system

Abstract

We provide the system. [Solution] A means for acquiring learner characteristic information and generating a profile, A means of selecting and customizing the optimal learning content based on the generated profile, A means of providing customized learning content to learners via communication means, A means of tracking learners' learning progress and generating feedback, A means of saving learning content created by learners as shareable data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern education and reskilling, when learners engage in fields or difficult genres they are learning for the first time, there is a problem that the learning motivation decreases because the initial hurdle is high. Also, individual optimization according to diverse learning needs is insufficient, and among multiple learners with different backgrounds and purposes, an optimal learning approach cannot be provided for each.

Means for Solving the Problems

[0005] This invention provides means for acquiring learner characteristic information and generating profiles, thereby enabling the customization of learning content to suit each learner. Furthermore, by selecting and customizing appropriate learning content based on the generated profiles, it enables the provision of learning tailored to each individual learner. This system provides customized learning content to learners via communication means, tracks progress, and generates feedback, thereby improving motivation and supporting effective learning. In addition, learning content created by learners can be saved as shareable data, and learning resources can be shared with other learners, thereby broadening the scope of learning.

[0006] A "learner" refers to an individual receiving education or training, whose purpose is to acquire specific knowledge or skills.

[0007] "Characteristic information" refers to a collection of information that indicates a learner's personal attributes and characteristics, such as their interests, skill level, and learning objectives.

[0008] A "profile" is a data structure generated based on learner characteristics, which allows for the customization of teaching methods and content to best suit each learner.

[0009] "Customization" is the process of adjusting and adapting the content of a product or service to meet the specific needs and characteristics of a particular user.

[0010] "Communication methods" refer to devices and protocols for sending and receiving information, and in this context, include the infrastructure for delivering learning content to learners.

[0011] "Progress" refers to the degree of progress toward achieving a goal in a given process or plan, and is an indicator of how much learning has been done.

[0012] "Feedback" refers to information that includes evaluations and suggestions regarding a learner's activities, or advice for the next step in their learning.

[0013] "Shareable data" refers to information that is stored in a format that allows different users to access or use it, and that can be utilized by a large number of users. [Brief explanation of the drawing]

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

Embodiments for Carrying out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention constructs an application platform that provides personalized learning by utilizing learner characteristic information. This system mainly consists of the following elements:

[0036] User profile generation

[0037] When users first access the system, they enter detailed information such as their interests, current skill level, and learning objectives. Based on this information, the server generates a user profile and stores it in a database. This profile serves as a foundation for appropriately customizing learning content based on the individual characteristics of each learner.

[0038] Selection and customization of learning content

[0039] Based on the generated user profiles, the server uses a generated AI model to select the most effective learning content for each learner. This process includes evaluating the difficulty level of the learning and how well it meets the learner's needs. The selected content is then customized to the user's profile.

[0040] Distribution of learning content

[0041] Customized learning content is delivered to the user's device, such as a smartphone or computer, via communication methods. In particular, messaging platforms like LINE ensure that content is easily delivered to devices that learners use daily.

[0042] Progress management and feedback provision

[0043] When a user accesses learning content, their usage and results are recorded via their device, and the server uses this information to manage their learning progress. This progress data is used to generate feedback for the learner. The feedback suggests the next learning steps and is intended to maintain and improve the learner's motivation.

[0044] Content posting and sharing

[0045] Users can create their own learning content and post it to the platform to share with other learners. The server stores the shared content in a database, providing other users with the opportunity to freely access and expand their learning.

[0046] As a concrete example, if a 30-year-old engineer uses this system to learn a new programming language, and the user requests an introduction to programming, the server generates an optimal list of learning materials based on their profile, customizes it, and delivers an appropriate amount of content daily via LINE. In this way, the user can continue learning without burden, receive personalized advice based on their progress data, and share their original projects with other users.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] When a user first accesses the system, the terminal prompts them to enter detailed information about their areas of interest, current skill level, and learning objectives.

[0050] Step 2:

[0051] The server generates a user profile based on information received from the terminal and stores it in a database. The generated profile is used as foundational data to address each user's learning needs.

[0052] Step 3:

[0053] The server uses a generated AI model to select the most suitable learning content based on the user profile. The selection process evaluates materials that match the user's skill level and interests, and automatically adjusts the content accordingly.

[0054] Step 4:

[0055] Customized learning content is delivered from the server to the user's device via communication means. The content received on the device is then used for learning through applications that the user uses on a daily basis.

[0056] Step 5:

[0057] The device records the user's learning progress and sends data such as completed tasks and study time to the server.

[0058] Step 6:

[0059] The server analyzes the collected progress data to evaluate the user's learning achievement and generates feedback for the next step. The generated feedback is intended to maintain and improve the user's motivation.

[0060] Step 7:

[0061] Users upload their self-created learning content to a server via their device and post it to a sharing platform. The server stores the posted content in a database and makes it available to other users.

[0062] (Example 1)

[0063] 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."

[0064] In today's educational environment, providing learning content tailored to the individual characteristics of learners is time-consuming and labor-intensive, presenting numerous obstacles. Furthermore, adequately tracking and providing feedback on learning progress is not easy. Additionally, there is a lack of platforms for facilitating content sharing among learners. This invention aims to solve these problems and provide an individualized and effective learning experience.

[0065] 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.

[0066] In this invention, the server includes means for acquiring learner characteristic data and generating a user profile, means for optimizing optimal educational content using generative AI technology, and means for supporting the content selection process using prompt sentences. This enables the provision of personalized educational content, appropriate monitoring of learning progress, and provision of evaluation information.

[0067] A "learner" refers to an individual who uses educational content to acquire new knowledge and skills.

[0068] "Characteristic data" refers to information related to individual attributes of learners, such as their interests, skill levels, and learning objectives.

[0069] A "user profile" is an individual record generated based on learner characteristic data, and refers to the basic information used to customize educational content.

[0070] "Educational content" refers to teaching materials and information resources that learners use to acquire new knowledge and skills.

[0071] "Generative AI technology" refers to a method that uses artificial intelligence technology to analyze data and generate optimal results or predictions.

[0072] A "prompt" refers to an instruction or question used by generative AI technology to select appropriate educational content.

[0073] "Evaluation information" refers to feedback and improvement suggestions generated based on the learner's progress and learning results.

[0074] This invention provides a system that delivers optimized educational content based on individual learner characteristic data. This system utilizes generative AI technology to achieve both efficiency and personalization in education. The following describes an embodiment of the system.

[0075] First, users input information such as their interests, current skill level, and learning objectives via their device upon their initial access. Based on this, the server creates a user profile using the generated information and stores it in a database. The hardware used includes general-purpose computers and smartphones, and the software used is a database management system.

[0076] After a profile is created, the server optimizes the educational content provided using generative AI technology. Specifically, it selects the most suitable educational content by inputting prompt sentences appropriate for content selection into the generative AI model while referring to the user profile. One example of generative AI software used is a generative model that employs natural language processing technology.

[0077] Educational content is delivered to users' devices, such as smartphones and computers, and provided via messaging platforms like LINE. This allows learners to easily continue their studies using devices they use daily.

[0078] As a concrete example, let's consider a scenario where a 30-year-old engineer uses this system to learn a new programming language. In this case, when the user enters "I want to learn programming for beginners," the server generates a list of optimal learning materials based on their profile and provides an appropriate amount of content daily via LINE, allowing the user to progress with their learning without burden.

[0079] An example of a prompt message would be, "A 30-year-old engineer is looking for learning materials for programming beginners. Based on their profile information, please suggest the most suitable content for this user." This system enables an efficient and personalized learning experience.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] When a user first accesses a learning application on their device, they enter information about their interests, skill level, and learning objectives. The device sends this entered characteristic data to a server. The server analyzes the received data and generates a user profile. This profile is stored in a database as foundational information to help select personalized educational content.

[0083] Step 2:

[0084] The server retrieves user profiles from the database. Next, the server uses a generative AI model to select the most suitable educational content based on the prompt. For example, if the prompt is "Suggest the most suitable content for this user," the generative AI model outputs a list of recommended educational content tailored to the profile. This ensures that content optimized for the user is selected.

[0085] Step 3:

[0086] The server prepares to deliver selected and customized educational content. Next, the server uses a communication method, such as a messaging platform like LINE, to send the selected content to the user's device. The device then displays the received content to the user, allowing them to begin learning.

[0087] Step 4:

[0088] When a user learns educational content through their device, usage and progress data are recorded on the device. The device sends this data to a server. The server analyzes the received data and evaluates the learning progress. Based on this evaluation, the server generates and provides feedback to the user regarding the next learning step.

[0089] Step 5:

[0090] Users can create their own learning content and post it to the platform. The device provides the interface for doing so. The server stores the posted content in a database, making it accessible to other learners. This enables content sharing among users and broadens the scope of learning.

[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] Conventional learning systems struggle to provide personalized learning for each learner, and often fail to adequately provide feedback or suggest learning content tailored to each learner's progress. Furthermore, the methods for delivering learning content using flexible communication channels are often limited, hindering efficient learning progress.

[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 acquiring learner characteristic information and generating a profile, means for selecting and customizing optimal learning content based on the generated profile, and means for providing the customized learning content to the learner via communication means. This makes it possible to provide an efficient and effective learning experience through the provision of learning content optimized for each individual learner, followed by progress management and feedback.

[0096] "Learner characteristic information" refers to information that indicates the individual characteristics of each learner, including their interests, skill level, and learning objectives.

[0097] A "profile" is a collection of data generated based on learner characteristics and used to optimize learning content.

[0098] "Customization" refers to the process of adjusting and individualizing learning content based on each learner's profile.

[0099] "Communication methods" refer to electronic media and platforms used to provide learning content to learners.

[0100] "Progress tracking" is a technique for understanding and recording the extent to which learners have completed the learning material.

[0101] "Feedback" refers to information that provides advice and evaluations tailored to the learner's progress, guiding them through the next learning steps.

[0102] "Shareable data" refers to digital information saved in a format that allows learners to share their learning content with other learners.

[0103] A "messaging platform" is a type of communication tool or service that allows information to be sent and received via electronic messages.

[0104] A "machine learning model" is an algorithm or mathematical model that learns from data and makes predictions or decisions.

[0105] A "prompt statement" is an initial input statement used to give instructions to a generative AI model and is used to guide the model's output.

[0106] To implement this invention, the server must first acquire learner characteristic information and generate a profile based on it. By having learners input their interests, skill levels, and learning objectives through a smartphone or PC application, the server uses this data to generate a profile for each learner. The technologies used at this stage are an interface developed with React Native and a Firebase database.

[0107] Next, based on the generated profile, the server utilizes a generative AI model, such as OpenAI's GPT-4, to select and customize the most suitable learning content for the learner. It uses Python to manipulate the AI ​​model and generate prompt messages. These prompt messages, such as "Create learning content that best suits this user's skill level and areas of interest," provide the necessary instructions to the generative AI model.

[0108] Subsequently, the server delivers customized learning content to the learner's device via the LINE API or other messaging platforms. This allows learners to efficiently receive content daily. Furthermore, Google Analytics is used to track user learning progress and provide appropriate feedback. This feedback suggests the next learning steps and plays a role in maintaining learner motivation.

[0109] Furthermore, users can create their own content, which is stored on storage services such as AWS® S3. Other learners can also share and freely access this content. This allows learners to have a platform to share their learning with others.

[0110] In this system, the server, terminal, and user work together to create a learning environment and achieve efficient individualized learning.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The user operates the device to access the application interface and input information about their learning interests, skill level, and learning objectives. The device receives this data and sends it to the server. The input is learner characteristic information, and the output is the data sent to the server.

[0114] Step 2:

[0115] The server generates a profile based on the learner's characteristics information it receives. The server stores this data in the Firebase database and outputs it as a unique profile for each user. Data processing includes organizing the information and storing it in the database.

[0116] Step 3:

[0117] The server uses the generated profile data to call the generated AI model and select and customize the learning content. Specifically, it inputs prompt sentences into the AI ​​model via a Python program to generate optimal learning content. The input is profile data and prompt sentences, and the output is the learning content.

[0118] Step 4:

[0119] The server distributes the developed learning content to the device using APIs from messaging platforms such as LINE. At this point, the server packages the content and delivers it to the learner via communication. The input is the learning content, and the output is the distributed content.

[0120] Step 5:

[0121] The terminal displays the received learning content to the user, and the learner processes the content. The user's progress and responses are recorded on the terminal in real time and sent to the server. The input is the user's operation data, and the output is the transmission of progress data to the server.

[0122] Step 6:

[0123] The server uses Google Analytics to analyze the user's learning progress based on the received progress data and generates feedback. This feedback includes suggestions for the next learning steps, and this information is also returned to the device via the messaging platform. The input is progress data, and the output is the feedback content.

[0124] Step 7:

[0125] Users create their own learning content and upload it to the server via their device. The server stores this content in AWS S3 and generates a link for sharing with other users. The input is user-created content, and the output is a shareable data link.

[0126] 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.

[0127] This invention provides a customized learning system that combines learner characteristic information with a function to recognize emotions. By using an emotion engine, it is possible to analyze the learner's current emotional state and design an optimal learning experience accordingly.

[0128] User Profile and Sentiment Data Generation

[0129] When a user first accesses the system, the terminal prompts them to input information about their areas of interest, skill level, learning objectives, and emotional state. The emotion engine analyzes the user's emotions using methods such as speech recognition, facial recognition, or text input. The server then generates a user profile and emotion data based on this information and stores it in a database.

[0130] Emotion-based selection and customization of learning content

[0131] The server uses a generative AI model to select learning content based on user profiles and sentiment data. Sentiment data reflects the user's motivation level and stress levels, and the difficulty of the content is adjusted accordingly. For example, if a user is stressed, the system presents simple and intuitive content.

[0132] Content delivery and real-time feedback

[0133] Customized learning content is delivered to the device via communication. As the user engages with the content, the emotion engine monitors the user's emotional changes in real time, and the server adjusts the feedback accordingly. For example, if the user shows a positive reaction, a more challenging task may be presented.

[0134] Progress management and emotionally sensitive next step proposals

[0135] User learning progress is recorded via the device and analyzed by the server. Based on the integrated sentiment data and progress data, the server suggests the next learning content. For example, if the user shows signs of fatigue, it suggests more relaxing learning content, while if the user is highly motivated, it recommends more advanced content.

[0136] Content sharing feature

[0137] Users can upload their own learning content to the server via their device and share it with other users. The server stores this data in a database and grants access rights so that other users can use it.

[0138] As a concrete example, let's say a middle school student is studying English vocabulary. Based on the data recognized by the emotion engine, if the user is tired, the server will suggest game-style content to help them memorize simple words. Conversely, if the system detects that the user is enjoying themselves, it will offer a quiz containing slightly more difficult words. This provides a comfortable learning environment that takes the user's concentration into consideration.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] When a user first accesses the system, the terminal prompts them to input information about their learning genre, skill level, learning objectives, and current emotional state. The emotional state is recognized by the emotion engine through voice input and image analysis using the camera.

[0142] Step 2:

[0143] The server generates user profiles and sentiment data based on information sent from the terminal and stores them in a database. Here, the sentiment data is used as an indicator of the user's motivation and stress level.

[0144] Step 3:

[0145] Using a generative AI model, the server selects learning content based on user profiles and emotion data. For example, if the emotion engine detects user tension, the server will select content that promotes relaxation.

[0146] Step 4:

[0147] The server delivers selected and customized content to the device via communication. The user begins learning on their device. Meanwhile, the emotion engine continues to monitor the user's emotional state in real time.

[0148] Step 5:

[0149] If the user's emotions change during the learning process, the server adjusts its feedback accordingly. For example, if positive emotions are detected, the server automatically presents more motivating content next.

[0150] Step 6:

[0151] The device records the user's learning progress and sends it to the server. The server integrates this data with sentiment data to recommend the next content to learn and its difficulty level.

[0152] Step 7:

[0153] Users upload newly created learning content from their devices, and the server saves it to a database. This gives other users the opportunity to use that content and expand their learning.

[0154] (Example 2)

[0155] 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".

[0156] While conventional learning systems offer personalization based on learner characteristics, their ability to consider learners' emotional states is limited, making it difficult to quickly address learners' stress and decreased motivation. This leads to reduced learning efficiency and decreased learner satisfaction. Furthermore, utilizing emotional data for real-time feedback adjustments and suggestions for future learning content remains a challenge.

[0157] 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.

[0158] In this invention, the server includes means for acquiring learner characteristic information and emotional state and generating a profile and emotional data; means for selecting and customizing optimal learning content based on the generated profile and emotional data; and means for providing the customized learning content to the learner via communication means, monitoring emotional changes in real time, and adjusting feedback. This makes it possible to provide appropriate learning content and adjust feedback based on the learner's emotional state, thereby improving the efficiency and satisfaction of learning.

[0159] "Learner characteristic information" refers to individual information such as learners' interests, skill levels, and learning objectives, and is data that indicates how individuals should approach learning.

[0160] "Emotional state" refers to information that describes a learner's current emotions and psychological state, including elements such as motivation and stress levels.

[0161] A "profile" is a comprehensive set of information about a learner, generated based on their characteristics and emotional state.

[0162] "Emotional data" refers to emotional states presented in data format, forming the basis for recording and analyzing learners' psychological states.

[0163] A "generative AI model" refers to artificial intelligence methods and systems used to determine the optimal learning content based on user profiles and sentiment data.

[0164] "Communication means" refers to the technologies and methods used to send and receive digital data, such as connections via the Internet.

[0165] "Feedback" refers to providing information to evaluate and improve the learning process based on the learner's progress and emotional state.

[0166] "Learning content" refers to the specific materials and assignments that learners should work on, and includes all information that is the subject of learning activities.

[0167] "Next learning content" refers to the subjects or tasks that should be provided next, based on the progress and results of the current learning content.

[0168] "Monitoring emotional changes in real time" refers to the process of immediately checking the learner's emotional state during learning and providing immediate feedback to the learning system based on the results.

[0169] This invention provides a customized learning system that takes into account the learner's emotional state in addition to their characteristic information. The invention can be specifically implemented through the following combination of hardware and software.

[0170] The user accesses the device and initially enters information such as areas of interest, skill level, learning objectives, and emotional state. This information is collected via a terminal that includes voice recognition software (general-purpose voice recognition technology), facial recognition software (general-purpose facial recognition technology), and text input options. This enables the collection and initial processing of a wide range of user data.

[0171] Based on the information the server reads, it generates user profiles and sentiment data. Using a general natural language processing AI model, for example, it selects the most suitable content for the learner and provides guidelines for customization.

[0172] The server selects the most suitable learning content and adjusts the difficulty level based on the learner's profile and emotional data. To achieve this, it maintains a content database and retrieves appropriate materials from the accumulated learning resources according to the user's state.

[0173] As a concrete example, if the emotion engine detects fatigue while a middle school student is studying English vocabulary, the server will suggest a simple, game-based vocabulary learning content to that user. In this way, a learning approach that responds to the user's emotional state is important for maintaining their motivation to learn.

[0174] Example prompt text

[0175] "Design an AI model that suggests optimal learning content based on the current stress level."

[0176] In this way, the present invention makes it possible to enhance individual learning efficiency and provide users with a learning experience that reduces stress by incorporating emotion recognition into the learning system.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] Users use a device to input information about their areas of interest, skill level, learning objectives, and emotional state. This information is collected by the device, with options for facial recognition and voice recognition also available. The entered data is sent from the device to a server and used as foundational data for profile generation.

[0180] Step 2:

[0181] The server receives user information transmitted from the terminal and generates profile and sentiment data. This data processing involves aggregating user characteristic information and analyzing sentiment data based on it. A generative AI model is used to analyze this integrated data and construct profiles tailored to individual needs. The profile and sentiment data are stored in a database.

[0182] Step 3:

[0183] The server uses user profiles and emotional data generated by the server as input to select the most suitable learning content. A generative AI model is used to extract relevant learning content from the database based on the user's emotional state and learning objectives. For example, a user experiencing stress will be given simpler content. The selected content is then sent to the device.

[0184] Step 4:

[0185] The device provides the user with customized learning content it has received. As the user uses the content, the device monitors their emotional changes in real time. An emotion engine analyzes the user's reactions and sends feedback information to the server based on the data obtained. Based on this feedback information, the system may switch to more difficult content if necessary.

[0186] Step 5:

[0187] The server integrates the user's learning progress with real-time sentiment data to suggest the next learning step. At this stage, data analysis considers the user's motivation and fatigue level to determine the recommendations. For example, if the user's motivation is high, a more difficult task will be recommended, and the recommendations will be provided to the user again via the terminal.

[0188] Step 6:

[0189] The learning content created by the user is uploaded from the device to the server and saved as data for sharing with other users. This data is registered in a database by the server and becomes accessible to other users after they are granted appropriate access permissions.

[0190] (Application Example 2)

[0191] 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".

[0192] In today's world, learners often struggle to receive appropriate learning content that effectively considers their individual emotional states and progress. Furthermore, the lack of personalized suggestions based on user emotions highlights the need to create an environment where learners can study efficiently and comfortably.

[0193] 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.

[0194] In this invention, the server includes means for acquiring learner characteristic information and generating a profile, means for acquiring information using an emotion recognition device and optimizing suggestions according to the user's situation, and means for suggesting the next learning content based on emotions. This makes it possible for learners to receive optimal learning content that matches their current emotional state.

[0195] "Learner characteristic information" refers to information such as an individual learner's interests, skill level, and learning objectives, and serves as the basic data for generating a profile.

[0196] A "device for recognizing emotions" is a device that uses speech recognition or facial recognition technology to analyze the emotional state of learners.

[0197] "Means for generating a profile" refers to a means that includes a process of organizing and recording information tailored to each individual learner, based on the learner's characteristic information.

[0198] "Methods for optimizing proposals" refer to methods for optimizing the content and services provided based on the results of recognizing emotions.

[0199] A "means for suggesting the next learning content" refers to a method that automatically presents the next learning topic, taking into account the learner's progress and emotional state.

[0200] "Learning content" is a general term for the information and learning materials that learners receive during their learning activities.

[0201] "Means of generating feedback" refers to methods that include a process of generating and presenting appropriate evaluations and areas for improvement based on the learner's learning progress and emotional state.

[0202] In this embodiment of the invention, a system is provided in which a server and a terminal cooperate to optimize the user's learning experience.

[0203] The server first generates a learner profile based on the user's characteristics received during their initial access. This profile includes the user's areas of interest, skill level, and learning objectives. The server then uses an emotion recognition device to analyze the user's voice data and facial images to identify their current emotions in real time. This process utilizes speech recognition and facial recognition technologies.

[0204] Based on profiles and emotional data, a generative AI model selects appropriate learning content and adjusts and customizes the difficulty level. The device provides the selected learning content to the user, and during learning, the emotional engine monitors the user's facial expressions and voice. This allows the system to adapt in real time: challenging content when positive reactions are detected, and relaxing content when fatigue or other negative reactions are recognized.

[0205] The server also tracks learning progress and generates feedback, which is then used to suggest future learning content. The data obtained through this process is stored and shared in a database accessible to other users.

[0206] For example, if a user is feeling stressed while learning, the system can suggest a dessert recipe to promote relaxation. Conversely, if the user is feeling energetic and seeking a challenge, recipes using protein-rich ingredients will be recommended.

[0207] An example of a prompt for a generative AI model is, "Please suggest a recipe for when the user needs to relax." Such a prompt automatically generates and provides content to the user.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server receives characteristic information upon the user's first access and generates a user profile. The input is information provided by the user regarding their areas of interest, skill level, and learning objectives, and the output is the user profile created based on this information. This profile creation process involves saving the information to a database.

[0211] Step 2:

[0212] The device collects the user's emotional state using an emotion recognition device. The input is the user's voice data and facial image, and the output is analyzed emotion data. This uses voice recognition and facial recognition technology to perform emotion analysis in real time.

[0213] Step 3:

[0214] The server uses a generated AI model based on user profiles and sentiment data to select and customize learning content. In this step, user profiles and sentiment data are used as input, and learning content with adjusted difficulty levels is generated as output. Data processing includes calculations using the AI ​​model.

[0215] Step 4:

[0216] The device delivers selected learning content to the user. The input here is the customized learning content, and the output is the display of that content to the user. The content is displayed through an interface and becomes accessible to the user.

[0217] Step 5:

[0218] The server continuously monitors the user's emotional changes during the learning process and adjusts the content as needed. The input is real-time updated emotional data, and the output is fine-tuning of the content in response to those emotions. This process involves continuous data calculations.

[0219] Step 6:

[0220] The server tracks learning progress and generates feedback. The input for this step is the user's learning progress data, and the output is the generated feedback and suggestions for the next learning session. This includes analyzing the progress data and extracting areas for improvement.

[0221] Step 7:

[0222] When a user shares learning content with other users, the server saves that data to a database and configures sharing settings. The input is the learning content uploaded by the user, and the output is the data made accessible to other users. This process involves writing to a database.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] This invention constructs an application platform that provides personalized learning by utilizing learner characteristic information. This system mainly consists of the following elements:

[0240] User profile generation

[0241] When users first access the system, they enter detailed information such as their interests, current skill level, and learning objectives. Based on this information, the server generates a user profile and stores it in a database. This profile serves as a foundation for appropriately customizing learning content based on the individual characteristics of each learner.

[0242] Selection and customization of learning content

[0243] Based on the generated user profiles, the server uses a generated AI model to select the most effective learning content for each learner. This process includes evaluating the difficulty level of the learning and how well it meets the learner's needs. The selected content is then customized to the user's profile.

[0244] Distribution of learning content

[0245] Customized learning content is delivered to the user's device, such as a smartphone or computer, via communication methods. In particular, messaging platforms like LINE ensure that content is easily delivered to devices that learners use daily.

[0246] Progress management and feedback provision

[0247] When a user accesses learning content, their usage and results are recorded via their device, and the server uses this information to manage their learning progress. This progress data is used to generate feedback for the learner. The feedback suggests the next learning steps and is intended to maintain and improve the learner's motivation.

[0248] Content posting and sharing

[0249] Users can create their own learning content and post it to the platform to share with other learners. The server stores the shared content in a database, providing other users with the opportunity to freely access and expand their learning.

[0250] As a concrete example, if a 30-year-old engineer uses this system to learn a new programming language, and the user requests an introduction to programming, the server generates an optimal list of learning materials based on their profile, customizes it, and delivers an appropriate amount of content daily via LINE. In this way, the user can continue learning without burden, receive personalized advice based on their progress data, and share their original projects with other users.

[0251] The following describes the processing flow.

[0252] Step 1:

[0253] When a user first accesses the system, the terminal prompts them to enter detailed information about their areas of interest, current skill level, and learning objectives.

[0254] Step 2:

[0255] The server generates a user profile based on information received from the terminal and stores it in a database. The generated profile is used as foundational data to address each user's learning needs.

[0256] Step 3:

[0257] The server uses a generated AI model to select the most suitable learning content based on the user profile. The selection process evaluates materials that match the user's skill level and interests, and automatically adjusts the content accordingly.

[0258] Step 4:

[0259] Customized learning content is delivered from the server to the user's device via communication means. The content received on the device is then used for learning through applications that the user uses on a daily basis.

[0260] Step 5:

[0261] The device records the user's learning progress and sends data such as completed tasks and study time to the server.

[0262] Step 6:

[0263] The server analyzes the collected progress data to evaluate the user's learning achievement and generates feedback for the next step. The generated feedback is intended to maintain and improve the user's motivation.

[0264] Step 7:

[0265] Users upload their self-created learning content to a server via their device and post it to a sharing platform. The server stores the posted content in a database and makes it available to other users.

[0266] (Example 1)

[0267] 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."

[0268] In today's educational environment, providing learning content tailored to the individual characteristics of learners is time-consuming and labor-intensive, presenting numerous obstacles. Furthermore, adequately tracking and providing feedback on learning progress is not easy. Additionally, there is a lack of platforms for facilitating content sharing among learners. This invention aims to solve these problems and provide an individualized and effective learning experience.

[0269] 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.

[0270] In this invention, the server includes means for acquiring learner characteristic data and generating a user profile, means for optimizing optimal educational content using generative AI technology, and means for supporting the content selection process using prompt sentences. This enables the provision of personalized educational content, appropriate monitoring of learning progress, and provision of evaluation information.

[0271] A "learner" refers to an individual who uses educational content to acquire new knowledge and skills.

[0272] "Characteristic data" refers to information related to individual attributes of learners, such as their interests, skill levels, and learning objectives.

[0273] A "user profile" is an individual record generated based on learner characteristic data, and refers to the basic information used to customize educational content.

[0274] "Educational content" refers to teaching materials and information resources that learners use to acquire new knowledge and skills.

[0275] "Generative AI technology" refers to a method that uses artificial intelligence technology to analyze data and generate optimal results or predictions.

[0276] A "prompt" refers to an instruction or question used by generative AI technology to select appropriate educational content.

[0277] "Evaluation information" refers to feedback and improvement suggestions generated based on the learner's progress and learning results.

[0278] This invention provides a system that delivers optimized educational content based on individual learner characteristic data. This system utilizes generative AI technology to achieve both efficiency and personalization in education. The following describes an embodiment of the system.

[0279] First, at the first access, the user inputs information such as interests, current skill level, and learning objectives through the terminal. Based on this, the server creates a user profile based on the generated information and stores it in the database. The hardware used includes general computers and smartphones, and a database management system is used for the software.

[0280] After the profile is created, the server optimizes the educational content provided using generative AI technology. Specifically, while referring to the user profile, by inputting a prompt sentence suitable for content selection into the generative AI model, the optimal educational content is selected. As an example of the generative AI software used, there is a generative model using natural language processing technology.

[0281] The educational content is distributed to the user's terminal, such as a smartphone or a personal computer, and provided via a messaging platform such as LINE. As a result, learners can easily continue learning on the devices they use daily.

[0282] As a specific example, assume the case where a 30-year-old engineer uses this system when learning a new programming language. In this case, when the user inputs "want to start programming", the server generates an optimal list of teaching materials based on the profile and provides an appropriate amount of content every day via LINE, enabling the user to proceed with learning without burden.

[0283] An example of the prompt sentence is "A 30-year-old engineer hopes for teaching materials for beginners in programming. Based on the profile information, please propose the most suitable content for this user." This system enables an efficient and personalized learning experience.

[0284] The flow of the specific process in Example 1 will be described using FIG. 11.

[0285] Step 1:

[0286] When the user first accesses the learning application on the terminal, the user inputs information regarding interests, skill level, and learning objectives. The terminal transmits this input characteristic data to the server. The server analyzes the received data and generates a user profile. This profile is stored in the database as basic information useful for selecting individualized educational content.

[0287] Step 2:

[0288] The server retrieves the user profile from the database. Next, the server uses a generative AI model to select optimal educational content based on a prompt sentence. For example, when the prompt sentence "Please recommend the most suitable content for this user." is input, the generative AI model outputs a list of recommended educational content according to the profile. Thereby, content optimized for the user is selected.

[0289] Step 3:

[0290] The server prepares to deliver the selected and customized educational content. Next, the server uses communication means to transmit the selected content to the user's terminal through a messaging platform such as LINE. The terminal displays the received content to the user, enabling the user to start learning.

[0291] Step 4:

[0292] When the user learns educational content through the terminal, the usage status and progress data are recorded on the terminal. The terminal transmits this data to the server. The server analyzes the received data and evaluates the learning progress. Based on this evaluation, the server generates feedback regarding the next learning step and provides it to the user.

[0293] Step 5:

[0294] Users can create their own learning content and post it to the platform. The device provides the interface for doing so. The server stores the posted content in a database, making it accessible to other learners. This enables content sharing among users and broadens the scope of learning.

[0295] (Application Example 1)

[0296] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0297] Conventional learning systems struggle to provide personalized learning for each learner, and often fail to adequately provide feedback or suggest learning content tailored to each learner's progress. Furthermore, the methods for delivering learning content using flexible communication channels are often limited, hindering efficient learning progress.

[0298] 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.

[0299] In this invention, the server includes means for acquiring learner characteristic information and generating a profile, means for selecting and customizing optimal learning content based on the generated profile, and means for providing the customized learning content to the learner via communication means. This makes it possible to provide an efficient and effective learning experience through the provision of learning content optimized for each individual learner, followed by progress management and feedback.

[0300] "Learner characteristic information" refers to information that indicates the individual characteristics of each learner, including their interests, skill level, and learning objectives.

[0301] A "profile" is a collection of data generated based on learner characteristics and used to optimize learning content.

[0302] "Customization" refers to the operation of adjusting and individualizing learning content based on the profile of each learner.

[0303] "Communication means" refers to the electronic media and platforms used to provide learning content to learners.

[0304] "Progress tracking" is a technology for grasping and recording the degree to which a learner has completed learning content.

[0305] "Feedback" is information that provides advice and evaluation according to the progress of a learner and guides the next learning step.

[0306] "Shareable data" is digital information stored in a format that allows learners to share the learning content they have created with other learners.

[0307] "Messaging platform" is a type of communication tool or service that can send and receive information via electronic messages.

[0308] "Machine learning model" is an algorithm or mathematical model for learning from data and making predictions or judgments.

[0309] "Prompt text" is the initial input text for giving instructions to a generative AI model and is used to induce the output of the model.

[0310] To implement this invention, first, the server needs to obtain the characteristic information of the learner and generate a profile based on it. By the learner inputting their interests, skill levels, and learning objectives through the application of a smartphone or personal computer, the server uses this data to generate a profile for each learner. The technologies used at this stage are the interface developed with React Native and the Firebase database.

[0311] Next, based on the generated profile, the server utilizes a generative AI model, such as OpenAI's GPT-4, to select and customize the most suitable learning content for the learner. It uses Python to manipulate the AI ​​model and generate prompt messages. These prompt messages, such as "Create learning content that best suits this user's skill level and areas of interest," provide the necessary instructions to the generative AI model.

[0312] The server then delivers customized learning content to learners' devices via the LINE API and other messaging platforms. This allows learners to efficiently receive content daily. Furthermore, Google Analytics is used to track users' learning progress and provide appropriate feedback. This feedback suggests the next learning steps and plays a role in maintaining learner motivation.

[0313] Furthermore, users can create their own content, which is stored on storage services such as AWS S3. Other learners can also share and freely access this content. This allows learners to have a platform to share their learning with others.

[0314] In this system, the server, terminal, and user work together to create a learning environment and achieve efficient individualized learning.

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The user operates the device to access the application interface and input information about their learning interests, skill level, and learning objectives. The device receives this data and sends it to the server. The input is learner characteristic information, and the output is the data sent to the server.

[0318] Step 2:

[0319] The server generates a profile based on the learner's characteristics information it receives. The server stores this data in the Firebase database and outputs it as a unique profile for each user. Data processing includes organizing the information and storing it in the database.

[0320] Step 3:

[0321] The server uses the generated profile data to call the generated AI model and select and customize the learning content. Specifically, it inputs prompt sentences into the AI ​​model via a Python program to generate optimal learning content. The input is profile data and prompt sentences, and the output is the learning content.

[0322] Step 4:

[0323] The server distributes the developed learning content to the device using APIs from messaging platforms such as LINE. At this point, the server packages the content and delivers it to the learner via communication. The input is the learning content, and the output is the distributed content.

[0324] Step 5:

[0325] The terminal displays the received learning content to the user, and the learner processes the content. The user's progress and responses are recorded on the terminal in real time and sent to the server. The input is the user's operation data, and the output is the transmission of progress data to the server.

[0326] Step 6:

[0327] The server uses Google Analytics to analyze the user's learning progress based on the received progress data and generates feedback. This feedback includes suggestions for the next learning steps, and this information is also returned to the device via the messaging platform. The input is progress data, and the output is the feedback content.

[0328] Step 7:

[0329] Users create their own learning content and upload it to the server via their device. The server stores this content in AWS S3 and generates a link for sharing with other users. The input is user-created content, and the output is a shareable data link.

[0330] 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.

[0331] This invention provides a customized learning system that combines learner characteristic information with a function to recognize emotions. By using an emotion engine, it is possible to analyze the learner's current emotional state and design an optimal learning experience accordingly.

[0332] User Profile and Sentiment Data Generation

[0333] When a user first accesses the system, the terminal prompts them to input information about their areas of interest, skill level, learning objectives, and emotional state. The emotion engine analyzes the user's emotions using methods such as speech recognition, facial recognition, or text input. The server then generates a user profile and emotion data based on this information and stores it in a database.

[0334] Emotion-based selection and customization of learning content

[0335] The server uses a generative AI model to select learning content based on user profiles and sentiment data. Sentiment data reflects the user's motivation level and stress levels, and the difficulty of the content is adjusted accordingly. For example, if a user is stressed, the system presents simple and intuitive content.

[0336] Content delivery and real-time feedback

[0337] Customized learning content is delivered to the device via communication. As the user engages with the content, the emotion engine monitors the user's emotional changes in real time, and the server adjusts the feedback accordingly. For example, if the user shows a positive reaction, a more challenging task may be presented.

[0338] Progress management and emotionally sensitive next step proposals

[0339] User learning progress is recorded via the device and analyzed by the server. Based on the integrated sentiment data and progress data, the server suggests the next learning content. For example, if the user shows signs of fatigue, it suggests more relaxing learning content, while if the user is highly motivated, it recommends more advanced content.

[0340] Content sharing feature

[0341] Users can upload their own learning content to the server via their device and share it with other users. The server stores this data in a database and grants access rights so that other users can use it.

[0342] As a concrete example, let's say a middle school student is studying English vocabulary. Based on the data recognized by the emotion engine, if the user is tired, the server will suggest game-style content to help them memorize simple words. Conversely, if the system detects that the user is enjoying themselves, it will offer a quiz containing slightly more difficult words. This provides a comfortable learning environment that takes the user's concentration into consideration.

[0343] The following describes the processing flow.

[0344] Step 1:

[0345] When a user first accesses the system, the terminal prompts them to input information about their learning genre, skill level, learning objectives, and current emotional state. The emotional state is recognized by the emotion engine through voice input and image analysis using the camera.

[0346] Step 2:

[0347] The server generates user profiles and sentiment data based on information sent from the terminal and stores them in a database. Here, the sentiment data is used as an indicator of the user's motivation and stress level.

[0348] Step 3:

[0349] Using a generative AI model, the server selects learning content based on user profiles and emotion data. For example, if the emotion engine detects user tension, the server will select content that promotes relaxation.

[0350] Step 4:

[0351] The server delivers selected and customized content to the device via communication. The user begins learning on their device. Meanwhile, the emotion engine continues to monitor the user's emotional state in real time.

[0352] Step 5:

[0353] If the user's emotions change during the learning process, the server adjusts its feedback accordingly. For example, if positive emotions are detected, the server automatically presents more motivating content next.

[0354] Step 6:

[0355] The device records the user's learning progress and sends it to the server. The server integrates this data with sentiment data to recommend the next content to learn and its difficulty level.

[0356] Step 7:

[0357] Users upload newly created learning content from their devices, and the server saves it to a database. This gives other users the opportunity to use that content and expand their learning.

[0358] (Example 2)

[0359] 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".

[0360] While conventional learning systems offer personalization based on learner characteristics, their ability to consider learners' emotional states is limited, making it difficult to quickly address learners' stress and decreased motivation. This leads to reduced learning efficiency and decreased learner satisfaction. Furthermore, utilizing emotional data for real-time feedback adjustments and suggestions for future learning content remains a challenge.

[0361] 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.

[0362] In this invention, the server includes means for acquiring learner characteristic information and emotional state and generating a profile and emotional data; means for selecting and customizing optimal learning content based on the generated profile and emotional data; and means for providing the customized learning content to the learner via communication means, monitoring emotional changes in real time, and adjusting feedback. This makes it possible to provide appropriate learning content and adjust feedback based on the learner's emotional state, thereby improving the efficiency and satisfaction of learning.

[0363] "Learner characteristic information" refers to individual information such as learners' interests, skill levels, and learning objectives, and is data that indicates how individuals should approach learning.

[0364] "Emotional state" refers to information that describes a learner's current emotions and psychological state, including elements such as motivation and stress levels.

[0365] A "profile" is a comprehensive set of information about a learner, generated based on their characteristics and emotional state.

[0366] "Emotional data" refers to emotional states presented in data format, forming the basis for recording and analyzing learners' psychological states.

[0367] A "generative AI model" refers to artificial intelligence methods and systems used to determine the optimal learning content based on user profiles and sentiment data.

[0368] "Communication means" refers to the technologies and methods used to send and receive digital data, such as connections via the Internet.

[0369] "Feedback" refers to providing information to evaluate and improve the learning process based on the learner's progress and emotional state.

[0370] "Learning content" refers to the specific materials and assignments that learners should work on, and includes all information that is the subject of learning activities.

[0371] "Next learning content" refers to the subjects or tasks that should be provided next, based on the progress and results of the current learning content.

[0372] "Monitoring emotional changes in real time" refers to the process of immediately checking the learner's emotional state during learning and providing immediate feedback to the learning system based on the results.

[0373] This invention provides a customized learning system that takes into account the learner's emotional state in addition to their characteristic information. The invention can be specifically implemented through the following combination of hardware and software.

[0374] The user accesses the device and initially enters information such as areas of interest, skill level, learning objectives, and emotional state. This information is collected via a terminal that includes voice recognition software (general-purpose voice recognition technology), facial recognition software (general-purpose facial recognition technology), and text input options. This enables the collection and initial processing of a wide range of user data.

[0375] Based on the information the server reads, it generates user profiles and sentiment data. Using a general natural language processing AI model, for example, it selects the most suitable content for the learner and provides guidelines for customization.

[0376] The server selects the most suitable learning content and adjusts the difficulty level based on the learner's profile and emotional data. To achieve this, it maintains a content database and retrieves appropriate materials from the accumulated learning resources according to the user's state.

[0377] As a concrete example, if the emotion engine detects fatigue while a middle school student is studying English vocabulary, the server will suggest a simple, game-based vocabulary learning content to that user. In this way, a learning approach that responds to the user's emotional state is important for maintaining their motivation to learn.

[0378] Example prompt text

[0379] "Design an AI model that suggests optimal learning content based on the current stress level."

[0380] In this way, the present invention makes it possible to enhance individual learning efficiency and provide users with a learning experience that reduces stress by incorporating emotion recognition into the learning system.

[0381] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0382] Step 1:

[0383] Users use a device to input information about their areas of interest, skill level, learning objectives, and emotional state. This information is collected by the device, with options for facial recognition and voice recognition also available. The entered data is sent from the device to a server and used as foundational data for profile generation.

[0384] Step 2:

[0385] The server receives user information transmitted from the terminal and generates profile and sentiment data. This data processing involves aggregating user characteristic information and analyzing sentiment data based on it. A generative AI model is used to analyze this integrated data and construct profiles tailored to individual needs. The profile and sentiment data are stored in a database.

[0386] Step 3:

[0387] The server uses user profiles and emotional data generated by the server as input to select the most suitable learning content. A generative AI model is used to extract relevant learning content from the database based on the user's emotional state and learning objectives. For example, a user experiencing stress will be given simpler content. The selected content is then sent to the device.

[0388] Step 4:

[0389] The device provides the user with customized learning content it has received. As the user uses the content, the device monitors their emotional changes in real time. An emotion engine analyzes the user's reactions and sends feedback information to the server based on the data obtained. Based on this feedback information, the system may switch to more difficult content if necessary.

[0390] Step 5:

[0391] The server integrates the user's learning progress with real-time sentiment data to suggest the next learning step. At this stage, data analysis considers the user's motivation and fatigue level to determine the recommendations. For example, if the user's motivation is high, a more difficult task will be recommended, and the recommendations will be provided to the user again via the terminal.

[0392] Step 6:

[0393] The learning content created by the user is uploaded from the device to the server and saved as data for sharing with other users. This data is registered in a database by the server and becomes accessible to other users after they are granted appropriate access permissions.

[0394] (Application Example 2)

[0395] 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."

[0396] In today's world, learners often struggle to receive appropriate learning content that effectively considers their individual emotional states and progress. Furthermore, the lack of personalized suggestions based on user emotions highlights the need to create an environment where learners can study efficiently and comfortably.

[0397] 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.

[0398] In this invention, the server includes means for acquiring learner characteristic information and generating a profile, means for acquiring information using an emotion recognition device and optimizing suggestions according to the user's situation, and means for suggesting the next learning content based on emotions. This makes it possible for learners to receive optimal learning content that matches their current emotional state.

[0399] "Learner characteristic information" refers to information such as an individual learner's interests, skill level, and learning objectives, and serves as the basic data for generating a profile.

[0400] A "device for recognizing emotions" is a device that uses speech recognition or facial recognition technology to analyze the emotional state of learners.

[0401] "Means for generating a profile" refers to a means that includes a process of organizing and recording information tailored to each individual learner, based on the learner's characteristic information.

[0402] "Methods for optimizing proposals" refer to methods for optimizing the content and services provided based on the results of recognizing emotions.

[0403] A "means for suggesting the next learning content" refers to a method that automatically presents the next learning topic, taking into account the learner's progress and emotional state.

[0404] "Learning content" is a general term for the information and learning materials that learners receive during their learning activities.

[0405] "Means of generating feedback" refers to methods that include a process of generating and presenting appropriate evaluations and areas for improvement based on the learner's learning progress and emotional state.

[0406] In this embodiment of the invention, a system is provided in which a server and a terminal cooperate to optimize the user's learning experience.

[0407] The server first generates a learner profile based on the user's characteristics received during their initial access. This profile includes the user's areas of interest, skill level, and learning objectives. The server then uses an emotion recognition device to analyze the user's voice data and facial images to identify their current emotions in real time. This process utilizes speech recognition and facial recognition technologies.

[0408] Based on profiles and emotional data, a generative AI model selects appropriate learning content and adjusts and customizes the difficulty level. The device provides the selected learning content to the user, and during learning, the emotional engine monitors the user's facial expressions and voice. This allows the system to adapt in real time: challenging content when positive reactions are detected, and relaxing content when fatigue or other negative reactions are recognized.

[0409] The server also tracks learning progress and generates feedback, which is then used to suggest future learning content. The data obtained through this process is stored and shared in a database accessible to other users.

[0410] For example, if a user is feeling stressed while learning, the system can suggest a dessert recipe to promote relaxation. Conversely, if the user is feeling energetic and seeking a challenge, recipes using protein-rich ingredients will be recommended.

[0411] An example of a prompt for a generative AI model is, "Please suggest a recipe for when the user needs to relax." Such a prompt automatically generates and provides content to the user.

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The server receives characteristic information upon the user's first access and generates a user profile. The input is information provided by the user regarding their areas of interest, skill level, and learning objectives, and the output is the user profile created based on this information. This profile creation process involves saving the information to a database.

[0415] Step 2:

[0416] The device collects the user's emotional state using an emotion recognition device. The input is the user's voice data and facial image, and the output is analyzed emotion data. This uses voice recognition and facial recognition technology to perform emotion analysis in real time.

[0417] Step 3:

[0418] The server uses a generated AI model based on user profiles and sentiment data to select and customize learning content. In this step, user profiles and sentiment data are used as input, and learning content with adjusted difficulty levels is generated as output. Data processing includes calculations using the AI ​​model.

[0419] Step 4:

[0420] The device delivers selected learning content to the user. The input here is the customized learning content, and the output is the display of that content to the user. The content is displayed through an interface and becomes accessible to the user.

[0421] Step 5:

[0422] The server continuously monitors the user's emotional changes during the learning process and adjusts the content as needed. The input is real-time updated emotional data, and the output is fine-tuning of the content in response to those emotions. This process involves continuous data calculations.

[0423] Step 6:

[0424] The server tracks learning progress and generates feedback. The input for this step is the user's learning progress data, and the output is the generated feedback and suggestions for the next learning session. This includes analyzing the progress data and extracting areas for improvement.

[0425] Step 7:

[0426] When a user shares learning content with other users, the server saves that data to a database and configures sharing settings. The input is the learning content uploaded by the user, and the output is the data made accessible to other users. This process involves writing to a database.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] [Third Embodiment]

[0431] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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".

[0443] This invention constructs an application platform that provides personalized learning by utilizing learner characteristic information. This system mainly consists of the following elements:

[0444] User profile generation

[0445] When users first access the system, they enter detailed information such as their interests, current skill level, and learning objectives. Based on this information, the server generates a user profile and stores it in a database. This profile serves as a foundation for appropriately customizing learning content based on the individual characteristics of each learner.

[0446] Selection and customization of learning content

[0447] Based on the generated user profiles, the server uses a generated AI model to select the most effective learning content for each learner. This process includes evaluating the difficulty level of the learning and how well it meets the learner's needs. The selected content is then customized to the user's profile.

[0448] Distribution of learning content

[0449] Customized learning content is delivered to the user's device, such as a smartphone or computer, via communication methods. In particular, messaging platforms like LINE ensure that content is easily delivered to devices that learners use daily.

[0450] Progress management and feedback provision

[0451] When a user accesses learning content, their usage and results are recorded via their device, and the server uses this information to manage their learning progress. This progress data is used to generate feedback for the learner. The feedback suggests the next learning steps and is intended to maintain and improve the learner's motivation.

[0452] Content posting and sharing

[0453] Users can create their own learning content and post it to the platform to share with other learners. The server stores the shared content in a database, providing other users with the opportunity to freely access and expand their learning.

[0454] As a concrete example, if a 30-year-old engineer uses this system to learn a new programming language, and the user requests an introduction to programming, the server generates an optimal list of learning materials based on their profile, customizes it, and delivers an appropriate amount of content daily via LINE. In this way, the user can continue learning without burden, receive personalized advice based on their progress data, and share their original projects with other users.

[0455] The following describes the processing flow.

[0456] Step 1:

[0457] When a user first accesses the system, the terminal prompts them to enter detailed information about their areas of interest, current skill level, and learning objectives.

[0458] Step 2:

[0459] The server generates a user profile based on information received from the terminal and stores it in a database. The generated profile is used as foundational data to address each user's learning needs.

[0460] Step 3:

[0461] The server uses a generated AI model to select the most suitable learning content based on the user profile. The selection process evaluates materials that match the user's skill level and interests, and automatically adjusts the content accordingly.

[0462] Step 4:

[0463] Customized learning content is delivered from the server to the user's device via communication means. The content received on the device is then used for learning through applications that the user uses on a daily basis.

[0464] Step 5:

[0465] The device records the user's learning progress and sends data such as completed tasks and study time to the server.

[0466] Step 6:

[0467] The server analyzes the collected progress data to evaluate the user's learning achievement and generates feedback for the next step. The generated feedback is intended to maintain and improve the user's motivation.

[0468] Step 7:

[0469] Users upload their self-created learning content to a server via their device and post it to a sharing platform. The server stores the posted content in a database and makes it available to other users.

[0470] (Example 1)

[0471] 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."

[0472] In today's educational environment, providing learning content tailored to the individual characteristics of learners is time-consuming and labor-intensive, presenting numerous obstacles. Furthermore, adequately tracking and providing feedback on learning progress is not easy. Additionally, there is a lack of platforms for facilitating content sharing among learners. This invention aims to solve these problems and provide an individualized and effective learning experience.

[0473] 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.

[0474] In this invention, the server includes means for acquiring learner characteristic data and generating a user profile, means for optimizing optimal educational content using generative AI technology, and means for supporting the content selection process using prompt sentences. This enables the provision of personalized educational content, appropriate monitoring of learning progress, and provision of evaluation information.

[0475] A "learner" refers to an individual who uses educational content to acquire new knowledge and skills.

[0476] "Characteristic data" refers to information related to individual attributes of learners, such as their interests, skill levels, and learning objectives.

[0477] A "user profile" is an individual record generated based on learner characteristic data, and refers to the basic information used to customize educational content.

[0478] "Educational content" refers to teaching materials and information resources that learners use to acquire new knowledge and skills.

[0479] "Generative AI technology" refers to a method that uses artificial intelligence technology to analyze data and generate optimal results or predictions.

[0480] A "prompt" refers to an instruction or question used by generative AI technology to select appropriate educational content.

[0481] "Evaluation information" refers to feedback and improvement suggestions generated based on the learner's progress and learning results.

[0482] This invention provides a system that delivers optimized educational content based on individual learner characteristic data. This system utilizes generative AI technology to achieve both efficiency and personalization in education. The following describes an embodiment of the system.

[0483] First, users input information such as their interests, current skill level, and learning objectives via their device upon their initial access. Based on this, the server creates a user profile using the generated information and stores it in a database. The hardware used includes general-purpose computers and smartphones, and the software used is a database management system.

[0484] After a profile is created, the server optimizes the educational content provided using generative AI technology. Specifically, it selects the most suitable educational content by inputting prompt sentences appropriate for content selection into the generative AI model while referring to the user profile. One example of generative AI software used is a generative model that employs natural language processing technology.

[0485] Educational content is delivered to users' devices, such as smartphones and computers, and provided via messaging platforms like LINE. This allows learners to easily continue their studies using devices they use daily.

[0486] As a concrete example, let's consider a scenario where a 30-year-old engineer uses this system to learn a new programming language. In this case, when the user enters "I want to learn programming for beginners," the server generates a list of optimal learning materials based on their profile and provides an appropriate amount of content daily via LINE, allowing the user to progress with their learning without burden.

[0487] An example of a prompt message would be, "A 30-year-old engineer is looking for learning materials for programming beginners. Based on their profile information, please suggest the most suitable content for this user." This system enables an efficient and personalized learning experience.

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] When a user first accesses a learning application on their device, they enter information about their interests, skill level, and learning objectives. The device sends this entered characteristic data to a server. The server analyzes the received data and generates a user profile. This profile is stored in a database as foundational information to help select personalized educational content.

[0491] Step 2:

[0492] The server retrieves user profiles from the database. Next, the server uses a generative AI model to select the most suitable educational content based on the prompt. For example, if the prompt is "Suggest the most suitable content for this user," the generative AI model outputs a list of recommended educational content tailored to the profile. This ensures that content optimized for the user is selected.

[0493] Step 3:

[0494] The server prepares to deliver selected and customized educational content. Next, the server uses a communication method, such as a messaging platform like LINE, to send the selected content to the user's device. The device then displays the received content to the user, allowing them to begin learning.

[0495] Step 4:

[0496] When a user learns educational content through their device, usage and progress data are recorded on the device. The device sends this data to a server. The server analyzes the received data and evaluates the learning progress. Based on this evaluation, the server generates and provides feedback to the user regarding the next learning step.

[0497] Step 5:

[0498] Users can create their own learning content and post it to the platform. The device provides the interface for doing so. The server stores the posted content in a database, making it accessible to other learners. This enables content sharing among users and broadens the scope of learning.

[0499] (Application Example 1)

[0500] 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."

[0501] Conventional learning systems struggle to provide personalized learning for each learner, and often fail to adequately provide feedback or suggest learning content tailored to each learner's progress. Furthermore, the methods for delivering learning content using flexible communication channels are often limited, hindering efficient learning progress.

[0502] 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.

[0503] In this invention, the server includes means for acquiring learner characteristic information and generating a profile, means for selecting and customizing optimal learning content based on the generated profile, and means for providing the customized learning content to the learner via communication means. This makes it possible to provide an efficient and effective learning experience through the provision of learning content optimized for each individual learner, followed by progress management and feedback.

[0504] "Learner characteristic information" refers to information that indicates the individual characteristics of each learner, including their interests, skill level, and learning objectives.

[0505] A "profile" is a collection of data generated based on learner characteristics and used to optimize learning content.

[0506] "Customization" refers to the process of adjusting and individualizing learning content based on each learner's profile.

[0507] "Communication methods" refer to electronic media and platforms used to provide learning content to learners.

[0508] "Progress tracking" is a technique for understanding and recording the extent to which learners have completed the learning material.

[0509] "Feedback" refers to information that provides advice and evaluations tailored to the learner's progress, guiding them through the next learning steps.

[0510] "Shareable data" refers to digital information saved in a format that allows learners to share their learning content with other learners.

[0511] A "messaging platform" is a type of communication tool or service that allows information to be sent and received via electronic messages.

[0512] A "machine learning model" is an algorithm or mathematical model that learns from data and makes predictions or decisions.

[0513] A "prompt statement" is an initial input statement used to give instructions to a generative AI model and is used to guide the model's output.

[0514] To implement this invention, the server must first acquire learner characteristic information and generate a profile based on it. By having learners input their interests, skill levels, and learning objectives through a smartphone or PC application, the server uses this data to generate a profile for each learner. The technologies used at this stage are an interface developed with React Native and a Firebase database.

[0515] Next, based on the generated profile, the server utilizes a generative AI model, such as OpenAI's GPT-4, to select and customize the most suitable learning content for the learner. It uses Python to manipulate the AI ​​model and generate prompt messages. These prompt messages, such as "Create learning content that best suits this user's skill level and areas of interest," provide the necessary instructions to the generative AI model.

[0516] The server then delivers customized learning content to learners' devices via the LINE API and other messaging platforms. This allows learners to efficiently receive content daily. Furthermore, Google Analytics is used to track users' learning progress and provide appropriate feedback. This feedback suggests the next learning steps and plays a role in maintaining learner motivation.

[0517] Furthermore, users can create their own content, which is stored on storage services such as AWS S3. Other learners can also share and freely access this content. This allows learners to have a platform to share their learning with others.

[0518] In this system, the server, terminal, and user work together to create a learning environment and achieve efficient individualized learning.

[0519] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0520] Step 1:

[0521] The user operates the device to access the application interface and input information about their learning interests, skill level, and learning objectives. The device receives this data and sends it to the server. The input is learner characteristic information, and the output is the data sent to the server.

[0522] Step 2:

[0523] The server generates a profile based on the learner's characteristics information it receives. The server stores this data in the Firebase database and outputs it as a unique profile for each user. Data processing includes organizing the information and storing it in the database.

[0524] Step 3:

[0525] The server uses the generated profile data to call the generated AI model and select and customize the learning content. Specifically, it inputs prompt sentences into the AI ​​model via a Python program to generate optimal learning content. The input is profile data and prompt sentences, and the output is the learning content.

[0526] Step 4:

[0527] The server distributes the developed learning content to the device using APIs from messaging platforms such as LINE. At this point, the server packages the content and delivers it to the learner via communication. The input is the learning content, and the output is the distributed content.

[0528] Step 5:

[0529] The terminal displays the received learning content to the user, and the learner processes the content. The user's progress and responses are recorded on the terminal in real time and sent to the server. The input is the user's operation data, and the output is the transmission of progress data to the server.

[0530] Step 6:

[0531] The server uses Google Analytics to analyze the user's learning progress based on the received progress data and generates feedback. This feedback includes suggestions for the next learning steps, and this information is also returned to the device via the messaging platform. The input is progress data, and the output is the feedback content.

[0532] Step 7:

[0533] Users create their own learning content and upload it to the server via their device. The server stores this content in AWS S3 and generates a link for sharing with other users. The input is user-created content, and the output is a shareable data link.

[0534] 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.

[0535] This invention provides a customized learning system that combines learner characteristic information with a function to recognize emotions. By using an emotion engine, it is possible to analyze the learner's current emotional state and design an optimal learning experience accordingly.

[0536] User Profile and Sentiment Data Generation

[0537] When a user first accesses the system, the terminal prompts them to input information about their areas of interest, skill level, learning objectives, and emotional state. The emotion engine analyzes the user's emotions using methods such as speech recognition, facial recognition, or text input. The server then generates a user profile and emotion data based on this information and stores it in a database.

[0538] Emotion-based selection and customization of learning content

[0539] The server uses a generative AI model to select learning content based on user profiles and sentiment data. Sentiment data reflects the user's motivation level and stress levels, and the difficulty of the content is adjusted accordingly. For example, if a user is stressed, the system presents simple and intuitive content.

[0540] Content delivery and real-time feedback

[0541] Customized learning content is delivered to the device via communication. As the user engages with the content, the emotion engine monitors the user's emotional changes in real time, and the server adjusts the feedback accordingly. For example, if the user shows a positive reaction, a more challenging task may be presented.

[0542] Progress management and emotionally sensitive next step proposals

[0543] User learning progress is recorded via the device and analyzed by the server. Based on the integrated sentiment data and progress data, the server suggests the next learning content. For example, if the user shows signs of fatigue, it suggests more relaxing learning content, while if the user is highly motivated, it recommends more advanced content.

[0544] Content sharing feature

[0545] Users can upload their own learning content to the server via their device and share it with other users. The server stores this data in a database and grants access rights so that other users can use it.

[0546] As a concrete example, let's say a middle school student is studying English vocabulary. Based on the data recognized by the emotion engine, if the user is tired, the server will suggest game-style content to help them memorize simple words. Conversely, if the system detects that the user is enjoying themselves, it will offer a quiz containing slightly more difficult words. This provides a comfortable learning environment that takes the user's concentration into consideration.

[0547] The following describes the processing flow.

[0548] Step 1:

[0549] When a user first accesses the system, the terminal prompts them to input information about their learning genre, skill level, learning objectives, and current emotional state. The emotional state is recognized by the emotion engine through voice input and image analysis using the camera.

[0550] Step 2:

[0551] The server generates user profiles and sentiment data based on information sent from the terminal and stores them in a database. Here, the sentiment data is used as an indicator of the user's motivation and stress level.

[0552] Step 3:

[0553] Using a generative AI model, the server selects learning content based on user profiles and emotion data. For example, if the emotion engine detects user tension, the server will select content that promotes relaxation.

[0554] Step 4:

[0555] The server delivers selected and customized content to the device via communication. The user begins learning on their device. Meanwhile, the emotion engine continues to monitor the user's emotional state in real time.

[0556] Step 5:

[0557] If the user's emotions change during the learning process, the server adjusts its feedback accordingly. For example, if positive emotions are detected, the server automatically presents more motivating content next.

[0558] Step 6:

[0559] The device records the user's learning progress and sends it to the server. The server integrates this data with sentiment data to recommend the next content to learn and its difficulty level.

[0560] Step 7:

[0561] Users upload newly created learning content from their devices, and the server saves it to a database. This gives other users the opportunity to use that content and expand their learning.

[0562] (Example 2)

[0563] 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."

[0564] While conventional learning systems offer personalization based on learner characteristics, their ability to consider learners' emotional states is limited, making it difficult to quickly address learners' stress and decreased motivation. This leads to reduced learning efficiency and decreased learner satisfaction. Furthermore, utilizing emotional data for real-time feedback adjustments and suggestions for future learning content remains a challenge.

[0565] 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.

[0566] In this invention, the server includes means for acquiring learner characteristic information and emotional state and generating a profile and emotional data; means for selecting and customizing optimal learning content based on the generated profile and emotional data; and means for providing the customized learning content to the learner via communication means, monitoring emotional changes in real time, and adjusting feedback. This makes it possible to provide appropriate learning content and adjust feedback based on the learner's emotional state, thereby improving the efficiency and satisfaction of learning.

[0567] "Learner characteristic information" refers to individual information such as learners' interests, skill levels, and learning objectives, and is data that indicates how individuals should approach learning.

[0568] "Emotional state" refers to information that describes a learner's current emotions and psychological state, including elements such as motivation and stress levels.

[0569] A "profile" is a comprehensive set of information about a learner, generated based on their characteristics and emotional state.

[0570] "Emotional data" refers to emotional states presented in data format, forming the basis for recording and analyzing learners' psychological states.

[0571] A "generative AI model" refers to artificial intelligence methods and systems used to determine the optimal learning content based on user profiles and sentiment data.

[0572] "Communication means" refers to the technologies and methods used to send and receive digital data, such as connections via the Internet.

[0573] "Feedback" refers to providing information to evaluate and improve the learning process based on the learner's progress and emotional state.

[0574] "Learning content" refers to the specific materials and assignments that learners should work on, and includes all information that is the subject of learning activities.

[0575] "Next learning content" refers to the subjects or tasks that should be provided next, based on the progress and results of the current learning content.

[0576] "Monitoring emotional changes in real time" refers to the process of immediately checking the learner's emotional state during learning and providing immediate feedback to the learning system based on the results.

[0577] This invention provides a customized learning system that takes into account the learner's emotional state in addition to their characteristic information. The invention can be specifically implemented through the following combination of hardware and software.

[0578] The user accesses the device and initially enters information such as areas of interest, skill level, learning objectives, and emotional state. This information is collected via a terminal that includes voice recognition software (general-purpose voice recognition technology), facial recognition software (general-purpose facial recognition technology), and text input options. This enables the collection and initial processing of a wide range of user data.

[0579] Based on the information the server reads, it generates user profiles and sentiment data. Using a general natural language processing AI model, for example, it selects the most suitable content for the learner and provides guidelines for customization.

[0580] The server selects the most suitable learning content and adjusts the difficulty level based on the learner's profile and emotional data. To achieve this, it maintains a content database and retrieves appropriate materials from the accumulated learning resources according to the user's state.

[0581] As a concrete example, if the emotion engine detects fatigue while a middle school student is studying English vocabulary, the server will suggest a simple, game-based vocabulary learning content to that user. In this way, a learning approach that responds to the user's emotional state is important for maintaining their motivation to learn.

[0582] Example prompt text

[0583] "Design an AI model that suggests optimal learning content based on the current stress level."

[0584] In this way, the present invention makes it possible to enhance individual learning efficiency and provide users with a learning experience that reduces stress by incorporating emotion recognition into the learning system.

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] Users use a device to input information about their areas of interest, skill level, learning objectives, and emotional state. This information is collected by the device, with options for facial recognition and voice recognition also available. The entered data is sent from the device to a server and used as foundational data for profile generation.

[0588] Step 2:

[0589] The server receives user information transmitted from the terminal and generates profile and sentiment data. This data processing involves aggregating user characteristic information and analyzing sentiment data based on it. A generative AI model is used to analyze this integrated data and construct profiles tailored to individual needs. The profile and sentiment data are stored in a database.

[0590] Step 3:

[0591] The server uses user profiles and emotional data generated by the server as input to select the most suitable learning content. A generative AI model is used to extract relevant learning content from the database based on the user's emotional state and learning objectives. For example, a user experiencing stress will be given simpler content. The selected content is then sent to the device.

[0592] Step 4:

[0593] The device provides the user with customized learning content it has received. As the user uses the content, the device monitors their emotional changes in real time. An emotion engine analyzes the user's reactions and sends feedback information to the server based on the data obtained. Based on this feedback information, the system may switch to more difficult content if necessary.

[0594] Step 5:

[0595] The server integrates the user's learning progress with real-time sentiment data to suggest the next learning step. At this stage, data analysis considers the user's motivation and fatigue level to determine the recommendations. For example, if the user's motivation is high, a more difficult task will be recommended, and the recommendations will be provided to the user again via the terminal.

[0596] Step 6:

[0597] The learning content created by the user is uploaded from the device to the server and saved as data for sharing with other users. This data is registered in a database by the server and becomes accessible to other users after they are granted appropriate access permissions.

[0598] (Application Example 2)

[0599] 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."

[0600] In today's world, learners often struggle to receive appropriate learning content that effectively considers their individual emotional states and progress. Furthermore, the lack of personalized suggestions based on user emotions highlights the need to create an environment where learners can study efficiently and comfortably.

[0601] 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.

[0602] In this invention, the server includes means for acquiring learner characteristic information and generating a profile, means for acquiring information using an emotion recognition device and optimizing suggestions according to the user's situation, and means for suggesting the next learning content based on emotions. This makes it possible for learners to receive optimal learning content that matches their current emotional state.

[0603] "Learner characteristic information" refers to information such as an individual learner's interests, skill level, and learning objectives, and serves as the basic data for generating a profile.

[0604] A "device for recognizing emotions" is a device that uses speech recognition or facial recognition technology to analyze the emotional state of learners.

[0605] "Means for generating a profile" refers to a means that includes a process of organizing and recording information tailored to each individual learner, based on the learner's characteristic information.

[0606] "Methods for optimizing proposals" refer to methods for optimizing the content and services provided based on the results of recognizing emotions.

[0607] A "means for suggesting the next learning content" refers to a method that automatically presents the next learning topic, taking into account the learner's progress and emotional state.

[0608] "Learning content" is a general term for the information and learning materials that learners receive during their learning activities.

[0609] "Means of generating feedback" refers to methods that include a process of generating and presenting appropriate evaluations and areas for improvement based on the learner's learning progress and emotional state.

[0610] In this embodiment of the invention, a system is provided in which a server and a terminal cooperate to optimize the user's learning experience.

[0611] The server first generates a learner profile based on the user's characteristics received during their initial access. This profile includes the user's areas of interest, skill level, and learning objectives. The server then uses an emotion recognition device to analyze the user's voice data and facial images to identify their current emotions in real time. This process utilizes speech recognition and facial recognition technologies.

[0612] Based on profiles and emotional data, a generative AI model selects appropriate learning content and adjusts and customizes the difficulty level. The device provides the selected learning content to the user, and during learning, the emotional engine monitors the user's facial expressions and voice. This allows the system to adapt in real time: challenging content when positive reactions are detected, and relaxing content when fatigue or other negative reactions are recognized.

[0613] The server also tracks learning progress and generates feedback, which is then used to suggest future learning content. The data obtained through this process is stored and shared in a database accessible to other users.

[0614] For example, if a user is feeling stressed while learning, the system can suggest a dessert recipe to promote relaxation. Conversely, if the user is feeling energetic and seeking a challenge, recipes using protein-rich ingredients will be recommended.

[0615] An example of a prompt for a generative AI model is, "Please suggest a recipe for when the user needs to relax." Such a prompt automatically generates and provides content to the user.

[0616] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0617] Step 1:

[0618] The server receives characteristic information upon the user's first access and generates a user profile. The input is information provided by the user regarding their areas of interest, skill level, and learning objectives, and the output is the user profile created based on this information. This profile creation process involves saving the information to a database.

[0619] Step 2:

[0620] The device collects the user's emotional state using an emotion recognition device. The input is the user's voice data and facial image, and the output is analyzed emotion data. This uses voice recognition and facial recognition technology to perform emotion analysis in real time.

[0621] Step 3:

[0622] The server uses a generated AI model based on user profiles and sentiment data to select and customize learning content. In this step, user profiles and sentiment data are used as input, and learning content with adjusted difficulty levels is generated as output. Data processing includes calculations using the AI ​​model.

[0623] Step 4:

[0624] The device delivers selected learning content to the user. The input here is the customized learning content, and the output is the display of that content to the user. The content is displayed through an interface and becomes accessible to the user.

[0625] Step 5:

[0626] The server continuously monitors the user's emotional changes during the learning process and adjusts the content as needed. The input is real-time updated emotional data, and the output is fine-tuning of the content in response to those emotions. This process involves continuous data calculations.

[0627] Step 6:

[0628] The server tracks learning progress and generates feedback. The input for this step is the user's learning progress data, and the output is the generated feedback and suggestions for the next learning session. This includes analyzing the progress data and extracting areas for improvement.

[0629] Step 7:

[0630] When a user shares learning content with other users, the server saves that data to a database and configures sharing settings. The input is the learning content uploaded by the user, and the output is the data made accessible to other users. This process involves writing to a database.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] [Fourth Embodiment]

[0635] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0636] 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.

[0637] 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).

[0638] 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.

[0639] 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.

[0640] 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).

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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".

[0648] This invention constructs an application platform that provides personalized learning by utilizing learner characteristic information. This system mainly consists of the following elements:

[0649] User profile generation

[0650] When users first access the system, they enter detailed information such as their interests, current skill level, and learning objectives. Based on this information, the server generates a user profile and stores it in a database. This profile serves as a foundation for appropriately customizing learning content based on the individual characteristics of each learner.

[0651] Selection and customization of learning content

[0652] Based on the generated user profiles, the server uses a generated AI model to select the most effective learning content for each learner. This process includes evaluating the difficulty level of the learning and how well it meets the learner's needs. The selected content is then customized to the user's profile.

[0653] Distribution of learning content

[0654] Customized learning content is delivered to the user's device, such as a smartphone or computer, via communication methods. In particular, messaging platforms like LINE ensure that content is easily delivered to devices that learners use daily.

[0655] Progress management and feedback provision

[0656] When a user accesses learning content, their usage and results are recorded via their device, and the server uses this information to manage their learning progress. This progress data is used to generate feedback for the learner. The feedback suggests the next learning steps and is intended to maintain and improve the learner's motivation.

[0657] Content posting and sharing

[0658] Users can create their own learning content and post it to the platform to share with other learners. The server stores the shared content in a database, providing other users with the opportunity to freely access and expand their learning.

[0659] As a concrete example, if a 30-year-old engineer uses this system to learn a new programming language, and the user requests an introduction to programming, the server generates an optimal list of learning materials based on their profile, customizes it, and delivers an appropriate amount of content daily via LINE. In this way, the user can continue learning without burden, receive personalized advice based on their progress data, and share their original projects with other users.

[0660] The following describes the processing flow.

[0661] Step 1:

[0662] When a user first accesses the system, the terminal prompts them to enter detailed information about their areas of interest, current skill level, and learning objectives.

[0663] Step 2:

[0664] The server generates a user profile based on information received from the terminal and stores it in a database. The generated profile is used as foundational data to address each user's learning needs.

[0665] Step 3:

[0666] The server uses a generated AI model to select the most suitable learning content based on the user profile. The selection process evaluates materials that match the user's skill level and interests, and automatically adjusts the content accordingly.

[0667] Step 4:

[0668] Customized learning content is delivered from the server to the user's device via communication means. The content received on the device is then used for learning through applications that the user uses on a daily basis.

[0669] Step 5:

[0670] The device records the user's learning progress and sends data such as completed tasks and study time to the server.

[0671] Step 6:

[0672] The server analyzes the collected progress data to evaluate the user's learning achievement and generates feedback for the next step. The generated feedback is intended to maintain and improve the user's motivation.

[0673] Step 7:

[0674] Users upload their self-created learning content to a server via their device and post it to a sharing platform. The server stores the posted content in a database and makes it available to other users.

[0675] (Example 1)

[0676] 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".

[0677] In today's educational environment, providing learning content tailored to the individual characteristics of learners is time-consuming and labor-intensive, presenting numerous obstacles. Furthermore, adequately tracking and providing feedback on learning progress is not easy. Additionally, there is a lack of platforms for facilitating content sharing among learners. This invention aims to solve these problems and provide an individualized and effective learning experience.

[0678] 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.

[0679] In this invention, the server includes means for acquiring learner characteristic data and generating a user profile, means for optimizing optimal educational content using generative AI technology, and means for supporting the content selection process using prompt sentences. This enables the provision of personalized educational content, appropriate monitoring of learning progress, and provision of evaluation information.

[0680] A "learner" refers to an individual who uses educational content to acquire new knowledge and skills.

[0681] "Characteristic data" refers to information related to individual attributes of learners, such as their interests, skill levels, and learning objectives.

[0682] A "user profile" is an individual record generated based on learner characteristic data, and refers to the basic information used to customize educational content.

[0683] "Educational content" refers to teaching materials and information resources that learners use to acquire new knowledge and skills.

[0684] "Generative AI technology" refers to a method that uses artificial intelligence technology to analyze data and generate optimal results or predictions.

[0685] A "prompt" refers to an instruction or question used by generative AI technology to select appropriate educational content.

[0686] "Evaluation information" refers to feedback and improvement suggestions generated based on the learner's progress and learning results.

[0687] This invention provides a system that delivers optimized educational content based on individual learner characteristic data. This system utilizes generative AI technology to achieve both efficiency and personalization in education. The following describes an embodiment of the system.

[0688] First, users input information such as their interests, current skill level, and learning objectives via their device upon their initial access. Based on this, the server creates a user profile using the generated information and stores it in a database. The hardware used includes general-purpose computers and smartphones, and the software used is a database management system.

[0689] After a profile is created, the server optimizes the educational content provided using generative AI technology. Specifically, it selects the most suitable educational content by inputting prompt sentences appropriate for content selection into the generative AI model while referring to the user profile. One example of generative AI software used is a generative model that employs natural language processing technology.

[0690] Educational content is delivered to users' devices, such as smartphones and computers, and provided via messaging platforms like LINE. This allows learners to easily continue their studies using devices they use daily.

[0691] As a concrete example, let's consider a scenario where a 30-year-old engineer uses this system to learn a new programming language. In this case, when the user enters "I want to learn programming for beginners," the server generates a list of optimal learning materials based on their profile and provides an appropriate amount of content daily via LINE, allowing the user to progress with their learning without burden.

[0692] An example of a prompt message would be, "A 30-year-old engineer is looking for learning materials for programming beginners. Based on their profile information, please suggest the most suitable content for this user." This system enables an efficient and personalized learning experience.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] When a user first accesses a learning application on their device, they enter information about their interests, skill level, and learning objectives. The device sends this entered characteristic data to a server. The server analyzes the received data and generates a user profile. This profile is stored in a database as foundational information to help select personalized educational content.

[0696] Step 2:

[0697] The server retrieves user profiles from the database. Next, the server uses a generative AI model to select the most suitable educational content based on the prompt. For example, if the prompt is "Suggest the most suitable content for this user," the generative AI model outputs a list of recommended educational content tailored to the profile. This ensures that content optimized for the user is selected.

[0698] Step 3:

[0699] The server prepares to deliver selected and customized educational content. Next, the server uses a communication method, such as a messaging platform like LINE, to send the selected content to the user's device. The device then displays the received content to the user, allowing them to begin learning.

[0700] Step 4:

[0701] When a user learns educational content through their device, usage and progress data are recorded on the device. The device sends this data to a server. The server analyzes the received data and evaluates the learning progress. Based on this evaluation, the server generates and provides feedback to the user regarding the next learning step.

[0702] Step 5:

[0703] Users can create their own learning content and post it to the platform. The device provides the interface for doing so. The server stores the posted content in a database, making it accessible to other learners. This enables content sharing among users and broadens the scope of learning.

[0704] (Application Example 1)

[0705] 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".

[0706] Conventional learning systems struggle to provide personalized learning for each learner, and often fail to adequately provide feedback or suggest learning content tailored to each learner's progress. Furthermore, the methods for delivering learning content using flexible communication channels are often limited, hindering efficient learning progress.

[0707] 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.

[0708] In this invention, the server includes means for acquiring learner characteristic information and generating a profile, means for selecting and customizing optimal learning content based on the generated profile, and means for providing the customized learning content to the learner via communication means. This makes it possible to provide an efficient and effective learning experience through the provision of learning content optimized for each individual learner, followed by progress management and feedback.

[0709] "Learner characteristic information" refers to information that indicates the individual characteristics of each learner, including their interests, skill level, and learning objectives.

[0710] A "profile" is a collection of data generated based on learner characteristics and used to optimize learning content.

[0711] "Customization" refers to the process of adjusting and individualizing learning content based on each learner's profile.

[0712] "Communication methods" refer to electronic media and platforms used to provide learning content to learners.

[0713] "Progress tracking" is a technique for understanding and recording the extent to which learners have completed the learning material.

[0714] "Feedback" refers to information that provides advice and evaluations tailored to the learner's progress, guiding them through the next learning steps.

[0715] "Shareable data" refers to digital information saved in a format that allows learners to share their learning content with other learners.

[0716] A "messaging platform" is a type of communication tool or service that allows information to be sent and received via electronic messages.

[0717] A "machine learning model" is an algorithm or mathematical model that learns from data and makes predictions or decisions.

[0718] A "prompt statement" is an initial input statement used to give instructions to a generative AI model and is used to guide the model's output.

[0719] To implement this invention, the server must first acquire learner characteristic information and generate a profile based on it. By having learners input their interests, skill levels, and learning objectives through a smartphone or PC application, the server uses this data to generate a profile for each learner. The technologies used at this stage are an interface developed with React Native and a Firebase database.

[0720] Next, based on the generated profile, the server utilizes a generative AI model, such as OpenAI's GPT-4, to select and customize the most suitable learning content for the learner. It uses Python to manipulate the AI ​​model and generate prompt messages. These prompt messages, such as "Create learning content that best suits this user's skill level and areas of interest," provide the necessary instructions to the generative AI model.

[0721] The server then delivers customized learning content to learners' devices via the LINE API and other messaging platforms. This allows learners to efficiently receive content daily. Furthermore, Google Analytics is used to track users' learning progress and provide appropriate feedback. This feedback suggests the next learning steps and plays a role in maintaining learner motivation.

[0722] Furthermore, users can create their own content, which is stored on storage services such as AWS S3. Other learners can also share and freely access this content. This allows learners to have a platform to share their learning with others.

[0723] In this system, the server, terminal, and user work together to create a learning environment and achieve efficient individualized learning.

[0724] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0725] Step 1:

[0726] The user operates the device to access the application interface and input information about their learning interests, skill level, and learning objectives. The device receives this data and sends it to the server. The input is learner characteristic information, and the output is the data sent to the server.

[0727] Step 2:

[0728] The server generates a profile based on the learner's characteristics information it receives. The server stores this data in the Firebase database and outputs it as a unique profile for each user. Data processing includes organizing the information and storing it in the database.

[0729] Step 3:

[0730] The server uses the generated profile data to call the generated AI model and select and customize the learning content. Specifically, it inputs prompt sentences into the AI ​​model via a Python program to generate optimal learning content. The input is profile data and prompt sentences, and the output is the learning content.

[0731] Step 4:

[0732] The server distributes the developed learning content to the device using APIs from messaging platforms such as LINE. At this point, the server packages the content and delivers it to the learner via communication. The input is the learning content, and the output is the distributed content.

[0733] Step 5:

[0734] The terminal displays the received learning content to the user, and the learner processes the content. The user's progress and responses are recorded on the terminal in real time and sent to the server. The input is the user's operation data, and the output is the transmission of progress data to the server.

[0735] Step 6:

[0736] The server uses Google Analytics to analyze the user's learning progress based on the received progress data and generates feedback. This feedback includes suggestions for the next learning steps, and this information is also returned to the device via the messaging platform. The input is progress data, and the output is the feedback content.

[0737] Step 7:

[0738] Users create their own learning content and upload it to the server via their device. The server stores this content in AWS S3 and generates a link for sharing with other users. The input is user-created content, and the output is a shareable data link.

[0739] 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.

[0740] This invention provides a customized learning system that combines learner characteristic information with a function to recognize emotions. By using an emotion engine, it is possible to analyze the learner's current emotional state and design an optimal learning experience accordingly.

[0741] User Profile and Sentiment Data Generation

[0742] When a user first accesses the system, the terminal prompts them to input information about their areas of interest, skill level, learning objectives, and emotional state. The emotion engine analyzes the user's emotions using methods such as speech recognition, facial recognition, or text input. The server then generates a user profile and emotion data based on this information and stores it in a database.

[0743] Emotion-based selection and customization of learning content

[0744] The server uses a generative AI model to select learning content based on user profiles and sentiment data. Sentiment data reflects the user's motivation level and stress levels, and the difficulty of the content is adjusted accordingly. For example, if a user is stressed, the system presents simple and intuitive content.

[0745] Content delivery and real-time feedback

[0746] Customized learning content is delivered to the device via communication. As the user engages with the content, the emotion engine monitors the user's emotional changes in real time, and the server adjusts the feedback accordingly. For example, if the user shows a positive reaction, a more challenging task may be presented.

[0747] Progress management and emotionally sensitive next step proposals

[0748] User learning progress is recorded via the device and analyzed by the server. Based on the integrated sentiment data and progress data, the server suggests the next learning content. For example, if the user shows signs of fatigue, it suggests more relaxing learning content, while if the user is highly motivated, it recommends more advanced content.

[0749] Content sharing feature

[0750] Users can upload their own learning content to the server via their device and share it with other users. The server stores this data in a database and grants access rights so that other users can use it.

[0751] As a concrete example, let's say a middle school student is studying English vocabulary. Based on the data recognized by the emotion engine, if the user is tired, the server will suggest game-style content to help them memorize simple words. Conversely, if the system detects that the user is enjoying themselves, it will offer a quiz containing slightly more difficult words. This provides a comfortable learning environment that takes the user's concentration into consideration.

[0752] The following describes the processing flow.

[0753] Step 1:

[0754] When a user first accesses the system, the terminal prompts them to input information about their learning genre, skill level, learning objectives, and current emotional state. The emotional state is recognized by the emotion engine through voice input and image analysis using the camera.

[0755] Step 2:

[0756] The server generates user profiles and sentiment data based on information sent from the terminal and stores them in a database. Here, the sentiment data is used as an indicator of the user's motivation and stress level.

[0757] Step 3:

[0758] Using a generative AI model, the server selects learning content based on user profiles and emotion data. For example, if the emotion engine detects user tension, the server will select content that promotes relaxation.

[0759] Step 4:

[0760] The server delivers selected and customized content to the device via communication. The user begins learning on their device. Meanwhile, the emotion engine continues to monitor the user's emotional state in real time.

[0761] Step 5:

[0762] If the user's emotions change during the learning process, the server adjusts its feedback accordingly. For example, if positive emotions are detected, the server automatically presents more motivating content next.

[0763] Step 6:

[0764] The device records the user's learning progress and sends it to the server. The server integrates this data with sentiment data to recommend the next content to learn and its difficulty level.

[0765] Step 7:

[0766] Users upload newly created learning content from their devices, and the server saves it to a database. This gives other users the opportunity to use that content and expand their learning.

[0767] (Example 2)

[0768] 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".

[0769] While conventional learning systems offer personalization based on learner characteristics, their ability to consider learners' emotional states is limited, making it difficult to quickly address learners' stress and decreased motivation. This leads to reduced learning efficiency and decreased learner satisfaction. Furthermore, utilizing emotional data for real-time feedback adjustments and suggestions for future learning content remains a challenge.

[0770] 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.

[0771] In this invention, the server includes means for acquiring learner characteristic information and emotional state and generating a profile and emotional data; means for selecting and customizing optimal learning content based on the generated profile and emotional data; and means for providing the customized learning content to the learner via communication means, monitoring emotional changes in real time, and adjusting feedback. This makes it possible to provide appropriate learning content and adjust feedback based on the learner's emotional state, thereby improving the efficiency and satisfaction of learning.

[0772] "Learner characteristic information" refers to individual information such as learners' interests, skill levels, and learning objectives, and is data that indicates how individuals should approach learning.

[0773] "Emotional state" refers to information that describes a learner's current emotions and psychological state, including elements such as motivation and stress levels.

[0774] A "profile" is a comprehensive set of information about a learner, generated based on their characteristics and emotional state.

[0775] "Emotional data" refers to emotional states presented in data format, forming the basis for recording and analyzing learners' psychological states.

[0776] A "generative AI model" refers to artificial intelligence methods and systems used to determine the optimal learning content based on user profiles and sentiment data.

[0777] "Communication means" refers to the technologies and methods used to send and receive digital data, such as connections via the Internet.

[0778] "Feedback" refers to providing information to evaluate and improve the learning process based on the learner's progress and emotional state.

[0779] "Learning content" refers to the specific materials and assignments that learners should work on, and includes all information that is the subject of learning activities.

[0780] "Next learning content" refers to the subjects or tasks that should be provided next, based on the progress and results of the current learning content.

[0781] "Monitoring emotional changes in real time" refers to the process of immediately checking the learner's emotional state during learning and providing immediate feedback to the learning system based on the results.

[0782] This invention provides a customized learning system that takes into account the learner's emotional state in addition to their characteristic information. The invention can be specifically implemented through the following combination of hardware and software.

[0783] The user accesses the device and initially enters information such as areas of interest, skill level, learning objectives, and emotional state. This information is collected via a terminal that includes voice recognition software (general-purpose voice recognition technology), facial recognition software (general-purpose facial recognition technology), and text input options. This enables the collection and initial processing of a wide range of user data.

[0784] Based on the information the server reads, it generates user profiles and sentiment data. Using a general natural language processing AI model, for example, it selects the most suitable content for the learner and provides guidelines for customization.

[0785] The server selects the most suitable learning content and adjusts the difficulty level based on the learner's profile and emotional data. To achieve this, it maintains a content database and retrieves appropriate materials from the accumulated learning resources according to the user's state.

[0786] As a concrete example, if the emotion engine detects fatigue while a middle school student is studying English vocabulary, the server will suggest a simple, game-based vocabulary learning content to that user. In this way, a learning approach that responds to the user's emotional state is important for maintaining their motivation to learn.

[0787] Example prompt text

[0788] "Design an AI model that suggests optimal learning content based on the current stress level."

[0789] In this way, the present invention makes it possible to enhance individual learning efficiency and provide users with a learning experience that reduces stress by incorporating emotion recognition into the learning system.

[0790] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0791] Step 1:

[0792] Users use a device to input information about their areas of interest, skill level, learning objectives, and emotional state. This information is collected by the device, with options for facial recognition and voice recognition also available. The entered data is sent from the device to a server and used as foundational data for profile generation.

[0793] Step 2:

[0794] The server receives user information transmitted from the terminal and generates profile and sentiment data. This data processing involves aggregating user characteristic information and analyzing sentiment data based on it. A generative AI model is used to analyze this integrated data and construct profiles tailored to individual needs. The profile and sentiment data are stored in a database.

[0795] Step 3:

[0796] The server uses user profiles and emotional data generated by the server as input to select the most suitable learning content. A generative AI model is used to extract relevant learning content from the database based on the user's emotional state and learning objectives. For example, a user experiencing stress will be given simpler content. The selected content is then sent to the device.

[0797] Step 4:

[0798] The device provides the user with customized learning content it has received. As the user uses the content, the device monitors their emotional changes in real time. An emotion engine analyzes the user's reactions and sends feedback information to the server based on the data obtained. Based on this feedback information, the system may switch to more difficult content if necessary.

[0799] Step 5:

[0800] The server integrates the user's learning progress with real-time sentiment data to suggest the next learning step. At this stage, data analysis considers the user's motivation and fatigue level to determine the recommendations. For example, if the user's motivation is high, a more difficult task will be recommended, and the recommendations will be provided to the user again via the terminal.

[0801] Step 6:

[0802] The learning content created by the user is uploaded from the device to the server and saved as data for sharing with other users. This data is registered in a database by the server and becomes accessible to other users after they are granted appropriate access permissions.

[0803] (Application Example 2)

[0804] 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".

[0805] In today's world, learners often struggle to receive appropriate learning content that effectively considers their individual emotional states and progress. Furthermore, the lack of personalized suggestions based on user emotions highlights the need to create an environment where learners can study efficiently and comfortably.

[0806] 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.

[0807] In this invention, the server includes means for acquiring learner characteristic information and generating a profile, means for acquiring information using an emotion recognition device and optimizing suggestions according to the user's situation, and means for suggesting the next learning content based on emotions. This makes it possible for learners to receive optimal learning content that matches their current emotional state.

[0808] "Learner characteristic information" refers to information such as an individual learner's interests, skill level, and learning objectives, and serves as the basic data for generating a profile.

[0809] A "device for recognizing emotions" is a device that uses speech recognition or facial recognition technology to analyze the emotional state of learners.

[0810] "Means for generating a profile" refers to a means that includes a process of organizing and recording information tailored to each individual learner, based on the learner's characteristic information.

[0811] "Methods for optimizing proposals" refer to methods for optimizing the content and services provided based on the results of recognizing emotions.

[0812] A "means for suggesting the next learning content" refers to a method that automatically presents the next learning topic, taking into account the learner's progress and emotional state.

[0813] "Learning content" is a general term for the information and learning materials that learners receive during their learning activities.

[0814] "Means of generating feedback" refers to methods that include a process of generating and presenting appropriate evaluations and areas for improvement based on the learner's learning progress and emotional state.

[0815] In this embodiment of the invention, a system is provided in which a server and a terminal cooperate to optimize the user's learning experience.

[0816] The server first generates a learner profile based on the user's characteristics received during their initial access. This profile includes the user's areas of interest, skill level, and learning objectives. The server then uses an emotion recognition device to analyze the user's voice data and facial images to identify their current emotions in real time. This process utilizes speech recognition and facial recognition technologies.

[0817] Based on profiles and emotional data, a generative AI model selects appropriate learning content and adjusts and customizes the difficulty level. The device provides the selected learning content to the user, and during learning, the emotional engine monitors the user's facial expressions and voice. This allows the system to adapt in real time: challenging content when positive reactions are detected, and relaxing content when fatigue or other negative reactions are recognized.

[0818] The server also tracks learning progress and generates feedback, which is then used to suggest future learning content. The data obtained through this process is stored and shared in a database accessible to other users.

[0819] For example, if a user is feeling stressed while learning, the system can suggest a dessert recipe to promote relaxation. Conversely, if the user is feeling energetic and seeking a challenge, recipes using protein-rich ingredients will be recommended.

[0820] An example of a prompt for a generative AI model is, "Please suggest a recipe for when the user needs to relax." Such a prompt automatically generates and provides content to the user.

[0821] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0822] Step 1:

[0823] The server receives characteristic information upon the user's first access and generates a user profile. The input is information provided by the user regarding their areas of interest, skill level, and learning objectives, and the output is the user profile created based on this information. This profile creation process involves saving the information to a database.

[0824] Step 2:

[0825] The device collects the user's emotional state using an emotion recognition device. The input is the user's voice data and facial image, and the output is analyzed emotion data. This uses voice recognition and facial recognition technology to perform emotion analysis in real time.

[0826] Step 3:

[0827] The server uses a generated AI model based on user profiles and sentiment data to select and customize learning content. In this step, user profiles and sentiment data are used as input, and learning content with adjusted difficulty levels is generated as output. Data processing includes calculations using the AI ​​model.

[0828] Step 4:

[0829] The device delivers selected learning content to the user. The input here is the customized learning content, and the output is the display of that content to the user. The content is displayed through an interface and becomes accessible to the user.

[0830] Step 5:

[0831] The server continuously monitors the user's emotional changes during the learning process and adjusts the content as needed. The input is real-time updated emotional data, and the output is fine-tuning of the content in response to those emotions. This process involves continuous data calculations.

[0832] Step 6:

[0833] The server tracks learning progress and generates feedback. The input for this step is the user's learning progress data, and the output is the generated feedback and suggestions for the next learning session. This includes analyzing the progress data and extracting areas for improvement.

[0834] Step 7:

[0835] When a user shares learning content with other users, the server saves that data to a database and configures sharing settings. The input is the learning content uploaded by the user, and the output is the data made accessible to other users. This process involves writing to a database.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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."

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0857] The following is further disclosed regarding the embodiments described above.

[0858] (Claim 1)

[0859] A means for acquiring learner characteristic information and generating a profile,

[0860] A means of selecting and customizing the optimal learning content based on the generated profile,

[0861] A means of providing customized learning content to learners via communication means,

[0862] A means of tracking learners' learning progress and generating feedback,

[0863] A means of saving learning content created by learners as shareable data,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, having a function for sharing learning content among multiple learners via communication means.

[0867] (Claim 3)

[0868] The system according to claim 1, comprising means for automatically suggesting the next learning content based on the generated feedback.

[0869] "Example 1"

[0870] (Claim 1)

[0871] A means for acquiring learner characteristic data and generating user profiles,

[0872] A means of selecting and personalizing the most suitable educational content based on the generated profile,

[0873] A means of supplying personalized educational content to learners via communication channels,

[0874] A means for monitoring learners' learning progress and generating evaluation information,

[0875] A means of saving educational content created by learners as shareable data,

[0876] A means of optimizing optimal educational content using generative AI technology,

[0877] A means of supporting the content selection process using prompt statements,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, having a function for sharing educational content among multiple learners via a communication path.

[0881] (Claim 3)

[0882] The system according to claim 1, comprising means for automatically suggesting the next educational content based on the generated evaluation information.

[0883] "Application Example 1"

[0884] (Claim 1)

[0885] A means for acquiring learner characteristic information and generating a profile,

[0886] A means of selecting and customizing the optimal learning content based on the generated profile,

[0887] A means of providing customized learning content to learners via communication means,

[0888] A means of tracking learners' learning progress and generating feedback,

[0889] A means of saving learning content created by learners as shareable data,

[0890] A means of providing personalized learning content through a messaging platform,

[0891] A method for generating prompt sentences using a machine learning model and customizing the learning content,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, having a function for sharing learning content among multiple learners via communication means.

[0895] (Claim 3)

[0896] The system according to claim 1, comprising means for automatically suggesting the next learning content based on the generated feedback.

[0897] "Example 2 of combining an emotion engine"

[0898] (Claim 1)

[0899] A means for acquiring learner characteristic information and emotional state, and generating a profile and emotional data,

[0900] A means for selecting and customizing the optimal learning content based on the generated profile and sentiment data,

[0901] A means of providing customized learning content to learners via communication, monitoring emotional changes in real time, and adjusting feedback accordingly.

[0902] A means of analyzing learners' learning progress and emotional data to suggest the next learning content,

[0903] A means of saving learning content created by learners as shareable data,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, having a function for sharing learning content among multiple learners via communication means.

[0907] (Claim 3)

[0908] The system according to claim 1, comprising means for automatically suggesting the next learning content based on the generated feedback and sentiment data.

[0909] "Application example 2 when combining with an emotional engine"

[0910] (Claim 1)

[0911] A means for acquiring learner characteristic information and generating a profile,

[0912] A means of selecting and customizing the optimal learning content based on the generated profile,

[0913] A means of acquiring information using an emotion-recognizing device and optimizing suggestions according to the user's situation,

[0914] A means of providing customized learning content to learners via communication media,

[0915] A means of tracking learners' learning progress and generating feedback,

[0916] A means of suggesting the next learning content based on emotions,

[0917] A means of saving learning content created by learners as shareable data,

[0918] Means of providing the selected proposals,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, having a function for sharing learning content among multiple learners via communication means.

[0922] (Claim 3)

[0923] The system according to claim 1, comprising means for automatically suggesting the next learning content based on sentiment data, based on the generated feedback. [Explanation of symbols]

[0924] 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 acquiring learner characteristic information and generating a profile, A means of selecting and customizing the optimal learning content based on the generated profile, A means of providing customized learning content to learners via communication means, A means of tracking learners' learning progress and generating feedback, A means of saving learning content created by learners as shareable data, A system that includes this.

2. The system according to claim 1, having a function for sharing learning content among multiple learners via communication means.

3. The system according to claim 1, further comprising means for automatically suggesting the next learning content based on the generated feedback.

Images