system

Abstract

We provide the system. [Solution] Means for collecting and integrating educational content, A means of training a generative AI model based on collected content, A means of suggesting optimal learning content based on the user's learning needs, A means of collecting feedback after the user has learned, A means of providing incentives to educators based on the aforementioned feedback, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern educational environment, there is a problem that the amount of information has increased too much and it is difficult to efficiently find appropriate learning content. Also, the number of teachers has decreased and educational resources and methods have not been fully utilized, so it is difficult to provide educational means optimized for individual learners. Furthermore, creating an educational curriculum according to regions and cultures has also become complicated. Against this background, there is a need for a system that enables learning according to the needs of individual learners and provides legitimate incentives to participants in education.

Means for Solving the Problems

[0005] To address the above challenges, the present invention employs a system that collects and integrates educational content and trains a generative AI model based on the collected content. This system has the function of analyzing the user's learning needs and suggesting optimal learning content. Furthermore, by collecting feedback after the user's learning, it forms a feedback loop that improves learning effectiveness. In addition, by providing incentives to educators based on the feedback, it aims to improve the overall quality of education and increase the motivation of those involved. This enables the provision of education adapted to local and cultural contexts, enhances the quality of education, and allows for appropriate compensation for all stakeholders involved in education.

[0006] "Educational content" refers to teaching materials, lecture materials, and related knowledge and information used for various educational purposes.

[0007] A "generative AI model" refers to an artificial intelligence algorithm that learns from large amounts of data and generates new data and content.

[0008] "User" refers to an individual or group that uses this system to engage in learning activities.

[0009] "Learning needs" refer to the learning goals and objectives that a user wishes to achieve, as well as any specific educational requirements associated with them.

[0010] "Feedback" refers to the act of providing evaluations, opinions, and information for improvement regarding learning outcomes.

[0011] An "incentive" refers to a reward or benefit given to encourage a particular behavior.

[0012] "Education-related personnel" refers to teachers, material providers, educational institutions, and others who are directly or indirectly involved in education.

[0013] "Region" refers to a specific geographical area and its culture and social characteristics.

[0014] "Culture" refers to the lifestyle, values, and customs established by a particular group or society. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0016] 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.

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

[0018] In the following embodiments, a processor with a reference numeral (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.

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

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

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] The present invention is implemented as a system that efficiently collects and integrates educational content and utilizes a generative AI model to provide customized learning based on learning needs. The embodiments thereof are described below with specific examples.

[0037] Data collection and integration

[0038] The server collects course content accessible from multiple educational platforms via the internet. This content is provided in text, audio, and video formats. The server manages the metadata of this content and integrates it into appropriate databases through advanced filtering.

[0039] Training of Generative AI Models

[0040] Based on the collected data, the server trains a generative AI model. This model has the ability to generate optimal learning materials tailored to user needs, encompassing a wide range of learning content including mathematics, science, and language learning. The thus trained model can accommodate learners from different regions and cultural backgrounds.

[0041] User profile creation and content suggestion

[0042] The device requires user information to be entered during initial setup. This includes the learner's age, areas of interest, and learning goals. This information is sent to the server, where a user profile is created. Based on this profile, the server uses a generative AI model to suggest the most suitable learning content for the user.

[0043] As a concrete example, consider an English learning program customized for elementary school students. In this case, the server generates animated learning materials that focus on English conversation practice and creates an efficient learning package that includes related practice exercises. This provides learners with content that is easy to see and enjoyable to learn from.

[0044] Utilizing learning history and feedback

[0045] Users learn using the provided content. After completing their learning, they can provide feedback via their device. This feedback is sent to the server and used to create and suggest future content. This enables flexible education that responds to the changing needs of learners.

[0046] The server provides incentives to educators based on the feedback information it collects. This mechanism increases the motivation to provide better content, thereby improving the overall quality of education.

[0047] These processes in the present invention enable the provision of customized education tailored to individual learning needs and are key to accommodating diverse learners.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The server collects lesson content from the educational platform. This involves using an API to retrieve data and adding metadata such as content tags and category information (e.g., subject and target age).

[0051] Step 2:

[0052] The server integrates the collected content into a database. The database is designed to allow for efficient data retrieval and searching.

[0053] Step 3:

[0054] The server trains a generative AI model using integrated data from the database. This AI model improves its ability to extract features from different data formats (text, audio, video) and generate optimized training content.

[0055] Step 4:

[0056] The device collects information from the user during initial setup. Specifically, it prompts the user to enter information such as their learning objectives, areas of interest, and preferred learning style.

[0057] Step 5:

[0058] The server creates a profile based on user information sent from the terminal. Using this profile, an AI model generates and delivers customized content tailored to the user's needs.

[0059] Step 6:

[0060] Users engage in educational activities using learning content provided via their devices. For example, they can watch video materials or work on practice problems.

[0061] Step 7:

[0062] After completing their learning, users provide feedback through their devices. This feedback concerns the usefulness of the content and the effectiveness of the learning experience.

[0063] Step 8:

[0064] The server collects user feedback and uses it to improve the entire system. Based on this data, the quality of the content provided next time will be improved.

[0065] Step 9:

[0066] The server provides incentives to educators based on the feedback it collects. This feedback loop leads to improvements in the quality of educational content and the provision of better services.

[0067] (Example 1)

[0068] 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."

[0069] In today's educational environment, there is a need to efficiently provide educational content that matches the needs of individual learners. However, existing systems fail to adequately collect content and provide personalized learning experiences, and the use of appropriate feedback to learners is also insufficient. In particular, the automatic generation of learning materials tailored to region and culture is difficult, and there is a lack of appropriate motivation for educators. These problems lead to challenges in the quality of learning and learner satisfaction.

[0070] 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.

[0071] In this invention, the server includes means for aggregating and centralizing educational materials, means for training a generation AI algorithm based on the aggregated materials, and means for suggesting optimal learning materials based on the user's learning needs. This makes it possible to provide customized educational content that utilizes the profile information of individual learners. By managing the metadata of the collected content and efficiently filtering it based on that metadata, appropriate educational materials are automatically suggested, providing a learning experience tailored to each learner. Furthermore, the quality of education can be improved by providing rewards to educators based on evaluation information.

[0072] "Educational materials" is a general term for information and content used for educational purposes, and includes a variety of formats such as text, audio, and video.

[0073] "Aggregation" refers to the process of collecting data from multiple sources and combining them into a single entity.

[0074] "Methods of centralization" refer to methods of integrating collected data and managing it in an organized manner.

[0075] A "generative AI algorithm" is an artificial intelligence technology that generates new information based on data, and is particularly useful for generating educational materials in the field of education.

[0076] "User learning needs" refers to information such as the learning content, goals, and interests that learners desire, and serves as the basis for providing individualized learning experiences based on this information.

[0077] "Metadata" refers to attribute information associated with the data in question, including content category, target audience, difficulty level, etc.

[0078] "Filtering" is a method of selecting data based on certain conditions, and it is a process performed to extract only the information that is relevant to the user.

[0079] "Profile information" refers to personal information such as the user's age, interests, and learning objectives, and is used to design a customized learning experience.

[0080] "Evaluation" refers to feedback that users provide after learning about the content, including their assessment of its effectiveness and satisfaction level.

[0081] "Rewards" refer to incentives provided to educators and content providers as a reward for their achievements and contributions.

[0082] This invention is a system that enables the efficient collection, integration, and generation of educational content, and provides personalized learning utilizing AI (artificial intelligence) models. Specific embodiments of this system are described below.

[0083] Data collection and integration

[0084] The server accesses multiple educational platforms via the internet to collect educational content. This process uses APIs and web scraping techniques to retrieve data in text, audio, and video formats. The collected content, along with metadata, is integrated into a database. For example, the server might collect math content for a specific grade level from educational websites, organize it by category, and create a database.

[0085] Training of Generative AI Models

[0086] The server trains a generative AI model based on learning materials obtained from an integrated database. Here, natural language processing and machine learning techniques are utilized to enable the generative AI model to autonomously create diverse learning content. Using a notebook-type server allows for rapid model training.

[0087] User profile creation and content suggestion

[0088] The terminal allows learners to input necessary personal information through an interface. This information includes the learner's age, desired field of study, and learning goals. This information is sent to a server, from which a user profile is created. The server uses this profile information and a generative AI model to suggest optimal learning content to the learner. An example of a prompt is, "Please create English dialogue practice material for fifth-grade elementary school students."

[0089] For example, in the case of an English learning program for elementary school students, the server generates and provides content that includes animated conversation materials and related practice exercises. This allows learners to receive visually easy-to-understand and enjoyable learning materials.

[0090] Utilizing learning history and feedback

[0091] Users learn through content provided via their devices and provide feedback using their devices after completing their studies. This feedback is sent to the server and used to generate the next learning content. The server has a system in place to reward appropriate educators and motivate them to create better content.

[0092] The objective of this invention is to provide a personalized educational experience and optimize the user's learning environment.

[0093] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0094] Step 1:

[0095] Data collection

[0096] The server accesses educational platforms via the internet. The input consists of API information and HTML structures from each platform. The server then uses APIs and executes web scraping scripts to collect educational content in text, audio, and video formats. The output is datasets in these formats.

[0097] Step 2:

[0098] Content filtering and integration

[0099] Based on the collected data, the server analyzes the metadata of each piece of content. This metadata includes category, difficulty level, and target age group. The server then uses this metadata to perform advanced filtering, selecting only relevant content. Finally, it organizes and integrates the selected content into a database. The output is this integrated database.

[0100] Step 3:

[0101] Training of Generative AI Models

[0102] The server uses educational data extracted from an integrated database. The input consists of digital data converted from text, audio, and video. The server feeds this data to a generative AI model for training, which includes feature extraction and optimization of model parameters. The output is the trained generative AI model.

[0103] Step 4:

[0104] Creating a User Profile

[0105] The terminal receives personal information entered by the user. This information includes the learner's age, areas of interest, and goals. The terminal sends this information to the server and stores it in the database as a user profile. The output is the user's profile information.

[0106] Step 5:

[0107] Suggestions for customized content

[0108] The server uses user profile information and a trained generative AI model. The input consists of profile data and requests to the generative AI model. Based on this, the server generates and selects optimal content tailored to the user's learning needs. The generated prompts are passed to the AI ​​model to obtain individual training materials. The output is customized training content suggested to the user.

[0109] Step 6:

[0110] Utilizing learning history and feedback

[0111] Users learn content provided on their devices and provide feedback during and after the learning process. This feedback data is sent from the device to the server. The input includes evaluations of learning progress, comprehension, and satisfaction. The server stores this data and analyzes it to use in generating future content. The output is improvements to the next learning content based on the analysis results.

[0112] (Application Example 1)

[0113] 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."

[0114] In modern society, providing educational content that meets the diverse needs of learners is crucial. However, traditional methods make it difficult to efficiently deliver optimal educational content to individual learners. In particular, there is a need for real-time customization and the suggestion of appropriate learning paths based on each learner's interests.

[0115] 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.

[0116] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, and means for delivering content to a smartphone according to the user's learning goals and interests. This makes it possible to efficiently and effectively provide educational content tailored to the individual needs of learners.

[0117] "Educational information" is a general term for data and materials used to support learners in acquiring knowledge.

[0118] A "generative AI model" is a type of artificial intelligence that creates new educational content based on collected data.

[0119] "User" refers to an individual or group that receives the educational services provided.

[0120] "Learning objectives" refer to the specific knowledge and skills that learners aim to acquire.

[0121] A "smartphone" is a multi-functional portable information terminal, an electronic device capable of voice calls, messaging, and internet connectivity.

[0122] "Feedback" refers to the act or content of providing evaluations or opinions on a learner's learning experience.

[0123] An "educational expert" refers to an individual or organization that possesses specialized knowledge and skills regarding the content and methods of education.

[0124] "Reward" refers to the economic or other benefits provided for a particular action or outcome.

[0125] "Learning history" refers to a record of past learning activities and is data that shows the learner's progress and acquisition status.

[0126] This invention is an educational content delivery system that adapts to the diverse needs of learners. For its implementation, three main elements—server, terminal, and user—interact with each other.

[0127] The server collects and integrates educational information from multiple educational sources via the internet. The collected information, in various formats including text, audio, and video, is integrated into a database that manages metadata. Based on the collected information, the server trains a generative AI model. This model is designed to generate educational materials tailored to the user's learning needs. Software used includes Python and Tensorflow®.

[0128] A device, such as a smartphone, provides an interface for inputting user information. This information includes learning goals and areas of interest, and is sent to a server. The server generates learning content optimized for the user and delivers it to the device. The delivered content can be viewed on the user's smartphone, and content is provided according to the learner's progress.

[0129] Users progress through their learning using content provided on their devices. After learning, they provide feedback, and the server updates the generated AI model based on the collected feedback, incorporating it into future content suggestions. A system that rewards educational professionals helps improve the quality of education.

[0130] As a concrete example, let's say there is a user who is an intermediate Japanese speaker and wants to learn English. Based on this user's learning goals, the server generates optimal content using a prompt message such as, "Generate English listening materials for intermediate Japanese learners. The target age is 10-12 years old, and the theme is animals." The generated materials are delivered to the user's smartphone and provide interactive videos that contribute to improving listening skills. By utilizing a feedback mechanism that measures performance and rewards educational professionals, the sustainable operation of the entire system becomes possible.

[0131] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0132] Step 1:

[0133] The server collects educational information from multiple educational sources via the internet. It accepts data in various formats, including text, audio, and video, as input. The collected information, along with metadata, is integrated into a database. This creates a large dataset of available educational information.

[0134] Step 2:

[0135] The server trains a generative AI model using the collected data as input. Supervised learning algorithms are used to process the data, extracting and learning features appropriate for each data format. The output of this process is a generative AI model optimized for user needs.

[0136] Step 3:

[0137] Users operating the terminal input their learning goals and areas of interest. This data is sent to the server, which creates a user profile. The creation of this profile allows the server to accumulate data based on each user's needs.

[0138] Step 4:

[0139] The server receives a user profile and a generated AI model as input and uses prompts to generate optimal educational content. Based on these prompts, the AI ​​model outputs the most appropriate educational materials for the user.

[0140] Step 5:

[0141] The generated educational content is delivered to the user's device. For example, English listening comprehension videos are provided to the smartphone. These videos are tailored to the user's learning objectives and are delivered in an interactive format.

[0142] Step 6:

[0143] Users use the content and progress through their learning. After completing their learning, they provide feedback based on their learning experience via their device. This feedback is sent to the server and used as data to improve future content creation.

[0144] Step 7:

[0145] The server generates information to reward education professionals based on the collected feedback. This enables an incentive system aimed at improving performance and content, supporting the overall operation of the system.

[0146] 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.

[0147] The present invention is implemented in a form that combines an emotion engine with a system that collects and integrates educational content and utilizes a generative AI model to provide a customized learning experience tailored to learning needs. Specific embodiments are described below.

[0148] Utilization of data collection and generative AI models

[0149] The server collects lesson content from various educational platforms on the internet. This content is provided in different formats (text, audio, video), integrated, and efficiently stored in a database. The server has the ability to use the collected data to train a generative AI model and generate learning content tailored to the user's learning needs.

[0150] Combination of emotional engines

[0151] This system incorporates an emotion engine that recognizes user emotions in real time. The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and evaluates the user's emotional state during learning. This emotion data is sent to a server and used to improve the learning experience.

[0152] As a concrete example, consider a scenario where a student is using video learning materials for language acquisition. While the user is watching the video, the emotion engine analyzes the user's level of concentration and interest. For example, if the user looks bored, the server immediately detects this and suggests more interactive and engaging materials, or content that encourages a break.

[0153] Utilizing learning history and feedback

[0154] After a learning session, users provide feedback via their device regarding the usefulness and educational effectiveness of the provided content. This feedback is integrated and analyzed by the server and used to improve future content creation and the learning experience.

[0155] Provision of incentives

[0156] The server analyzes user feedback and sentiment data to provide appropriate incentives to educators. This system allows educators to identify areas for improvement in their content and strive to provide better educational resources.

[0157] Thus, this invention is designed as a system that provides users with an optimized learning experience through the customization of educational content, dynamic adjustment based on emotion recognition, and continuous improvement through feedback, while also appropriately evaluating and rewarding the contributions of all stakeholders involved in education.

[0158] The following describes the processing flow.

[0159] Step 1:

[0160] The server collects educational content in various formats (text, audio, video, etc.) from educational platforms and other online resources. The collected data is integrated into a database along with metadata and organized for easy searching.

[0161] Step 2:

[0162] The server uses integrated educational content to train a generative AI model. During this training process, the AI ​​model learns the characteristics of different educational content and acquires the ability to generate and select content that meets the user's learning needs.

[0163] Step 3:

[0164] The device collects initial user information, including age, areas of interest, and learning goals. This information is sent to a server and stored as part of the user's learning profile.

[0165] Step 4:

[0166] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice during learning sessions. It uses the camera and microphone to assess the user's emotional state (e.g., joy, concentration, boredom, etc.) in real time.

[0167] Step 5:

[0168] The server receives data from the emotion engine and dynamically adjusts the learning content based on the user's emotional state. For example, if the user appears to be having difficulty understanding something, it will suggest additional explanatory videos or a different learning approach.

[0169] Step 6:

[0170] Users continue learning using tailored learning content provided by the server. Feedback and sentiment data during learning are continuously collected and reflected in the system in real time.

[0171] Step 7:

[0172] After a learning session ends, users provide feedback on their learning experience via their device. This includes information on content quality, comprehension, and overall satisfaction with the learning experience.

[0173] Step 8:

[0174] The server comprehensively analyzes user feedback and sentiment data to update its database and improve the quality of the next learning session. This process provides a more optimized experience for each individual learner.

[0175] Step 9:

[0176] Ultimately, the server provides educators with feedback-based incentives. These incentives motivate content providers to continuously improve the quality of their content.

[0177] (Example 2)

[0178] 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".

[0179] In today's educational environment, there is a demand for customized educational resources that meet the diverse needs of learners. However, existing systems often fail to reflect individual learners' emotional states and learning tendencies in real time, resulting in uniform education. Furthermore, mechanisms for effectively utilizing learner feedback and providing appropriate rewards to educators are insufficient.

[0180] 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.

[0181] In this invention, the server includes means for collecting and integrating educational information, means for training a machine learning model based on the collected information, and means for recognizing the user's emotional state in real time and providing information according to the learning situation. This enables the provision of educational resources adapted to the individual needs of learners, as well as effective feedback and rewards for educators.

[0182] "Educational information" refers to all forms of data and content provided to learners (e.g., text, audio, video, etc.) that are intended for knowledge acquisition in learning.

[0183] A "machine learning model" is an algorithm that analyzes data, learns patterns, and automatically makes predictions and decisions, and its performance improves with the use of training data.

[0184] "Users" refers to individuals or groups who use the system to access educational information and engage in learning activities.

[0185] "Emotional state" refers to the user's psychological and physiological state at a specific time, and is determined through analysis of facial expressions and voice tone.

[0186] "Rewards" refer to compensation or evaluations provided to educators based on user feedback and system analysis, and are intended to promote quality improvement.

[0187] This invention provides a system for appropriately customizing educational information for each user. Specific embodiments thereof are described below.

[0188] The server scans educational information sources on the internet to collect and integrate various types of information. It utilizes web crawlers and API calls to collect data in multiple formats, including text, audio, and video. This allows a wide range of information to be efficiently stored in a database. The database uses data management systems such as MySQL® or MongoDB.

[0189] Based on this collected data, the server trains a generative AI model. Training utilizes machine learning techniques such as OpenAI's GPT series, learning from large amounts of data. The generated model has the ability to adapt to the user's learning needs and provide appropriate educational resources.

[0190] The device recognizes the user's emotional state in real time. Specifically, it analyzes the user's facial expressions and voice tone using a camera and microphone. This allows it to monitor the user's level of concentration and interest, and send emotional data to the server as needed. This process utilizes libraries such as OpenCV and TensorFlow.

[0191] As a concrete example, consider a situation where a user appears bored while learning a language. In this case, the server inputs a prompt message such as "Generate recommended interactive learning materials for a user who appears bored" into the AI ​​model, providing more appropriate educational resources. By linking the user's emotional state with learning resources in this way, it becomes possible to provide a dynamic learning experience.

[0192] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0193] Step 1:

[0194] The server scans educational platforms on the internet to collect educational information. It uses URLs and API credentials from various educational websites as input and retrieves data in text, audio, and video formats as output. It uses a web crawler to collect data and processes it to integrate data in different formats. This ensures that a wide range of learning content is stored in a unified database format.

[0195] Step 2:

[0196] The server trains machine learning models using information stored in the database. Collected training data is used as input, and a trained generative AI model adapted to the user's learning needs is generated as output. Specifically, the data is divided into appropriate batch sizes, and the model parameters are optimized by applying a learning algorithm.

[0197] Step 3:

[0198] The device monitors the user's emotional state in real time. It acquires video and audio data from devices such as cameras and microphones as input, and analyzes the user's emotional state based on their facial expressions and tone of voice as output. Specifically, it utilizes image recognition and voice analysis technologies to evaluate the emotions the user is experiencing.

[0199] Step 4:

[0200] The server receives emotion data sent from the terminal and generates new educational information tailored to the user's learning progress. It receives user state information through emotion recognition as input and provides the user with customized learning content generated using a generative AI model as output. Specifically, it inputs a prompt such as "Generate recommended interactive learning materials for a user who appears bored" into the generative AI model, and then selects and sends the content output by the model.

[0201] Step 5:

[0202] Users provide feedback via their device after learning. The system receives evaluation data provided by the user as input and sends feedback information to the server as output. Specific actions include filling out and submitting a feedback form, which the system records in a database.

[0203] Step 6:

[0204] The server analyzes user feedback and learning history data to determine rewards for educators. It utilizes collected feedback data and past learning history as input, and provides educators with suggestions for improving educational resources and reward information as output. Specifically, it uses data analysis algorithms to evaluate educators' contributions and assign incentives.

[0205] (Application Example 2)

[0206] 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 device 14 will be referred to as the "terminal."

[0207] In modern learning systems, providing customized learning experiences tailored to individual users' learning needs and emotional states is challenging. In particular, real-time emotional recognition and dynamic adjustment of learning content based on that recognition are required, but conventional systems have failed to effectively address this issue. Furthermore, there are insufficient methods for appropriately utilizing user feedback for educators and providing rewards for their contributions.

[0208] 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.

[0209] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, means for suggesting optimal learning information based on the user's learning needs, means for recognizing the user's emotional state during learning and dynamically adjusting the learning information based on emotional data, means for collecting feedback after the user's learning, and means for providing rewards to educators based on the feedback. This makes it possible to provide a customized educational experience suited to individual users and improve learning effectiveness.

[0210] "Educational information" refers to all materials and data used by learners to acquire knowledge and skills.

[0211] A "generative AI model" refers to artificial intelligence technology used to generate learning content based on input data and provide it to learners.

[0212] "Learning needs" refer to the demands and necessities that individual learners face during the learning process, and include requirements for promoting effective learning.

[0213] "Emotional state" refers to the psychological state a learner exhibits during learning, such as interest, concentration, boredom, and frustration.

[0214] "Emotional data" refers to information about emotions obtained from the learner's facial expressions and tone of voice.

[0215] "Opinions" refer to feedback, suggestions for improvement, and comments that learners provide after using the learning content.

[0216] "Education professionals" refers to individuals and organizations involved in the provision, management, and instruction of educational content.

[0217] "Rewards" refer to incentives or rewards that educators receive when they provide valuable educational content or learning support.

[0218] This invention realizes a system for providing customized educational experiences tailored to individual users. Specifically, it utilizes multiple hardware and software components to collect educational information, train a generation AI model, and recognize and evaluate the user's emotional state.

[0219] The server collects educational information from various educational platforms on the internet, integrates it, and stores it in a database. The collected information is used to train a generative AI model built using programming languages ​​such as Python. This AI model has the ability to generate optimal learning information based on the user's learning needs.

[0220] Meanwhile, the device uses a camera and microphone to detect the user's facial expressions and voice tone in real time during the learning process. This allows it to recognize the user's emotional state and transmit that data to a server. The emotion recognition technology used includes state-of-the-art image processing software and voice analysis tools. This emotional data serves as the foundation for the generative AI model to dynamically adjust and provide learning information.

[0221] Users provide feedback on the content using their devices after a learning session. This feedback is used to improve future content creation and the learning experience. Educators are also rewarded based on the collected feedback and sentiment data. This reward system incentivizes educators to improve the quality of the content they provide.

[0222] For example, if a user looks bored while watching a history video lesson, the server can immediately detect this and use a generative AI model to provide more interactive and engaging material. An example of such a prompt might be, "If the user's emotional state indicates moderate interest and attention, generate new interactive visual content."

[0223] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0224] Step 1:

[0225] The server collects educational information from online educational platforms, integrates it, and stores it in a database. In this step, the server automatically retrieves content in various formats (text, audio, video) and converts it into a unified data format. The input is educational content retrieved from the web, and the output is formalized data stored in the integrated database on the server.

[0226] Step 2:

[0227] The server trains a generative AI model using integrated educational information. The input is processed training data, and the output is the trained generative AI model. In this step, the model learns the logic to generate optimal content based on the user's learning needs using the data. In particular, the AI ​​model analyzes patterns within the dataset and uses this to improve future content delivery.

[0228] Step 3:

[0229] The device uses its camera and microphone to record facial expressions and voice tone in real time while the user is using learning content. The input is live data from the device's camera and microphone, and the output is emotional state data analyzed in real time. The device uses an emotion recognition engine to process this data and identify the user's emotional state.

[0230] Step 4:

[0231] After the emotional state is acquired, the emotional data is sent to the server. The server receives this data and uses a generative AI model to dynamically adjust the learning content based on it. The input is real-time emotional data, and the output is the optimal learning information provided to the user. This adjustment selects content optimized to increase the user's attention and interest.

[0232] Step 5:

[0233] After completing a learning session, users provide feedback via their device. The input is the feedback information entered by the user through their device, and the output is integrated feedback data processed on the server. In this step, the collected feedback is used to improve future content creation and the user experience.

[0234] Step 6:

[0235] The server rewards educators based on feedback and sentiment data. The input is analyzed feedback and sentiment data, and the output is instructions for the reward system. This allows educators to evaluate the quality of their content and identify areas for improvement.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] [Second Embodiment]

[0240] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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).

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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".

[0252] The present invention is implemented as a system that efficiently collects and integrates educational content and utilizes a generative AI model to provide customized learning based on learning needs. The embodiments thereof are described below with specific examples.

[0253] Data collection and integration

[0254] The server collects course content accessible from multiple educational platforms via the internet. This content is provided in text, audio, and video formats. The server manages the metadata of this content and integrates it into appropriate databases through advanced filtering.

[0255] Training of Generative AI Models

[0256] Based on the collected data, the server trains a generative AI model. This model has the ability to generate optimal learning materials tailored to user needs, encompassing a wide range of learning content including mathematics, science, and language learning. The thus trained model can accommodate learners from different regions and cultural backgrounds.

[0257] User profile creation and content suggestion

[0258] The device requires user information to be entered during initial setup. This includes the learner's age, areas of interest, and learning goals. This information is sent to the server, where a user profile is created. Based on this profile, the server uses a generative AI model to suggest the most suitable learning content for the user.

[0259] As a concrete example, consider an English learning program customized for elementary school students. In this case, the server generates animated learning materials that focus on English conversation practice and creates an efficient learning package that includes related practice exercises. This provides learners with content that is easy to see and enjoyable to learn from.

[0260] Utilizing learning history and feedback

[0261] Users learn using the provided content. After completing their learning, they can provide feedback via their device. This feedback is sent to the server and used to create and suggest future content. This enables flexible education that responds to the changing needs of learners.

[0262] The server provides incentives to educators based on the feedback information it collects. This mechanism increases the motivation to provide better content, thereby improving the overall quality of education.

[0263] These processes in the present invention enable the provision of customized education tailored to individual learning needs and are key to accommodating diverse learners.

[0264] The following describes the processing flow.

[0265] Step 1:

[0266] The server collects lesson content from the educational platform. This involves using an API to retrieve data and adding metadata such as content tags and category information (e.g., subject and target age).

[0267] Step 2:

[0268] The server integrates the collected content into a database. The database is designed to allow for efficient data retrieval and searching.

[0269] Step 3:

[0270] The server trains a generative AI model using integrated data from the database. This AI model improves its ability to extract features from different data formats (text, audio, video) and generate optimized learning content.

[0271] Step 4:

[0272] The device collects information from the user during initial setup. Specifically, it prompts the user to enter information such as their learning objectives, areas of interest, and preferred learning style.

[0273] Step 5:

[0274] The server creates a profile based on user information sent from the terminal. Using this profile, an AI model generates and delivers customized content tailored to the user's needs.

[0275] Step 6:

[0276] Users engage in educational activities using learning content provided via their devices. For example, they can watch video materials or work on practice problems.

[0277] Step 7:

[0278] After completing their learning, users provide feedback through their devices. This feedback concerns the usefulness of the content and the effectiveness of the learning experience.

[0279] Step 8:

[0280] The server collects user feedback and uses it to improve the entire system. Based on this data, the quality of the content provided next time will be improved.

[0281] Step 9:

[0282] The server provides incentives to educators based on the feedback it collects. This feedback loop leads to improvements in the quality of educational content and the provision of better services.

[0283] (Example 1)

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

[0285] In a modern educational environment, it is required to efficiently provide educational content that meets the needs of individual learners. However, in existing systems, the collection of content and the provision of individualized learning experiences have not been fully realized, and the utilization of appropriate feedback for learners has not advanced. In particular, it is difficult to automatically generate learning materials according to regions and cultures, and there is a lack of appropriate motivation for educators. Due to such problems, there are issues where the quality of learning and learner satisfaction decline.

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

[0287] In this invention, the server includes means for aggregating and unifying educational materials, means for training a generation AI algorithm based on the aggregated materials, and means for proposing optimal learning materials based on the learning requirements of users. As a result, it becomes possible to provide customized educational content that utilizes the profile information of individual learners. By managing the meta-information of the collected content and performing efficient filtering based on it, automatic proposal of appropriate educational materials is realized, and a learning experience suitable for each learner is provided. Also, based on the evaluation information, it is possible to improve the quality of education by providing rewards to educators.

[0288] "Educational materials" is a general term for information and content used for educational purposes, and includes various forms such as text, audio, and video.

[0289] "Aggregation" refers to the process of collecting data from multiple information sources and putting them together into one.

[0290] "Means for unifying" refers to a method of integrating the collected data and managing it in an organized form.

[0291] A "generative AI algorithm" is an artificial intelligence technology that generates new information based on data, and is particularly useful for generating educational materials in the field of education.

[0292] "User learning needs" refers to information such as the learning content, goals, and interests that learners desire, and serves as the basis for providing individualized learning experiences based on this information.

[0293] "Metadata" refers to attribute information associated with the data in question, including content category, target audience, difficulty level, etc.

[0294] "Filtering" is a method of selecting data based on certain conditions, and it is a process performed to extract only the information that is relevant to the user.

[0295] "Profile information" refers to personal information such as the user's age, interests, and learning objectives, and is used to design a customized learning experience.

[0296] "Evaluation" refers to feedback that users provide after learning about the content, including their assessment of its effectiveness and satisfaction level.

[0297] "Rewards" refer to incentives provided to educators and content providers as a reward for their achievements and contributions.

[0298] This invention is a system that enables the efficient collection, integration, and generation of educational content, and provides personalized learning utilizing AI (artificial intelligence) models. Specific embodiments of this system are described below.

[0299] Data collection and integration

[0300] The server accesses multiple educational platforms via the internet to collect educational content. This process uses APIs and web scraping techniques to retrieve data in text, audio, and video formats. The collected content, along with metadata, is integrated into a database. For example, the server might collect math content for a specific grade level from educational websites, organize it by category, and create a database.

[0301] Training of Generative AI Models

[0302] The server trains a generative AI model based on learning materials obtained from an integrated database. Here, natural language processing and machine learning techniques are utilized to enable the generative AI model to autonomously create diverse learning content. Using a notebook-type server allows for rapid model training.

[0303] User profile creation and content suggestion

[0304] The terminal allows learners to input necessary personal information through an interface. This information includes the learner's age, desired field of study, and learning goals. This information is sent to a server, from which a user profile is created. The server uses this profile information and a generative AI model to suggest optimal learning content to the learner. An example of a prompt is, "Please create English dialogue practice material for fifth-grade elementary school students."

[0305] For example, in an English learning program for elementary school students, the server generates and provides content including animated conversation materials and related practice exercises. This allows learners to receive visually easy-to-understand and enjoyable learning materials.

[0306] Utilizing learning history and feedback

[0307] The user advances learning with the content provided through the terminal and provides feedback using the terminal after learning. This feedback is sent to the server and reflected in the generation of the next learning content. The server incorporates a mechanism to provide rewards to appropriate educators to enhance motivation for better content creation.

[0308] To provide an individualized educational experience in this way and optimize the user's learning environment is the objective of this invention.

[0309] The flow of the specific process in Example 1 will be described using FIG. 11.

[0310] Step 1:

[0311] Data collection

[0312] The server accesses the educational platform through the Internet. The inputs are the API information and HTML structure of each platform. In response, the server uses the API or executes a web scraping script to collect educational content in text, audio, and video formats. The output is a dataset in these formats.

[0313] Step 2:

[0314] Content filtering and integration

[0315] Based on the collected data, the server analyzes the meta information of each content. The meta information to be input includes category, difficulty level, and target age. The server performs advanced filtering based on this meta information and selects only relevant content. Then, the selected content is sorted and integrated into the database. The output is the integrated database.

[0316] Step 3:

[0317] Training of Generative AI Models

[0318] The server uses educational data extracted from an integrated database. The input consists of digital data converted from text, audio, and video. The server feeds this data to a generative AI model for training, which includes feature extraction and optimization of model parameters. The output is the trained generative AI model.

[0319] Step 4:

[0320] Creating a User Profile

[0321] The terminal receives personal information entered by the user. This information includes the learner's age, areas of interest, and goals. The terminal sends this information to the server and stores it in the database as a user profile. The output is the user's profile information.

[0322] Step 5:

[0323] Suggestions for customized content

[0324] The server uses user profile information and a trained generative AI model. The input consists of profile data and requests to the generative AI model. Based on this, the server generates and selects optimal content tailored to the user's learning needs. The generated prompts are passed to the AI ​​model to obtain individual training materials. The output is customized training content suggested to the user.

[0325] Step 6:

[0326] Utilizing learning history and feedback

[0327] Users learn content provided on their devices and provide feedback during and after the learning process. This feedback data is sent from the device to the server. The input includes evaluations of learning progress, comprehension, and satisfaction. The server stores this data and analyzes it to use in generating future content. The output is improvements to the next learning content based on the analysis results.

[0328] (Application Example 1)

[0329] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0330] In modern society, providing educational content that meets the diverse needs of learners is crucial. However, traditional methods make it difficult to efficiently deliver optimal educational content to individual learners. In particular, there is a need for real-time customization and the suggestion of appropriate learning paths based on each learner's interests.

[0331] 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.

[0332] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, and means for delivering content to a smartphone according to the user's learning goals and interests. This makes it possible to efficiently and effectively provide educational content tailored to the individual needs of learners.

[0333] "Educational information" is a general term for data and materials used to support learners in acquiring knowledge.

[0334] A "generative AI model" is a type of artificial intelligence that creates new educational content based on collected data.

[0335] "User" refers to an individual or group that receives the educational services provided.

[0336] "Learning objectives" refer to the specific knowledge and skills that learners aim to acquire.

[0337] A "smartphone" is a multi-functional portable information terminal, an electronic device capable of voice calls, messaging, and internet connectivity.

[0338] "Feedback" refers to the act or content of providing evaluations or opinions on a learner's learning experience.

[0339] An "educational expert" refers to an individual or organization that possesses specialized knowledge and skills regarding the content and methods of education.

[0340] "Reward" refers to the economic or other benefits provided for a particular action or outcome.

[0341] "Learning history" refers to a record of past learning activities and is data that shows the learner's progress and acquisition status.

[0342] This invention is an educational content delivery system that adapts to the diverse needs of learners. For its implementation, three main elements—server, terminal, and user—interact with each other.

[0343] The server collects and integrates educational information from multiple educational sources via the internet. The collected information, in various formats including text, audio, and video, is integrated into a database that manages metadata. Based on the collected information, the server trains a generative AI model. This model is designed to generate educational materials tailored to the user's learning needs. Software used includes Python and TensorFlow.

[0344] A device, such as a smartphone, provides an interface for inputting user information. This information includes learning goals and areas of interest, and is sent to a server. The server generates learning content optimized for the user and delivers it to the device. The delivered content can be viewed on the user's smartphone, and content is provided according to the learner's progress.

[0345] Users progress through their learning using content provided on their devices. After learning, they provide feedback, and the server updates the generated AI model based on the collected feedback, incorporating it into future content suggestions. A system that rewards educational professionals helps improve the quality of education.

[0346] As a concrete example, let's say there is a user who is an intermediate Japanese speaker and wants to learn English. Based on this user's learning goals, the server generates optimal content using a prompt message such as, "Generate English listening materials for intermediate Japanese learners. The target age is 10-12 years old, and the theme is animals." The generated materials are delivered to the user's smartphone and provide interactive videos that contribute to improving listening skills. By utilizing a feedback mechanism that measures performance and rewards educational professionals, the sustainable operation of the entire system becomes possible.

[0347] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0348] Step 1:

[0349] The server collects educational information from multiple educational sources via the internet. It accepts data in various formats, including text, audio, and video, as input. The collected information, along with metadata, is integrated into a database. This creates a large dataset of available educational information.

[0350] Step 2:

[0351] The server trains a generative AI model using the collected data as input. Supervised learning algorithms are used to process the data, extracting and learning features appropriate for each data format. The output of this process is a generative AI model optimized for user needs.

[0352] Step 3:

[0353] Users operating the terminal input their learning goals and areas of interest. This data is sent to the server, which creates a user profile. The creation of this profile allows the server to accumulate data based on each user's needs.

[0354] Step 4:

[0355] The server receives a user profile and a generated AI model as input and uses prompts to generate optimal educational content. Based on these prompts, the AI ​​model outputs the most appropriate educational materials for the user.

[0356] Step 5:

[0357] The generated educational content is delivered to the user's device. For example, English listening comprehension videos are provided to the smartphone. These videos are tailored to the user's learning objectives and are delivered in an interactive format.

[0358] Step 6:

[0359] Users use the content and progress through their learning. After completing their learning, they provide feedback based on their learning experience via their device. This feedback is sent to the server and used as data to improve future content creation.

[0360] Step 7:

[0361] The server generates information to reward education professionals based on the collected feedback. This enables an incentive system aimed at improving performance and content, supporting the overall operation of the system.

[0362] 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.

[0363] The present invention is implemented in a form that combines an emotion engine with a system that collects and integrates educational content and utilizes a generative AI model to provide a customized learning experience tailored to learning needs. Specific embodiments are described below.

[0364] Utilization of data collection and generative AI models

[0365] The server collects lesson content from various educational platforms on the internet. This content is provided in different formats (text, audio, video), integrated, and efficiently stored in a database. The server has the ability to use the collected data to train a generative AI model and generate learning content tailored to the user's learning needs.

[0366] Combination of emotional engines

[0367] This system incorporates an emotion engine that recognizes user emotions in real time. The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and evaluates the user's emotional state during learning. This emotion data is sent to a server and used to improve the learning experience.

[0368] As a concrete example, consider a scenario where a student is using video learning materials for language acquisition. While the user is watching the video, the emotion engine analyzes the user's level of concentration and interest. For example, if the user looks bored, the server immediately detects this and suggests more interactive and engaging materials, or content that encourages a break.

[0369] Utilizing learning history and feedback

[0370] After a learning session, users provide feedback via their device regarding the usefulness and educational effectiveness of the provided content. This feedback is integrated and analyzed by the server and used to improve future content creation and the learning experience.

[0371] Provision of incentives

[0372] The server analyzes user feedback and sentiment data to provide appropriate incentives to educators. This system allows educators to identify areas for improvement in their content and strive to provide better educational resources.

[0373] Thus, this invention is designed as a system that provides users with an optimized learning experience through the customization of educational content, dynamic adjustment based on emotion recognition, and continuous improvement through feedback, while also appropriately evaluating and rewarding the contributions of all stakeholders involved in education.

[0374] The following describes the processing flow.

[0375] Step 1:

[0376] The server collects educational content in various formats (text, audio, video, etc.) from educational platforms and other online resources. The collected data is integrated into a database along with metadata and organized for easy searching.

[0377] Step 2:

[0378] The server uses integrated educational content to train a generative AI model. During this training process, the AI ​​model learns the characteristics of different educational content and acquires the ability to generate and select content that meets the user's learning needs.

[0379] Step 3:

[0380] The device collects initial user information, including age, areas of learning interest, and learning goals. This information is sent to the server and stored as part of the user's learning profile.

[0381] Step 4:

[0382] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice during learning sessions. It uses the camera and microphone to assess the user's emotional state (e.g., joy, concentration, boredom, etc.) in real time.

[0383] Step 5:

[0384] The server receives data from the emotion engine and dynamically adjusts the learning content based on the user's emotional state. For example, if the user appears to be having difficulty understanding something, it will suggest additional explanatory videos or a different learning approach.

[0385] Step 6:

[0386] Users continue learning using tailored learning content provided by the server. Feedback and sentiment data during learning are continuously collected and reflected by the system in real time.

[0387] Step 7:

[0388] After a learning session ends, users provide feedback on their learning experience via their device. This includes information on content quality, comprehension, and overall satisfaction with the learning experience.

[0389] Step 8:

[0390] The server comprehensively analyzes user feedback and sentiment data to update its database and improve the quality of the next learning session. This process provides a more optimized experience for each individual learner.

[0391] Step 9:

[0392] Ultimately, the server provides educators with feedback-based incentives. These incentives motivate content providers to continuously improve the quality of their content.

[0393] (Example 2)

[0394] 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".

[0395] In today's educational environment, there is a demand for customized educational resources that meet the diverse needs of learners. However, existing systems often fail to reflect individual learners' emotional states and learning tendencies in real time, resulting in uniform education. Furthermore, mechanisms for effectively utilizing learner feedback and providing appropriate rewards to educators are insufficient.

[0396] 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.

[0397] In this invention, the server includes means for collecting and integrating educational information, means for training a machine learning model based on the collected information, and means for recognizing the user's emotional state in real time and providing information according to the learning situation. This enables the provision of educational resources adapted to the individual needs of learners, as well as effective feedback and rewards for educators.

[0398] "Educational information" refers to all forms of data and content provided to learners (e.g., text, audio, video, etc.) that are intended for knowledge acquisition in learning.

[0399] A "machine learning model" is an algorithm that analyzes data, learns patterns, and automatically makes predictions and decisions, and its performance improves with the use of training data.

[0400] "Users" refers to individuals or groups who use the system to access educational information and engage in learning activities.

[0401] "Emotional state" refers to the user's psychological and physiological state at a specific time, and is determined through analysis of facial expressions and voice tone.

[0402] "Rewards" refer to compensation or evaluations provided to educators based on user feedback and system analysis, with the aim of promoting quality improvement.

[0403] This invention provides a system for appropriately customizing educational information for each user. Specific embodiments thereof are described below.

[0404] The server scans educational information sources on the internet to collect and integrate various types of information. It utilizes web crawlers and API calls to collect data in multiple formats, including text, audio, and video. This allows a wide range of information to be efficiently stored in a database. Data management systems such as MySQL or MongoDB are used for the database.

[0405] Based on this collected data, the server trains a generative AI model. Training uses machine learning techniques such as OpenAI's GPT series, learning from large amounts of data. The generated model has the ability to adapt to the user's learning needs and provide appropriate educational resources.

[0406] The device recognizes the user's emotional state in real time. Specifically, it analyzes the user's facial expressions and voice tone using a camera and microphone. This allows it to monitor the user's level of concentration and interest, and send emotional data to the server as needed. This process utilizes libraries such as OpenCV and TensorFlow.

[0407] As a concrete example, consider a situation where a user appears bored while learning a language. In this case, the server inputs a prompt message such as "Generate recommended interactive learning materials for a user who appears bored" into the AI ​​model, providing more appropriate educational resources. By linking the user's emotional state with learning resources in this way, it becomes possible to provide a dynamic learning experience.

[0408] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0409] Step 1:

[0410] The server scans educational platforms on the internet to collect educational information. It uses URLs and API credentials from various educational websites as input and retrieves data in text, audio, and video formats as output. It uses a web crawler to collect data and processes it to integrate data in different formats. This ensures that a wide range of learning content is stored in a unified database format.

[0411] Step 2:

[0412] The server trains machine learning models using information stored in the database. Collected training data is used as input, and a trained generative AI model adapted to the user's learning needs is generated as output. Specifically, the data is divided into appropriate batch sizes, and the model parameters are optimized by applying a learning algorithm.

[0413] Step 3:

[0414] The device monitors the user's emotional state in real time. It acquires video and audio data from devices such as cameras and microphones as input, and analyzes the user's emotional state based on their facial expressions and tone of voice as output. Specifically, it utilizes image recognition and voice analysis technologies to evaluate the emotions the user is experiencing.

[0415] Step 4:

[0416] The server receives emotion data sent from the terminal and generates new educational information tailored to the user's learning progress. It receives user state information through emotion recognition as input and provides the user with customized learning content generated using a generative AI model as output. Specifically, it inputs a prompt such as "Generate recommended interactive learning materials for a user who appears bored" into the generative AI model, and then selects and sends the content output by the model.

[0417] Step 5:

[0418] Users provide feedback via their device after learning. The system receives evaluation data provided by the user as input and sends feedback information to the server as output. Specific actions include filling out and submitting a feedback form, which the system records in a database.

[0419] Step 6:

[0420] The server analyzes user feedback and learning history data to determine rewards for educators. It utilizes collected feedback data and past learning history as input, and provides educators with suggestions for improving educational resources and reward information as output. Specifically, it uses data analysis algorithms to evaluate educators' contributions and assign incentives.

[0421] (Application Example 2)

[0422] 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."

[0423] In modern learning systems, providing customized learning experiences tailored to individual users' learning needs and emotional states is challenging. In particular, real-time emotional recognition and dynamic adjustment of learning content based on that recognition are required, but conventional systems have failed to effectively address this issue. Furthermore, there are insufficient methods for appropriately utilizing user feedback for educators and providing rewards for their contributions.

[0424] 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.

[0425] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, means for suggesting optimal learning information based on the user's learning needs, means for recognizing the user's emotional state during learning and dynamically adjusting the learning information based on emotional data, means for collecting feedback after the user's learning, and means for providing rewards to educators based on the feedback. This makes it possible to provide a customized educational experience suited to individual users and improve learning effectiveness.

[0426] "Educational information" refers to all materials and data used by learners to acquire knowledge and skills.

[0427] A "generative AI model" refers to artificial intelligence technology used to generate learning content based on input data and provide it to learners.

[0428] "Learning needs" refer to the demands and necessities that individual learners face during the learning process, and include requirements for promoting effective learning.

[0429] "Emotional state" refers to the psychological state a learner exhibits during learning, such as interest, concentration, boredom, and frustration.

[0430] "Emotional data" refers to information about emotions obtained from the learner's facial expressions and tone of voice.

[0431] "Opinions" refer to feedback, suggestions for improvement, and comments that learners provide after using the learning content.

[0432] "Education professionals" refers to individuals and organizations involved in the provision, management, and instruction of educational content.

[0433] "Rewards" refer to incentives or rewards that educators receive when they provide valuable educational content or learning support.

[0434] This invention realizes a system for providing customized educational experiences tailored to individual users. Specifically, it utilizes multiple hardware and software components to collect educational information, train a generation AI model, and recognize and evaluate the user's emotional state.

[0435] The server collects educational information from various educational platforms on the internet, integrates it, and stores it in a database. The collected information is used to train a generative AI model built using programming languages ​​such as Python. This AI model has the ability to generate optimal learning information based on the user's learning needs.

[0436] Meanwhile, the device uses a camera and microphone to detect the user's facial expressions and voice tone in real time during the learning process. This allows it to recognize the user's emotional state and transmit that data to a server. The emotion recognition technology used includes state-of-the-art image processing software and voice analysis tools. This emotional data serves as the foundation for the generative AI model to dynamically adjust and provide learning information.

[0437] Users provide feedback on the content using their devices after a learning session. This feedback is used to improve future content creation and the learning experience. Educators are also rewarded based on the collected feedback and sentiment data. This reward system incentivizes educators to improve the quality of the content they provide.

[0438] For example, if a user looks bored while watching a history video lesson, the server can immediately detect this and use a generative AI model to provide more interactive and engaging material. An example of such a prompt might be, "If the user's emotional state indicates moderate interest and attention, generate new interactive visual content."

[0439] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0440] Step 1:

[0441] The server collects educational information from online educational platforms, integrates it, and stores it in a database. In this step, the server automatically retrieves content in various formats (text, audio, video) and converts it into a unified data format. The input is educational content retrieved from the web, and the output is formalized data stored in the integrated database on the server.

[0442] Step 2:

[0443] The server trains a generative AI model using integrated educational information. The input is processed training data, and the output is the trained generative AI model. In this step, the model learns the logic to generate optimal content based on the user's learning needs using the data. In particular, the AI ​​model analyzes patterns within the dataset and uses this to improve future content delivery.

[0444] Step 3:

[0445] The device uses its camera and microphone to record facial expressions and voice tone in real time while the user is using learning content. The input is live data from the device's camera and microphone, and the output is emotional state data analyzed in real time. The device uses an emotion recognition engine to process this data and identify the user's emotional state.

[0446] Step 4:

[0447] After the emotional state is acquired, the emotional data is sent to the server. The server receives this data and uses a generative AI model to dynamically adjust the learning content based on it. The input is real-time emotional data, and the output is the optimal learning information provided to the user. This adjustment selects content optimized to increase the user's attention and interest.

[0448] Step 5:

[0449] After completing a learning session, users provide feedback via their device. The input is the feedback information entered by the user through their device, and the output is integrated feedback data processed on the server. In this step, the collected feedback is used to improve future content creation and the user experience.

[0450] Step 6:

[0451] The server rewards educators based on feedback and sentiment data. The input is analyzed feedback and sentiment data, and the output is instructions for the reward system. This allows educators to evaluate the quality of their content and identify areas for improvement.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] [Third Embodiment]

[0456] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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".

[0468] The present invention is implemented as a system that efficiently collects and integrates educational content and utilizes a generative AI model to provide customized learning based on learning needs. The embodiments thereof are described below with specific examples.

[0469] Data collection and integration

[0470] The server collects course content accessible from multiple educational platforms via the internet. This content is provided in text, audio, and video formats. The server manages the metadata of this content and integrates it into appropriate databases through advanced filtering.

[0471] Training of Generative AI Models

[0472] Based on the collected data, the server trains a generative AI model. This model has the ability to generate optimal learning materials tailored to user needs, encompassing a wide range of learning content including mathematics, science, and language learning. The thus trained model can accommodate learners from different regions and cultural backgrounds.

[0473] User profile creation and content suggestion

[0474] The device requires user information to be entered during initial setup. This includes the learner's age, areas of interest, and learning goals. This information is sent to the server, where a user profile is created. Based on this profile, the server uses a generative AI model to suggest the most suitable learning content for the user.

[0475] As a concrete example, consider an English learning program customized for elementary school students. In this case, the server generates animated learning materials that focus on English conversation practice and creates an efficient learning package that includes related practice exercises. This provides learners with content that is easy to see and enjoyable to learn from.

[0476] Utilizing learning history and feedback

[0477] Users learn using the provided content. After completing their learning, they can provide feedback via their device. This feedback is sent to the server and used to create and suggest future content. This enables flexible education that responds to the changing needs of learners.

[0478] The server provides incentives to educators based on the feedback information it collects. This mechanism increases the motivation to provide better content, thereby improving the overall quality of education.

[0479] These processes in the present invention enable the provision of customized education tailored to individual learning needs and are key to accommodating diverse learners.

[0480] The following describes the processing flow.

[0481] Step 1:

[0482] The server collects lesson content from the educational platform. This involves using an API to retrieve data and adding metadata such as content tags and category information (e.g., subject and target age).

[0483] Step 2:

[0484] The server integrates the collected content into a database. The database is designed to allow for efficient data retrieval and searching.

[0485] Step 3:

[0486] The server trains a generative AI model using integrated data from the database. This AI model improves its ability to extract features from different data formats (text, audio, video) and generate optimized learning content.

[0487] Step 4:

[0488] The device collects information from the user during initial setup. Specifically, it prompts the user to enter information such as their learning objectives, areas of interest, and preferred learning style.

[0489] Step 5:

[0490] The server creates a profile based on user information sent from the terminal. Using this profile, an AI model generates and delivers customized content tailored to the user's needs.

[0491] Step 6:

[0492] Users engage in educational activities using learning content provided via their devices. For example, they can watch video materials or work on practice problems.

[0493] Step 7:

[0494] After completing their learning, users provide feedback through their devices. This feedback concerns the usefulness of the content and the effectiveness of the learning experience.

[0495] Step 8:

[0496] The server collects user feedback and uses it to improve the entire system. Based on this data, the quality of the content provided next time will be improved.

[0497] Step 9:

[0498] The server provides incentives to educators based on the feedback it collects. This feedback loop leads to improvements in the quality of educational content and the provision of better services.

[0499] (Example 1)

[0500] 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."

[0501] In today's educational environment, there is a need to efficiently provide educational content that matches the needs of individual learners. However, existing systems fail to adequately collect content and provide personalized learning experiences, and the use of appropriate feedback to learners is also insufficient. In particular, the automatic generation of learning materials tailored to region and culture is difficult, and there is a lack of appropriate motivation for educators. These problems lead to challenges in the quality of learning and learner satisfaction.

[0502] 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.

[0503] In this invention, the server includes means for aggregating and centralizing educational materials, means for training a generation AI algorithm based on the aggregated materials, and means for suggesting optimal learning materials based on the user's learning needs. This makes it possible to provide customized educational content that utilizes the profile information of individual learners. By managing the metadata of the collected content and efficiently filtering it based on that metadata, appropriate educational materials are automatically suggested, providing a learning experience tailored to each learner. Furthermore, the quality of education can be improved by providing rewards to educators based on evaluation information.

[0504] "Educational materials" is a general term for information and content used for educational purposes, and includes a variety of formats such as text, audio, and video.

[0505] "Aggregation" refers to the process of collecting data from multiple sources and combining them into a single entity.

[0506] "Methods of centralization" refer to methods of integrating collected data and managing it in an organized manner.

[0507] A "generative AI algorithm" is an artificial intelligence technology that generates new information based on data, and is particularly useful for generating educational materials in the field of education.

[0508] "User learning needs" refers to information such as the learning content, goals, and interests that learners desire, and serves as the basis for providing individualized learning experiences based on this information.

[0509] "Metadata" refers to attribute information associated with the data in question, including content category, target audience, difficulty level, etc.

[0510] "Filtering" is a method of selecting data based on certain conditions, and it is a process performed to extract only the information that is relevant to the user.

[0511] "Profile information" refers to personal information such as the user's age, interests, and learning objectives, and is used to design a customized learning experience.

[0512] "Evaluation" refers to feedback that users provide after learning about the content, including their assessment of its effectiveness and satisfaction level.

[0513] "Rewards" refer to incentives provided to educators and content providers as a reward for their achievements and contributions.

[0514] This invention is a system that enables the efficient collection, integration, and generation of educational content, and provides personalized learning utilizing AI (artificial intelligence) models. Specific embodiments of this system are described below.

[0515] Data collection and integration

[0516] The server accesses multiple educational platforms via the internet to collect educational content. This process uses APIs and web scraping techniques to retrieve data in text, audio, and video formats. The collected content, along with metadata, is integrated into a database. For example, the server might collect math content for a specific grade level from educational websites, organize it by category, and create a database.

[0517] Training of Generative AI Models

[0518] The server trains a generative AI model based on learning materials obtained from an integrated database. Here, natural language processing and machine learning techniques are utilized to enable the generative AI model to autonomously create diverse learning content. Using a notebook-type server allows for rapid model training.

[0519] User profile creation and content suggestion

[0520] The terminal allows learners to input necessary personal information through an interface. This information includes the learner's age, desired field of study, and learning goals. This information is sent to a server, from which a user profile is created. The server uses this profile information and a generative AI model to suggest optimal learning content to the learner. An example of a prompt is, "Please create English dialogue practice material for fifth-grade elementary school students."

[0521] For example, in the case of an English learning program for elementary school students, the server generates and provides content that includes animated conversation materials and related practice exercises. This allows learners to receive visually easy-to-understand and enjoyable learning materials.

[0522] Utilizing learning history and feedback

[0523] Users learn through content provided via their devices and provide feedback using their devices after completing their studies. This feedback is sent to the server and used to generate the next learning content. The server has a system in place to reward appropriate educators and motivate them to create better content.

[0524] The objective of this invention is to provide a personalized educational experience and optimize the user's learning environment.

[0525] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0526] Step 1:

[0527] Data collection

[0528] The server accesses educational platforms via the internet. The input consists of API information and HTML structures from each platform. The server then uses APIs and executes web scraping scripts to collect educational content in text, audio, and video formats. The output is datasets in these formats.

[0529] Step 2:

[0530] Content filtering and integration

[0531] Based on the collected data, the server analyzes the metadata of each piece of content. This metadata includes category, difficulty level, and target age group. The server then uses this metadata to perform advanced filtering, selecting only relevant content. Finally, it organizes and integrates the selected content into a database. The output is this integrated database.

[0532] Step 3:

[0533] Training of Generative AI Models

[0534] The server uses educational data extracted from an integrated database. The input consists of digital data converted from text, audio, and video. The server feeds this data to a generative AI model for training, which includes feature extraction and optimization of model parameters. The output is the trained generative AI model.

[0535] Step 4:

[0536] Creating a User Profile

[0537] The terminal receives personal information entered by the user. This information includes the learner's age, areas of interest, and goals. The terminal sends this information to the server and stores it in the database as a user profile. The output is the user's profile information.

[0538] Step 5:

[0539] Suggestions for customized content

[0540] The server uses user profile information and a trained generative AI model. The input consists of profile data and requests to the generative AI model. Based on this, the server generates and selects optimal content tailored to the user's learning needs. The generated prompts are passed to the AI ​​model to obtain individual training materials. The output is customized training content suggested to the user.

[0541] Step 6:

[0542] Utilizing learning history and feedback

[0543] Users learn content provided on their devices and provide feedback during and after the learning process. This feedback data is sent from the device to the server. The input includes evaluations of learning progress, comprehension, and satisfaction. The server stores this data and analyzes it to use in generating future content. The output is improvements to the next learning content based on the analysis results.

[0544] (Application Example 1)

[0545] 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."

[0546] In modern society, providing educational content that meets the diverse needs of learners is crucial. However, traditional methods make it difficult to efficiently deliver optimal educational content to individual learners. In particular, there is a need for real-time customization and the suggestion of appropriate learning paths based on each learner's interests.

[0547] 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.

[0548] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, and means for delivering content to a smartphone according to the user's learning goals and interests. This makes it possible to efficiently and effectively provide educational content tailored to the individual needs of learners.

[0549] "Educational information" is a general term for data and materials used to support learners in acquiring knowledge.

[0550] A "generative AI model" is a type of artificial intelligence that creates new educational content based on collected data.

[0551] "User" refers to an individual or group that receives the educational services provided.

[0552] "Learning objectives" refer to the specific knowledge and skills that learners aim to acquire.

[0553] A "smartphone" is a multi-functional portable information terminal, an electronic device capable of voice calls, messaging, and internet connectivity.

[0554] "Feedback" refers to the act or content of providing evaluations or opinions on a learner's learning experience.

[0555] An "educational expert" refers to an individual or organization that possesses specialized knowledge and skills regarding the content and methods of education.

[0556] "Reward" refers to the economic or other benefits provided for a particular action or outcome.

[0557] "Learning history" refers to a record of past learning activities and is data that shows the learner's progress and acquisition status.

[0558] This invention is an educational content delivery system that adapts to the diverse needs of learners. For its implementation, three main elements—server, terminal, and user—interact with each other.

[0559] The server collects and integrates educational information from multiple educational sources via the internet. The collected information, in various formats including text, audio, and video, is integrated into a database that manages metadata. Based on the collected information, the server trains a generative AI model. This model is designed to generate educational materials tailored to the user's learning needs. Software used includes Python and TensorFlow.

[0560] A device, such as a smartphone, provides an interface for inputting user information. This information includes learning goals and areas of interest, and is sent to a server. The server generates learning content optimized for the user and delivers it to the device. The delivered content can be viewed on the user's smartphone, and content is provided according to the learner's progress.

[0561] Users progress through their learning using content provided on their devices. After learning, they provide feedback, and the server updates the generated AI model based on the collected feedback, incorporating it into future content suggestions. A system that rewards educational professionals helps improve the quality of education.

[0562] As a concrete example, let's say there is a user who is an intermediate Japanese speaker and wants to learn English. Based on this user's learning goals, the server generates optimal content using a prompt message such as, "Generate English listening materials for intermediate Japanese learners. The target age is 10-12 years old, and the theme is animals." The generated materials are delivered to the user's smartphone and provide interactive videos that contribute to improving listening skills. By utilizing a feedback mechanism that measures performance and rewards educational professionals, the sustainable operation of the entire system becomes possible.

[0563] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0564] Step 1:

[0565] The server collects educational information from multiple educational sources via the internet. It accepts data in various formats, including text, audio, and video, as input. The collected information, along with metadata, is integrated into a database. This creates a large dataset of available educational information.

[0566] Step 2:

[0567] The server trains a generative AI model using the collected data as input. Supervised learning algorithms are used to process the data, extracting and learning features appropriate for each data format. The output of this process is a generative AI model optimized for user needs.

[0568] Step 3:

[0569] Users operating the terminal input their learning goals and areas of interest. This data is sent to the server, which creates a user profile. The creation of this profile allows the server to accumulate data based on each user's needs.

[0570] Step 4:

[0571] The server receives a user profile and a generated AI model as input and uses prompts to generate optimal educational content. Based on these prompts, the AI ​​model outputs the most appropriate educational materials for the user.

[0572] Step 5:

[0573] The generated educational content is delivered to the user's device. For example, English listening comprehension videos are provided to the smartphone. These videos are tailored to the user's learning objectives and are delivered in an interactive format.

[0574] Step 6:

[0575] Users use the content and progress through their learning. After completing their learning, they provide feedback based on their learning experience via their device. This feedback is sent to the server and used as data to improve future content creation.

[0576] Step 7:

[0577] The server generates information to reward education professionals based on the collected feedback. This enables an incentive system aimed at improving performance and content, supporting the overall operation of the system.

[0578] 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.

[0579] The present invention is implemented in a form that combines an emotion engine with a system that collects and integrates educational content and utilizes a generative AI model to provide a customized learning experience tailored to learning needs. Specific embodiments are described below.

[0580] Utilization of data collection and generative AI models

[0581] The server collects lesson content from various educational platforms on the internet. This content is provided in different formats (text, audio, video), integrated, and efficiently stored in a database. The server has the ability to use the collected data to train a generative AI model and generate learning content tailored to the user's learning needs.

[0582] Combination of emotional engines

[0583] This system incorporates an emotion engine that recognizes user emotions in real time. The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and evaluates the user's emotional state during learning. This emotion data is sent to a server and used to improve the learning experience.

[0584] As a concrete example, consider a scenario where a student is using video learning materials for language acquisition. While the user is watching the video, the emotion engine analyzes the user's level of concentration and interest. For example, if the user looks bored, the server immediately detects this and suggests more interactive and engaging materials, or content that encourages a break.

[0585] Utilizing learning history and feedback

[0586] After a learning session, users provide feedback via their device regarding the usefulness and educational effectiveness of the provided content. This feedback is integrated and analyzed by the server and used to improve future content creation and the learning experience.

[0587] Provision of incentives

[0588] The server analyzes user feedback and sentiment data to provide appropriate incentives to educators. This system allows educators to identify areas for improvement in their content and strive to provide better educational resources.

[0589] Thus, this invention is designed as a system that provides users with an optimized learning experience through the customization of educational content, dynamic adjustment based on emotion recognition, and continuous improvement through feedback, while also appropriately evaluating and rewarding the contributions of all stakeholders involved in education.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] The server collects educational content in various formats (text, audio, video, etc.) from educational platforms and other online resources. The collected data is integrated into a database along with metadata and organized for easy searching.

[0593] Step 2:

[0594] The server uses integrated educational content to train a generative AI model. During this training process, the AI ​​model learns the characteristics of different educational content and acquires the ability to generate and select content that meets the user's learning needs.

[0595] Step 3:

[0596] The device collects initial user information, including age, areas of interest, and learning goals. This information is sent to a server and stored as part of the user's learning profile.

[0597] Step 4:

[0598] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice during learning sessions. It uses the camera and microphone to assess the user's emotional state (e.g., joy, concentration, boredom, etc.) in real time.

[0599] Step 5:

[0600] The server receives data from the emotion engine and dynamically adjusts the learning content based on the user's emotional state. For example, if the user appears to be having difficulty understanding something, it will suggest additional explanatory videos or a different learning approach.

[0601] Step 6:

[0602] Users continue learning using tailored learning content provided by the server. Feedback and sentiment data during learning are continuously collected and reflected in the system in real time.

[0603] Step 7:

[0604] After a learning session ends, users provide feedback on their learning experience via their device. This includes information on content quality, comprehension, and overall satisfaction with the learning experience.

[0605] Step 8:

[0606] The server comprehensively analyzes user feedback and sentiment data to update its database and improve the quality of the next learning session. This process provides a more optimized experience for each individual learner.

[0607] Step 9:

[0608] Ultimately, the server provides educators with feedback-based incentives. These incentives motivate content providers to continuously improve the quality of their content.

[0609] (Example 2)

[0610] 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."

[0611] In today's educational environment, there is a demand for customized educational resources that meet the diverse needs of learners. However, existing systems often fail to reflect individual learners' emotional states and learning tendencies in real time, resulting in uniform education. Furthermore, mechanisms for effectively utilizing learner feedback and providing appropriate rewards to educators are insufficient.

[0612] 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.

[0613] In this invention, the server includes means for collecting and integrating educational information, means for training a machine learning model based on the collected information, and means for recognizing the user's emotional state in real time and providing information according to the learning situation. This enables the provision of educational resources adapted to the individual needs of learners, as well as effective feedback and rewards for educators.

[0614] "Educational information" refers to all forms of data and content provided to learners (e.g., text, audio, video, etc.) that are intended for knowledge acquisition in learning.

[0615] A "machine learning model" is an algorithm that analyzes data, learns patterns, and automatically makes predictions and decisions, and its performance improves with the use of training data.

[0616] "Users" refers to individuals or groups who use the system to access educational information and engage in learning activities.

[0617] "Emotional state" refers to the user's psychological and physiological state at a specific time, and is determined through analysis of facial expressions and voice tone.

[0618] "Rewards" refer to compensation or evaluations provided to educators based on user feedback and system analysis, and are intended to promote quality improvement.

[0619] This invention provides a system for appropriately customizing educational information for each user. Specific embodiments thereof are described below.

[0620] The server scans educational information sources on the internet to collect and integrate various types of information. It utilizes web crawlers and API calls to collect data in multiple formats, including text, audio, and video. This allows a wide range of information to be efficiently stored in a database. Data management systems such as MySQL or MongoDB are used for the database.

[0621] Based on this collected data, the server trains a generative AI model. Training uses machine learning techniques such as OpenAI's GPT series, learning from large amounts of data. The generated model has the ability to adapt to the user's learning needs and provide appropriate educational resources.

[0622] The device recognizes the user's emotional state in real time. Specifically, it analyzes the user's facial expressions and voice tone using a camera and microphone. This allows it to monitor the user's level of concentration and interest, and send emotional data to the server as needed. This process utilizes libraries such as OpenCV and TensorFlow.

[0623] As a concrete example, consider a situation where a user appears bored while learning a language. In this case, the server inputs a prompt message such as "Generate recommended interactive learning materials for a user who appears bored" into the AI ​​model, providing more appropriate educational resources. By linking the user's emotional state with learning resources in this way, it becomes possible to provide a dynamic learning experience.

[0624] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0625] Step 1:

[0626] The server scans educational platforms on the internet to collect educational information. It uses URLs and API credentials from various educational websites as input and retrieves data in text, audio, and video formats as output. It uses a web crawler to collect data and processes it to integrate data in different formats. This ensures that a wide range of learning content is stored in a unified database format.

[0627] Step 2:

[0628] The server trains machine learning models using information stored in the database. Collected training data is used as input, and a trained generative AI model adapted to the user's learning needs is generated as output. Specifically, the data is divided into appropriate batch sizes, and the model parameters are optimized by applying a learning algorithm.

[0629] Step 3:

[0630] The device monitors the user's emotional state in real time. It acquires video and audio data from devices such as cameras and microphones as input, and analyzes the user's emotional state based on their facial expressions and tone of voice as output. Specifically, it utilizes image recognition and voice analysis technologies to evaluate the emotions the user is experiencing.

[0631] Step 4:

[0632] The server receives emotion data sent from the terminal and generates new educational information tailored to the user's learning progress. It receives user state information through emotion recognition as input and provides the user with customized learning content generated using a generative AI model as output. Specifically, it inputs a prompt such as "Generate recommended interactive learning materials for a user who appears bored" into the generative AI model, and then selects and sends the content output by the model.

[0633] Step 5:

[0634] Users provide feedback via their device after learning. The system receives evaluation data provided by the user as input and sends feedback information to the server as output. Specific actions include filling out and submitting a feedback form, which the system records in a database.

[0635] Step 6:

[0636] The server analyzes user feedback and learning history data to determine rewards for educators. It utilizes collected feedback data and past learning history as input, and provides educators with suggestions for improving educational resources and reward information as output. Specifically, it uses data analysis algorithms to evaluate educators' contributions and assign incentives.

[0637] (Application Example 2)

[0638] 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."

[0639] In modern learning systems, providing customized learning experiences tailored to individual users' learning needs and emotional states is challenging. In particular, real-time emotional recognition and dynamic adjustment of learning content based on that recognition are required, but conventional systems have failed to effectively address this issue. Furthermore, there are insufficient methods for appropriately utilizing user feedback for educators and providing rewards for their contributions.

[0640] 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.

[0641] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, means for suggesting optimal learning information based on the user's learning needs, means for recognizing the user's emotional state during learning and dynamically adjusting the learning information based on emotional data, means for collecting feedback after the user's learning, and means for providing rewards to educators based on the feedback. This makes it possible to provide a customized educational experience suited to individual users and improve learning effectiveness.

[0642] "Educational information" refers to all materials and data used by learners to acquire knowledge and skills.

[0643] A "generative AI model" refers to artificial intelligence technology used to generate learning content based on input data and provide it to learners.

[0644] "Learning needs" refer to the demands and necessities that individual learners face during the learning process, and include requirements for promoting effective learning.

[0645] "Emotional state" refers to the psychological state a learner exhibits during learning, such as interest, concentration, boredom, and frustration.

[0646] "Emotional data" refers to information about emotions obtained from the learner's facial expressions and tone of voice.

[0647] "Opinions" refer to feedback, suggestions for improvement, and comments that learners provide after using the learning content.

[0648] "Education professionals" refers to individuals and organizations involved in the provision, management, and instruction of educational content.

[0649] "Rewards" refer to incentives or rewards that educators receive when they provide valuable educational content or learning support.

[0650] This invention realizes a system for providing customized educational experiences tailored to individual users. Specifically, it utilizes multiple hardware and software components to collect educational information, train a generation AI model, and recognize and evaluate the user's emotional state.

[0651] The server collects educational information from various educational platforms on the internet, integrates it, and stores it in a database. The collected information is used to train a generative AI model built using programming languages ​​such as Python. This AI model has the ability to generate optimal learning information based on the user's learning needs.

[0652] Meanwhile, the device uses a camera and microphone to detect the user's facial expressions and voice tone in real time during the learning process. This allows it to recognize the user's emotional state and transmit that data to a server. The emotion recognition technology used includes state-of-the-art image processing software and voice analysis tools. This emotional data serves as the foundation for the generative AI model to dynamically adjust and provide learning information.

[0653] Users provide feedback on the content using their devices after a learning session. This feedback is used to improve future content creation and the learning experience. Educators are also rewarded based on the collected feedback and sentiment data. This reward system incentivizes educators to improve the quality of the content they provide.

[0654] For example, if a user looks bored while watching a history video lesson, the server can immediately detect this and use a generative AI model to provide more interactive and engaging material. An example of such a prompt might be, "If the user's emotional state indicates moderate interest and attention, generate new interactive visual content."

[0655] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0656] Step 1:

[0657] The server collects educational information from online educational platforms, integrates it, and stores it in a database. In this step, the server automatically retrieves content in various formats (text, audio, video) and converts it into a unified data format. The input is educational content retrieved from the web, and the output is formalized data stored in the integrated database on the server.

[0658] Step 2:

[0659] The server trains a generative AI model using integrated educational information. The input is processed training data, and the output is the trained generative AI model. In this step, the model learns the logic to generate optimal content based on the user's learning needs using the data. In particular, the AI ​​model analyzes patterns within the dataset and uses this to improve future content delivery.

[0660] Step 3:

[0661] The device uses its camera and microphone to record facial expressions and voice tone in real time while the user is using learning content. The input is live data from the device's camera and microphone, and the output is emotional state data analyzed in real time. The device uses an emotion recognition engine to process this data and identify the user's emotional state.

[0662] Step 4:

[0663] After the emotional state is acquired, the emotional data is sent to the server. The server receives this data and uses a generative AI model to dynamically adjust the learning content based on it. The input is real-time emotional data, and the output is the optimal learning information provided to the user. This adjustment selects content optimized to increase the user's attention and interest.

[0664] Step 5:

[0665] After completing a learning session, users provide feedback via their device. The input is the feedback information entered by the user through their device, and the output is integrated feedback data processed on the server. In this step, the collected feedback is used to improve future content creation and the user experience.

[0666] Step 6:

[0667] The server rewards educators based on feedback and sentiment data. The input is analyzed feedback and sentiment data, and the output is instructions for the reward system. This allows educators to evaluate the quality of their content and identify areas for improvement.

[0668] 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.

[0669] 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.

[0670] 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.

[0671] [Fourth Embodiment]

[0672] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0673] 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.

[0674] 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).

[0675] 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.

[0676] 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.

[0677] 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).

[0678] 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.

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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".

[0685] The present invention is implemented as a system that efficiently collects and integrates educational content and utilizes a generative AI model to provide customized learning based on learning needs. The embodiments thereof are described below with specific examples.

[0686] Data collection and integration

[0687] The server collects course content accessible from multiple educational platforms via the internet. This content is provided in text, audio, and video formats. The server manages the metadata of this content and integrates it into appropriate databases through advanced filtering.

[0688] Training of Generative AI Models

[0689] Based on the collected data, the server trains a generative AI model. This model has the ability to generate optimal learning materials tailored to user needs, encompassing a wide range of learning content including mathematics, science, and language learning. The thus trained model can accommodate learners from different regions and cultural backgrounds.

[0690] User profile creation and content suggestion

[0691] The device requires user information to be entered during initial setup. This includes the learner's age, areas of interest, and learning goals. This information is sent to the server, where a user profile is created. Based on this profile, the server uses a generative AI model to suggest the most suitable learning content for the user.

[0692] As a concrete example, consider an English learning program customized for elementary school students. In this case, the server generates animated learning materials that focus on English conversation practice and creates an efficient learning package that includes related practice exercises. This provides learners with content that is easy to see and enjoyable to learn from.

[0693] Utilizing learning history and feedback

[0694] Users learn using the provided content. After completing their learning, they can provide feedback via their device. This feedback is sent to the server and used to create and suggest future content. This enables flexible education that responds to the changing needs of learners.

[0695] The server provides incentives to educators based on the feedback information it collects. This mechanism increases the motivation to provide better content, thereby improving the overall quality of education.

[0696] These processes in the present invention enable the provision of customized education tailored to individual learning needs and are key to accommodating diverse learners.

[0697] The following describes the processing flow.

[0698] Step 1:

[0699] The server collects lesson content from the educational platform. This involves using an API to retrieve data and adding metadata such as content tags and category information (e.g., subject and target age).

[0700] Step 2:

[0701] The server integrates the collected content into a database. The database is designed to allow for efficient data retrieval and searching.

[0702] Step 3:

[0703] The server trains a generative AI model using integrated data from the database. This AI model improves its ability to extract features from different data formats (text, audio, video) and generate optimized learning content.

[0704] Step 4:

[0705] The device collects information from the user during initial setup. Specifically, it prompts the user to enter information such as their learning objectives, areas of interest, and preferred learning style.

[0706] Step 5:

[0707] The server creates a profile based on user information sent from the terminal. Using this profile, an AI model generates and delivers customized content tailored to the user's needs.

[0708] Step 6:

[0709] Users engage in educational activities using learning content provided via their devices. For example, they can watch video materials or work on practice problems.

[0710] Step 7:

[0711] After completing their learning, users provide feedback through their devices. This feedback concerns the usefulness of the content and the effectiveness of the learning experience.

[0712] Step 8:

[0713] The server collects user feedback and uses it to improve the entire system. Based on this data, the quality of the content provided next time will be improved.

[0714] Step 9:

[0715] The server provides incentives to educators based on the feedback it collects. This feedback loop leads to improvements in the quality of educational content and the provision of better services.

[0716] (Example 1)

[0717] 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".

[0718] In today's educational environment, there is a need to efficiently provide educational content that matches the needs of individual learners. However, existing systems fail to adequately collect content and provide personalized learning experiences, and the use of appropriate feedback to learners is also insufficient. In particular, the automatic generation of learning materials tailored to region and culture is difficult, and there is a lack of appropriate motivation for educators. These problems lead to challenges in the quality of learning and learner satisfaction.

[0719] 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.

[0720] In this invention, the server includes means for aggregating and centralizing educational materials, means for training a generation AI algorithm based on the aggregated materials, and means for suggesting optimal learning materials based on the user's learning needs. This makes it possible to provide customized educational content that utilizes the profile information of individual learners. By managing the metadata of the collected content and efficiently filtering it based on that metadata, appropriate educational materials are automatically suggested, providing a learning experience tailored to each learner. Furthermore, the quality of education can be improved by providing rewards to educators based on evaluation information.

[0721] "Educational materials" is a general term for information and content used for educational purposes, and includes a variety of formats such as text, audio, and video.

[0722] "Aggregation" refers to the process of collecting data from multiple sources and combining them into a single entity.

[0723] "Methods of centralization" refer to methods of integrating collected data and managing it in an organized manner.

[0724] A "generative AI algorithm" is an artificial intelligence technology that generates new information based on data, and is particularly useful for generating educational materials in the field of education.

[0725] "User learning needs" refers to information such as the learning content, goals, and interests that learners desire, and serves as the basis for providing individualized learning experiences based on this information.

[0726] "Metadata" refers to attribute information associated with the data in question, including content category, target audience, difficulty level, etc.

[0727] "Filtering" is a method of selecting data based on certain conditions, and it is a process performed to extract only the information that is relevant to the user.

[0728] "Profile information" refers to personal information such as the user's age, interests, and learning objectives, and is used to design a customized learning experience.

[0729] "Evaluation" refers to feedback that users provide after learning about the content, including their assessment of its effectiveness and satisfaction level.

[0730] "Rewards" refer to incentives provided to educators and content providers as a reward for their achievements and contributions.

[0731] This invention is a system that enables the efficient collection, integration, and generation of educational content, and provides personalized learning utilizing AI (artificial intelligence) models. Specific embodiments of this system are described below.

[0732] Data collection and integration

[0733] The server accesses multiple educational platforms via the internet to collect educational content. This process uses APIs and web scraping techniques to retrieve data in text, audio, and video formats. The collected content, along with metadata, is integrated into a database. For example, the server might collect math content for a specific grade level from educational websites, organize it by category, and create a database.

[0734] Training of Generative AI Models

[0735] The server trains a generative AI model based on learning materials obtained from an integrated database. Here, natural language processing and machine learning techniques are utilized to enable the generative AI model to autonomously create diverse learning content. Using a notebook-type server allows for rapid model training.

[0736] User profile creation and content suggestion

[0737] The terminal allows learners to input necessary personal information through an interface. This information includes the learner's age, desired field of study, and learning goals. This information is sent to a server, from which a user profile is created. The server uses this profile information and a generative AI model to suggest optimal learning content to the learner. An example of a prompt is, "Please create English dialogue practice material for fifth-grade elementary school students."

[0738] For example, in the case of an English learning program for elementary school students, the server generates and provides content that includes animated conversation materials and related practice exercises. This allows learners to receive visually easy-to-understand and enjoyable learning materials.

[0739] Utilizing learning history and feedback

[0740] Users learn through content provided via their devices and provide feedback using their devices after completing their studies. This feedback is sent to the server and used to generate the next learning content. The server has a system in place to reward appropriate educators and motivate them to create better content.

[0741] The objective of this invention is to provide a personalized educational experience and optimize the user's learning environment.

[0742] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0743] Step 1:

[0744] Data collection

[0745] The server accesses educational platforms via the internet. The input consists of API information and HTML structures from each platform. The server then uses APIs and executes web scraping scripts to collect educational content in text, audio, and video formats. The output is datasets in these formats.

[0746] Step 2:

[0747] Content filtering and integration

[0748] Based on the collected data, the server analyzes the metadata of each piece of content. This metadata includes category, difficulty level, and target age group. The server then uses this metadata to perform advanced filtering, selecting only relevant content. Finally, it organizes and integrates the selected content into a database. The output is this integrated database.

[0749] Step 3:

[0750] Training of Generative AI Models

[0751] The server uses educational data extracted from an integrated database. The input consists of digital data converted from text, audio, and video. The server feeds this data to a generative AI model for training, which includes feature extraction and optimization of model parameters. The output is the trained generative AI model.

[0752] Step 4:

[0753] Creating a User Profile

[0754] The terminal receives personal information entered by the user. This information includes the learner's age, areas of interest, and goals. The terminal sends this information to the server and stores it in the database as a user profile. The output is the user's profile information.

[0755] Step 5:

[0756] Suggestions for customized content

[0757] The server uses user profile information and a trained generative AI model. The input consists of profile data and requests to the generative AI model. Based on this, the server generates and selects optimal content tailored to the user's learning needs. The generated prompts are passed to the AI ​​model to obtain individual training materials. The output is customized training content suggested to the user.

[0758] Step 6:

[0759] Utilizing learning history and feedback

[0760] Users learn content provided on their devices and provide feedback during and after the learning process. This feedback data is sent from the device to the server. The input includes evaluations of learning progress, comprehension, and satisfaction. The server stores this data and analyzes it to use in generating future content. The output is improvements to the next learning content based on the analysis results.

[0761] (Application Example 1)

[0762] 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".

[0763] In modern society, providing educational content that meets the diverse needs of learners is crucial. However, traditional methods make it difficult to efficiently deliver optimal educational content to individual learners. In particular, there is a need for real-time customization and the suggestion of appropriate learning paths based on each learner's interests.

[0764] 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.

[0765] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, and means for delivering content to a smartphone according to the user's learning goals and interests. This makes it possible to efficiently and effectively provide educational content tailored to the individual needs of learners.

[0766] "Educational information" is a general term for data and materials used to support learners in acquiring knowledge.

[0767] A "generative AI model" is a type of artificial intelligence that creates new educational content based on collected data.

[0768] "User" refers to an individual or group that receives the educational services provided.

[0769] "Learning objectives" refer to the specific knowledge and skills that learners aim to acquire.

[0770] A "smartphone" is a multi-functional portable information terminal, an electronic device capable of voice calls, messaging, and internet connectivity.

[0771] "Feedback" refers to the act or content of providing evaluations or opinions on a learner's learning experience.

[0772] An "educational expert" refers to an individual or organization that possesses specialized knowledge and skills regarding the content and methods of education.

[0773] "Reward" refers to the economic or other benefits provided for a particular action or outcome.

[0774] "Learning history" refers to a record of past learning activities and is data that shows the learner's progress and acquisition status.

[0775] This invention is an educational content delivery system that adapts to the diverse needs of learners. For its implementation, three main elements—server, terminal, and user—interact with each other.

[0776] The server collects and integrates educational information from multiple educational sources via the internet. The collected information, in various formats including text, audio, and video, is integrated into a database that manages metadata. Based on the collected information, the server trains a generative AI model. This model is designed to generate educational materials tailored to the user's learning needs. Software used includes Python and TensorFlow.

[0777] A device, such as a smartphone, provides an interface for inputting user information. This information includes learning goals and areas of interest, and is sent to a server. The server generates learning content optimized for the user and delivers it to the device. The delivered content can be viewed on the user's smartphone, and content is provided according to the learner's progress.

[0778] Users progress through their learning using content provided on their devices. After learning, they provide feedback, and the server updates the generated AI model based on the collected feedback, incorporating it into future content suggestions. A system that rewards educational professionals helps improve the quality of education.

[0779] As a concrete example, let's say there is a user who is an intermediate Japanese speaker and wants to learn English. Based on this user's learning goals, the server generates optimal content using a prompt message such as, "Generate English listening materials for intermediate Japanese learners. The target age is 10-12 years old, and the theme is animals." The generated materials are delivered to the user's smartphone and provide interactive videos that contribute to improving listening skills. By utilizing a feedback mechanism that measures performance and rewards educational professionals, the sustainable operation of the entire system becomes possible.

[0780] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0781] Step 1:

[0782] The server collects educational information from multiple educational sources via the internet. It accepts data in various formats, including text, audio, and video, as input. The collected information, along with metadata, is integrated into a database. This creates a large dataset of available educational information.

[0783] Step 2:

[0784] The server trains a generative AI model using the collected data as input. Supervised learning algorithms are used to process the data, extracting and learning features appropriate for each data format. The output of this process is a generative AI model optimized for user needs.

[0785] Step 3:

[0786] Users operating the terminal input their learning goals and areas of interest. This data is sent to the server, which creates a user profile. The creation of this profile allows the server to accumulate data based on each user's needs.

[0787] Step 4:

[0788] The server receives a user profile and a generated AI model as input and uses prompts to generate optimal educational content. Based on these prompts, the AI ​​model outputs the most appropriate educational materials for the user.

[0789] Step 5:

[0790] The generated educational content is delivered to the user's device. For example, English listening comprehension videos are provided to the smartphone. These videos are tailored to the user's learning objectives and are delivered in an interactive format.

[0791] Step 6:

[0792] Users use the content and progress through their learning. After completing their learning, they provide feedback based on their learning experience via their device. This feedback is sent to the server and used as data to improve future content creation.

[0793] Step 7:

[0794] The server generates information to reward education professionals based on the collected feedback. This enables an incentive system aimed at improving performance and content, supporting the overall operation of the system.

[0795] 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.

[0796] The present invention is implemented in a form that combines an emotion engine with a system that collects and integrates educational content and utilizes a generative AI model to provide a customized learning experience tailored to learning needs. Specific embodiments are described below.

[0797] Utilization of data collection and generative AI models

[0798] The server collects lesson content from various educational platforms on the internet. This content is provided in different formats (text, audio, video), integrated, and efficiently stored in a database. The server has the ability to use the collected data to train a generative AI model and generate learning content tailored to the user's learning needs.

[0799] Combination of emotional engines

[0800] This system incorporates an emotion engine that recognizes user emotions in real time. The device uses a camera and microphone to analyze the user's facial expressions and tone of voice, and evaluates the user's emotional state during learning. This emotion data is sent to a server and used to improve the learning experience.

[0801] As a concrete example, consider a scenario where a student is using video learning materials for language acquisition. While the user is watching the video, the emotion engine analyzes the user's level of concentration and interest. For example, if the user looks bored, the server immediately detects this and suggests more interactive and engaging materials, or content that encourages a break.

[0802] Utilizing learning history and feedback

[0803] After a learning session, users provide feedback via their device regarding the usefulness and educational effectiveness of the provided content. This feedback is integrated and analyzed by the server and used to improve future content creation and the learning experience.

[0804] Provision of incentives

[0805] The server analyzes user feedback and sentiment data to provide appropriate incentives to educators. This system allows educators to identify areas for improvement in their content and strive to provide better educational resources.

[0806] Thus, this invention is designed as a system that provides users with an optimized learning experience through the customization of educational content, dynamic adjustment based on emotion recognition, and continuous improvement through feedback, while also appropriately evaluating and rewarding the contributions of all stakeholders involved in education.

[0807] The following describes the processing flow.

[0808] Step 1:

[0809] The server collects educational content in various formats (text, audio, video, etc.) from educational platforms and other online resources. The collected data is integrated into a database along with metadata and organized for easy searching.

[0810] Step 2:

[0811] The server uses integrated educational content to train a generative AI model. During this training process, the AI ​​model learns the characteristics of different educational content and acquires the ability to generate and select content that meets the user's learning needs.

[0812] Step 3:

[0813] The device collects initial user information, including age, areas of interest, and learning goals. This information is sent to a server and stored as part of the user's learning profile.

[0814] Step 4:

[0815] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice during learning sessions. It uses the camera and microphone to assess the user's emotional state (e.g., joy, concentration, boredom, etc.) in real time.

[0816] Step 5:

[0817] The server receives data from the emotion engine and dynamically adjusts the learning content based on the user's emotional state. For example, if the user appears to be having difficulty understanding something, it will suggest additional explanatory videos or a different learning approach.

[0818] Step 6:

[0819] Users continue learning using tailored learning content provided by the server. Feedback and sentiment data during learning are continuously collected and reflected in the system in real time.

[0820] Step 7:

[0821] After a learning session ends, users provide feedback on their learning experience via their device. This includes information on content quality, comprehension, and overall satisfaction with the learning experience.

[0822] Step 8:

[0823] The server comprehensively analyzes user feedback and sentiment data to update its database and improve the quality of the next learning session. This process provides a more optimized experience for each individual learner.

[0824] Step 9:

[0825] Ultimately, the server provides educators with feedback-based incentives. These incentives motivate content providers to continuously improve the quality of their content.

[0826] (Example 2)

[0827] 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".

[0828] In today's educational environment, there is a demand for customized educational resources that meet the diverse needs of learners. However, existing systems often fail to reflect individual learners' emotional states and learning tendencies in real time, resulting in uniform education. Furthermore, mechanisms for effectively utilizing learner feedback and providing appropriate rewards to educators are insufficient.

[0829] 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.

[0830] In this invention, the server includes means for collecting and integrating educational information, means for training a machine learning model based on the collected information, and means for recognizing the user's emotional state in real time and providing information according to the learning situation. This enables the provision of educational resources adapted to the individual needs of learners, as well as effective feedback and rewards for educators.

[0831] "Educational information" refers to all forms of data and content provided to learners (e.g., text, audio, video, etc.) that are intended for knowledge acquisition in learning.

[0832] A "machine learning model" is an algorithm that analyzes data, learns patterns, and automatically makes predictions and decisions, and its performance improves with the use of training data.

[0833] "Users" refers to individuals or groups who use the system to access educational information and engage in learning activities.

[0834] "Emotional state" refers to the user's psychological and physiological state at a specific time, and is determined through analysis of facial expressions and voice tone.

[0835] "Rewards" refer to compensation or evaluations provided to educators based on user feedback and system analysis, and are intended to promote quality improvement.

[0836] This invention provides a system for appropriately customizing educational information for each user. Specific embodiments thereof are described below.

[0837] The server scans educational information sources on the internet to collect and integrate various types of information. It utilizes web crawlers and API calls to collect data in multiple formats, including text, audio, and video. This allows a wide range of information to be efficiently stored in a database. Data management systems such as MySQL or MongoDB are used for the database.

[0838] Based on this collected data, the server trains a generative AI model. Training uses machine learning techniques such as OpenAI's GPT series, learning from large amounts of data. The generated model has the ability to adapt to the user's learning needs and provide appropriate educational resources.

[0839] The device recognizes the user's emotional state in real time. Specifically, it analyzes the user's facial expressions and voice tone using a camera and microphone. This allows it to monitor the user's level of concentration and interest, and send emotional data to the server as needed. This process utilizes libraries such as OpenCV and TensorFlow.

[0840] As a concrete example, consider a situation where a user appears bored while learning a language. In this case, the server inputs a prompt message such as "Generate recommended interactive learning materials for a user who appears bored" into the AI ​​model, providing more appropriate educational resources. By linking the user's emotional state with learning resources in this way, it becomes possible to provide a dynamic learning experience.

[0841] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0842] Step 1:

[0843] The server scans educational platforms on the internet to collect educational information. It uses URLs and API credentials from various educational websites as input and retrieves data in text, audio, and video formats as output. It uses a web crawler to collect data and processes it to integrate data in different formats. This ensures that a wide range of learning content is stored in a unified database format.

[0844] Step 2:

[0845] The server trains machine learning models using information stored in the database. Collected training data is used as input, and a trained generative AI model adapted to the user's learning needs is generated as output. Specifically, the data is divided into appropriate batch sizes, and the model parameters are optimized by applying a learning algorithm.

[0846] Step 3:

[0847] The device monitors the user's emotional state in real time. It acquires video and audio data from devices such as cameras and microphones as input, and analyzes the user's emotional state based on their facial expressions and tone of voice as output. Specifically, it utilizes image recognition and voice analysis technologies to evaluate the emotions the user is experiencing.

[0848] Step 4:

[0849] The server receives emotion data sent from the terminal and generates new educational information tailored to the user's learning progress. It receives user state information through emotion recognition as input and provides the user with customized learning content generated using a generative AI model as output. Specifically, it inputs a prompt such as "Generate recommended interactive learning materials for a user who appears bored" into the generative AI model, and then selects and sends the content output by the model.

[0850] Step 5:

[0851] Users provide feedback via their device after learning. The system receives evaluation data provided by the user as input and sends feedback information to the server as output. Specific actions include filling out and submitting a feedback form, which the system records in a database.

[0852] Step 6:

[0853] The server analyzes user feedback and learning history data to determine rewards for educators. It utilizes collected feedback data and past learning history as input, and provides educators with suggestions for improving educational resources and reward information as output. Specifically, it uses data analysis algorithms to evaluate educators' contributions and assign incentives.

[0854] (Application Example 2)

[0855] 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".

[0856] In modern learning systems, providing customized learning experiences tailored to individual users' learning needs and emotional states is challenging. In particular, real-time emotional recognition and dynamic adjustment of learning content based on that recognition are required, but conventional systems have failed to effectively address this issue. Furthermore, there are insufficient methods for appropriately utilizing user feedback for educators and providing rewards for their contributions.

[0857] 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.

[0858] In this invention, the server includes means for collecting and integrating educational information, means for training a generative AI model based on the collected information, means for suggesting optimal learning information based on the user's learning needs, means for recognizing the user's emotional state during learning and dynamically adjusting the learning information based on emotional data, means for collecting feedback after the user's learning, and means for providing rewards to educators based on the feedback. This makes it possible to provide a customized educational experience suited to individual users and improve learning effectiveness.

[0859] "Educational information" refers to all materials and data used by learners to acquire knowledge and skills.

[0860] A "generative AI model" refers to artificial intelligence technology used to generate learning content based on input data and provide it to learners.

[0861] "Learning needs" refer to the demands and necessities that individual learners face during the learning process, and include requirements for promoting effective learning.

[0862] "Emotional state" refers to the psychological state a learner exhibits during learning, such as interest, concentration, boredom, and frustration.

[0863] "Emotional data" refers to information about emotions obtained from the learner's facial expressions and tone of voice.

[0864] "Opinions" refer to feedback, suggestions for improvement, and comments that learners provide after using the learning content.

[0865] "Education professionals" refers to individuals and organizations involved in the provision, management, and instruction of educational content.

[0866] "Rewards" refer to incentives or rewards that educators receive when they provide valuable educational content or learning support.

[0867] This invention realizes a system for providing customized educational experiences tailored to individual users. Specifically, it utilizes multiple hardware and software components to collect educational information, train a generation AI model, and recognize and evaluate the user's emotional state.

[0868] The server collects educational information from various educational platforms on the internet, integrates it, and stores it in a database. The collected information is used to train a generative AI model built using programming languages ​​such as Python. This AI model has the ability to generate optimal learning information based on the user's learning needs.

[0869] Meanwhile, the device uses a camera and microphone to detect the user's facial expressions and voice tone in real time during the learning process. This allows it to recognize the user's emotional state and transmit that data to a server. The emotion recognition technology used includes state-of-the-art image processing software and voice analysis tools. This emotional data serves as the foundation for the generative AI model to dynamically adjust and provide learning information.

[0870] Users provide feedback on the content using their devices after a learning session. This feedback is used to improve future content creation and the learning experience. Educators are also rewarded based on the collected feedback and sentiment data. This reward system incentivizes educators to improve the quality of the content they provide.

[0871] For example, if a user looks bored while watching a history video lesson, the server can immediately detect this and use a generative AI model to provide more interactive and engaging material. An example of such a prompt might be, "If the user's emotional state indicates moderate interest and attention, generate new interactive visual content."

[0872] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0873] Step 1:

[0874] The server collects educational information from online educational platforms, integrates it, and stores it in a database. In this step, the server automatically retrieves content in various formats (text, audio, video) and converts it into a unified data format. The input is educational content retrieved from the web, and the output is formalized data stored in the integrated database on the server.

[0875] Step 2:

[0876] The server trains a generative AI model using integrated educational information. The input is processed training data, and the output is the trained generative AI model. In this step, the model learns the logic to generate optimal content based on the user's learning needs using the data. In particular, the AI ​​model analyzes patterns within the dataset and uses this to improve future content delivery.

[0877] Step 3:

[0878] The device uses its camera and microphone to record facial expressions and voice tone in real time while the user is using learning content. The input is live data from the device's camera and microphone, and the output is emotional state data analyzed in real time. The device uses an emotion recognition engine to process this data and identify the user's emotional state.

[0879] Step 4:

[0880] After the emotional state is acquired, the emotional data is sent to the server. The server receives this data and uses a generative AI model to dynamically adjust the learning content based on it. The input is real-time emotional data, and the output is the optimal learning information provided to the user. This adjustment selects content optimized to increase the user's attention and interest.

[0881] Step 5:

[0882] After completing a learning session, users provide feedback via their device. The input is the feedback information entered by the user through their device, and the output is integrated feedback data processed on the server. In this step, the collected feedback is used to improve future content creation and the user experience.

[0883] Step 6:

[0884] The server rewards educators based on feedback and sentiment data. The input is analyzed feedback and sentiment data, and the output is instructions for the reward system. This allows educators to evaluate the quality of their content and identify areas for improvement.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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."

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0906] The following is further disclosed regarding the embodiments described above.

[0907] (Claim 1)

[0908] Means for collecting and integrating educational content,

[0909] A means of training a generative AI model based on collected content,

[0910] A means of suggesting optimal learning content based on the user's learning needs,

[0911] A means of collecting feedback after the user has learned,

[0912] A means of providing incentives to educators based on the aforementioned feedback,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, characterized in that the generation AI model includes means for generating learning content suitable for a region and culture.

[0916] (Claim 3)

[0917] The system according to claim 1, characterized in that it includes means for analyzing the user's learning history and determining learning tendencies.

[0918] "Example 1"

[0919] (Claim 1)

[0920] A means of consolidating and centralizing educational materials,

[0921] A means of training a generative AI algorithm based on aggregated data,

[0922] A means of suggesting the most suitable learning materials based on the user's learning needs,

[0923] A means of collecting evaluations after users have learned,

[0924] A means of providing rewards to educators based on the aforementioned evaluation,

[0925] A means of managing the metadata of collected content and filtering the content based on that metadata,

[0926] A method for suggesting customized learning materials using user profiles,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, characterized in that the generation AI algorithm includes means for generating learning materials that are appropriate to the region and culture.

[0930] (Claim 3)

[0931] The system according to claim 1, characterized in that it includes means for analyzing the user's learning history and determining learning tendencies.

[0932] "Application Example 1"

[0933] (Claim 1)

[0934] Means for collecting and integrating educational information,

[0935] A means of training a generative AI model based on collected information,

[0936] A means of suggesting the most suitable learning materials based on the user's learning needs,

[0937] A means of collecting feedback from users after they have learned,

[0938] A means of providing compensation to education professionals based on the aforementioned feedback,

[0939] A means of delivering content to smartphones according to the user's learning goals and interests,

[0940] A system that includes this.

[0941] (Claim 2)

[0942] The system according to claim 1, characterized in that the generating AI model includes means for generating learning materials suitable for a region and culture.

[0943] (Claim 3)

[0944] The system according to claim 1, characterized in that it includes means for analyzing the user's learning history and determining their learning tendencies.

[0945] "Example 2 of combining an emotion engine"

[0946] (Claim 1)

[0947] Means for collecting and integrating educational information,

[0948] A means of training a machine learning model based on the collected information,

[0949] A means of suggesting the most suitable educational resources based on the user's learning needs,

[0950] A means of recognizing the user's emotional state in real time and providing information tailored to their learning progress,

[0951] A means of collecting evaluations after users have learned,

[0952] A means of providing compensation to educators based on the aforementioned evaluation,

[0953] A system that includes this.

[0954] (Claim 2)

[0955] The system according to claim 1, characterized in that the machine learning model includes means for generating educational resources suitable for a region and culture.

[0956] (Claim 3)

[0957] The system according to claim 1, characterized in that it includes means for analyzing the user's learning history and determining a learning pattern.

[0958] "Application example 2 when combining with an emotional engine"

[0959] (Claim 1)

[0960] Means for collecting and integrating educational information,

[0961] A means of training a generative AI model based on collected information,

[0962] A means of suggesting optimal learning information based on the user's learning needs,

[0963] A means for recognizing the user's emotional state during learning and dynamically adjusting learning information based on emotional data,

[0964] A means of collecting feedback after users have learned,

[0965] A means of providing compensation to educators based on the aforementioned opinion,

[0966] A system that includes this.

[0967] (Claim 2)

[0968] The system according to claim 1, characterized in that the generation AI model includes means for generating learning information suitable for a region and culture.

[0969] (Claim 3)

[0970] The system according to claim 1, characterized in that it includes means for analyzing the user's learning history and determining learning tendencies. [Explanation of symbols]

[0971] 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 and integrating educational content, A means of training a generative AI model based on collected content, A means of suggesting optimal learning content based on the user's learning needs, A means of collecting feedback after the user has learned, A means of providing incentives to educators based on the aforementioned feedback, A system that includes this.

2. The system according to claim 1, characterized in that the generation AI model includes means for generating learning content suitable for a region and culture.

3. The system according to claim 1, characterized in that it includes means for analyzing the user's learning history and determining learning tendencies.

Images