system

Abstract

We provide the system. [Solution] A means for receiving learners' cognitive characteristics and generating profiles, A means for analyzing the learning content based on the aforementioned profile and determining the conversion format, A means for converting learning content according to a determined conversion format, A means of sending converted content to learners and supporting their learning, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Since learners have different cognitive characteristics, there is a problem that the learning efficiency of each cannot be maximized with uniform learning content. In addition, since a mechanism for providing optimal learning content according to the characteristics of learners, such as visual dominance, auditory dominance, and language dominance, has not been sufficiently established, it is difficult to provide an environment in which learners can learn efficiently.

Means for Solving the Problems

[0005] This invention provides a system that receives the cognitive characteristics of learners, analyzes learning content based on those characteristics, and determines the optimal conversion format. This system converts the content according to the determined conversion format and transmits the converted content to the learner, thereby providing a learning environment optimized for each learner. Specifically, for example, it has the function of converting text into video format for visually dominant learners and converting text into audio format for auditorily dominant learners.

[0006] A "learner" refers to an individual who acquires knowledge and skills as part of educational activities or self-development.

[0007] "Cognitive characteristics" refer to each individual's unique tendencies and styles when perceiving and processing information.

[0008] A "profile" refers to data that systematically organizes information about a learner's characteristics and learning situation.

[0009] "Learning content" refers to educational materials and resources intended to transmit specific knowledge or skills.

[0010] "Conversion format" refers to the specific format or specifications used when changing learning content to a different format.

[0011] A "system" refers to a combination of multiple elements or devices designed to achieve a specific purpose. [Brief explanation of the drawing]

[0012] [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]It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention provides a method for realizing a system that converts learning content into an optimal format according to the characteristics of the learner, thereby improving the efficiency of learning. The system mainly consists of three components: a server, a terminal, and a user.

[0034] The server receives cognitive characteristics data from the user, provided through methods such as facial recognition or simple selections. This data includes information such as visual dominance, auditory dominance, and linguistic dominance. The server generates a profile from this information and stores it in the user database.

[0035] The terminal provides an interface for sending user-selected learning content to the server. Through the terminal, the user selects content and enters additional information such as learning objectives. This information is sent to the server for analysis.

[0036] The server determines the optimal conversion format for the content based on the user's profile. For example, for a visually-oriented user, an algorithm is applied that converts text information into video format. The converted content undergoes a quality check on the server before being sent to the device.

[0037] Users efficiently progress through their learning using the converted content sent to their device. In this way, the device functions as a platform for users to advance their learning. For example, for users who are auditorily dominant, text information is played back as an audio file. This process allows learners to learn in a way that is optimized for their own cognitive characteristics.

[0038] As a concrete example, let's assume that chemistry lecture notes are selected. For visually dominant users, the server converts the chemical reactions and structures into animated videos that visually represent them and delivers these resources to the terminal. On the other hand, for auditorily dominant users, the text content is converted into an audiobook with narration and provided as a fluent audio file.

[0039] The entire system is designed to dynamically generate the optimal learning environment tailored to each learner's individual characteristics, maximizing the efficiency of knowledge acquisition.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user starts up the device and logs into their learning account. The device displays a screen for setting up a cognitive characteristics profile and prompts the user to select one of the following: visual, auditory, or verbal.

[0043] Step 2:

[0044] The device sends cognitive characteristic information selected by the user to the server. The server receives this information, generates a profile for each user, and stores it in a database.

[0045] Step 3:

[0046] The user selects learning content on their device and enters their learning objectives and any additional individual requirements. This selection information is then sent from the device to the server.

[0047] Step 4:

[0048] Based on the content selection information received by the server and the cognitive characteristics profiles stored in the database, the server begins analyzing the content. The server evaluates the type and format of the content and determines which transformation is optimal.

[0049] Step 5:

[0050] The server converts learning content into a format best suited to the user's cognitive characteristics based on a selected conversion algorithm. For example, it converts text data into a video format for visually-oriented users.

[0051] Step 6:

[0052] The server verifies the converted content to ensure its accuracy and quality, thereby guaranteeing that knowledge is effectively transmitted.

[0053] Step 7:

[0054] The server sends the converted learning content to the device. The user receives the content through the device and uses it for learning.

[0055] Step 8:

[0056] Users utilize the learning content provided on their devices to engage in efficient learning. The device periodically sends the user's learning progress to the server, providing continuous learning support.

[0057] (Example 1)

[0058] 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."

[0059] A challenge exists in that learning efficiency is not improving due to a lack of learning information provided in a format suited to the cognitive characteristics of individual learners. This challenge stems from the limitations of existing operating systems and methods that cannot convert information into a format suitable for the characteristics of individual learners.

[0060] 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.

[0061] In this invention, the server includes means for collecting learner cognitive characteristic data, means for analyzing the data and generating and storing a learner profile, means for determining the optimal conversion format of learning information based on the profile, means for converting the learning information according to the conversion format determined using a generation AI model, and means for quality checking the converted learning information and providing it to the learner. This makes it possible to provide learning information optimized for each learner, thereby improving learning efficiency.

[0062] A "learner" is a person whose purpose is to receive learning information, understand it, and acquire it.

[0063] "Cognitive characteristics data" refers to data about learners' information processing characteristics, such as whether they are visually dominant, auditorily dominant, or linguistically dominant.

[0064] A "profile" is a collection of information that represents the individual characteristics of a learner, generated based on collected cognitive characteristics data.

[0065] "Learning information" refers to content intended for learners to study, and includes various formats such as text, audio, and video.

[0066] A "conversion format" is a format selected to transform learning information into a format optimized for the learner's cognitive characteristics.

[0067] A "generative AI model" is an artificial intelligence algorithm that generates new information or formats based on input data.

[0068] "Quality check" is the process of verifying that the converted learning information functions properly and meets the expected quality standards.

[0069] The embodiment for carrying out the present invention is a system consisting of three main elements: a server, a terminal, and a user.

[0070] The server receives cognitive characteristics data transmitted from the user (learner) through their device. This data is primarily acquired through facial recognition technology and selection-based input interfaces, and includes cognitive characteristics such as visual dominance, auditory dominance, and linguistic dominance. The server analyzes this data, generates a learner profile, and stores it in a database. Based on the profile, the server determines a format for transforming learning information that is optimized for the learner's characteristics.

[0071] Using a generative AI model, the server transforms the training information according to a predetermined conversion format. For example, for visually dominant learners, text information can be converted into an animated video format. The converted information undergoes quality checks before being sent to the terminal.

[0072] The terminal provides the user with an interface for selecting learning content. The user selects learning information of interest and enters their learning objectives, and all information is sent to the server.

[0073] Users can efficiently progress through their learning using content received from their devices. For example, if a visually-oriented user selects chemistry lecture notes, the server converts them into animated videos of chemical reactions and sends them to the device. Meanwhile, an auditorily-oriented user is provided with the same content as an audiobook with narration.

[0074] In this way, the entire system dynamically generates an optimal learning environment tailored to each user's individual cognitive characteristics, maximizing the efficiency of knowledge acquisition.

[0075] As an example of a prompt, you can use the format: "Convert the chemistry lecture notes into an animated video for visually-oriented learners."

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

[0077] Step 1:

[0078] The terminal collects cognitive characteristic data from the user. The user answers facial recognition and multiple-choice questions using the terminal's input interface. The input for this process is the user's cognitive characteristic data, and the output is data sent to the server. The terminal completes the data collection process by sending this data to the server.

[0079] Step 2:

[0080] The server analyzes cognitive characteristics data received from the terminal. Specifically, it uses a data analysis algorithm to generate profile information such as the user's visual dominance, auditory dominance, and linguistic dominance. The input for this step is the cognitive characteristics data received from the terminal, and the output is the generated user profile. The server saves this profile to a database.

[0081] Step 3:

[0082] The user selects the content they want to learn through their device. This selection is based on the user's learning objectives and interests. In this step, the learning content selected by the user becomes input, and this selection information is sent to the server. Specifically, users can choose from things like chemistry lecture notes or math problem sets.

[0083] Step 4:

[0084] The server determines the optimal content conversion format based on the received learning content information and the user's profile. Specifically, it uses a generative AI model to determine how to convert the content to a format that suits the learner's characteristics, along with prompt messages. The input for this step is the user's profile and the selected learning content information, and the output is the selected conversion format.

[0085] Step 5:

[0086] The server converts the training content based on the selected conversion format. In this step, a generative AI model is utilized, and specific conversion tasks are performed using prompts. For example, text can be converted to a video format. The input for this step is the conversion format and training content selected in the previous step, and the output is the converted content.

[0087] Step 6:

[0088] The server performs a quality check on the converted content before sending it to the terminal. Specifically, this involves verifying that the output content is accurate and suitable for the user's characteristics. The input for this step is the converted content, and the output is the content whose quality has been verified.

[0089] Step 7:

[0090] Users learn using the converted content delivered to their devices. The input for this step is quality-checked content delivered to the device, and users can proceed with their learning based on it. Specific examples include watching animated videos or listening to audiobooks.

[0091] (Application Example 1)

[0092] 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."

[0093] In recent years, despite the increasing need for efficient learning based on individual cognitive characteristics, traditional learning content is often provided in a generic format, making it difficult to optimize for individual user needs. This can hinder users' learning efficiency, comprehension, and learning speed. Especially in today's world, where various content is distributed via the internet, providing individually optimized learning support is a critical challenge.

[0094] 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.

[0095] In this invention, the server includes means for receiving learners' cognitive characteristics and generating a profile, means for analyzing learning content and determining a conversion format based on the profile, and means for dynamically distributing the content over a network. This makes it possible to deliver optimized content tailored to the cognitive characteristics of each individual learner, thereby improving the efficiency of learning.

[0096] "Learner cognitive characteristics" refer to the distinctive features of the cognitive processes that learners utilize to effectively understand and remember information, and include the dominance of visual, auditory, and linguistic learning.

[0097] A "profile" is an individual dataset formed based on a learner's cognitive characteristics and preferences, and serves as fundamental information for optimally transforming content.

[0098] "Learning content" refers to educational materials and teaching aids used by learners for specific purposes, and includes a variety of formats such as text, images, videos, and audio.

[0099] "Conversion format" refers to the format of display or playback determined to provide learning content in a form that is optimal for the learner's cognitive characteristics.

[0100] "Dynamic delivery via network" refers to the process of transmitting learning content to user terminals in real time via communication networks such as the internet.

[0101] "Visual devices" refer to devices used to present information visually, such as displays and screens.

[0102] "Audio equipment" refers to devices that present information through sound, such as speakers and headphones.

[0103] The system implementing this invention is designed to dynamically provide optimal learning content tailored to the learner's cognitive characteristics. The system mainly consists of three components: a server, a terminal, and a user.

[0104] The server receives facial recognition data and simple selection-based data sent by the user. This data includes the user's cognitive profile, namely, whether they are visually dominant, auditorily dominant, or linguistically dominant. The server uses this information to generate a profile and register it in a database. The server analyzes the learning content requested from the terminal and determines the optimal conversion format based on the profile. This conversion uses an algorithm that converts text content into video or audio using a generative AI model. The generated content is quality-checked and sent to the user's terminal via the network.

[0105] The device functions as a platform that sends user-selected learning content to a server and plays the converted content received from the server. Users can receive the content using visual and auditory devices, enabling them to learn efficiently. For example, visually-oriented learners can use animated videos illustrating chemical reactions, while auditorily-oriented learners can use audiobooks with narration.

[0106] For example, when a high school student reviews chemistry, an animated video is provided if they are good at receiving information visually, and a fluent audio file is provided if they are good at receiving information auditorily. Examples of prompts include, "Generate a learning video that is best suited to this user's visual learning style," and "Provide audio materials for users with auditory learning styles."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] Users select learning content through their devices and input facial recognition data and information in the form of selections. This information is sent from the device to the server as input data to understand the user's cognitive characteristics.

[0110] Step 2:

[0111] The server analyzes the received user facial recognition data and selected information to evaluate the dominance of each of the visual, auditory, and linguistic senses. Based on this, it identifies the user's cognitive characteristics and generates a profile. In this process, machine learning algorithms are used to process the data and extract characteristics.

[0112] Step 3:

[0113] The server analyzes the input learning content based on the generated profile. During this process, it determines the optimal conversion format for the content according to the user's characteristics. This determination involves matching the content type with the user profile and selecting a conversion algorithm.

[0114] Step 4:

[0115] The server converts the training content according to the determined conversion format. A generative AI model is used to convert text into video or audio. During this process, the content is visualized or audiotized, and the converted content is temporarily stored.

[0116] Step 5:

[0117] The server checks the quality of the converted content and transmits it to the terminal via the network. During this transmission, it verifies the accuracy and smoothness of the content to ensure it is provided to the user in the most optimal format.

[0118] Step 6:

[0119] The device receives the transmitted converted content and plays it back using visual and audio devices. The user experiences the converted content and learns in a way that is optimized for their own cognitive characteristics. This process improves learning efficiency.

[0120] 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.

[0121] This invention provides a method for implementing a system that optimizes learning content and improves individual learning experiences based on learners' cognitive characteristics and emotional states. The system consists of a server, a terminal, an emotion engine, and a user interface.

[0122] The server receives cognitive characteristics information provided by the user and stores it as a profile in the database. This system determines the format of learning content according to the learner's cognitive characteristics and further provides a more highly personalized learning experience by analyzing the learner's emotional state in real time using an emotion engine.

[0123] The device provides an interface for sending user-selected learning content and emotional data analyzed by the emotion engine to the server. Users select learning content from the device and receive the content as it is readjusted as needed.

[0124] The emotion engine analyzes input data from the user's device usage (e.g., facial expression analysis via camera and voice data) to determine the learner's emotional state. It can identify states such as decreased concentration, anxiety, or interest.

[0125] The server dynamically adjusts how learning content is presented based on the analysis results of the emotion engine. For example, if a learner is experiencing difficulty, the server provides feedback such as lowering the difficulty level of the content or slowing down the pace. Furthermore, if a learner shows interest, it can provide more advanced content or applied examples.

[0126] For example, if a user learning a math problem shows signs of anxiety, the server, based on the emotion engine's results, adds step-by-step explanations and simplifies the practice problems before sending them to the device. Conversely, if the user shows high concentration and interest in the problem, the difficulty level of the problem is increased, and application problems are provided.

[0127] In this way, learners can always receive content that is appropriate to their abilities and emotional state, creating an efficient and comfortable learning environment. This invention further improves learning effectiveness by integrating a learner's emotion analysis function.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The user logs into the device and inputs their cognitive characteristics, learning objectives, and areas of interest. The device sends this information to the server, where it is stored as foundational data for their profile.

[0131] Step 2:

[0132] The server analyzes cognitive characteristics information received from the user and generates a profile indicating either visual dominance, auditory dominance, or linguistic dominance. This profile is used to optimize learning content.

[0133] Step 3:

[0134] The device displays a list of selectable learning content to the user. The user selects the content they wish to learn and sends that information from the device to the server.

[0135] Step 4:

[0136] The server analyzes the selected learning content based on the user's profile and determines the optimal conversion format. For example, for a visually-oriented user, it might choose to convert text information into video.

[0137] Step 5:

[0138] Once the user begins learning, the device collects the user's emotional data (such as facial recognition results from the camera and voice tone) and sends it to the server in real time.

[0139] Step 6:

[0140] An emotion engine within the server analyzes the user's emotional state, evaluating factors such as concentration, stress levels, and anxiety. This information is then used to adjust the learning content.

[0141] Step 7:

[0142] The server dynamically changes how learning content is presented based on sentiment analysis results. It provides additional guidance and hints to users who show difficulty, and more challenging content to users who show interest.

[0143] Step 8:

[0144] The server sends the adjusted learning content to the device and presents it to the user. The user can continue learning through this updated content.

[0145] Step 9:

[0146] Once the user's learning is complete, the device sends final feedback and emotional changes to the server, which stores this information in the user's profile and uses it for future learning sessions.

[0147] (Example 2)

[0148] 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".

[0149] Conventional learning support systems have suffered from reduced learning efficiency because they cannot adaptively optimize learning content based on learners' cognitive characteristics and emotional states. Furthermore, the difficulty in providing individualized support tailored to each learner's situation means that maximizing learning effectiveness remains a challenge.

[0150] 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.

[0151] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating identification information, means for analyzing the information and determining a conversion format based on the identification information and emotional state, and means for converting the information according to the determined conversion format and providing a personalized learning experience. This enables real-time adaptive learning that is tailored to the learner's characteristics and state.

[0152] "Identifying information" refers to information that characterizes individual learners, generated based on their cognitive characteristics.

[0153] "Emotional state" refers to the learner's current psychological or emotional state, including interest, concentration, and anxiety.

[0154] "Analyzing information" is the process of conducting an analysis based on learner identification information and emotional states to determine the format and structure of the learning content to be provided.

[0155] A "conversion format" is a format for presenting information that is optimized for the learner, determined as a result of information analysis.

[0156] A "personalized learning experience" refers to individually optimized learning opportunities that are tailored to the learner's cognitive characteristics and emotional state.

[0157] This invention constructs a system that optimizes learning content based on the learner's cognitive characteristics and emotional state, providing a personalized learning experience. The system mainly consists of a server, terminals, an emotion analysis engine, and a user interface.

[0158] The server first generates identification information based on cognitive characteristics information received from the user. A database management system is used for this purpose, ensuring that information is efficiently stored and identified. Next, the server combines this information with the user's emotional state data provided by the emotion analysis engine, analyzes the learning content, and determines the conversion format. In this process, machine learning algorithms are used to determine an optimized content delivery strategy based on the given data.

[0159] The device displays learning content selected by the user and provides an interface for sending data obtained from the emotion analysis engine to the server. The emotion analysis engine uses the camera and microphone to analyze the user's facial expressions and voice patterns, thereby evaluating the user's emotional state in real time.

[0160] For example, if the sentiment analysis engine indicates that a user learning math problems is experiencing anxiety, the server will use that information to resend learning content to the device, including step-by-step explanations and simple practice problems. This ensures that the user's learning experience is optimized in real time.

[0161] As a concrete example of a prompt, the instruction "Optimize learning content based on the user's emotions and cognitive characteristics" is given to the generative AI model. This prompt provides the foundational information for delivering a learning experience that dynamically changes according to the user's state.

[0162] Thus, the present invention aims to provide users with optimized learning content and improve learning effectiveness and experience.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] Users input their cognitive characteristics information using a terminal. This is done using questionnaires or settings panels, clearly indicating the user's learning style and areas of expertise. The input information is sent from the terminal to a server as digital data and used to generate identification information.

[0166] Step 2:

[0167] The server generates identification information based on the received cognitive characteristics information. Here, the information is organized and stored using a database system. This identification information forms the basis for creating customized learning profiles for individual users. The generated profiles are stored in the database and used for future content optimization.

[0168] Step 3:

[0169] The user selects learning content through their device. The selected content is sent to the server via the device's interface. Simultaneously, the device sends data collected using its camera and microphone to an emotion analysis engine. This data serves as input for analyzing the user's real-time emotional state.

[0170] Step 4:

[0171] The emotion analysis engine uses data received from the device to determine the user's emotional state. It analyzes the user's facial expressions and tone of voice using image processing and voice analysis algorithms. The analysis identifies states such as concentration, anxiety, and interest, and these are sent back to the server.

[0172] Step 5:

[0173] The server analyzes the training content based on the results and identification information from the sentiment analysis engine. It runs a machine learning model to determine the optimal content presentation format and difficulty level for the user. In this process, it selects the optimal option from multiple candidates and generates it as transformed content.

[0174] Step 6:

[0175] The server sends optimized learning content to the device. The device displays this to the user, assisting with learning. By receiving content tailored to their cognitive characteristics and emotions, users can have a more effective learning experience.

[0176] This process allows users to continuously receive learning content tailored to their needs, improving both learning efficiency and satisfaction.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0179] Conventional learning systems optimized content based on learners' cognitive characteristics, but they failed to dynamically adjust content based on learners' emotional states. As a result, it was difficult to maintain learners' motivation and concentration. This invention aims to solve these problems and provide a more effective and personalized learning experience.

[0180] 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.

[0181] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating a profile; means for analyzing learning content and determining a conversion format based on the profile; and means for analyzing the emotional state in real time and dynamically adjusting the difficulty level and presentation method of the content based on the analysis results. This makes it possible to provide personalized learning content that matches the learner's cognitive characteristics and emotional state.

[0182] "Learner cognitive characteristics" refer to the individual abilities and preferences of learners when it comes to understanding and remembering information.

[0183] A "profile" is an individual information structure generated based on the learner's cognitive characteristics, and is used to optimize learning content.

[0184] A "conversion format" is a format used to change how learning content is presented, and it is determined according to the learner's profile.

[0185] "Emotional state" refers to the psychological and emotional responses that learners exhibit during learning, including concentration, interest, and anxiety.

[0186] "Real-time analysis" is a process that instantly analyzes the learner's emotional state and uses the results to respond quickly.

[0187] "Dynamic adjustment" is a method that supports more effective learning by continuously changing the difficulty level and presentation method of content according to the learner's state.

[0188] This invention provides a system that optimizes learning content based on the learner's cognitive characteristics and emotional state. The server first receives the learner's cognitive characteristics based on information collected from the user's terminal and generates a corresponding profile. This profile reflects the learner's information processing ability and preferences and is used to determine the presentation format of the learning content.

[0189] Emotional state analysis utilizes software that analyzes the user's facial expressions and voice in real time using the camera and microphone built into the device. Specifically, facial expression recognition APIs and voice analysis software (e.g., Google® Cloud Vision API and Amazon Rekognition) are used. Based on these analysis results, the server determines the learner's emotional state and dynamically adjusts the difficulty level and presentation method of the content accordingly.

[0190] When a user selects specific learning content, the server considers profile and sentiment analysis information to send the most suitable content to the device. For example, if the user shows signs of fatigue, the pace of the content is slowed down; if they show interest, more advanced and challenging content is provided.

[0191] For example, if a student shows signs of fatigue while watching online video learning materials, the application will slow down the video playback speed and suggest a break. Furthermore, if the student shows interest in a particular learning point, it will present detailed materials or application problems related to that point.

[0192] Examples of prompt statements to be input to a generative AI model include the following:

[0193] "Please select the most suitable learning content considering the learner's situation below. Content in an easy-to-understand format is preferable."

[0194] Slow eye movements are a sign of fatigue.

[0195] An uneasy tone can be heard in the audio.

[0196] Audio responses showing interest in recent learning items

[0197] In this way, learners receive learning content in a format that is best suited to them, maximizing their learning effectiveness.

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The device uses a camera and microphone to collect the user's facial expression and voice data. This data is collected in real time and used as input to determine emotional state. The collected data is processed into a format necessary for emotion analysis and then sent to the server.

[0201] Step 2:

[0202] The server analyzes the received facial expression data and audio data. This is done using facial expression recognition APIs and audio analysis software (e.g., Google Cloud Vision API or Amazon Rekognition). The data is analyzed and outputted to indicate the learner's emotional state (e.g., fatigue, anxiety, interest).

[0203] Step 3:

[0204] The server integrates a profile based on cognitive characteristics previously received from the user with emotional states obtained through analysis to determine the optimal learning content. In this process, the content format and difficulty level are selected according to the user's level of interest and understanding.

[0205] Step 4:

[0206] The server sends the selected learning content to the device. This content is tailored to the user's current emotional state; for example, if the user is feeling tired, they will be provided with materials at a slower pace, while if they are showing interest, they will be presented with more in-depth content.

[0207] Step 5:

[0208] The device displays learning content sent from the server to the user. The user receives this optimized learning content, allowing for a more comfortable and effective learning experience. Further optimization is possible as the user continues to provide sentiment data, adapting to their learning progress.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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".

[0225] This invention provides a method for realizing a system that converts learning content into an optimal format according to the characteristics of the learner, thereby improving the efficiency of learning. The system mainly consists of three components: a server, a terminal, and a user.

[0226] The server receives cognitive characteristics data from the user, provided through methods such as facial recognition or simple selections. This data includes information such as visual dominance, auditory dominance, and linguistic dominance. The server generates a profile from this information and stores it in the user database.

[0227] The terminal provides an interface for sending user-selected learning content to the server. Through the terminal, the user selects content and enters additional information such as learning objectives. This information is sent to the server for analysis.

[0228] The server determines the optimal conversion format for the content based on the user's profile. For example, for a visually-oriented user, an algorithm is applied that converts text information into video format. The converted content undergoes a quality check on the server before being sent to the device.

[0229] Users efficiently progress through their learning using the converted content sent to their device. In this way, the device functions as a platform for users to advance their learning. For example, for users who are auditorily dominant, text information is played back as an audio file. This process allows learners to learn in a way that is optimized for their own cognitive characteristics.

[0230] As a concrete example, let's assume that chemistry lecture notes are selected. For visually dominant users, the server converts the chemical reactions and structures into animated videos that visually represent them and delivers these resources to the terminal. On the other hand, for auditorily dominant users, the text content is converted into an audiobook with narration and provided as a fluent audio file.

[0231] The entire system is designed to dynamically generate the optimal learning environment tailored to each learner's individual characteristics, maximizing the efficiency of knowledge acquisition.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The user starts up the device and logs into their learning account. The device displays a screen for setting up a cognitive characteristics profile and prompts the user to select one of the following: visual, auditory, or verbal.

[0235] Step 2:

[0236] The device sends cognitive characteristic information selected by the user to the server. The server receives this information, generates a profile for each user, and stores it in a database.

[0237] Step 3:

[0238] The user selects learning content on their device and enters their learning objectives and any additional individual requirements. This selection information is then sent from the device to the server.

[0239] Step 4:

[0240] Based on the content selection information received by the server and the cognitive characteristics profiles stored in the database, the server begins analyzing the content. The server evaluates the type and format of the content and determines which transformation is optimal.

[0241] Step 5:

[0242] The server converts learning content into a format best suited to the user's cognitive characteristics based on a selected conversion algorithm. For example, it converts text data into a video format for visually-oriented users.

[0243] Step 6:

[0244] The server verifies the converted content to ensure its accuracy and quality, thereby guaranteeing that knowledge is effectively transmitted.

[0245] Step 7:

[0246] The server sends the converted learning content to the device. The user receives the content through the device and uses it for learning.

[0247] Step 8:

[0248] Users utilize the learning content provided on their devices to engage in efficient learning. The device periodically sends the user's learning progress to the server, providing continuous learning support.

[0249] (Example 1)

[0250] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0251] A challenge exists in that learning efficiency is not improving due to a lack of learning information provided in a format suited to the cognitive characteristics of individual learners. This challenge stems from the limitations of existing operating systems and methods that cannot convert information into a format suitable for the characteristics of individual learners.

[0252] 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.

[0253] In this invention, the server includes means for collecting learner cognitive characteristic data, means for analyzing the data and generating and storing a learner profile, means for determining the optimal conversion format of learning information based on the profile, means for converting the learning information according to the conversion format determined using a generation AI model, and means for quality checking the converted learning information and providing it to the learner. This makes it possible to provide learning information optimized for each learner, thereby improving learning efficiency.

[0254] A "learner" is a person whose purpose is to receive learning information, understand it, and acquire it.

[0255] "Cognitive characteristics data" refers to data about learners' information processing characteristics, such as whether they are visually dominant, auditorily dominant, or linguistically dominant.

[0256] A "profile" is a collection of information that represents the individual characteristics of a learner, generated based on collected cognitive characteristics data.

[0257] "Learning information" refers to content intended for learners to study, and includes various formats such as text, audio, and video.

[0258] A "conversion format" is a format selected to transform learning information into a format optimized for the learner's cognitive characteristics.

[0259] A "generative AI model" is an artificial intelligence algorithm that generates new information or formats based on input data.

[0260] "Quality check" is the process of verifying that the converted learning information functions properly and meets the expected quality standards.

[0261] The embodiment for carrying out the present invention is a system consisting of three main elements: a server, a terminal, and a user.

[0262] The server receives cognitive characteristics data transmitted from the user (learner) through their device. This data is primarily acquired through facial recognition technology and selection-based input interfaces, and includes cognitive characteristics such as visual dominance, auditory dominance, and linguistic dominance. The server analyzes this data, generates a learner profile, and stores it in a database. Based on the profile, the server determines a format for transforming learning information that is optimized for the learner's characteristics.

[0263] Using a generative AI model, the server transforms the training information according to a predetermined conversion format. For example, for visually dominant learners, text information can be converted into an animated video format. The converted information undergoes quality checks before being sent to the terminal.

[0264] The terminal provides the user with an interface for selecting learning content. The user selects learning information of interest and enters their learning objectives, and all information is sent to the server.

[0265] Users can efficiently progress through their learning using content received from their devices. For example, if a visually-oriented user selects chemistry lecture notes, the server converts them into animated videos of chemical reactions and sends them to the device. Meanwhile, an auditorily-oriented user is provided with the same content as an audiobook with narration.

[0266] In this way, the entire system dynamically generates an optimal learning environment tailored to each user's individual cognitive characteristics, maximizing the efficiency of knowledge acquisition.

[0267] As an example of a prompt, you can use the format: "Convert the chemistry lecture notes into an animated video for visually-oriented learners."

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The terminal collects cognitive characteristic data from the user. The user answers facial recognition and multiple-choice questions using the terminal's input interface. The input for this process is the user's cognitive characteristic data, and the output is data sent to the server. The terminal completes the data collection process by sending this data to the server.

[0271] Step 2:

[0272] The server analyzes cognitive characteristics data received from the terminal. Specifically, it uses a data analysis algorithm to generate profile information such as the user's visual dominance, auditory dominance, and linguistic dominance. The input for this step is the cognitive characteristics data received from the terminal, and the output is the generated user profile. The server saves this profile to a database.

[0273] Step 3:

[0274] The user selects the content they want to learn through their device. This selection is based on the user's learning objectives and interests. In this step, the learning content selected by the user becomes input, and this selection information is sent to the server. Specifically, users can choose from things like chemistry lecture notes or math problem sets.

[0275] Step 4:

[0276] The server determines the optimal content conversion format based on the received learning content information and the user's profile. Specifically, it uses a generative AI model to determine how to convert the content to a format that suits the learner's characteristics, along with prompt messages. The input for this step is the user's profile and the selected learning content information, and the output is the selected conversion format.

[0277] Step 5:

[0278] The server converts the training content based on the selected conversion format. In this step, a generative AI model is utilized, and specific conversion tasks are performed using prompts. For example, text can be converted to a video format. The input for this step is the conversion format and training content selected in the previous step, and the output is the converted content.

[0279] Step 6:

[0280] The server performs a quality check on the converted content before sending it to the terminal. Specifically, this involves verifying that the output content is accurate and suitable for the user's characteristics. The input for this step is the converted content, and the output is the content whose quality has been verified.

[0281] Step 7:

[0282] The user conducts learning using the converted content distributed to the terminal. The input for this step is the content with confirmed quality distributed to the terminal, and the user can proceed with learning based on it. Specific examples include watching an animation video or listening to an audiobook.

[0283] (Application Example 1)

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

[0285] In recent years, despite the increasing need to efficiently promote learning based on individual cognitive characteristics, conventional learning content is difficult to optimize according to the individual needs of users and is often provided in a general form. Therefore, it is inefficient for users to proceed with learning according to their own characteristics, and the improvement of understanding and learning speed may be hindered. In particular, in modern times when various contents are distributed via the Internet, providing individually optimized learning support is an issue.

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

[0287] In this invention, the server includes means for receiving the cognitive characteristics of the learner and generating a profile, means for analyzing the learning content and determining the conversion format based on the profile, and means for dynamically distributing it via the network. Thereby, optimized content corresponding to the cognitive characteristics of each learner is distributed, and it becomes possible to improve the efficiency of learning.

[0288] The "cognitive characteristics of the learner" refers to the characteristics of the cognitive process that the learner utilizes to effectively understand and remember information, and includes the superiority of vision, hearing, and language.

[0289] A "profile" is an individual dataset formed based on a learner's cognitive characteristics and preferences, and serves as fundamental information for optimally transforming content.

[0290] "Learning content" refers to educational materials and teaching aids used by learners for specific purposes, and includes a variety of formats such as text, images, videos, and audio.

[0291] "Conversion format" refers to the format of display or playback determined to provide learning content in a form that is optimal for the learner's cognitive characteristics.

[0292] "Dynamic delivery via network" refers to the process of transmitting learning content to user terminals in real time via communication networks such as the internet.

[0293] "Visual devices" refer to devices used to present information visually, such as displays and screens.

[0294] "Audio equipment" refers to devices that present information through sound, such as speakers and headphones.

[0295] The system implementing this invention is designed to dynamically provide optimal learning content tailored to the learner's cognitive characteristics. The system mainly consists of three components: a server, a terminal, and a user.

[0296] The server receives facial recognition data and simple selection-based data sent by the user. This data includes the user's cognitive profile, namely, whether they are visually dominant, auditorily dominant, or linguistically dominant. The server uses this information to generate a profile and register it in a database. The server analyzes the learning content requested from the terminal and determines the optimal conversion format based on the profile. This conversion uses an algorithm that converts text content into video or audio using a generative AI model. The generated content is quality-checked and sent to the user's terminal via the network.

[0297] The device functions as a platform that sends user-selected learning content to a server and plays the converted content received from the server. Users can receive the content using visual and auditory devices, enabling them to learn efficiently. For example, visually-oriented learners can use animated videos illustrating chemical reactions, while auditorily-oriented learners can use audiobooks with narration.

[0298] For example, when a high school student reviews chemistry, an animated video is provided if they are good at receiving information visually, and a fluent audio file is provided if they are good at receiving information auditorily. Examples of prompts include, "Generate a learning video that is best suited to this user's visual learning style," and "Provide audio materials for users with auditory learning styles."

[0299] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0300] Step 1:

[0301] Users select learning content through their devices and input facial recognition data and information in the form of selections. This information is sent from the device to the server as input data to understand the user's cognitive characteristics.

[0302] Step 2:

[0303] The server analyzes the received user facial recognition data and selected information to evaluate the dominance of each of the visual, auditory, and linguistic senses. Based on this, it identifies the user's cognitive characteristics and generates a profile. In this process, machine learning algorithms are used to process the data and extract characteristics.

[0304] Step 3:

[0305] Based on the generated profile, the server analyzes the input learning content. At this time, it determines the optimal conversion format of the content according to the characteristics of the user. To make this determination, it matches the type of content with the user profile and selects a conversion algorithm.

[0306] Step 4:

[0307] The server converts the learning content according to the determined conversion format. It uses the generated AI model to convert text into video or audio. In this process, the visualization or vocalization of the content is performed, and the converted content is temporarily saved.

[0308] Step 5:

[0309] The server checks the quality of the converted content and sends it to the terminal via the network. When sending, it checks the accuracy of the content and the smoothness of the display, etc., so as to provide it to the user in an optimal form.

[0310] Step 6:

[0311] The terminal receives the converted content sent and plays it on a visual device or an acoustic device. The user experiences the converted content and proceeds with learning in a form optimized for their cognitive characteristics. Through this process, the learning efficiency is improved.

[0312] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0313] The present invention provides a method for implementing a system that optimizes learning content based on the cognitive characteristics and emotional state of a learner and improves individual learning experiences. The system is composed of a server, a terminal, an emotion engine, and a user interface.

[0314] The server receives cognitive characteristics information provided by the user and stores it as a profile in the database. This system determines the format of learning content according to the learner's cognitive characteristics and further provides a more highly personalized learning experience by analyzing the learner's emotional state in real time using an emotion engine.

[0315] The device provides an interface for sending user-selected learning content and emotional data analyzed by the emotion engine to the server. Users select learning content from the device and receive the content as it is readjusted as needed.

[0316] The emotion engine analyzes input data from the user's device usage (e.g., facial expression analysis via camera and voice data) to determine the learner's emotional state. It can identify states such as decreased concentration, anxiety, or interest.

[0317] The server dynamically adjusts how learning content is presented based on the analysis results of the emotion engine. For example, if a learner is experiencing difficulty, the server provides feedback such as lowering the difficulty level of the content or slowing down the pace. Furthermore, if a learner shows interest, it can provide more advanced content or applied examples.

[0318] For example, if a user learning a math problem shows signs of anxiety, the server, based on the emotion engine's results, adds step-by-step explanations and simplifies the practice problems before sending them to the device. Conversely, if the user shows high concentration and interest in the problem, the difficulty level of the problem is increased, and application problems are provided.

[0319] In this way, learners can always receive content that is appropriate to their abilities and emotional state, creating an efficient and comfortable learning environment. This invention further improves learning effectiveness by integrating a learner's emotion analysis function.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] The user logs into the device and inputs their cognitive characteristics, learning objectives, and areas of interest. The device sends this information to the server, where it is stored as foundational data for their profile.

[0323] Step 2:

[0324] The server analyzes cognitive characteristics information received from the user and generates a profile indicating either visual dominance, auditory dominance, or linguistic dominance. This profile is used to optimize learning content.

[0325] Step 3:

[0326] The device displays a list of selectable learning content to the user. The user selects the content they wish to learn and sends that information from the device to the server.

[0327] Step 4:

[0328] The server analyzes the selected learning content based on the user's profile and determines the optimal conversion format. For example, for a visually-oriented user, it might choose to convert text information into video.

[0329] Step 5:

[0330] Once the user begins learning, the device collects the user's emotional data (such as facial recognition results from the camera and voice tone) and sends it to the server in real time.

[0331] Step 6:

[0332] An emotion engine within the server analyzes the user's emotional state, evaluating factors such as concentration, stress levels, and anxiety. This information is then used to adjust the learning content.

[0333] Step 7:

[0334] The server dynamically changes how learning content is presented based on sentiment analysis results. It provides additional guidance and hints to users who show difficulty, and more challenging content to users who show interest.

[0335] Step 8:

[0336] The server sends the adjusted learning content to the device and presents it to the user. The user can continue learning through this updated content.

[0337] Step 9:

[0338] Once the user's learning is complete, the device sends final feedback and emotional changes to the server, which stores this information in the user's profile and uses it for future learning sessions.

[0339] (Example 2)

[0340] 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".

[0341] Conventional learning support systems have suffered from reduced learning efficiency because they cannot adaptively optimize learning content based on learners' cognitive characteristics and emotional states. Furthermore, the difficulty in providing individualized support tailored to each learner's situation means that maximizing learning effectiveness remains a challenge.

[0342] 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.

[0343] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating identification information, means for analyzing the information and determining a conversion format based on the identification information and emotional state, and means for converting the information according to the determined conversion format and providing a personalized learning experience. This enables real-time adaptive learning that is tailored to the learner's characteristics and state.

[0344] "Identifying information" refers to information that characterizes individual learners, generated based on their cognitive characteristics.

[0345] "Emotional state" refers to the learner's current psychological or emotional state, including interest, concentration, and anxiety.

[0346] "Analyzing information" is the process of conducting an analysis based on learner identification information and emotional states to determine the format and structure of the learning content to be provided.

[0347] A "conversion format" is a format for presenting information that is optimized for the learner, determined as a result of information analysis.

[0348] A "personalized learning experience" refers to individually optimized learning opportunities that are tailored to the learner's cognitive characteristics and emotional state.

[0349] This invention constructs a system that optimizes learning content based on the learner's cognitive characteristics and emotional state, providing a personalized learning experience. The system mainly consists of a server, terminals, an emotion analysis engine, and a user interface.

[0350] The server first generates identification information based on cognitive characteristics information received from the user. A database management system is used for this purpose, ensuring that information is efficiently stored and identified. Next, the server combines this information with the user's emotional state data provided by the emotion analysis engine, analyzes the learning content, and determines the conversion format. In this process, machine learning algorithms are used to determine an optimized content delivery strategy based on the given data.

[0351] The device displays learning content selected by the user and provides an interface for sending data obtained from the emotion analysis engine to the server. The emotion analysis engine uses the camera and microphone to analyze the user's facial expressions and voice patterns, thereby evaluating the user's emotional state in real time.

[0352] For example, if the sentiment analysis engine indicates that a user learning math problems is experiencing anxiety, the server will use that information to resend learning content to the device, including step-by-step explanations and simple practice problems. This ensures that the user's learning experience is optimized in real time.

[0353] As a concrete example of a prompt, the instruction "Optimize learning content based on the user's emotions and cognitive characteristics" is given to the generative AI model. This prompt provides the foundational information for delivering a learning experience that dynamically changes according to the user's state.

[0354] Thus, the present invention aims to provide users with optimized learning content and improve learning effectiveness and experience.

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

[0356] Step 1:

[0357] Users input their cognitive characteristics information using a terminal. This is done using questionnaires or settings panels, clearly indicating the user's learning style and areas of expertise. The input information is sent from the terminal to a server as digital data and used to generate identification information.

[0358] Step 2:

[0359] The server generates identification information based on the received cognitive characteristics information. Here, the information is organized and stored using a database system. This identification information forms the basis for creating customized learning profiles for individual users. The generated profiles are stored in the database and used for future content optimization.

[0360] Step 3:

[0361] The user selects learning content through their device. The selected content is sent to the server via the device's interface. Simultaneously, the device sends data collected using its camera and microphone to an emotion analysis engine. This data serves as input for analyzing the user's real-time emotional state.

[0362] Step 4:

[0363] The emotion analysis engine uses data received from the device to determine the user's emotional state. It analyzes the user's facial expressions and tone of voice using image processing and voice analysis algorithms. The analysis identifies states such as concentration, anxiety, and interest, and these are sent back to the server.

[0364] Step 5:

[0365] The server analyzes the training content based on the results and identification information from the sentiment analysis engine. It runs a machine learning model to determine the optimal content presentation format and difficulty level for the user. In this process, it selects the optimal option from multiple candidates and generates it as transformed content.

[0366] Step 6:

[0367] The server sends optimized learning content to the device. The device displays this to the user, assisting with learning. By receiving content tailored to their cognitive characteristics and emotions, users can have a more effective learning experience.

[0368] This process allows users to continuously receive learning content tailored to their needs, improving both learning efficiency and satisfaction.

[0369] (Application Example 2)

[0370] 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."

[0371] Conventional learning systems optimized content based on learners' cognitive characteristics, but they failed to dynamically adjust content based on learners' emotional states. As a result, it was difficult to maintain learners' motivation and concentration. This invention aims to solve these problems and provide a more effective and personalized learning experience.

[0372] 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.

[0373] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating a profile; means for analyzing learning content and determining a conversion format based on the profile; and means for analyzing the emotional state in real time and dynamically adjusting the difficulty level and presentation method of the content based on the analysis results. This makes it possible to provide personalized learning content that matches the learner's cognitive characteristics and emotional state.

[0374] "Learner cognitive characteristics" refer to the individual abilities and preferences of learners when it comes to understanding and remembering information.

[0375] A "profile" is an individual information structure generated based on the learner's cognitive characteristics, and is used to optimize learning content.

[0376] A "conversion format" is a format used to change how learning content is presented, and it is determined according to the learner's profile.

[0377] "Emotional state" refers to the psychological and emotional responses that learners exhibit during learning, including concentration, interest, and anxiety.

[0378] "Real-time analysis" is a process that instantly analyzes the learner's emotional state and uses the results to respond quickly.

[0379] "Dynamic adjustment" is a method that supports more effective learning by continuously changing the difficulty level and presentation method of content according to the learner's state.

[0380] This invention provides a system that optimizes learning content based on the learner's cognitive characteristics and emotional state. The server first receives the learner's cognitive characteristics based on information collected from the user's terminal and generates a corresponding profile. This profile reflects the learner's information processing ability and preferences and is used to determine the presentation format of the learning content.

[0381] Emotional state analysis utilizes software that analyzes the user's facial expressions and voice in real time using the camera and microphone built into the device. Specifically, facial expression recognition APIs and voice analysis software (e.g., Google Cloud Vision API and Amazon Rekognition) are used. Based on these analysis results, the server determines the learner's emotional state and dynamically adjusts the difficulty level and presentation method of the content accordingly.

[0382] When a user selects specific learning content, the server considers profile and sentiment analysis information to send the most suitable content to the device. For example, if the user shows signs of fatigue, the pace of the content is slowed down; if they show interest, more advanced and challenging content is provided.

[0383] For example, if a student shows signs of fatigue while watching online video learning materials, the application will slow down the video playback speed and suggest a break. Furthermore, if the student shows interest in a particular learning point, it will present detailed materials or application problems related to that point.

[0384] Examples of prompt statements to be input to a generative AI model include the following:

[0385] "Please select the most suitable learning content considering the learner's situation below. Content in an easy-to-understand format is preferable."

[0386] Slow eye movements are a sign of fatigue.

[0387] An uneasy tone can be heard in the audio.

[0388] Audio responses showing interest in recent learning items

[0389] In this way, learners receive learning content in a format that is best suited to them, maximizing their learning effectiveness.

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The device uses a camera and microphone to collect the user's facial expression and voice data. This data is collected in real time and used as input to determine emotional state. The collected data is processed into a format necessary for emotion analysis and then sent to the server.

[0393] Step 2:

[0394] The server analyzes the received facial expression data and audio data. This is done using facial expression recognition APIs and audio analysis software (e.g., Google Cloud Vision API or Amazon Rekognition). The data is analyzed and outputted to indicate the learner's emotional state (e.g., fatigue, anxiety, interest).

[0395] Step 3:

[0396] The server integrates a profile based on cognitive characteristics previously received from the user with emotional states obtained through analysis to determine the optimal learning content. In this process, the content format and difficulty level are selected according to the user's level of interest and understanding.

[0397] Step 4:

[0398] The server sends the selected learning content to the device. This content is tailored to the user's current emotional state; for example, if the user is feeling tired, they will be provided with materials at a slower pace, while if they are showing interest, they will be presented with more in-depth content.

[0399] Step 5:

[0400] The device displays learning content sent from the server to the user. The user receives this optimized learning content, allowing for a more comfortable and effective learning experience. Further optimization is possible as the user continues to provide sentiment data, adapting to their learning progress.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] [Third Embodiment]

[0405] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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".

[0417] This invention provides a method for realizing a system that converts learning content into an optimal format according to the characteristics of the learner, thereby improving the efficiency of learning. The system mainly consists of three components: a server, a terminal, and a user.

[0418] The server receives cognitive characteristics data from the user, provided through methods such as facial recognition or simple selections. This data includes information such as visual dominance, auditory dominance, and linguistic dominance. The server generates a profile from this information and stores it in the user database.

[0419] The terminal provides an interface for sending user-selected learning content to the server. Through the terminal, the user selects content and enters additional information such as learning objectives. This information is sent to the server for analysis.

[0420] The server determines the optimal conversion format for the content based on the user's profile. For example, for a visually-oriented user, an algorithm is applied that converts text information into video format. The converted content undergoes a quality check on the server before being sent to the device.

[0421] Users efficiently progress through their learning using the converted content sent to their device. In this way, the device functions as a platform for users to advance their learning. For example, for users who are auditorily dominant, text information is played back as an audio file. This process allows learners to learn in a way that is optimized for their own cognitive characteristics.

[0422] As a concrete example, let's assume that chemistry lecture notes are selected. For visually dominant users, the server converts the chemical reactions and structures into animated videos that visually represent them and delivers these resources to the terminal. On the other hand, for auditorily dominant users, the text content is converted into an audiobook with narration and provided as a fluent audio file.

[0423] The entire system is designed to dynamically generate the optimal learning environment tailored to each learner's individual characteristics, maximizing the efficiency of knowledge acquisition.

[0424] The following describes the processing flow.

[0425] Step 1:

[0426] The user starts up the device and logs into their learning account. The device displays a screen for setting up a cognitive characteristics profile and prompts the user to select one of the following: visual, auditory, or verbal.

[0427] Step 2:

[0428] The device sends cognitive characteristic information selected by the user to the server. The server receives this information, generates a profile for each user, and stores it in a database.

[0429] Step 3:

[0430] The user selects learning content on their device and enters their learning objectives and any additional individual requirements. This selection information is then sent from the device to the server.

[0431] Step 4:

[0432] Based on the content selection information received by the server and the cognitive characteristics profiles stored in the database, the server begins analyzing the content. The server evaluates the type and format of the content and determines which transformation is optimal.

[0433] Step 5:

[0434] The server converts learning content into a format best suited to the user's cognitive characteristics based on a selected conversion algorithm. For example, it converts text data into a video format for visually-oriented users.

[0435] Step 6:

[0436] The server verifies the converted content to ensure its accuracy and quality, thereby guaranteeing that knowledge is effectively transmitted.

[0437] Step 7:

[0438] The server sends the converted learning content to the device. The user receives the content through the device and uses it for learning.

[0439] Step 8:

[0440] Users utilize the learning content provided on their devices to engage in efficient learning. The device periodically sends the user's learning progress to the server, providing continuous learning support.

[0441] (Example 1)

[0442] 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."

[0443] A challenge exists in that learning efficiency is not improving due to a lack of learning information provided in a format suited to the cognitive characteristics of individual learners. This challenge stems from the limitations of existing operating systems and methods that cannot convert information into a format suitable for the characteristics of individual learners.

[0444] 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.

[0445] In this invention, the server includes means for collecting learner cognitive characteristic data, means for analyzing the data and generating and storing a learner profile, means for determining the optimal conversion format of learning information based on the profile, means for converting the learning information according to the conversion format determined using a generation AI model, and means for quality checking the converted learning information and providing it to the learner. This makes it possible to provide learning information optimized for each learner, thereby improving learning efficiency.

[0446] A "learner" is a person whose purpose is to receive learning information, understand it, and acquire it.

[0447] "Cognitive characteristics data" refers to data about learners' information processing characteristics, such as whether they are visually dominant, auditorily dominant, or linguistically dominant.

[0448] A "profile" is a collection of information that represents the individual characteristics of a learner, generated based on collected cognitive characteristics data.

[0449] "Learning information" refers to content intended for learners to study, and includes various formats such as text, audio, and video.

[0450] A "conversion format" is a format selected to transform learning information into a format optimized for the learner's cognitive characteristics.

[0451] A "generative AI model" is an artificial intelligence algorithm that generates new information or formats based on input data.

[0452] "Quality check" is the process of verifying that the converted learning information functions properly and meets the expected quality standards.

[0453] The embodiment for carrying out the present invention is a system consisting of three main elements: a server, a terminal, and a user.

[0454] The server receives cognitive characteristics data transmitted from the user (learner) through their device. This data is primarily acquired through facial recognition technology and selection-based input interfaces, and includes cognitive characteristics such as visual dominance, auditory dominance, and linguistic dominance. The server analyzes this data, generates a learner profile, and stores it in a database. Based on the profile, the server determines a format for transforming learning information that is optimized for the learner's characteristics.

[0455] Using a generative AI model, the server transforms the training information according to a predetermined conversion format. For example, for visually dominant learners, text information can be converted into an animated video format. The converted information undergoes quality checks before being sent to the terminal.

[0456] The terminal provides the user with an interface for selecting learning content. The user selects learning information of interest and enters their learning objectives, and all information is sent to the server.

[0457] Users can efficiently progress through their learning using content received from their devices. For example, if a visually-oriented user selects chemistry lecture notes, the server converts them into animated videos of chemical reactions and sends them to the device. Meanwhile, an auditorily-oriented user is provided with the same content as an audiobook with narration.

[0458] In this way, the entire system dynamically generates an optimal learning environment tailored to each user's individual cognitive characteristics, maximizing the efficiency of knowledge acquisition.

[0459] As an example of a prompt, you can use the format: "Convert the chemistry lecture notes into an animated video for visually-oriented learners."

[0460] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0461] Step 1:

[0462] The terminal collects cognitive characteristic data from the user. The user answers facial recognition and multiple-choice questions using the terminal's input interface. The input for this process is the user's cognitive characteristic data, and the output is data sent to the server. The terminal completes the data collection process by sending this data to the server.

[0463] Step 2:

[0464] The server analyzes cognitive characteristics data received from the terminal. Specifically, it uses a data analysis algorithm to generate profile information such as the user's visual dominance, auditory dominance, and linguistic dominance. The input for this step is the cognitive characteristics data received from the terminal, and the output is the generated user profile. The server saves this profile to a database.

[0465] Step 3:

[0466] The user selects the content they want to learn through their device. This selection is based on the user's learning objectives and interests. In this step, the learning content selected by the user becomes input, and this selection information is sent to the server. Specifically, users can choose from things like chemistry lecture notes or math problem sets.

[0467] Step 4:

[0468] The server determines the optimal content conversion format based on the received learning content information and the user's profile. Specifically, it uses a generative AI model to determine how to convert the content to a format that suits the learner's characteristics, along with prompt messages. The input for this step is the user's profile and the selected learning content information, and the output is the selected conversion format.

[0469] Step 5:

[0470] The server converts the training content based on the selected conversion format. In this step, a generative AI model is utilized, and specific conversion tasks are performed using prompts. For example, text can be converted to a video format. The input for this step is the conversion format and training content selected in the previous step, and the output is the converted content.

[0471] Step 6:

[0472] The server performs a quality check on the converted content before sending it to the terminal. Specifically, this involves verifying that the output content is accurate and suitable for the user's characteristics. The input for this step is the converted content, and the output is the content whose quality has been verified.

[0473] Step 7:

[0474] Users learn using the converted content delivered to their devices. The input for this step is quality-checked content delivered to the device, and users can proceed with their learning based on it. Specific examples include watching animated videos or listening to audiobooks.

[0475] (Application Example 1)

[0476] 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."

[0477] In recent years, despite the increasing need for efficient learning based on individual cognitive characteristics, traditional learning content is often provided in a generic format, making it difficult to optimize for individual user needs. This can hinder users' learning efficiency, comprehension, and learning speed. Especially in today's world, where various content is distributed via the internet, providing individually optimized learning support is a critical challenge.

[0478] 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.

[0479] In this invention, the server includes means for receiving learners' cognitive characteristics and generating a profile, means for analyzing learning content and determining a conversion format based on the profile, and means for dynamically distributing the content over a network. This makes it possible to deliver optimized content tailored to the cognitive characteristics of each individual learner, thereby improving the efficiency of learning.

[0480] "Learner cognitive characteristics" refer to the distinctive features of the cognitive processes that learners utilize to effectively understand and remember information, and include the dominance of visual, auditory, and linguistic learning.

[0481] A "profile" is an individual dataset formed based on a learner's cognitive characteristics and preferences, and serves as fundamental information for optimally transforming content.

[0482] "Learning content" refers to educational materials and teaching aids used by learners for specific purposes, and includes a variety of formats such as text, images, videos, and audio.

[0483] "Conversion format" refers to the format of display or playback determined to provide learning content in a form that is optimal for the learner's cognitive characteristics.

[0484] "Dynamic delivery via network" refers to the process of transmitting learning content to user terminals in real time via communication networks such as the internet.

[0485] "Visual devices" refer to devices used to present information visually, such as displays and screens.

[0486] "Audio equipment" refers to devices that present information through sound, such as speakers and headphones.

[0487] The system implementing this invention is designed to dynamically provide optimal learning content tailored to the learner's cognitive characteristics. The system mainly consists of three components: a server, a terminal, and a user.

[0488] The server receives facial recognition data and simple selection-based data sent by the user. This data includes the user's cognitive profile, namely, whether they are visually dominant, auditorily dominant, or linguistically dominant. The server uses this information to generate a profile and register it in a database. The server analyzes the learning content requested from the terminal and determines the optimal conversion format based on the profile. This conversion uses an algorithm that converts text content into video or audio using a generative AI model. The generated content is quality-checked and sent to the user's terminal via the network.

[0489] The device functions as a platform that sends user-selected learning content to a server and plays the converted content received from the server. Users can receive the content using visual and auditory devices, enabling them to learn efficiently. For example, visually-oriented learners can use animated videos illustrating chemical reactions, while auditorily-oriented learners can use audiobooks with narration.

[0490] For example, when a high school student reviews chemistry, an animated video is provided if they are good at receiving information visually, and a fluent audio file is provided if they are good at receiving information auditorily. Examples of prompts include, "Generate a learning video that is best suited to this user's visual learning style," and "Provide audio materials for users with auditory learning styles."

[0491] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0492] Step 1:

[0493] Users select learning content through their devices and input facial recognition data and information in the form of selections. This information is sent from the device to the server as input data to understand the user's cognitive characteristics.

[0494] Step 2:

[0495] The server analyzes the received user facial recognition data and selected information to evaluate the dominance of each of the visual, auditory, and linguistic senses. Based on this, it identifies the user's cognitive characteristics and generates a profile. In this process, machine learning algorithms are used to process the data and extract characteristics.

[0496] Step 3:

[0497] The server analyzes the input learning content based on the generated profile. During this process, it determines the optimal conversion format for the content according to the user's characteristics. This determination involves matching the content type with the user profile and selecting a conversion algorithm.

[0498] Step 4:

[0499] The server converts the training content according to the determined conversion format. A generative AI model is used to convert text into video or audio. During this process, the content is visualized or audiotized, and the converted content is temporarily stored.

[0500] Step 5:

[0501] The server checks the quality of the converted content and transmits it to the terminal via the network. During this transmission, it verifies the accuracy and smoothness of the content to ensure it is provided to the user in the most optimal format.

[0502] Step 6:

[0503] The device receives the transmitted converted content and plays it back using visual and audio devices. The user experiences the converted content and learns in a way that is optimized for their own cognitive characteristics. This process improves learning efficiency.

[0504] 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.

[0505] This invention provides a method for implementing a system that optimizes learning content and improves individual learning experiences based on learners' cognitive characteristics and emotional states. The system consists of a server, a terminal, an emotion engine, and a user interface.

[0506] The server receives cognitive characteristics information provided by the user and stores it as a profile in the database. This system determines the format of learning content according to the learner's cognitive characteristics and further provides a more highly personalized learning experience by analyzing the learner's emotional state in real time using an emotion engine.

[0507] The device provides an interface for sending user-selected learning content and emotional data analyzed by the emotion engine to the server. Users select learning content from the device and receive the content as it is readjusted as needed.

[0508] The emotion engine analyzes input data from the user's device usage (e.g., facial expression analysis via camera and voice data) to determine the learner's emotional state. It can identify states such as decreased concentration, anxiety, or interest.

[0509] The server dynamically adjusts how learning content is presented based on the analysis results of the emotion engine. For example, if a learner is experiencing difficulty, the server provides feedback such as lowering the difficulty level of the content or slowing down the pace. Furthermore, if a learner shows interest, it can provide more advanced content or applied examples.

[0510] For example, if a user learning a math problem shows signs of anxiety, the server, based on the emotion engine's results, adds step-by-step explanations and simplifies the practice problems before sending them to the device. Conversely, if the user shows high concentration and interest in the problem, the difficulty level of the problem is increased, and application problems are provided.

[0511] In this way, learners can always receive content that is appropriate to their abilities and emotional state, creating an efficient and comfortable learning environment. This invention further improves learning effectiveness by integrating a learner's emotion analysis function.

[0512] The following describes the processing flow.

[0513] Step 1:

[0514] The user logs into the device and inputs their cognitive characteristics, learning objectives, and areas of interest. The device sends this information to the server, where it is stored as foundational data for their profile.

[0515] Step 2:

[0516] The server analyzes cognitive characteristics information received from the user and generates a profile indicating either visual dominance, auditory dominance, or linguistic dominance. This profile is used to optimize learning content.

[0517] Step 3:

[0518] The device displays a list of selectable learning content to the user. The user selects the content they wish to learn and sends that information from the device to the server.

[0519] Step 4:

[0520] The server analyzes the selected learning content based on the user's profile and determines the optimal conversion format. For example, for a visually-oriented user, it might choose to convert text information into video.

[0521] Step 5:

[0522] Once the user begins learning, the device collects the user's emotional data (such as facial recognition results from the camera and voice tone) and sends it to the server in real time.

[0523] Step 6:

[0524] An emotion engine within the server analyzes the user's emotional state, evaluating factors such as concentration, stress levels, and anxiety. This information is then used to adjust the learning content.

[0525] Step 7:

[0526] The server dynamically changes how learning content is presented based on sentiment analysis results. It provides additional guidance and hints to users who show difficulty, and more challenging content to users who show interest.

[0527] Step 8:

[0528] The server sends the adjusted learning content to the device and presents it to the user. The user can continue learning through this updated content.

[0529] Step 9:

[0530] Once the user's learning is complete, the device sends final feedback and emotional changes to the server, which stores this information in the user's profile and uses it for future learning sessions.

[0531] (Example 2)

[0532] 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."

[0533] Conventional learning support systems have suffered from reduced learning efficiency because they cannot adaptively optimize learning content based on learners' cognitive characteristics and emotional states. Furthermore, the difficulty in providing individualized support tailored to each learner's situation means that maximizing learning effectiveness remains a challenge.

[0534] 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.

[0535] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating identification information, means for analyzing the information and determining a conversion format based on the identification information and emotional state, and means for converting the information according to the determined conversion format and providing a personalized learning experience. This enables real-time adaptive learning that is tailored to the learner's characteristics and state.

[0536] "Identifying information" refers to information that characterizes individual learners, generated based on their cognitive characteristics.

[0537] "Emotional state" refers to the learner's current psychological or emotional state, including interest, concentration, and anxiety.

[0538] "Analyzing information" is the process of conducting an analysis based on learner identification information and emotional states to determine the format and structure of the learning content to be provided.

[0539] A "conversion format" is a format for presenting information that is optimized for the learner, determined as a result of information analysis.

[0540] A "personalized learning experience" refers to individually optimized learning opportunities that are tailored to the learner's cognitive characteristics and emotional state.

[0541] This invention constructs a system that optimizes learning content based on the learner's cognitive characteristics and emotional state, providing a personalized learning experience. The system mainly consists of a server, terminals, an emotion analysis engine, and a user interface.

[0542] The server first generates identification information based on cognitive characteristics information received from the user. A database management system is used for this purpose, ensuring that information is efficiently stored and identified. Next, the server combines this information with the user's emotional state data provided by the emotion analysis engine, analyzes the learning content, and determines the conversion format. In this process, machine learning algorithms are used to determine an optimized content delivery strategy based on the given data.

[0543] The device displays learning content selected by the user and provides an interface for sending data obtained from the emotion analysis engine to the server. The emotion analysis engine uses the camera and microphone to analyze the user's facial expressions and voice patterns, thereby evaluating the user's emotional state in real time.

[0544] For example, if the sentiment analysis engine indicates that a user learning math problems is experiencing anxiety, the server will use that information to resend learning content to the device, including step-by-step explanations and simple practice problems. This ensures that the user's learning experience is optimized in real time.

[0545] As a concrete example of a prompt, the instruction "Optimize learning content based on the user's emotions and cognitive characteristics" is given to the generative AI model. This prompt provides the foundational information for delivering a learning experience that dynamically changes according to the user's state.

[0546] Thus, the present invention aims to provide users with optimized learning content and improve learning effectiveness and experience.

[0547] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0548] Step 1:

[0549] Users input their cognitive characteristics information using a terminal. This is done using questionnaires or settings panels, clearly indicating the user's learning style and areas of expertise. The input information is sent from the terminal to a server as digital data and used to generate identification information.

[0550] Step 2:

[0551] The server generates identification information based on the received cognitive characteristics information. Here, the information is organized and stored using a database system. This identification information forms the basis for creating customized learning profiles for individual users. The generated profiles are stored in the database and used for future content optimization.

[0552] Step 3:

[0553] The user selects learning content through their device. The selected content is sent to the server via the device's interface. Simultaneously, the device sends data collected using its camera and microphone to an emotion analysis engine. This data serves as input for analyzing the user's real-time emotional state.

[0554] Step 4:

[0555] The emotion analysis engine uses data received from the device to determine the user's emotional state. It analyzes the user's facial expressions and tone of voice using image processing and voice analysis algorithms. The analysis identifies states such as concentration, anxiety, and interest, and these are sent back to the server.

[0556] Step 5:

[0557] The server analyzes the training content based on the results and identification information from the sentiment analysis engine. It runs a machine learning model to determine the optimal content presentation format and difficulty level for the user. In this process, it selects the optimal option from multiple candidates and generates it as transformed content.

[0558] Step 6:

[0559] The server sends optimized learning content to the device. The device displays this to the user, assisting with learning. By receiving content tailored to their cognitive characteristics and emotions, users can have a more effective learning experience.

[0560] This process allows users to continuously receive learning content tailored to their needs, improving both learning efficiency and satisfaction.

[0561] (Application Example 2)

[0562] 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."

[0563] Conventional learning systems optimized content based on learners' cognitive characteristics, but they failed to dynamically adjust content based on learners' emotional states. As a result, it was difficult to maintain learners' motivation and concentration. This invention aims to solve these problems and provide a more effective and personalized learning experience.

[0564] 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.

[0565] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating a profile; means for analyzing learning content and determining a conversion format based on the profile; and means for analyzing the emotional state in real time and dynamically adjusting the difficulty level and presentation method of the content based on the analysis results. This makes it possible to provide personalized learning content that matches the learner's cognitive characteristics and emotional state.

[0566] "Learner cognitive characteristics" refer to the individual abilities and preferences of learners when it comes to understanding and remembering information.

[0567] A "profile" is an individual information structure generated based on the learner's cognitive characteristics, and is used to optimize learning content.

[0568] A "conversion format" is a format used to change how learning content is presented, and it is determined according to the learner's profile.

[0569] "Emotional state" refers to the psychological and emotional responses that learners exhibit during learning, including concentration, interest, and anxiety.

[0570] "Real-time analysis" is a process that instantly analyzes the learner's emotional state and uses the results to respond quickly.

[0571] "Dynamic adjustment" is a method that supports more effective learning by continuously changing the difficulty level and presentation method of content according to the learner's state.

[0572] This invention provides a system that optimizes learning content based on the learner's cognitive characteristics and emotional state. The server first receives the learner's cognitive characteristics based on information collected from the user's terminal and generates a corresponding profile. This profile reflects the learner's information processing ability and preferences and is used to determine the presentation format of the learning content.

[0573] Emotional state analysis utilizes software that analyzes the user's facial expressions and voice in real time using the camera and microphone built into the device. Specifically, facial expression recognition APIs and voice analysis software (e.g., Google Cloud Vision API and Amazon Rekognition) are used. Based on these analysis results, the server determines the learner's emotional state and dynamically adjusts the difficulty level and presentation method of the content accordingly.

[0574] When a user selects specific learning content, the server considers profile and sentiment analysis information to send the most suitable content to the device. For example, if the user shows signs of fatigue, the pace of the content is slowed down; if they show interest, more advanced and challenging content is provided.

[0575] For example, if a student shows signs of fatigue while watching online video learning materials, the application will slow down the video playback speed and suggest a break. Furthermore, if the student shows interest in a particular learning point, it will present detailed materials or application problems related to that point.

[0576] Examples of prompt statements to be input to a generative AI model include the following:

[0577] "Please select the most suitable learning content considering the learner's situation below. Content in an easy-to-understand format is preferable."

[0578] Slow eye movements are a sign of fatigue.

[0579] An uneasy tone can be heard in the audio.

[0580] Audio responses showing interest in recent learning items

[0581] In this way, learners receive learning content in a format that is best suited to them, maximizing their learning effectiveness.

[0582] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0583] Step 1:

[0584] The device uses a camera and microphone to collect the user's facial expression and voice data. This data is collected in real time and used as input to determine emotional state. The collected data is processed into a format necessary for emotion analysis and then sent to the server.

[0585] Step 2:

[0586] The server analyzes the received facial expression data and audio data. This is done using facial expression recognition APIs and audio analysis software (e.g., Google Cloud Vision API or Amazon Rekognition). The data is analyzed and outputted to indicate the learner's emotional state (e.g., fatigue, anxiety, interest).

[0587] Step 3:

[0588] The server integrates a profile based on cognitive characteristics previously received from the user with emotional states obtained through analysis to determine the optimal learning content. In this process, the content format and difficulty level are selected according to the user's level of interest and understanding.

[0589] Step 4:

[0590] The server sends the selected learning content to the device. This content is tailored to the user's current emotional state; for example, if the user is feeling tired, they will be provided with materials at a slower pace, while if they are showing interest, they will be presented with more in-depth content.

[0591] Step 5:

[0592] The device displays learning content sent from the server to the user. The user receives this optimized learning content, allowing for a more comfortable and effective learning experience. Further optimization is possible as the user continues to provide sentiment data, adapting to their learning progress.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] [Fourth Embodiment]

[0597] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0598] 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.

[0599] 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).

[0600] 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.

[0601] 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.

[0602] 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).

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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".

[0610] This invention provides a method for realizing a system that converts learning content into an optimal format according to the characteristics of the learner, thereby improving the efficiency of learning. The system mainly consists of three components: a server, a terminal, and a user.

[0611] The server receives cognitive characteristics data from the user, provided through methods such as facial recognition or simple selections. This data includes information such as visual dominance, auditory dominance, and linguistic dominance. The server generates a profile from this information and stores it in the user database.

[0612] The terminal provides an interface for sending user-selected learning content to the server. Through the terminal, the user selects content and enters additional information such as learning objectives. This information is sent to the server for analysis.

[0613] The server determines the optimal conversion format for the content based on the user's profile. For example, for a visually-oriented user, an algorithm is applied that converts text information into video format. The converted content undergoes a quality check on the server before being sent to the device.

[0614] Users efficiently progress through their learning using the converted content sent to their device. In this way, the device functions as a platform for users to advance their learning. For example, for users who are auditorily dominant, text information is played back as an audio file. This process allows learners to learn in a way that is optimized for their own cognitive characteristics.

[0615] As a concrete example, let's assume that chemistry lecture notes are selected. For visually dominant users, the server converts the chemical reactions and structures into animated videos that visually represent them and delivers these resources to the terminal. On the other hand, for auditorily dominant users, the text content is converted into an audiobook with narration and provided as a fluent audio file.

[0616] The entire system is designed to dynamically generate the optimal learning environment tailored to each learner's individual characteristics, maximizing the efficiency of knowledge acquisition.

[0617] The following describes the processing flow.

[0618] Step 1:

[0619] The user starts up the device and logs into their learning account. The device displays a screen for setting up a cognitive characteristics profile and prompts the user to select one of the following: visual, auditory, or verbal.

[0620] Step 2:

[0621] The device sends cognitive characteristic information selected by the user to the server. The server receives this information, generates a profile for each user, and stores it in a database.

[0622] Step 3:

[0623] The user selects learning content on their device and enters their learning objectives and any additional individual requirements. This selection information is then sent from the device to the server.

[0624] Step 4:

[0625] Based on the content selection information received by the server and the cognitive characteristics profiles stored in the database, the server begins analyzing the content. The server evaluates the type and format of the content and determines which transformation is optimal.

[0626] Step 5:

[0627] The server converts learning content into a format best suited to the user's cognitive characteristics based on a selected conversion algorithm. For example, it converts text data into a video format for visually-oriented users.

[0628] Step 6:

[0629] The server verifies the converted content to ensure its accuracy and quality, thereby guaranteeing that knowledge is effectively transmitted.

[0630] Step 7:

[0631] The server sends the converted learning content to the device. The user receives the content through the device and uses it for learning.

[0632] Step 8:

[0633] Users utilize the learning content provided on their devices to engage in efficient learning. The device periodically sends the user's learning progress to the server, providing continuous learning support.

[0634] (Example 1)

[0635] 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".

[0636] A challenge exists in that learning efficiency is not improving due to a lack of learning information provided in a format suited to the cognitive characteristics of individual learners. This challenge stems from the limitations of existing operating systems and methods that cannot convert information into a format suitable for the characteristics of individual learners.

[0637] 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.

[0638] In this invention, the server includes means for collecting learner cognitive characteristic data, means for analyzing the data and generating and storing a learner profile, means for determining the optimal conversion format of learning information based on the profile, means for converting the learning information according to the conversion format determined using a generation AI model, and means for quality checking the converted learning information and providing it to the learner. This makes it possible to provide learning information optimized for each learner, thereby improving learning efficiency.

[0639] A "learner" is a person whose purpose is to receive learning information, understand it, and acquire it.

[0640] "Cognitive characteristics data" refers to data about learners' information processing characteristics, such as whether they are visually dominant, auditorily dominant, or linguistically dominant.

[0641] A "profile" is a collection of information that represents the individual characteristics of a learner, generated based on collected cognitive characteristics data.

[0642] "Learning information" refers to content intended for learners to study, and includes various formats such as text, audio, and video.

[0643] A "conversion format" is a format selected to transform learning information into a format optimized for the learner's cognitive characteristics.

[0644] A "generative AI model" is an artificial intelligence algorithm that generates new information or formats based on input data.

[0645] "Quality check" is the process of verifying that the converted learning information functions properly and meets the expected quality standards.

[0646] The embodiment for carrying out the present invention is a system consisting of three main elements: a server, a terminal, and a user.

[0647] The server receives cognitive characteristics data transmitted from the user (learner) through their device. This data is primarily acquired through facial recognition technology and selection-based input interfaces, and includes cognitive characteristics such as visual dominance, auditory dominance, and linguistic dominance. The server analyzes this data, generates a learner profile, and stores it in a database. Based on the profile, the server determines a format for transforming learning information that is optimized for the learner's characteristics.

[0648] Using a generative AI model, the server transforms the training information according to a predetermined conversion format. For example, for visually dominant learners, text information can be converted into an animated video format. The converted information undergoes quality checks before being sent to the terminal.

[0649] The terminal provides the user with an interface for selecting learning content. The user selects learning information of interest and enters their learning objectives, and all information is sent to the server.

[0650] Users can efficiently progress through their learning using content received from their devices. For example, if a visually-oriented user selects chemistry lecture notes, the server converts them into animated videos of chemical reactions and sends them to the device. Meanwhile, an auditorily-oriented user is provided with the same content as an audiobook with narration.

[0651] In this way, the entire system dynamically generates an optimal learning environment tailored to each user's individual cognitive characteristics, maximizing the efficiency of knowledge acquisition.

[0652] As an example of a prompt, you can use the format: "Convert the chemistry lecture notes into an animated video for visually-oriented learners."

[0653] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0654] Step 1:

[0655] The terminal collects cognitive characteristic data from the user. The user answers facial recognition and multiple-choice questions using the terminal's input interface. The input for this process is the user's cognitive characteristic data, and the output is data sent to the server. The terminal completes the data collection process by sending this data to the server.

[0656] Step 2:

[0657] The server analyzes cognitive characteristics data received from the terminal. Specifically, it uses a data analysis algorithm to generate profile information such as the user's visual dominance, auditory dominance, and linguistic dominance. The input for this step is the cognitive characteristics data received from the terminal, and the output is the generated user profile. The server saves this profile to a database.

[0658] Step 3:

[0659] The user selects the content they want to learn through their device. This selection is based on the user's learning objectives and interests. In this step, the learning content selected by the user becomes input, and this selection information is sent to the server. Specifically, users can choose from things like chemistry lecture notes or math problem sets.

[0660] Step 4:

[0661] The server determines the optimal content conversion format based on the received learning content information and the user's profile. Specifically, it uses a generative AI model to determine how to convert the content to a format that suits the learner's characteristics, along with prompt messages. The input for this step is the user's profile and the selected learning content information, and the output is the selected conversion format.

[0662] Step 5:

[0663] The server converts the training content based on the selected conversion format. In this step, a generative AI model is utilized, and specific conversion tasks are performed using prompts. For example, text can be converted to a video format. The input for this step is the conversion format and training content selected in the previous step, and the output is the converted content.

[0664] Step 6:

[0665] The server performs a quality check on the converted content before sending it to the terminal. Specifically, this involves verifying that the output content is accurate and suitable for the user's characteristics. The input for this step is the converted content, and the output is the content whose quality has been verified.

[0666] Step 7:

[0667] Users learn using the converted content delivered to their devices. The input for this step is quality-checked content delivered to the device, and users can proceed with their learning based on it. Specific examples include watching animated videos or listening to audiobooks.

[0668] (Application Example 1)

[0669] 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".

[0670] In recent years, despite the increasing need for efficient learning based on individual cognitive characteristics, traditional learning content is often provided in a generic format, making it difficult to optimize for individual user needs. This can hinder users' learning efficiency, comprehension, and learning speed. Especially in today's world, where various content is distributed via the internet, providing individually optimized learning support is a critical challenge.

[0671] 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.

[0672] In this invention, the server includes means for receiving learners' cognitive characteristics and generating a profile, means for analyzing learning content and determining a conversion format based on the profile, and means for dynamically distributing the content over a network. This makes it possible to deliver optimized content tailored to the cognitive characteristics of each individual learner, thereby improving the efficiency of learning.

[0673] "Learner cognitive characteristics" refer to the distinctive features of the cognitive processes that learners utilize to effectively understand and remember information, and include the dominance of visual, auditory, and linguistic learning.

[0674] A "profile" is an individual dataset formed based on a learner's cognitive characteristics and preferences, and serves as fundamental information for optimally transforming content.

[0675] "Learning content" refers to educational materials and teaching aids used by learners for specific purposes, and includes a variety of formats such as text, images, videos, and audio.

[0676] "Conversion format" refers to the format of display or playback determined to provide learning content in a form that is optimal for the learner's cognitive characteristics.

[0677] "Dynamic delivery via network" refers to the process of transmitting learning content to user terminals in real time via communication networks such as the internet.

[0678] "Visual devices" refer to devices used to present information visually, such as displays and screens.

[0679] "Audio equipment" refers to devices that present information through sound, such as speakers and headphones.

[0680] The system implementing this invention is designed to dynamically provide optimal learning content tailored to the learner's cognitive characteristics. The system mainly consists of three components: a server, a terminal, and a user.

[0681] The server receives facial recognition data and simple selection-based data sent by the user. This data includes the user's cognitive profile, namely, whether they are visually dominant, auditorily dominant, or linguistically dominant. The server uses this information to generate a profile and register it in a database. The server analyzes the learning content requested from the terminal and determines the optimal conversion format based on the profile. This conversion uses an algorithm that converts text content into video or audio using a generative AI model. The generated content is quality-checked and sent to the user's terminal via the network.

[0682] The device functions as a platform that sends user-selected learning content to a server and plays the converted content received from the server. Users can receive the content using visual and auditory devices, enabling them to learn efficiently. For example, visually-oriented learners can use animated videos illustrating chemical reactions, while auditorily-oriented learners can use audiobooks with narration.

[0683] For example, when a high school student reviews chemistry, an animated video is provided if they are good at receiving information visually, and a fluent audio file is provided if they are good at receiving information auditorily. Examples of prompts include, "Generate a learning video that is best suited to this user's visual learning style," and "Provide audio materials for users with auditory learning styles."

[0684] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0685] Step 1:

[0686] Users select learning content through their devices and input facial recognition data and information in the form of selections. This information is sent from the device to the server as input data to understand the user's cognitive characteristics.

[0687] Step 2:

[0688] The server analyzes the received user facial recognition data and selected information to evaluate the dominance of each of the visual, auditory, and linguistic senses. Based on this, it identifies the user's cognitive characteristics and generates a profile. In this process, machine learning algorithms are used to process the data and extract characteristics.

[0689] Step 3:

[0690] The server analyzes the input learning content based on the generated profile. During this process, it determines the optimal conversion format for the content according to the user's characteristics. This determination involves matching the content type with the user profile and selecting a conversion algorithm.

[0691] Step 4:

[0692] The server converts the training content according to the determined conversion format. A generative AI model is used to convert text into video or audio. During this process, the content is visualized or audiotized, and the converted content is temporarily stored.

[0693] Step 5:

[0694] The server checks the quality of the converted content and transmits it to the terminal via the network. During this transmission, it verifies the accuracy and smoothness of the content to ensure it is provided to the user in the most optimal format.

[0695] Step 6:

[0696] The device receives the transmitted converted content and plays it back using visual and audio devices. The user experiences the converted content and learns in a way that is optimized for their own cognitive characteristics. This process improves learning efficiency.

[0697] 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.

[0698] This invention provides a method for implementing a system that optimizes learning content and improves individual learning experiences based on learners' cognitive characteristics and emotional states. The system consists of a server, a terminal, an emotion engine, and a user interface.

[0699] The server receives cognitive characteristics information provided by the user and stores it as a profile in the database. This system determines the format of learning content according to the learner's cognitive characteristics and further provides a more highly personalized learning experience by analyzing the learner's emotional state in real time using an emotion engine.

[0700] The device provides an interface for sending user-selected learning content and emotional data analyzed by the emotion engine to the server. Users select learning content from the device and receive the content as it is readjusted as needed.

[0701] The emotion engine analyzes input data from the user's device usage (e.g., facial expression analysis via camera and voice data) to determine the learner's emotional state. It can identify states such as decreased concentration, anxiety, or interest.

[0702] The server dynamically adjusts how learning content is presented based on the analysis results of the emotion engine. For example, if a learner is experiencing difficulty, the server provides feedback such as lowering the difficulty level of the content or slowing down the pace. Furthermore, if a learner shows interest, it can provide more advanced content or applied examples.

[0703] For example, if a user learning a math problem shows signs of anxiety, the server, based on the emotion engine's results, adds step-by-step explanations and simplifies the practice problems before sending them to the device. Conversely, if the user shows high concentration and interest in the problem, the difficulty level of the problem is increased, and application problems are provided.

[0704] In this way, learners can always receive content that is appropriate to their abilities and emotional state, creating an efficient and comfortable learning environment. This invention further improves learning effectiveness by integrating a learner's emotion analysis function.

[0705] The following describes the processing flow.

[0706] Step 1:

[0707] The user logs into the device and inputs their cognitive characteristics, learning objectives, and areas of interest. The device sends this information to the server, where it is stored as foundational data for their profile.

[0708] Step 2:

[0709] The server analyzes cognitive characteristics information received from the user and generates a profile indicating either visual dominance, auditory dominance, or linguistic dominance. This profile is used to optimize learning content.

[0710] Step 3:

[0711] The device displays a list of selectable learning content to the user. The user selects the content they wish to learn and sends that information from the device to the server.

[0712] Step 4:

[0713] The server analyzes the selected learning content based on the user's profile and determines the optimal conversion format. For example, for a visually-oriented user, it might choose to convert text information into video.

[0714] Step 5:

[0715] Once the user begins learning, the device collects the user's emotional data (such as facial recognition results from the camera and voice tone) and sends it to the server in real time.

[0716] Step 6:

[0717] An emotion engine within the server analyzes the user's emotional state, evaluating factors such as concentration, stress levels, and anxiety. This information is then used to adjust the learning content.

[0718] Step 7:

[0719] The server dynamically changes how learning content is presented based on sentiment analysis results. It provides additional guidance and hints to users who show difficulty, and more challenging content to users who show interest.

[0720] Step 8:

[0721] The server sends the adjusted learning content to the device and presents it to the user. The user can continue learning through this updated content.

[0722] Step 9:

[0723] Once the user's learning is complete, the device sends final feedback and emotional changes to the server, which stores this information in the user's profile and uses it for future learning sessions.

[0724] (Example 2)

[0725] 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".

[0726] Conventional learning support systems have suffered from reduced learning efficiency because they cannot adaptively optimize learning content based on learners' cognitive characteristics and emotional states. Furthermore, the difficulty in providing individualized support tailored to each learner's situation means that maximizing learning effectiveness remains a challenge.

[0727] 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.

[0728] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating identification information, means for analyzing the information and determining a conversion format based on the identification information and emotional state, and means for converting the information according to the determined conversion format and providing a personalized learning experience. This enables real-time adaptive learning that is tailored to the learner's characteristics and state.

[0729] "Identifying information" refers to information that characterizes individual learners, generated based on their cognitive characteristics.

[0730] "Emotional state" refers to the learner's current psychological or emotional state, including interest, concentration, and anxiety.

[0731] "Analyzing information" is the process of conducting an analysis based on learner identification information and emotional states to determine the format and structure of the learning content to be provided.

[0732] A "conversion format" is a format for presenting information that is optimized for the learner, determined as a result of information analysis.

[0733] A "personalized learning experience" refers to individually optimized learning opportunities that are tailored to the learner's cognitive characteristics and emotional state.

[0734] This invention constructs a system that optimizes learning content based on the learner's cognitive characteristics and emotional state, providing a personalized learning experience. The system mainly consists of a server, terminals, an emotion analysis engine, and a user interface.

[0735] The server first generates identification information based on cognitive characteristics information received from the user. A database management system is used for this purpose, ensuring that information is efficiently stored and identified. Next, the server combines this information with the user's emotional state data provided by the emotion analysis engine, analyzes the learning content, and determines the conversion format. In this process, machine learning algorithms are used to determine an optimized content delivery strategy based on the given data.

[0736] The device displays learning content selected by the user and provides an interface for sending data obtained from the emotion analysis engine to the server. The emotion analysis engine uses the camera and microphone to analyze the user's facial expressions and voice patterns, thereby evaluating the user's emotional state in real time.

[0737] For example, if the sentiment analysis engine indicates that a user learning math problems is experiencing anxiety, the server will use that information to resend learning content to the device, including step-by-step explanations and simple practice problems. This ensures that the user's learning experience is optimized in real time.

[0738] As a concrete example of a prompt, the instruction "Optimize learning content based on the user's emotions and cognitive characteristics" is given to the generative AI model. This prompt provides the foundational information for delivering a learning experience that dynamically changes according to the user's state.

[0739] Thus, the present invention aims to provide users with optimized learning content and improve learning effectiveness and experience.

[0740] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0741] Step 1:

[0742] Users input their cognitive characteristics information using a terminal. This is done using questionnaires or settings panels, clearly indicating the user's learning style and areas of expertise. The input information is sent from the terminal to a server as digital data and used to generate identification information.

[0743] Step 2:

[0744] The server generates identification information based on the received cognitive characteristics information. Here, the information is organized and stored using a database system. This identification information forms the basis for creating customized learning profiles for individual users. The generated profiles are stored in the database and used for future content optimization.

[0745] Step 3:

[0746] The user selects learning content through their device. The selected content is sent to the server via the device's interface. Simultaneously, the device sends data collected using its camera and microphone to an emotion analysis engine. This data serves as input for analyzing the user's real-time emotional state.

[0747] Step 4:

[0748] The emotion analysis engine uses data received from the device to determine the user's emotional state. It analyzes the user's facial expressions and tone of voice using image processing and voice analysis algorithms. The analysis identifies states such as concentration, anxiety, and interest, and these are sent back to the server.

[0749] Step 5:

[0750] The server analyzes the training content based on the results and identification information from the sentiment analysis engine. It runs a machine learning model to determine the optimal content presentation format and difficulty level for the user. In this process, it selects the optimal option from multiple candidates and generates it as transformed content.

[0751] Step 6:

[0752] The server sends optimized learning content to the device. The device displays this to the user, assisting with learning. By receiving content tailored to their cognitive characteristics and emotions, users can have a more effective learning experience.

[0753] This process allows users to continuously receive learning content tailored to their needs, improving both learning efficiency and satisfaction.

[0754] (Application Example 2)

[0755] 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".

[0756] Conventional learning systems optimized content based on learners' cognitive characteristics, but they failed to dynamically adjust content based on learners' emotional states. As a result, it was difficult to maintain learners' motivation and concentration. This invention aims to solve these problems and provide a more effective and personalized learning experience.

[0757] 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.

[0758] In this invention, the server includes means for receiving the learner's cognitive characteristics and generating a profile; means for analyzing learning content and determining a conversion format based on the profile; and means for analyzing the emotional state in real time and dynamically adjusting the difficulty level and presentation method of the content based on the analysis results. This makes it possible to provide personalized learning content that matches the learner's cognitive characteristics and emotional state.

[0759] "Learner cognitive characteristics" refer to the individual abilities and preferences of learners when it comes to understanding and remembering information.

[0760] A "profile" is an individual information structure generated based on the learner's cognitive characteristics, and is used to optimize learning content.

[0761] A "conversion format" is a format used to change how learning content is presented, and it is determined according to the learner's profile.

[0762] "Emotional state" refers to the psychological and emotional responses that learners exhibit during learning, including concentration, interest, and anxiety.

[0763] "Real-time analysis" is a process that instantly analyzes the learner's emotional state and uses the results to respond quickly.

[0764] "Dynamic adjustment" is a method that supports more effective learning by continuously changing the difficulty level and presentation method of content according to the learner's state.

[0765] This invention provides a system that optimizes learning content based on the learner's cognitive characteristics and emotional state. The server first receives the learner's cognitive characteristics based on information collected from the user's terminal and generates a corresponding profile. This profile reflects the learner's information processing ability and preferences and is used to determine the presentation format of the learning content.

[0766] Emotional state analysis utilizes software that analyzes the user's facial expressions and voice in real time using the camera and microphone built into the device. Specifically, facial expression recognition APIs and voice analysis software (e.g., Google Cloud Vision API and Amazon Rekognition) are used. Based on these analysis results, the server determines the learner's emotional state and dynamically adjusts the difficulty level and presentation method of the content accordingly.

[0767] When a user selects specific learning content, the server considers profile and sentiment analysis information to send the most suitable content to the device. For example, if the user shows signs of fatigue, the pace of the content is slowed down; if they show interest, more advanced and challenging content is provided.

[0768] For example, if a student shows signs of fatigue while watching online video learning materials, the application will slow down the video playback speed and suggest a break. Furthermore, if the student shows interest in a particular learning point, it will present detailed materials or application problems related to that point.

[0769] Examples of prompt statements to be input to a generative AI model include the following:

[0770] "Please select the most suitable learning content considering the learner's situation below. Content in an easy-to-understand format is preferable."

[0771] Slow eye movements are a sign of fatigue.

[0772] An uneasy tone can be heard in the audio.

[0773] Audio responses showing interest in recent learning items

[0774] In this way, learners receive learning content in a format that is best suited to them, maximizing their learning effectiveness.

[0775] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0776] Step 1:

[0777] The device uses a camera and microphone to collect the user's facial expression and voice data. This data is collected in real time and used as input to determine emotional state. The collected data is processed into a format necessary for emotion analysis and then sent to the server.

[0778] Step 2:

[0779] The server analyzes the received facial expression data and audio data. This is done using facial expression recognition APIs and audio analysis software (e.g., Google Cloud Vision API or Amazon Rekognition). The data is analyzed and outputted to indicate the learner's emotional state (e.g., fatigue, anxiety, interest).

[0780] Step 3:

[0781] The server integrates a profile based on cognitive characteristics previously received from the user with emotional states obtained through analysis to determine the optimal learning content. In this process, the content format and difficulty level are selected according to the user's level of interest and understanding.

[0782] Step 4:

[0783] The server sends the selected learning content to the device. This content is tailored to the user's current emotional state; for example, if the user is feeling tired, they will be provided with materials at a slower pace, while if they are showing interest, they will be presented with more in-depth content.

[0784] Step 5:

[0785] The device displays learning content sent from the server to the user. The user receives this optimized learning content, allowing for a more comfortable and effective learning experience. Further optimization is possible as the user continues to provide sentiment data, adapting to their learning progress.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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."

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] The following is further disclosed regarding the embodiments described above.

[0808] (Claim 1)

[0809] A means for receiving learners' cognitive characteristics and generating profiles,

[0810] A means for analyzing the learning content based on the aforementioned profile and determining the conversion format,

[0811] A means for converting learning content according to a determined conversion format,

[0812] A means of sending converted content to learners and supporting their learning,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, comprising means for converting text-based content into video format when the learner's cognitive characteristics are visually dominant.

[0816] (Claim 3)

[0817] The system according to claim 1, comprising means for converting text-based content into audio format when the learner's cognitive characteristics are auditory dominant.

[0818] "Example 1"

[0819] (Claim 1)

[0820] A means of collecting learners' cognitive characteristics data,

[0821] A means for analyzing the aforementioned data, generating and saving learner profiles,

[0822] A means for determining the optimal conversion format of the learning information based on the aforementioned profile,

[0823] A means for transforming training information according to a determined transformation format using a generative AI model,

[0824] A means of quality checking the converted learning information and providing it to the students,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, comprising means for converting text-based information into video format and providing it after quality verification, when the learner's cognitive characteristics are visually dominant.

[0828] (Claim 3)

[0829] The system according to claim 1, comprising means for converting text-based information into audio format and providing it after quality verification, when the learner's cognitive characteristics are auditory-dominant.

[0830] "Application Example 1"

[0831] (Claim 1)

[0832] A means for receiving learners' cognitive characteristics and generating profiles,

[0833] A means for analyzing the learning content based on the aforementioned profile and determining the conversion format,

[0834] A means for converting learning content according to a determined conversion format,

[0835] A means of sending converted content to learners and supporting their learning,

[0836] Means for dynamically distributing the aforementioned learning content via a network,

[0837] A means by which a terminal converts content received from a network and displays it on a visual or sound device,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, comprising means for converting text-based content into video format when the learner's cognitive characteristics are visually dominant.

[0841] (Claim 3)

[0842] The system according to claim 1, comprising means for converting text-based content into audio format when the learner's cognitive characteristics are auditory dominant.

[0843] "Example 2 of combining an emotion engine"

[0844] (Claim 1)

[0845] A means for receiving learner cognitive characteristics and generating identification information,

[0846] A means for analyzing information and determining a conversion format based on the aforementioned identification information and emotional state,

[0847] A means of transforming information according to a determined transformation format and providing a personalized learning experience,

[0848] A means of transmitting the converted information to the learner and supporting real-time adaptive learning,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, comprising means for converting text-based information into a visual format when the learner's cognitive characteristics are visually dominant and their emotional state indicates interest.

[0852] (Claim 3)

[0853] The system according to claim 1, further comprising means for converting text-based information into audio format when the learner's cognitive characteristics are auditory-dominant and their emotional state indicates decreased concentration.

[0854] "Application example 2 when combining with an emotional engine"

[0855] (Claim 1)

[0856] A means for receiving learners' cognitive characteristics and generating profiles,

[0857] A means for analyzing the learning content based on the aforementioned profile and determining the conversion format,

[0858] A means for converting learning content according to a determined conversion format,

[0859] A means of sending converted content to learners and supporting their learning,

[0860] A means to analyze the learner's emotional state in real time and dynamically adjust the difficulty level and presentation method of the content based on the analysis results,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, comprising means for converting text-based content into an advanced video format when the learner's cognitive characteristics are visually dominant and their emotional state indicates interest.

[0864] (Claim 3)

[0865] The system according to claim 1, comprising means for converting text-based content into a simple audio format when the learner's cognitive characteristics are auditory-dominant and their emotional state is anxious. [Explanation of symbols]

[0866] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving learners' cognitive characteristics and generating profiles, A means for analyzing the learning content based on the aforementioned profile and determining the conversion format, A means for converting learning content according to a determined conversion format, A means of sending converted content to learners and supporting their learning, A system that includes this.

2. The system according to claim 1, comprising means for converting text-based content into video format when the learner's cognitive characteristics are visually dominant.

3. The system according to claim 1, further comprising means for converting text-based content into audio format when the learner's cognitive characteristics are auditory-dominant.

Images