completed in a short time.

[0557] The generated learning plan is delivered to the device and provided to the user. Based on the individual learning plan, the device provides the user with video viewing, problem solving, and interactive simulation experiences. During learning, the device continuously records the user's feedback and emotional changes and sends them to the server.

[0558] The server dynamically adjusts the learning plan based on the feedback and sentiment data it receives. For example, if a user's sentiment towards a particular piece of content is positive, it might add related learning materials for that content. Conversely, if a user is frustrated with a particular issue, it might provide supplementary information or explanations from different angles to delve deeper into that issue.

[0559] Ultimately, the server visualizes the user's learning progress and displays it on the terminal. This progress display uses graphs and charts, allowing users to see their own achievements and changes in their emotions. Through this feature, learners can objectively understand their learning status, which motivates them to continue learning.

[0560] Based on the above, the present invention provides a system that offers a learning experience individually optimized from both the behavioral and emotional perspectives of learners, aiming to realize efficient and effective education.

[0561] The following describes the processing flow.

[0562] Step 1:

[0563] The user logs in and begins learning. When the user accesses the learning portal on their iPad, the device sends the user's identification information to the server. This is to associate past learning data with the current learning content.

[0564] Step 2:

[0565] The server retrieves the user's past activity data from the database based on the user's identification information sent from the terminal. This data includes answer history, viewing patterns, and existing learning tendencies.

[0566] Step 3:

[0567] The server analyzes past activity data and generates a personalized learning plan based on the user's learning needs. This analysis uses a generative AI model to identify the user's strengths and areas that need improvement.

[0568] Step 4:

[0569] The emotion engine is activated and captures the user's facial expressions and voice through the device. Furthermore, data such as pulse rate and skin reactions are acquired from wearable biosensors. This data is used to evaluate the user's emotional state.

[0570] Step 5:

[0571] The emotion engine analyzes the collected emotional data to identify the user's current emotional state. For example, if a user is feeling stressed, that information is sent to the server.

[0572] Step 6:

[0573] The server combines analysis results with emotional data to adapt individual learning plans to the user's emotions. The order of content and the materials presented are adjusted according to the user's emotional state.

[0574] Step 7:

[0575] A customized learning plan is sent to the device and displayed to the user. The user receives learning content such as videos, interactive exercises, and simulations.

[0576] Step 8:

[0577] The device continuously records the user's reactions and emotional changes during learning. This includes, for example, changes in facial expressions and answer results during the learning process.

[0578] Step 9:

[0579] The device sends feedback and sentiment data to the server. The server receives this data and analyzes it to incorporate it into the next learning plan.

[0580] Step 10:

[0581] The server visualizes learning progress data and sends visually represented graphs and charts to the user's device. Users can then check their learning achievements and emotional changes on a dashboard.

[0582] These steps enable a system where servers, terminals, users, and the emotion engine work together to provide a learning experience optimized for the learner.

[0583] (Example 2)

[0584] 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."

[0585] Traditional education systems often fail to adequately analyze learners' progress and activity data, making it difficult to provide individually optimized learning experiences. Furthermore, the lack of dynamic adjustments to learning plans that take learners' emotions into account can lead to decreased learning efficiency and motivation.

[0586] 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.

[0587] In this invention, the server includes means for collecting learner activity data, means for analyzing the data with a generative AI model to generate an individualized learning plan, and means for evaluating emotional states using facial recognition, voice analysis, and biosensors. This makes it possible to generate and provide an optimized individualized learning plan based on the individual characteristics and emotional states of each learner.

[0588] A "learner" refers to an individual who engages in learning activities using educational systems and materials.

[0589] "Activity data" refers to information about learners' behavior and performance, such as their answer history, viewing patterns, and interests.

[0590] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and generates a learning plan suitable for the learner.

[0591] An "individualized learning plan" refers to a learning curriculum and content optimized according to the learner's characteristics and progress.

[0592] "Emotional state" refers to the psychological and emotional state of a learner, assessed using information from their facial expressions, voice, and biosensors.

[0593] "Feedback" refers to reactions and comments on the learning experience provided by learners, and is used to improve the system.

[0594] "Learning progress" refers to information that indicates the degree to which a learner has progressed in learning and their level of understanding.

[0595] "Visual representation" refers to techniques that use graphs, charts, and other visual aids to present information in a way that can be understood by looking at it.

[0596] This invention is a system that provides education optimized according to the learner's characteristics and emotional state. The system mainly consists of four components: a server, a terminal, a user, and an emotion engine.

[0597] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests, allowing for a detailed understanding of the learner's behavior and progress. The collected data is analyzed by a generative AI model, which generates a personalized learning plan tailored to each learner. This AI model learns from large amounts of data and proposes learning plans quickly and accurately.

[0598] The emotion engine applies facial recognition and voice analysis technologies to assess the user's emotional state. Furthermore, it incorporates data from biosensors to enable more accurate emotion analysis. This allows the server to generate personalized learning plans that take the learner's emotions into account. For example, if a learner is lacking focus, the server adjusts the learning plan, providing content that engages the user and tasks that can be completed in a short amount of time.

[0599] The generated learning plan is provided to the user via the device. Based on the individual learning plan, the device provides the user with video viewing, problem-solving, and interactive simulation experiences. During learning, the device collects the user's reactions and feedback and sends the results to the server.

[0600] The server can dynamically rethink the learning plan based on feedback and sentiment data received from the device. If a user's sentiment towards a particular piece of content is positive, it will provide further related learning materials. Conversely, if a user is frustrated with a particular issue, it will provide supplementary information or explanations from different perspectives to help resolve that issue.

[0601] Ultimately, the server visualizes the learner's learning progress and displays it on the terminal. This visualization uses line graphs, bar graphs, and other methods, allowing users to check their achievements and changes in their emotions. This enables learners to objectively evaluate their learning status and motivates them to continue learning.

[0602] An example of a prompt statement is, "The user appears to have lost interest while learning calculus. What content or methods would you suggest to improve the user's engagement?" Using this prompt statement, the AI ​​model can suggest appropriate adjustments to the learning plan.

[0603] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0604] Step 1:

[0605] The server collects user activity data. Specifically, it retrieves digital information such as answer history, viewing patterns, and interests from various sensors and logs. This input data provides a detailed representation of the user's learning progress. The server organizes and stores this data, preparing it for the next analysis step.

[0606] Step 2:

[0607] The server analyzes the collected activity data using a generating AI model. By supplying the activity data obtained as input to the AI ​​model, the model extracts learner tendencies and learning progress from the data. As output, a personalized learning plan tailored to the learner's characteristics is generated. Specifically, the learning plan is customized based on information about which areas the learner is particularly strong in or interested in.

[0608] Step 3:

[0609] The server evaluates the user's emotional state using an emotion engine. This emotion engine utilizes facial recognition and voice analysis technologies, and also uses data from biosensors as input for analysis. This quantifies the user's mental state and adds it to the server's analysis process. This output leads to the adjustment of a personalized learning plan that takes emotions into account.

[0610] Step 4:

[0611] The server integrates analyzed sentiment and activity data to generate a learning plan that takes emotions into account. Based on the results of the sentiment analysis, it selects prompts and content that will help the user learn more effectively and adjusts the learning plan accordingly. As an output, an optimized learning plan is established.

[0612] Step 5:

[0613] The device receives a personalized learning plan sent from the server. Based on this input data, the device builds a platform that provides user-friendly video viewing, problem-solving, and interactive simulations. This output provides information that supports the user's specific learning actions on their device.

[0614] Step 6:

[0615] The device records user feedback and emotional changes during learning. Specifically, it collects logs such as which content the user is interested in and which problems they found difficult. This input data is sent to a server and used to adjust the next learning plan.

[0616] Step 7:

[0617] The server dynamically adjusts the learning plan based on the feedback and sentiment data received. It analyzes user reactions, adding relevant materials if there is a positive sentiment towards specific content, and providing supplementary materials if there is frustration. As an output, the deactivation plan, which will be applied to the next learning cycle, is updated.

[0618] Step 8:

[0619] The server visualizes the user's learning progress and displays it on the terminal. Based on the input data of the learning results, it outputs them in an easy-to-understand format as graphs and charts. This allows users to see at a glance what results their efforts are producing and helps them determine the direction of their future learning.

[0620] (Application Example 2)

[0621] 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."

[0622] In online learning and e-commerce, offering uniform content without considering the individual characteristics and emotions of users can decrease user satisfaction. In particular, in situations where users exhibit emotional reactions during the purchasing or learning process, a lack of appropriate feedback and suggestions can impair efficient decision-making and motivation to continue learning. Solving this problem is crucial.

[0623] 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.

[0624] In this invention, the server includes means for collecting user activity information, means for analyzing the activity information to generate an individualized learning plan, and means for distributing educational materials based on the generated individualized learning plan. This enables the analysis of the user's behavioral history and emotional state, and the recommendation of personalized content based on this analysis.

[0625] "Learner activity information" refers to information about learners' behavioral history, such as answering questions, watching videos, and showing interest in various topics.

[0626] An "individualized learning plan" is a plan that proposes the most suitable learning methods and content for each individual learner based on their activity information.

[0627] "Educational materials" is a general term for educational content such as textbooks and assignments provided to learners.

[0628] "Learner responses" refer to the feedback, emotions, and other reactions that learners show to educational materials.

[0629] "Visualization" is a technique that makes information easier to understand intuitively by displaying learning progress visually, such as in graphs or charts.

[0630] "User emotions" refers to the psychological state or reaction that a user exhibits in response to specific content or situations.

[0631] "Recommending relevant information" refers to the act of presenting more relevant products, services, or learning content based on the user's activity information and emotions.

[0632] In this embodiment of the invention, the program is primarily executed by a server and a terminal. The server collects user activity information and analyzes it using a generative AI model. This generates a personalized learning plan suitable for the user. Based on this personalized learning plan, the terminal delivers specific educational materials to the user.

[0633] Furthermore, this system incorporates an emotion engine that evaluates the user's emotional state using facial expression and speech data acquired through the user's device. This emotion data is sent to a server and reflected in individual learning strategies and content recommendations. For example, if a positive emotion is detected towards a product or service that the user has shown interest in, highly relevant products will be recommended, potentially increasing their purchase intent.

[0634] For example, if a user begins to lose focus while watching a particular educational video, the server detects this state through analysis by the emotion engine and provides new videos or interactive content to rekindle their interest. This allows the user to continue learning effectively.

[0635] The generative AI model plays a crucial role throughout these processes, generating prompts tailored to individual user needs based on insights gained from data analysis. An example of such a prompt might be: "The user has stayed on the product details page for 5 minutes and is showing positive emotions. Suggest related products or offers." This optimizes the user experience.

[0636] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0637] Step 1:

[0638] The server retrieves user activity information. This information includes answer history, viewing patterns, and interests. The activity information is sent to the server and stored in a database. This serves as input data for subsequent analysis.

[0639] Step 2:

[0640] The server analyzes activity information collected using a generative AI model. This analysis generates an optimized individual learning strategy for each user. Pattern recognition and machine learning algorithms are used in the analysis, and the output determines the selection of learning materials and the learning order.

[0641] Step 3:

[0642] Based on the generated individual learning plan, the server delivers specific educational materials to the terminal. These materials are then presented to the user on the terminal, initiating interactive learning activities. The input is the learning plan, and the output is the display of learning materials to the user.

[0643] Step 4:

[0644] The device collects user response information. The emotion engine evaluates the user's feedback and emotional state during their learning activities and sends the results to the server. This response information is then used to adjust individual learning strategies.

[0645] Step 5:

[0646] The server dynamically adjusts the individual learning strategy based on the received response information. Specifically, it enhances content in areas where the user shows interest and adds supplementary information to areas where understanding is insufficient. The input is response information, and the updated learning strategy is delivered to the terminal as output.

[0647] Step 6:

[0648] The server and terminal work together to visualize learning progress, clearly showing the user their current learning status. Graphs and charts are used for this visualization, allowing users to track their progress. The input for the visualization is the learning data and its results, while the output is a visually displayed learning interface.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] [Fourth Embodiment]

[0653] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0654] 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.

[0655] 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).

[0656] 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.

[0657] 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.

[0658] 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).

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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".

[0666] This invention is a system for providing optimized education tailored to the characteristics of learners. The system is primarily built around three components: a server, a terminal, and a user, each playing the following roles.

[0667] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests. By analyzing this data, the server evaluates the learner's aptitude and proficiency. Generative AI models are used for the analysis, enabling advanced data analysis.

[0668] Based on the analysis results, the server automatically generates an optimized, personalized learning plan for each user. This plan includes selecting content suitable for the learner, adjusting the difficulty level according to their progress, and even recommending learning paths. For example, a learner aiming to improve their English skills will be provided with a curriculum that balances listening and speaking.

[0669] The generated individual learning plan is delivered to the device by the server. The device then presents interactive learning content to the user according to this learning plan. Through their device, users engage in various learning activities, such as watching videos, answering questions, and practicing simulations. This makes learning more proactive and effective.

[0670] The device then collects user feedback and sends it to the server. This feedback includes the user's answers and reactions to the learning content. The server uses this feedback to dynamically adjust the learning plan using a generative AI model. For example, if a large number of incorrect answers occur on a particular topic, additional materials to reinforce that topic will be incorporated into the plan.

[0671] As a final step, the server visualizes the user's learning progress. This visualization uses graphs and charts to show the progress, allowing the user to check their current level of achievement. This makes it easy for users to understand the effectiveness of their learning, improve their motivation, and identify areas for improvement.

[0672] In this way, the present invention provides learners with an individually optimized learning experience, realizing a system that improves learning efficiency and the quality of education.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] The user logs into the learning portal using an iPad. Upon login, a request is sent from the device to the server to access the user's past learning data.

[0676] Step 2:

[0677] The server retrieves the user's past learning activity data from the database. This data includes answer history, viewing history, and tag information that reflects the user's interests.

[0678] Step 3:

[0679] The server inputs activity data into a generating AI model and begins analyzing the data. The model then analyzes the user's strengths, weaknesses, and learning tendencies in detail.

[0680] Step 4:

[0681] The generating AI model creates an optimal, personalized learning plan for the user based on the analysis results. This plan includes recommended learning materials, learning order, and learning goals.

[0682] Step 5:

[0683] The server sends the generated individual learning plan to the device. The device then prepares to provide the user with appropriate learning content according to the plan.

[0684] Step 6:

[0685] Users learn using the provided learning content. This includes watching videos, practicing problems, and experiencing simulations.

[0686] Step 7:

[0687] The device continuously records the user's learning activity data, including the user's answer results, viewing time, and operation history.

[0688] Step 8:

[0689] The device sends the recorded feedback data to the server. This feedback is important data that indicates the level of understanding and response to the learned material.

[0690] Step 9:

[0691] The server analyzes the feedback received and dynamically adjusts the learning plan. This includes revising the plan and recommending new content.

[0692] Step 10:

[0693] The server sends the adjusted learning plan back to the device. Based on the updated plan, the device presents the learner with the next learning step.

[0694] Step 11:

[0695] The server ultimately visualizes the user's learning progress using graphs and charts and displays them on the device. Users can check their own progress and feel the effectiveness of their learning.

[0696] (Example 1)

[0697] 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".

[0698] Traditional teaching methods make it difficult to provide optimal education tailored to the individual characteristics and proficiency levels of each learner. This results in learners being unable to learn effectively at their own pace, hindering improvements in the quality of education. Furthermore, insufficient tracking of learning progress makes it difficult for learners to perceive their own growth, which is another challenge.

[0699] 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.

[0700] In this invention, the server includes means for collecting learner activity information, means for using a generative artificial intelligence model to analyze the activity information and generate an individualized education plan suitable for the learner, and means for delivering educational content based on the generated individualized education plan. This makes it possible to provide effective individualized education tailored to the characteristics of each learner and to accurately grasp their learning progress.

[0701] "Learner activity information" refers to data generated when learners engage in educational activities, including answer history, viewing patterns, interests, and other relevant information.

[0702] A "generative artificial intelligence model" is a model that utilizes advanced artificial intelligence technology to analyze learner activity information and generate appropriate educational plans.

[0703] An "individualized education plan" is a plan designed to provide educational content optimized for each learner's individual characteristics and proficiency level.

[0704] "Educational content" refers to the materials and teaching methods that learners actually use to study, and includes information such as videos, textbooks, and practice problems.

[0705] A "server" is a computer system that plays a central role in a learning system, managing data collection, analysis, creation of educational plans, and distribution of educational content.

[0706] "Visual presentation" refers to a method of displaying information using images and diagrams to effectively communicate progress and results to learners.

[0707] This invention is a system that provides personalized education optimized for each learner. The system mainly consists of three elements: a server, a terminal, and a user, each playing a specific role.

[0708] The server first collects learner activity information. This information includes data such as the learner's answer history, viewing patterns, and interests. To collect this data, the server has functions to manage user behavior on the online learning platform.

[0709] The collected data is analyzed on the server using a generated artificial intelligence model. A machine learning algorithm is a possible AI model used to evaluate the learner's proficiency and interests. During program execution, prompts such as "Identify the user's weak areas based on past answer history" can be used.

[0710] Based on the analysis results, the server generates an individualized learning plan. This plan is tailored to the learner's characteristics and includes details such as, "This user needs intermediate-level listening skills, so we will focus on delivering listening materials next week."

[0711] The generated educational plan is delivered from the server to the terminal. The terminal has the functionality to interactively present various educational content to the user, such as videos, text, and practice problems. This allows the user to learn at their own pace.

[0712] The device also collects feedback information on the user's answers and activities. Sending this information to the server allows for dynamic adjustments to the educational plan. For example, a prompt such as, "Provide additional practice exercises on topics the user is struggling with," can be used to determine specific strategies.

[0713] Furthermore, the server visually presents and provides the user with learning progress. At this stage, the data is visualized as graphs and charts, designed so that the user can understand their progress at a glance.

[0714] In this way, the system can provide learners with an individually optimized learning experience, thereby improving the quality of education.

[0715] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0716] Step 1:

[0717] The server collects user activity information. It receives, as input, data such as user responses, viewing history, and interest-based data submitted via the user's device. Specifically, the server automatically logs this data and continuously updates it. As output, the collected activity information is used for analysis in the next step.

[0718] Step 2:

[0719] The server uses a generative artificial intelligence model to analyze the collected activity information. Data such as answer history and viewing patterns are supplied to the AI ​​model as input. Specifically, the prompt "Identify the user's weak areas based on past answer history" is input to the AI ​​model, and the user's learning tendencies are analyzed. As output, evaluation data regarding the user's aptitude and proficiency level is generated.

[0720] Step 3:

[0721] The server generates individualized learning plans based on the analyzed data. The evaluation data obtained in the previous step is used as input. Specifically, it utilizes a generative AI model to create plans such as, "For this user, please select learning materials to focus on next week to improve their listening skills." The output is an optimized individualized learning plan for each learner.

[0722] Step 4:

[0723] The server delivers the generated individualized learning plan to the terminal. The generated learning plan is provided as input. Specifically, the terminal prepares to interactively display learning materials (videos and practice problems) based on the learning plan. As output, the appropriate educational content is delivered to the user's terminal.

[0724] Step 5:

[0725] The device collects user feedback. It receives user responses and reactions to learning materials as input. Specifically, the device records correct / incorrect answer data and survey results after problem completion. The feedback data is sent to the server as output.

[0726] Step 6:

[0727] The server analyzes feedback from the terminal and dynamically adjusts the educational plan. Feedback data is supplied to the AI ​​model as input. Specifically, the model uses adjustment prompts such as, "Please provide additional practice exercises on topics the user is struggling with." An updated individualized educational plan is created as output.

[0728] Step 7:

[0729] The server visualizes and provides learning progress. As input, it aggregates and uses user learning result data. Specifically, it creates graphs and charts showing progress and displays them on the user's device in an easy-to-understand format. As output, it provides visual information to help the user understand their learning achievements and challenges.

[0730] (Application Example 1)

[0731] 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".

[0732] There is a need to efficiently provide educational content optimized based on the individual characteristics of learners and to realize a learning experience that matches the learner's level of understanding and progress. However, conventional systems have the challenge of not being able to quickly select appropriate content and dynamically adjust plans, making it difficult to provide an optimal educational experience for each learner.

[0733] 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.

[0734] In this invention, the server includes a device for collecting learner activity information, a device for analyzing the activity information to generate an individualized learning plan suitable for the learner, and a device for delivering educational content based on the generated individualized learning plan. This makes it possible to effectively provide individually optimized educational content according to the learner's characteristics and progress.

[0735] A "learner" refers to a user whose purpose is to acquire educational content and knowledge.

[0736] "Activity information" refers to a collection of information related to learning activities, including data such as learners' answer history, viewing behavior, and areas of interest.

[0737] An "individualized learning plan" is a plan of educational activities that is optimized and provided individually according to the learner's characteristics and progress.

[0738] "Educational content" refers to information that includes various learning resources provided to learners, such as textbooks, practice problems, and audiovisual content.

[0739] "Opinions" refer to feedback information that shows evaluations and reactions regarding learners' learning experiences.

[0740] "Learning progress" refers to the level of progress a learner has made through educational activities.

[0741] An "AI model" is a model that represents artificial intelligence technology used for data analysis and optimizing learning plans.

[0742] "Figures and tables" are graphical display formats used to visually represent data and information.

[0743] This invention includes a system that comprises a series of processes for collecting and analyzing learner activity information, generating individualized learning plans, and delivering educational content, in order to provide learners with an optimized educational experience. It is primarily composed of three components: a server, a terminal, and a user.

[0744] The server plays a crucial role in efficiently collecting learner activity information. This information includes learners' response history, viewing behavior, and areas of interest. This information is stored on the server and used for analysis. The server utilizes a generative AI model to analyze the activity information in an advanced manner, assessing learners' proficiency and interests, and automatically generating personalized learning plans. In this analysis process, the AI ​​model plays a central role in understanding data trends.

[0745] The generated individualized learning plan is delivered to the device. The device then presents the learner with interactive educational content based on this plan. Specifically, this includes playing video content, presenting practice problems, and providing simulations. This allows users to learn at their own pace and independently.

[0746] User feedback is sent to the server via the device. By receiving this feedback, the server dynamically adjusts the learning plan in real time. This process improves the quality of the educational experience, enabling a rapid response to learner needs. Learning progress is visualized using charts and graphs, allowing learners to intuitively understand their own progress.

[0747] For example, if a learner wishes to learn the basics of chemistry, the server can provide an optimized introductory chemistry course based on activity information it has collected. The content provided is automatically adjusted according to the learner's interests and level of understanding. For instance, based on a prompt such as, "Please provide a video that clearly explains the basics of chemistry," suitable materials will be suggested.

[0748] In this way, the interaction between the server, terminal, and user makes it possible to provide an optimized educational experience for each individual learner.

[0749] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0750] Step 1:

[0751] The server collects learner activity information. Its inputs include learner response history, viewing behavior, and interest data. Its output is stored in a centrally managed database. Specifically, it uses an API to periodically retrieve data from the device, organize it, and store it.

[0752] Step 2:

[0753] The server analyzes activity information using a generative AI model. The activity data collected in Step 1 is used as input. The analysis evaluates the learner's proficiency level and areas of interest. As output, an individualized learning plan is generated for each learner. Specifically, the AI ​​model is given analysis instructions using prompts, and the basic structure of the learning plan is created based on the results.

[0754] Step 3:

[0755] The generated individual learning plan is delivered from the server to the terminal. The learning plan generated in step 2 is used as input. The educational content based on this plan is displayed on the terminal as output. Specifically, the learning plan data is sent to the terminal using network communication, and the terminal interprets it and displays it in the user interface.

[0756] Step 4:

[0757] The device presents interactive educational content to the user. It uses learning plan data delivered from a server as input. The output is educational content displayed on the user's device. Specific actions include controlling video playback, presenting interactive exercises, and providing a feedback screen.

[0758] Step 5:

[0759] Users provide feedback on their learning through a device. Input includes their answers and reactions to their learning experience. Output is the transmission of this feedback information to the server. Specific actions include filling out survey forms and selecting answers.

[0760] Step 6:

[0761] The server dynamically adjusts the learning plan based on the feedback information. It uses the feedback data received in step 5 as input. A new learning plan is generated as output. Specifically, it analyzes the feedback and uses an AI model to adjust the learning plan. For example, it might incorporate additional practice questions for topics where the user frequently makes mistakes.

[0762] Step 7:

[0763] The server generates materials that visualize the learner's learning progress. It takes learning progress data as input and creates progress reports for learners in chart and graph format as output. Specifically, it uses data visualization tools to format the data so that learners can check their own progress.

[0764] 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.

[0765] This invention is a system for providing optimized education tailored to the characteristics and emotional state of learners. The system consists of four components: a server, a terminal, a user, and an emotion engine, each playing the following roles.

[0766] The server first collects learner activity data. This data includes the user's answer history, viewing patterns, interests, etc., and records the learner's behavior and progress in detail. The collected data is then analyzed by a generative AI model to generate a personalized learning plan suitable for the learner.

[0767] In addition, this system includes an emotion engine that recognizes the user's emotions. The emotion engine evaluates the user's emotional state through facial recognition and voice analysis. Furthermore, it also uses data from biosensors for emotion recognition, achieving highly accurate emotion analysis. The server incorporates this emotion data into the analysis results and generates an individualized learning plan that takes emotions into account. For example, if the emotion engine detects that the learner is lacking concentration, the server adjusts the learning plan, prioritizing the display of content that will interest the user or presenting tasks that can be completed in a short time.

[0768] The generated learning plan is delivered to the device and provided to the user. Based on the individual learning plan, the device provides the user with video viewing, problem solving, and interactive simulation experiences. During learning, the device continuously records the user's feedback and emotional changes and sends them to the server.

[0769] The server dynamically adjusts the learning plan based on the feedback and sentiment data it receives. For example, if a user's sentiment towards a particular piece of content is positive, it might add related learning materials for that content. Conversely, if a user is frustrated with a particular issue, it might provide supplementary information or explanations from different angles to delve deeper into that issue.

[0770] Ultimately, the server visualizes the user's learning progress and displays it on the terminal. This progress display uses graphs and charts, allowing users to see their own achievements and changes in their emotions. Through this feature, learners can objectively understand their learning status, which motivates them to continue learning.

[0771] Based on the above, the present invention provides a system that offers a learning experience individually optimized from both the behavioral and emotional perspectives of learners, aiming to realize efficient and effective education.

[0772] The following describes the processing flow.

[0773] Step 1:

[0774] The user logs in and begins learning. When the user accesses the learning portal on their iPad, the device sends the user's identification information to the server. This is to associate past learning data with the current learning content.

[0775] Step 2:

[0776] The server retrieves the user's past activity data from the database based on the user's identification information sent from the terminal. This data includes answer history, viewing patterns, and existing learning tendencies.

[0777] Step 3:

[0778] The server analyzes past activity data and generates a personalized learning plan based on the user's learning needs. This analysis uses a generative AI model to identify the user's strengths and areas that need improvement.

[0779] Step 4:

[0780] The emotion engine is activated and captures the user's facial expressions and voice through the device. Furthermore, data such as pulse rate and skin reactions are acquired from wearable biosensors. This data is used to evaluate the user's emotional state.

[0781] Step 5:

[0782] The emotion engine analyzes the collected emotional data to identify the user's current emotional state. For example, if a user is feeling stressed, that information is sent to the server.

[0783] Step 6:

[0784] The server combines analysis results with emotional data to adapt individual learning plans to the user's emotions. The order of content and the materials presented are adjusted according to the user's emotional state.

[0785] Step 7:

[0786] A customized learning plan is sent to the device and displayed to the user. The user receives learning content such as videos, interactive exercises, and simulations.

[0787] Step 8:

[0788] The device continuously records the user's reactions and emotional changes during learning. This includes, for example, changes in facial expressions and answer results during the learning process.

[0789] Step 9:

[0790] The device sends feedback and sentiment data to the server. The server receives this data and analyzes it to incorporate it into the next learning plan.

[0791] Step 10:

[0792] The server visualizes learning progress data and sends visually represented graphs and charts to the user's device. Users can then check their learning achievements and emotional changes on a dashboard.

[0793] These steps enable a system where servers, terminals, users, and the emotion engine work together to provide a learning experience optimized for the learner.

[0794] (Example 2)

[0795] 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".

[0796] Traditional education systems often fail to adequately analyze learners' progress and activity data, making it difficult to provide individually optimized learning experiences. Furthermore, the lack of dynamic adjustments to learning plans that take learners' emotions into account can lead to decreased learning efficiency and motivation.

[0797] 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.

[0798] In this invention, the server includes means for collecting learner activity data, means for analyzing the data with a generative AI model to generate an individualized learning plan, and means for evaluating emotional states using facial recognition, voice analysis, and biosensors. This makes it possible to generate and provide an optimized individualized learning plan based on the individual characteristics and emotional states of each learner.

[0799] A "learner" refers to an individual who engages in learning activities using educational systems and materials.

[0800] "Activity data" refers to information about learners' behavior and performance, such as their answer history, viewing patterns, and interests.

[0801] A "generative AI model" refers to an artificial intelligence algorithm that analyzes collected data and generates a learning plan suitable for the learner.

[0802] An "individualized learning plan" refers to a learning curriculum and content optimized according to the learner's characteristics and progress.

[0803] "Emotional state" refers to the psychological and emotional state of a learner, assessed using information from their facial expressions, voice, and biosensors.

[0804] "Feedback" refers to reactions and comments on the learning experience provided by learners, and is used to improve the system.

[0805] "Learning progress" refers to information that indicates the degree to which a learner has progressed in learning and their level of understanding.

[0806] "Visual representation" refers to techniques that use graphs, charts, and other visual aids to present information in a way that can be understood by looking at it.

[0807] This invention is a system that provides education optimized according to the learner's characteristics and emotional state. The system mainly consists of four components: a server, a terminal, a user, and an emotion engine.

[0808] The server first collects learner activity data. This activity data includes the user's answer history, viewing patterns, and interests, allowing for a detailed understanding of the learner's behavior and progress. The collected data is analyzed by a generative AI model, which generates a personalized learning plan tailored to each learner. This AI model learns from large amounts of data and proposes learning plans quickly and accurately.

[0809] The emotion engine applies facial recognition and voice analysis technologies to assess the user's emotional state. Furthermore, it incorporates data from biosensors to enable more accurate emotion analysis. This allows the server to generate personalized learning plans that take the learner's emotions into account. For example, if a learner is lacking focus, the server adjusts the learning plan, providing content that engages the user and tasks that can be completed in a short amount of time.

[0810] The generated learning plan is provided to the user via the device. Based on the individual learning plan, the device provides the user with video viewing, problem-solving, and interactive simulation experiences. During learning, the device collects the user's reactions and feedback and sends the results to the server.

[0811] The server can dynamically rethink the learning plan based on feedback and sentiment data received from the device. If a user's sentiment towards a particular piece of content is positive, it will provide further related learning materials. Conversely, if a user is frustrated with a particular issue, it will provide supplementary information or explanations from different perspectives to help resolve that issue.

[0812] Ultimately, the server visualizes the learner's learning progress and displays it on the terminal. This visualization uses line graphs, bar graphs, and other methods, allowing users to check their achievements and changes in their emotions. This enables learners to objectively evaluate their learning status and motivates them to continue learning.

[0813] An example of a prompt statement is, "The user appears to have lost interest while learning calculus. What content or methods would you suggest to improve the user's engagement?" Using this prompt statement, the AI ​​model can suggest appropriate adjustments to the learning plan.

[0814] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0815] Step 1:

[0816] The server collects user activity data. Specifically, it retrieves digital information such as answer history, viewing patterns, and interests from various sensors and logs. This input data provides a detailed representation of the user's learning progress. The server organizes and stores this data, preparing it for the next analysis step.

[0817] Step 2:

[0818] The server analyzes the collected activity data using a generating AI model. By supplying the activity data obtained as input to the AI ​​model, the model extracts learner tendencies and learning progress from the data. As output, a personalized learning plan tailored to the learner's characteristics is generated. Specifically, the learning plan is customized based on information about which areas the learner is particularly strong in or interested in.

[0819] Step 3:

[0820] The server evaluates the user's emotional state using an emotion engine. This emotion engine utilizes facial recognition and voice analysis technologies, and also uses data from biosensors as input for analysis. This quantifies the user's mental state and adds it to the server's analysis process. This output leads to the adjustment of a personalized learning plan that takes emotions into account.

[0821] Step 4:

[0822] The server integrates analyzed sentiment and activity data to generate a learning plan that takes emotions into account. Based on the results of the sentiment analysis, it selects prompts and content that will help the user learn more effectively and adjusts the learning plan accordingly. As an output, an optimized learning plan is established.

[0823] Step 5:

[0824] The device receives a personalized learning plan sent from the server. Based on this input data, the device builds a platform that provides user-friendly video viewing, problem-solving, and interactive simulations. This output provides information that supports the user's specific learning actions on their device.

[0825] Step 6:

[0826] The device records user feedback and emotional changes during learning. Specifically, it collects logs such as which content the user is interested in and which problems they found difficult. This input data is sent to a server and used to adjust the next learning plan.

[0827] Step 7:

[0828] The server dynamically adjusts the learning plan based on the feedback and sentiment data received. It analyzes user reactions, adding relevant materials if there is a positive sentiment towards specific content, and providing supplementary materials if there is frustration. As an output, the deactivation plan, which will be applied to the next learning cycle, is updated.

[0829] Step 8:

[0830] The server visualizes the user's learning progress and displays it on the terminal. Based on the input data of the learning results, it outputs them in an easy-to-understand format as graphs and charts. This allows users to see at a glance what results their efforts are producing and helps them determine the direction of their future learning.

[0831] (Application Example 2)

[0832] 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".

[0833] In online learning and e-commerce, offering uniform content without considering the individual characteristics and emotions of users can decrease user satisfaction. In particular, in situations where users exhibit emotional reactions during the purchasing or learning process, a lack of appropriate feedback and suggestions can impair efficient decision-making and motivation to continue learning. Solving this problem is crucial.

[0834] 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.

[0835] In this invention, the server includes means for collecting user activity information, means for analyzing the activity information to generate an individualized learning plan, and means for distributing educational materials based on the generated individualized learning plan. This enables the analysis of the user's behavioral history and emotional state, and the recommendation of personalized content based on this analysis.

[0836] "Learner activity information" refers to information about learners' behavioral history, such as answering questions, watching videos, and showing interest in various topics.

[0837] An "individualized learning plan" is a plan that proposes the most suitable learning methods and content for each individual learner based on their activity information.

[0838] "Educational materials" is a general term for educational content such as textbooks and assignments provided to learners.

[0839] "Learner responses" refer to the feedback, emotions, and other reactions that learners show to educational materials.

[0840] "Visualization" is a technique that makes information easier to understand intuitively by displaying learning progress visually, such as in graphs or charts.

[0841] "User emotions" refers to the psychological state or reaction that a user exhibits in response to specific content or situations.

[0842] "Recommending relevant information" refers to the act of presenting more relevant products, services, or learning content based on the user's activity information and emotions.

[0843] In this embodiment of the invention, the program is primarily executed by a server and a terminal. The server collects user activity information and analyzes it using a generative AI model. This generates a personalized learning plan suitable for the user. Based on this personalized learning plan, the terminal delivers specific educational materials to the user.

[0844] Furthermore, this system incorporates an emotion engine that evaluates the user's emotional state using facial expression and speech data acquired through the user's device. This emotion data is sent to a server and reflected in individual learning strategies and content recommendations. For example, if a positive emotion is detected towards a product or service that the user has shown interest in, highly relevant products will be recommended, potentially increasing their purchase intent.

[0845] For example, if a user begins to lose focus while watching a particular educational video, the server detects this state through analysis by the emotion engine and provides new videos or interactive content to rekindle their interest. This allows the user to continue learning effectively.

[0846] The generative AI model plays a crucial role throughout these processes, generating prompts tailored to individual user needs based on insights gained from data analysis. An example of such a prompt might be: "The user has stayed on the product details page for 5 minutes and is showing positive emotions. Suggest related products or offers." This optimizes the user experience.

[0847] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0848] Step 1:

[0849] The server retrieves user activity information. This information includes answer history, viewing patterns, and interests. The activity information is sent to the server and stored in a database. This serves as input data for subsequent analysis.

[0850] Step 2:

[0851] The server analyzes activity information collected using a generative AI model. This analysis generates an optimized individual learning strategy for each user. Pattern recognition and machine learning algorithms are used in the analysis, and the output determines the selection of learning materials and the learning order.

[0852] Step 3:

[0853] Based on the generated individual learning plan, the server delivers specific educational materials to the terminal. These materials are then presented to the user on the terminal, initiating interactive learning activities. The input is the learning plan, and the output is the display of learning materials to the user.

[0854] Step 4:

[0855] The device collects user response information. The emotion engine evaluates the user's feedback and emotional state during their learning activities and sends the results to the server. This response information is then used to adjust individual learning strategies.

[0856] Step 5:

[0857] The server dynamically adjusts the individual learning strategy based on the received response information. Specifically, it enhances content in areas where the user shows interest and adds supplementary information to areas where understanding is insufficient. The input is response information, and the updated learning strategy is delivered to the terminal as output.

[0858] Step 6:

[0859] The server and terminal work together to visualize learning progress, clearly showing the user their current learning status. Graphs and charts are used for this visualization, allowing users to track their progress. The input for the visualization is the learning data and its results, while the output is a visually displayed learning interface.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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."

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] The following is further disclosed regarding the embodiments described above.

[0882] (Claim 1)

[0883] Means for collecting learner activity data,

[0884] A means for analyzing the aforementioned activity data to generate an individualized learning plan suitable for the learner,

[0885] A means of delivering learning content based on the generated individual learning plan,

[0886] A means of collecting learner feedback and dynamically adjusting the learning plan,

[0887] A means of visualizing and providing learning progress to learners,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, characterized in that the activity data includes the learner's answer history, viewing patterns, and interests.

[0891] (Claim 3)

[0892] The system according to claim 1, characterized in that the visualization of learning progress uses a visual display including graphs and charts.

[0893] "Example 1"

[0894] (Claim 1)

[0895] Means for collecting learner activity information,

[0896] A means for generating an individualized education plan suitable for learners by using a generative artificial intelligence model to analyze the aforementioned activity information,

[0897] A means of delivering educational content based on the generated individualized education plan,

[0898] A means of collecting learner response information and dynamically adjusting the educational plan,

[0899] A means of visually presenting learning progress,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, characterized in that the activity information includes the learner's answer history, viewing patterns, and interests.

[0903] (Claim 3)

[0904] The system according to claim 1, characterized in that the visual presentation of the learning progress uses images and charts.

[0905] "Application Example 1"

[0906] (Claim 1)

[0907] A device for collecting learner activity information,

[0908] A device that analyzes the aforementioned activity information and generates an individualized learning plan suitable for the learner,

[0909] A device that delivers educational content based on the generated individual learning plan,

[0910] A device that collects learners' opinions and dynamically adjusts the learning plan,

[0911] A device that visualizes learning progress and provides it to learners,

[0912] A device that selects and provides individually optimized educational content based on the learner's learning history and interest information,

[0913] A device that dynamically modifies educational content based on analysis results using an AI model,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, characterized in that the activity information includes the learner's answer history, viewing patterns, and areas of interest.

[0917] (Claim 3)

[0918] The system according to claim 1, characterized in that the visualization of learning progress uses a visual display including figures and tables.

[0919] "Example 2 of combining an emotion engine"

[0920] (Claim 1)

[0921] Means for collecting learner activity data,

[0922] A means for analyzing the aforementioned activity data with a generating AI model and generating an individualized learning plan suitable for the learner,

[0923] A means for evaluating a learner's emotional state using facial recognition, voice analysis, and biosensors,

[0924] A means for reflecting the aforementioned emotional data in the analysis results and generating an individualized learning plan that takes emotions into account,

[0925] A means of delivering learning content based on the generated individual learning plan,

[0926] A means of collecting learner feedback and changes in emotional state, and dynamically adjusting the learning plan,

[0927] A means of visualizing and providing learning progress to learners,

[0928] A system that includes this.

[0929] (Claim 2)

[0930] The system according to claim 1, characterized in that the activity data includes the learner's answer history, viewing patterns, and interests.

[0931] (Claim 3)

[0932] The system according to claim 1, characterized in that the visualization of learning progress uses a visual display including graphs and charts.

[0933] "Application example 2 when combining with an emotional engine"

[0934] (Claim 1)

[0935] Means for collecting learner activity information,

[0936] A means for analyzing the aforementioned activity information to generate an individualized learning plan suitable for the learner,

[0937] A means of distributing educational materials based on the generated individual learning plan,

[0938] A means of collecting learner responses and dynamically adjusting the learning strategy,

[0939] A means of visualizing and providing learning progress to learners,

[0940] A means of analyzing the user's emotions and recommending relevant information based on the analysis results,

[0941] A system that includes this.

[0942] (Claim 2)

[0943] The system according to claim 1, characterized in that the activity information includes the learner's answer history, viewing patterns, and interests.

[0944] (Claim 3)

[0945] The system according to claim 1, characterized in that the visualization of learning progress uses a visual display including graphs and charts. [Explanation of symbols]

[0946] 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. Means for collecting learner activity data, A means for analyzing the aforementioned activity data to generate an individualized learning plan suitable for the learner, A means of delivering learning content based on the generated individual learning plan, A means of collecting learner feedback and dynamically adjusting the learning plan, A means of visualizing and providing learning progress to learners, A system that includes this.

2. The system according to claim 1, characterized in that the activity data includes the learner's answer history, viewing patterns, and interests.

3. The system according to claim 1, characterized in that the visualization of learning progress uses a visual display including graphs and charts.

Images