system

Abstract

We provide the system. [Solution] A means for receiving user learning progress information and analyzing the learning history based on that information, A means for generating a user-optimized learning plan based on the generated analysis results, A means of providing learning materials and assignments to the user terminal according to the learning plan, A means of monitoring users' learning progress in real time and providing feedback, Means for adjusting the learning plan based on the aforementioned feedback, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional online learning platforms, it is difficult to flexibly respond to the different levels of understanding, learning styles, and learning speeds of individual learners, and as a result, there is a problem that effective learning support cannot be provided. Therefore, in order to improve the quality of education and maximize the learning effect, it is required to provide a personalized learning plan according to the learning needs of each individual.

Means for Solving the Problems

[0005] The system of the present invention includes means for receiving user learning progress information and analyzing the learning history based on that information. Furthermore, it generates a learning plan optimized for the user based on the analysis results and provides learning materials and assignments to the user's terminal. This system can monitor the user's learning progress in real time and provide immediate feedback. By appropriately adjusting the learning plan based on the feedback, it realizes flexible learning support that responds to the learning needs of each user.

[0006] "User learning progress information" refers to data that shows how far a learner has progressed in their learning, and includes materials used, completed assignments, and level of understanding.

[0007] "Means for analyzing learning history" refers to a function that collects and analyzes a user's past learning activities in order to grasp and understand their learning patterns and trends.

[0008] "Means for generating optimized learning plans" refers to a function that builds individually customized learning strategies and sets of learning materials based on the user's learning history and progress.

[0009] "Means of providing information to the user's terminal" refers to technologies that ensure learning plans, materials, and assignments are properly transmitted to the user's device and made available for viewing and use.

[0010] "A means of monitoring and providing feedback in real time" refers to a technical process that collects data immediately as the user is learning, analyzes it, and then provides hints and additional information.

[0011] "Means for adjusting the learning plan based on feedback" refers to a function that dynamically changes the content and progress of the learning plan based on the feedback provided. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is applied to an online learning platform to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0034] When a user first logs into the learning platform, the server verifies the user's authentication information and retrieves the user's learning history data from the database. The retrieved data is then analyzed by a generating AI to identify the user's learning style, learning speed, and level of comprehension.

[0035] Based on identified learning characteristics, the server generates a personalized learning plan for the user. This plan includes appropriate learning materials, assignments, and a learning pace, which the generating AI adjusts to be optimal considering the user's past learning history and current progress. The learning plan is sent from the server to the user's device, and the user can access the learning content through their device.

[0036] As a concrete example, let's assume a user is taking a mathematics course. Through analysis, the server determines that this user is strong in computational problems and needs theoretical explanations. Therefore, the server generates a plan that combines advanced practice problems tailored to the user's skill level with video materials to complement their theoretical learning.

[0037] During the learning process, the server continuously monitors the user's progress and immediately provides temporary hints and additional explanations to the device when the user encounters difficulties. This real-time feedback allows the user to smoothly overcome learning obstacles. When the user completes a learning session, the server aggregates the progress data obtained and updates the database. This allows for more efficient adjustment of the next learning plan.

[0038] This invention can provide a flexible and effective individualized learning experience, thereby improving users' motivation and learning outcomes.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] A user accesses an online learning platform and sends their login information to the server. The server authenticates the user based on the received information and connects to a database where their learning history is stored.

[0042] Step 2:

[0043] The server retrieves the user's learning history data from the database. This data includes past learning activities, test results, and the history of learning materials used. The server then inputs this information into the generating AI for analysis.

[0044] Step 3:

[0045] Based on the analysis results, the server generates a personalized learning plan for the user. The generating AI takes into account the user's learning style and progress, adjusting the selection of learning materials, the difficulty level of assignments, and the learning pace. This learning plan is optimized to meet the user's needs.

[0046] Step 4:

[0047] The server sends the generated learning plan to the user's terminal. The user's terminal has the functionality to display the corresponding learning materials and assignments based on the received plan. The user starts a learning session and uses the content through the terminal.

[0048] Step 5:

[0049] While the user is learning, the server collects progress data in real time and monitors the user's learning activity. This progress data includes the user's frequency of using learning materials, assignment completion status, and accuracy of answers.

[0050] Step 6:

[0051] Based on the collected progress data, the server analyzes the areas where the user is experiencing problems and generates real-time feedback. This feedback, including additional hints and explanations, is immediately sent to the user's device.

[0052] Step 7:

[0053] When a learning session ends, the user terminates the session via their device and notifies the server. The server then updates the progress data obtained during the session in the learning history database, preparing it for use in generating future learning plans.

[0054] (Example 1)

[0055] 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."

[0056] Online learning platforms face the challenge of providing a learning experience that is appropriately optimized for each individual user. Specifically, it is difficult to provide effective learning plans tailored to each user's learning style and progress, and real-time feedback is required. However, existing systems have lacked the means to efficiently achieve these goals.

[0057] 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.

[0058] In this invention, the server includes means for verifying user identification information and obtaining user progress information, means for performing learning history analysis using a generated AI model with the progress information, and means for creating a user-specific learning plan based on the analysis results. This enables the provision of individually optimized learning plans to users and appropriate real-time feedback.

[0059] "Identification information" refers to information used to identify a user, and is data used for login authentication and verification of access rights.

[0060] A "generative AI model" refers to an artificial intelligence algorithm that analyzes user data to identify characteristics such as learning style and level of understanding.

[0061] "Learning history analysis" refers to the process of understanding a user's learning tendencies by analyzing past learning data, and then creating an optimal learning plan based on that understanding.

[0062] A "learning plan" refers to a plan that includes optimized learning materials, assignments, and a learning pace tailored to the user's learning style and progress.

[0063] "Feedback" refers to information, including advice, hints, and correction instructions, that are provided in real time regarding the user's learning progress.

[0064] A "database" refers to a system that serves as an information infrastructure for managing and storing users' learning history and progress information.

[0065] This invention is a system for providing an optimized educational experience for individual users on an online learning platform. Its components include a server, user terminals, and a network. The role of each component is described below.

[0066] server

[0067] The server first verifies the user's identity when they log in. The software used for this verification includes authentication protocols and secure communication methods. The server also accesses a database to retrieve the user's learning history data. This data is then analyzed using a generative AI model. The generative AI model executes algorithms to evaluate the user's learning style, speed, and comprehension. Based on this analysis, the server creates an individually optimized learning plan. This plan includes learning materials, assignments, and a learning pace selected by the AI.

[0068] User terminal

[0069] The learning plan, sent from the server, is configured to be received on the user's device. The user's device displays content based on this learning plan, making it accessible to the user. As the user progresses through the learning process, the device provides an interactive interface and receives new feedback and hints in real time.

[0070] Specific example

[0071] As a concrete example, let's assume a user is taking a mathematics course. The server uses an AI model to analyze the user and determine that they are strong at calculation problems but need more theoretical explanations. Based on these results, the server suggests advanced practice problems and supplementary video materials to the user.

[0072] Example of a prompt

[0073] An example of a prompt message to be input to a generative AI model is: "Based on the user's learning history data, identify their learning style and generate the most suitable learning materials."

[0074] In this way, users can effectively progress in their learning using materials and methods that are truly suited to their own learning style and progress.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] When a user accesses and logs into the online learning platform, the server receives identification information as input. Based on this information, the server activates an authentication protocol to verify that the user is authenticated, and if authentication is successful, outputs a user ID. Next, the server uses the user ID to retrieve the corresponding user's learning history data from the database.

[0078] Step 2:

[0079] The server inputs the acquired learning history data into the generating AI model. During this process, the data is processed to convert the user's past performance, preferences, and progress into an analyzable format. The generating AI model performs the analysis and outputs results regarding the user's learning style, speed, and comprehension. These analysis results are temporarily stored for use in the next step.

[0080] Step 3:

[0081] The server creates a user-specific learning plan based on the analysis results. This process includes learning materials, assignments, and a learning pace optimized by the AI ​​model. For example, it incorporates more challenging problems in areas where the user has a high level of understanding, and provides ample foundational materials in areas where their understanding is weaker. The output is a learning plan tailored to the user.

[0082] Step 4:

[0083] The generated learning plan is sent from the server to the user's terminal. The user's terminal receives this plan as input and displays learning materials and assignments to the user according to the plan. The user accesses learning content according to their progress, and the terminal adjusts the user interface as needed.

[0084] Step 5:

[0085] While the user is learning, the server receives the user's progress data in real time. The server analyzes this progress data as input and uses a generative AI model to instantly generate feedback. For example, if the user is stuck on a particular problem, it outputs hints or additional explanations. The generated feedback is sent to the user's device, which then displays it.

[0086] Step 6:

[0087] Once a learning session ends, the server aggregates the progress data generated by the user during their learning. This data is used to update the database and create the next learning plan. This allows for a more effective optimization of the user's next learning experience.

[0088] (Application Example 1)

[0089] 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."

[0090] The present invention aims to provide personalized learning and shopping experiences by analyzing users' historical information and real-time behavioral data, thereby offering plans and suggestions optimized for each individual user. Such an adaptive system aims to improve understanding and engagement in learning, as well as satisfaction in purchasing.

[0091] 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.

[0092] In this invention, the server includes means for receiving user history information from a computer device and analyzing the history data based on that information; means for generating a plan optimized for the user based on the generated analysis results; and means for providing materials and tests corresponding to the plan to the user's information terminal. This enables individual optimization tailored to the user's needs.

[0093] A "computer device" is an electronic device that collects and transmits user history information and real-time behavioral data.

[0094] "History information" refers to data that records the actions, browsing, and purchases a user has made in the past.

[0095] "Historical data" refers to a collection of data that accumulates information about a user's past behavior, and it forms the basis for analysis.

[0096] "Analysis results" refer to information that shows insights and trends derived from historical data.

[0097] "Planning" refers to action guidelines and suggestions optimized for the user, providing personalized support in learning and purchasing activities.

[0098] An "information terminal" is an electronic device owned by a user that receives and displays information from a server.

[0099] "Materials" refer to documents and media files that include learning content and product information provided to users.

[0100] A "test" refers to questions or tasks designed to assess a user's understanding and skills.

[0101] The system implementing this invention consists of a server, a user-carried information terminal, and a network. The server has the function of receiving historical information transmitted from the user and analyzing the historical data based on that information. Specifically, the server operates on a cloud environment (e.g., AWS®) and uses a deep learning framework (e.g., TENSORFLOW®) for data analysis. In addition, a database management system (e.g., MySQL®) is used to store historical data and utilize it for generating future plans.

[0102] The user's information terminal receives learning materials and product information in real time based on a personalized plan sent from the server. Based on this information, the user can proceed with learning and purchasing activities. Information terminals include smart glasses and smartphones, allowing users to receive real-time feedback and decide on their next actions as needed.

[0103] As a concrete example, suppose a user is wearing smart glasses in a shopping mall. Based on the user's past purchase history and current in-store behavior data, the server generates optimal product suggestions and displays them on the glasses' screen. In this case, a generative AI model is used, and prompts are used to select the suggested products. An example of a prompt is, "Please enter a request to the generative AI model to develop an algorithm that recommends relevant products in real time based on the customer's purchase history."

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

[0105] Step 1:

[0106] The server receives historical information sent from the user. The input is the user's past behavior and purchase history, and the output is historical data. This data is stored in a database and used in the next analysis step.

[0107] Step 2:

[0108] The server performs analysis based on the received historical data. It uses a generative AI model (e.g., TensorFlow) to extract user preferences and patterns from the data. The input is the accumulated historical data, and the output is the analysis result. This analysis reveals elements that require individual optimization.

[0109] Step 3:

[0110] The server generates a plan optimized for the user based on the analysis results. Utilizing prompts, the AI ​​generates personalized suggestions and plans for each individual user. The input is the analysis results, and the output is an optimized plan for each user.

[0111] Step 4:

[0112] The server sends the generated plan to the user's information terminal. The terminal (e.g., smart glasses) receives this information and provides the user with visual feedback. The input is the user's optimized plan, and the output is information provided to the user. This allows the user to carry out activities based on the plan.

[0113] Step 5:

[0114] The terminal presents the user with materials and tests corresponding to the received plan. This involves using a device to visually present information (e.g., smart glasses). The input is the materials and information sent from the server, and the output is the user's use of that information. Based on this information, the user decides on their next action.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] This invention relates to an online learning platform that incorporates an emotion engine to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0117] The server first authenticates the user when they log into the platform and retrieves their learning history from the database. Using an emotion engine, the server analyzes the user's emotional state based on the learning history data and real-time learning progress information. This analysis utilizes text analysis and facial recognition technology.

[0118] The analysis results form the basis of the learning plan, and the server uses this information to generate a customized learning plan specifically for the user. The learning plan takes into account the user's learning style, interests, and emotional state, and adjusts the selection of learning materials, assignment content, and learning pace accordingly. In particular, based on the user's emotions, the plan includes elements aimed at reducing stress and improving motivation.

[0119] The generated learning plan is sent to the user's device, and the user begins learning through it. The device displays learning materials, assignments, and feedback to the user via a graphical user interface, and continuously records changes in their emotional state.

[0120] As a concrete example, let's assume a user is conducting an English learning session. If this user shows signs of fatigue during the session, the emotion engine will detect this. The server will immediately adjust the plan and provide interactive, relaxing learning tools. This helps maintain the user's motivation and relieve stress.

[0121] When a user's learning session ends, the server updates the collected sentiment data and learning history, enabling further optimization for subsequent sessions. In this way, the present invention makes it possible to provide users with detailed learning support through the introduction of an emotion engine.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] A user accesses an online learning platform and sends their login information to the server. The server verifies the user's authentication information and retrieves the user's learning history data from the database. Simultaneously, the server prepares to activate the emotion engine.

[0125] Step 2:

[0126] The server passes the user's learning history and current learning progress information to the emotion engine, which then analyzes it. The emotion engine uses text data, visual data, and other information to analyze the user's emotional state and evaluate the user's stress level and motivation.

[0127] Step 3:

[0128] The server generates a personalized learning plan for each user based on the analysis results from the emotion engine. This plan includes learning materials and assignments optimized to take into account the user's learning style, areas of interest, and emotional state.

[0129] Step 4:

[0130] The server sends a learning plan to the user's terminal. The user's terminal provides the user with the learning content received from the server through its interface. The user begins learning on the terminal's interface.

[0131] Step 5:

[0132] During user learning, the device collects user reactions and facial expression data through sensors or camera functions and sends it to the server. The server then uses an emotion engine to re-analyze this data and monitor changes in the user's emotional state in real time.

[0133] Step 6:

[0134] The server generates immediate feedback based on the real-time data it collects and adjusts the learning plan as needed. For example, if the emotion engine detects user fatigue, the server will suggest a break or make adjustments such as changing the learning content.

[0135] Step 7:

[0136] Once a learning session ends, the user logs out of their device. The server records the sentiment data and learning progress data obtained during that session in a database and uses it to generate future learning plans. In this way, the next session becomes more efficient and personalized.

[0137] (Example 2)

[0138] 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".

[0139] Existing online learning systems fail to adequately optimize the user's learning experience based on their individual emotional state, leading to challenges such as decreased learning efficiency and reduced user motivation. Furthermore, providing learning content that fully reflects users' preferences and interests is not easy, which can impair learning continuity.

[0140] 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.

[0141] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information; means for generating a learning plan optimized for the user based on the generated analysis results; and means for analyzing the user's emotional state using text analysis and image recognition technology and adapting the learning plan based on the analysis results. This makes it possible to optimize the learning experience based on the individual emotional state of the user and to provide learning content that matches the user's preferences and interests.

[0142] "Learning progress information" refers to data that shows the degree of achievement and progress a user has made during their learning activities.

[0143] "Learning history" refers to the accumulation of information about the learning activities a user has undertaken in the past and the results of those activities.

[0144] "Analysis results" refer to the conclusions and insights derived from the analyzed data.

[0145] A "learning plan" is a plan that includes the learning process and content optimized for each individual user.

[0146] "Learning materials" refer to educational materials and resources provided to users, and are sources of information to support learning.

[0147] "Response" refers to feedback provided to the user, such as evaluations and advice.

[0148] "Text analysis" is a technique that analyzes written text data and extracts useful information from it.

[0149] "Image recognition technology" is a technology that analyzes images and recognizes the information and features they contain.

[0150] "Emotional state" refers to the user's mental state or emotional response.

[0151] "Preferences" refer to characteristics that indicate a user's likes and tendencies.

[0152] This invention is an online learning system designed to individually optimize the user's learning experience. The system mainly consists of a server, user terminals, and a network.

[0153] The server plays a central role, performing authentication when a user logs in. Upon successful login, the server retrieves the user's learning history from the database. A relational database management system (RDBMS) is used here. The database stores the user's learning progress and past learning history.

[0154] The server utilizes text analysis and image recognition technologies to analyze the user's emotional state. For text analysis, a natural language processing library is used to extract emotions from text data such as user comments and notes. If the device has a camera, image recognition technology is used to analyze emotions from the user's facial expressions. Open-source computer vision libraries are generally used for image analysis.

[0155] Users are provided with an optimized learning plan based on prompts generated by an AI model. For example, the prompt "Suggest the most effective learning plan for the next hour" is input to the AI ​​model based on the user's current learning progress and emotional data. In this way, the generated learning plan is customized to take into account the user's learning style, interests, and emotional state.

[0156] The user terminal visually displays learning materials and assignments according to the learning plan and records the user's performance and emotional changes during learning. The terminal's software is operated via a graphical user interface, providing the user with an interactive learning experience.

[0157] Thus, the present invention enables real-time sentiment analysis and the provision of optimized learning plans to individual users. This improves learning efficiency and enhances user motivation to learn.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The server receives login information provided by the user and performs authentication. The input consists of a username and password, and this information is compared against registered records in the database using database queries. If authentication is successful, the server starts the user's session and prepares to retrieve their learning history.

[0161] Step 2:

[0162] The server retrieves the user's learning history data from the database. The input is the user ID, which is used to search for relevant information in the database. The output is a set of data from past learning sessions, including completed assignments and performance information. This data forms the basis for subsequent analysis.

[0163] Step 3:

[0164] The terminal receives text input from the user and sends it to the server. This input consists of user comments and learning notes, and the server uses natural language processing technology to perform sentiment analysis. Through this analysis, emotional states such as positive, negative, and neutral are extracted. This allows the emotional state to be output from the text.

[0165] Step 4:

[0166] The device uses its built-in camera to capture the user's facial expressions and sends the data to the server. The input is a real-time image of the facial expression, which the server analyzes using an image recognition algorithm. Based on the analysis, the user's emotional state is determined and output as display data.

[0167] Step 5:

[0168] The server uses the sentiment analysis data obtained in steps 3 and 4 to prompt the generating AI model and generate a learning plan optimized for the user. The input consists of analyzed sentiment data and learning history, and the AI ​​model uses this to recommend learning styles and content. The output is a personalized learning plan.

[0169] Step 6:

[0170] The device receives the learning plan sent from the server and displays it visually to the user. The input is the generated learning plan, and the device provides learning materials and assignments based on that plan. It also continuously records the user's progress and responses and sends this information to the server.

[0171] Step 7:

[0172] The server updates the sentiment data and learning history collected at the end of each user's learning session. The input is the data accumulated during the session, which is then reflected in the database. The output is the latest learning history, which is used to optimize the next session. This ensures continuous improvement of the learning experience.

[0173] (Application Example 2)

[0174] 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".

[0175] Traditional learning platforms have struggled to accurately grasp users' emotional states and provide individually optimized experiences. This has led to problems such as decreased learning effectiveness and motivation. Furthermore, in commercial facilities and other settings, there has been a demand for customer service solutions that can analyze customer emotions in real time and respond individually. This is a crucial issue for improving customer satisfaction and increasing purchasing intent.

[0176] 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.

[0177] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information, means for generating a learning plan optimized for the user based on the generated analysis results, and means for providing learning materials and assignments to the user terminal according to the learning plan. This enables detailed learning support that takes into account each user's emotional state and effective communication with customers.

[0178] "User learning progress information" refers to information that shows the learning goals and activities that a learner achieved over a specific period of time.

[0179] "Means for analyzing learning history" refers to methods or devices for analyzing learning trends and patterns based on learner data accumulated in the past.

[0180] An "optimized learning plan" refers to a learning plan that is customized based on the individual learner's progress and interests.

[0181] "User terminal" refers to electronic devices such as computers, smartphones, and tablets used by learners.

[0182] "A means of monitoring and providing feedback in real time" refers to a system that continuously tracks the current learning progress and provides appropriate guidance and advice to learners on the spot.

[0183] "A means of analyzing facial expressions and voice in real time and displaying the results on staff terminals" refers to a method of instantly evaluating a customer's facial expressions and voice tone, and displaying the analysis results on a device for staff.

[0184] The system for realizing this invention is built to analyze the user's emotional state and provide optimized learning and customer experiences. Specifically, for emotion analysis, the server receives and analyzes the user's learning history, text data, and real-time facial expression information. The analysis utilizes facial recognition software such as OpenCV and Dlib, as well as cloud-based machine learning models such as Google Cloud AI. The server processes this data and generates learning plans and customer service plans optimized for the user.

[0185] The devices, such as smart glasses or smartphones, perform real-time sentiment analysis during interactions with users or staff and display the analysis results. This allows users and staff to respond adaptively. Additionally, a generated learning plan is sent to the user's device, and learning materials and assignments are provided via a GUI. Users can then use these resources to progress through their learning.

[0186] As a concrete example, consider a scenario in an electronics store where a customer picks up a new smartphone. In this case, the device analyzes the customer's facial expressions to determine their feelings of interest and anxiety, and presents this information visually to the staff. Based on this information, the staff can provide more detailed product explanations and suggestions, thereby improving the customer experience.

[0187] An example of a prompt for a generative AI model is: "Analyze the customer's current emotional state based on their facial expression when they pick up the product. Generate and display an action sign indicating interest."

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The server receives user learning progress information and facial expression data. The data sent from the user's device includes the history of the learning content being used and the current progress. The server stores this information in a database in preparation for future analysis.

[0191] Step 2:

[0192] The server performs emotion analysis based on the received facial expression data. Specifically, it extracts facial features using OpenCV and Dlib, and then estimates the emotional state from those features using Google Cloud AI. The input is facial image data, and the output is the type and intensity of the emotion.

[0193] Step 3:

[0194] The server generates an optimized learning plan based on the results of sentiment analysis and learning progress information. This process involves selecting learning materials and adjusting the learning pace according to the user's emotional state. Analysis results are used as input, and a customized learning plan is created as output.

[0195] Step 4:

[0196] The generated learning plan is sent to the user's device, and learning materials and assignments are displayed on the screen. The user then proceeds with their learning based on this. The input is the plan from the server, and the output is the content presented to the user.

[0197] Step 5:

[0198] During the learning process, the device sends facial expression data back to the server, tracking emotional changes in real time. This allows the server to adjust the learning plan as needed. In a retail setting, the customer's emotional state is displayed on a staff terminal, helping staff to respond appropriately.

[0199] In this way, continuous optimization based on emotions is performed, making it possible to provide users and customers with a highly adaptable experience.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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".

[0216] This invention is applied to an online learning platform to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0217] When a user first logs into the learning platform, the server verifies the user's authentication information and retrieves the user's learning history data from the database. The retrieved data is then analyzed by a generating AI to identify the user's learning style, learning speed, and level of comprehension.

[0218] Based on identified learning characteristics, the server generates a personalized learning plan for the user. This plan includes appropriate learning materials, assignments, and a learning pace, which the generating AI adjusts to be optimal considering the user's past learning history and current progress. The learning plan is sent from the server to the user's device, and the user can access the learning content through their device.

[0219] As a concrete example, let's assume a user is taking a mathematics course. Through analysis, the server determines that this user is strong in computational problems and needs theoretical explanations. Therefore, the server generates a plan that combines advanced practice problems tailored to the user's skill level with video materials to complement their theoretical learning.

[0220] During the learning process, the server continuously monitors the user's progress and immediately provides temporary hints and additional explanations to the device when the user encounters difficulties. This real-time feedback allows the user to smoothly overcome learning obstacles. When the user completes a learning session, the server aggregates the progress data obtained and updates the database. This allows for more efficient adjustment of the next learning plan.

[0221] This invention can provide a flexible and effective individualized learning experience, thereby improving users' motivation and learning outcomes.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] A user accesses an online learning platform and sends their login information to the server. The server authenticates the user based on the received information and connects to a database where their learning history is stored.

[0225] Step 2:

[0226] The server retrieves the user's learning history data from the database. This data includes past learning activities, test results, and the history of learning materials used. The server then inputs this information into the generating AI for analysis.

[0227] Step 3:

[0228] Based on the analysis results, the server generates a personalized learning plan for the user. The generating AI takes into account the user's learning style and progress, adjusting the selection of learning materials, the difficulty level of assignments, and the learning pace. This learning plan is optimized to meet the user's needs.

[0229] Step 4:

[0230] The server sends the generated learning plan to the user's terminal. The user's terminal has the functionality to display the corresponding learning materials and assignments based on the received plan. The user starts a learning session and uses the content through the terminal.

[0231] Step 5:

[0232] While the user is learning, the server collects progress data in real time and monitors the user's learning activity. This progress data includes the user's frequency of using learning materials, assignment completion status, and accuracy of answers.

[0233] Step 6:

[0234] Based on the collected progress data, the server analyzes the areas where the user is experiencing problems and generates real-time feedback. This feedback, including additional hints and explanations, is immediately sent to the user's device.

[0235] Step 7:

[0236] When a learning session ends, the user terminates the session via their device and notifies the server. The server then updates the progress data obtained during the session in the learning history database, preparing it for use in generating future learning plans.

[0237] (Example 1)

[0238] 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."

[0239] Online learning platforms face the challenge of providing a learning experience that is appropriately optimized for each individual user. Specifically, it is difficult to provide effective learning plans tailored to each user's learning style and progress, and real-time feedback is required. However, existing systems have lacked the means to efficiently achieve these goals.

[0240] 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.

[0241] In this invention, the server includes means for verifying user identification information and obtaining user progress information, means for performing learning history analysis using a generated AI model with the progress information, and means for creating a user-specific learning plan based on the analysis results. This enables the provision of individually optimized learning plans to users and appropriate real-time feedback.

[0242] "Identification information" refers to information used to identify a user, and is data used for login authentication and verification of access rights.

[0243] A "generative AI model" refers to an artificial intelligence algorithm that analyzes user data to identify characteristics such as learning style and level of understanding.

[0244] "Learning history analysis" refers to the process of understanding a user's learning tendencies by analyzing past learning data, and then creating an optimal learning plan based on that understanding.

[0245] A "learning plan" refers to a plan that includes optimized learning materials, assignments, and a learning pace tailored to the user's learning style and progress.

[0246] "Feedback" refers to information, including advice, hints, and correction instructions, that are provided in real time regarding the user's learning progress.

[0247] A "database" refers to a system that serves as an information infrastructure for managing and storing users' learning history and progress information.

[0248] This invention is a system for providing an optimized educational experience for individual users on an online learning platform. Its components include a server, user terminals, and a network. The role of each component is described below.

[0249] server

[0250] The server first verifies the user's identity when they log in. The software used for this verification includes authentication protocols and secure communication methods. The server also accesses a database to retrieve the user's learning history data. This data is then analyzed using a generative AI model. The generative AI model executes algorithms to evaluate the user's learning style, speed, and comprehension. Based on this analysis, the server creates an individually optimized learning plan. This plan includes learning materials, assignments, and a learning pace selected by the AI.

[0251] User terminal

[0252] The learning plan, sent from the server, is configured to be received on the user's device. The user's device displays content based on this learning plan, making it accessible to the user. As the user progresses through the learning process, the device provides an interactive interface and receives new feedback and hints in real time.

[0253] Specific example

[0254] As a concrete example, let's assume a user is taking a mathematics course. The server uses an AI model to analyze the user and determine that they are strong at calculation problems but need more theoretical explanations. Based on these results, the server suggests advanced practice problems and supplementary video materials to the user.

[0255] Example of a prompt

[0256] An example of a prompt message to be input to a generative AI model is: "Based on the user's learning history data, identify their learning style and generate the most suitable learning materials."

[0257] In this way, users can effectively progress in their learning using materials and methods that are truly suited to their own learning style and progress.

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] When a user accesses and logs into the online learning platform, the server receives identification information as input. Based on this information, the server activates an authentication protocol to verify that the user is authenticated, and if authentication is successful, outputs a user ID. Next, the server uses the user ID to retrieve the corresponding user's learning history data from the database.

[0261] Step 2:

[0262] The server inputs the acquired learning history data into the generating AI model. During this process, the data is processed to convert the user's past performance, preferences, and progress into an analyzable format. The generating AI model performs the analysis and outputs results regarding the user's learning style, speed, and comprehension. These analysis results are temporarily stored for use in the next step.

[0263] Step 3:

[0264] The server creates a user-specific learning plan based on the analysis results. This process includes learning materials, assignments, and a learning pace optimized by the AI ​​model. For example, it incorporates more challenging problems in areas where the user has a high level of understanding, and provides ample foundational materials in areas where their understanding is weaker. The output is a learning plan tailored to the user.

[0265] Step 4:

[0266] The generated learning plan is sent from the server to the user's terminal. The user's terminal receives this plan as input and displays learning materials and assignments to the user according to the plan. The user accesses learning content according to their progress, and the terminal adjusts the user interface as needed.

[0267] Step 5:

[0268] While the user is learning, the server receives the user's progress data in real time. The server analyzes this progress data as input and uses a generative AI model to instantly generate feedback. For example, if the user is stuck on a particular problem, it outputs hints or additional explanations. The generated feedback is sent to the user's device, which then displays it.

[0269] Step 6:

[0270] Once a learning session ends, the server aggregates the progress data generated by the user during their learning. This data is used to update the database and create the next learning plan. This allows for a more effective optimization of the user's next learning experience.

[0271] (Application Example 1)

[0272] 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."

[0273] The present invention aims to provide personalized learning and shopping experiences by analyzing users' historical information and real-time behavioral data, thereby offering plans and suggestions optimized for each individual user. Such an adaptive system aims to improve understanding and engagement in learning, as well as satisfaction in purchasing.

[0274] 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.

[0275] In this invention, the server includes means for receiving user history information from a computer device and analyzing the history data based on that information; means for generating a plan optimized for the user based on the generated analysis results; and means for providing materials and tests corresponding to the plan to the user's information terminal. This enables individual optimization tailored to the user's needs.

[0276] A "computer device" is an electronic device that collects and transmits user history information and real-time behavioral data.

[0277] "History information" refers to data that records the actions, browsing, and purchases a user has made in the past.

[0278] "Historical data" refers to a collection of data that accumulates information about a user's past behavior, and it forms the basis for analysis.

[0279] The "analysis result" is information indicating insights and trends obtained based on historical data.

[0280] The "plan" refers to action guidelines and proposals optimized for the user, which are individualized support in learning and purchasing activities.

[0281] The "information terminal" is an electronic device owned by the user, which is a device that receives and displays information from the server.

[0282] The "materials" are documents and media files containing learning content and product information provided to the user.

[0283] The "test" refers to questions and tasks for evaluating the user's understanding and skills.

[0284] The system for implementing this invention is composed of a server, an information terminal carried by the user, and a network. The server has a function of receiving historical information transmitted from the user and analyzing the historical data based on the information. Specifically, the server operates in a cloud environment (e.g., AWS), and a deep learning framework (e.g., TensorFlow) is used for data analysis. Also, a database management system (e.g., MySQL) is used to accumulate historical data and utilize it for the next plan generation.

[0285] The user's information terminal receives learning materials and product information in real time based on the individually optimized plan transmitted from the server. The user can proceed with learning and purchasing activities based on this information. The information terminal includes smart glasses and smartphones, and the user can receive real-time feedback and determine the next action as needed.

[0286] As a specific example, assume that a certain user is wearing smart glasses in a shopping mall. Based on the user's past purchase history and current in-store behavior data, the server generates an optimal product recommendation and displays it on the glasses' display. At this time, a generative AI model is utilized, and a prompt sentence is used to select the proposed products. An example of a prompt sentence is "Please input into the generative AI model the content of requesting the development of an algorithm for real-time recommendation of related products from the customer's purchase history."

[0287] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0288] Step 1:

[0289] The server receives the history information transmitted from the user. The input is the user's past actions and purchase history, and the output is history data. This data is stored in a database and used in the next analysis step.

[0290] Step 2:

[0291] The server performs analysis based on the received history data. Using a generative AI model (e.g., TensorFlow), the user's preferences and patterns are extracted from the data. The input is the accumulated history data, and the output is the analysis result. Through this analysis, the elements that require individual optimization are clarified.

[0292] Step 3:

[0293] Based on the analysis result, the server generates a plan optimized for the user. Utilizing the prompt sentence, proposals and plans specialized for individual users are constructed by the generative AI. The input is the analysis result, and the output is the plan optimized for each user.

[0294] Step 4:

[0295] The server sends the generated plan to the user's information terminal. The terminal (e.g., smart glasses) receives this information and provides the user with visual feedback. The input is the user's optimized plan, and the output is information provided to the user. This allows the user to carry out activities based on the plan.

[0296] Step 5:

[0297] The terminal presents the user with materials and tests corresponding to the received plan. This involves using a device to visually present information (e.g., smart glasses). The input is the materials and information sent from the server, and the output is the user's use of that information. Based on this information, the user decides on their next action.

[0298] 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.

[0299] This invention relates to an online learning platform that incorporates an emotion engine to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0300] The server first authenticates the user when they log into the platform and retrieves their learning history from the database. Using an emotion engine, the server analyzes the user's emotional state based on the learning history data and real-time learning progress information. This analysis utilizes text analysis and facial recognition technology.

[0301] The analysis results form the basis of the learning plan, and based on this information, the server generates a learning plan customized for the user. The learning plan takes into account the user's learning style, interests, and emotional state, and adjusts the selection of teaching materials, the content of assignments, and the learning pace. In particular, based on the user's emotions, the plan includes elements aimed at reducing stress and improving motivation.

[0302] The generated learning plan is sent to the user terminal, and the user starts learning through this. The terminal displays teaching materials, assignments, and feedback to the user via a graphical user interface, and records changes in the emotional state at any time.

[0303] As a specific example, assume that a user is conducting an English learning session. If this user shows signs of fatigue during progress, the emotion engine detects this. The server immediately adjusts the plan and provides an interactive and relaxing learning tool. This helps to maintain the user's motivation and relieve stress.

[0304] When the user's learning session ends, the server updates the collected emotional data and learning history, enabling further optimization in subsequent sessions. In this way, the present invention can provide meticulous learning support to the user by introducing an emotion engine.

[0305] The following describes the processing flow.

[0306] Step 1:

[0307] The user accesses the online learning platform and sends login information to the server. The server verifies the user's authentication information and retrieves the user's learning history data from the database. At the same time, the server prepares to activate the emotion engine.

[0308] Step 2:

[0309] The server passes the user's learning history and current learning progress information to the emotion engine, which then analyzes it. The emotion engine uses text data, visual data, and other information to analyze the user's emotional state and evaluate the user's stress level and motivation.

[0310] Step 3:

[0311] The server generates a personalized learning plan for each user based on the analysis results from the emotion engine. This plan includes learning materials and assignments optimized to take into account the user's learning style, areas of interest, and emotional state.

[0312] Step 4:

[0313] The server sends a learning plan to the user's terminal. The user's terminal provides the user with the learning content received from the server through its interface. The user begins learning on the terminal's interface.

[0314] Step 5:

[0315] During user learning, the device collects user reactions and facial expression data through sensors or camera functions and sends it to the server. The server then uses an emotion engine to re-analyze this data and monitor changes in the user's emotional state in real time.

[0316] Step 6:

[0317] The server generates immediate feedback based on the real-time data it collects and adjusts the learning plan as needed. For example, if the emotion engine detects user fatigue, the server will suggest a break or make adjustments such as changing the learning content.

[0318] Step 7:

[0319] Once a learning session ends, the user logs out of their device. The server records the sentiment data and learning progress data obtained during that session in a database and uses it to generate future learning plans. In this way, the next session becomes more efficient and personalized.

[0320] (Example 2)

[0321] 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".

[0322] Existing online learning systems fail to adequately optimize the user's learning experience based on their individual emotional state, leading to challenges such as decreased learning efficiency and reduced user motivation. Furthermore, providing learning content that fully reflects users' preferences and interests is not easy, which can impair learning continuity.

[0323] 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.

[0324] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information; means for generating a learning plan optimized for the user based on the generated analysis results; and means for analyzing the user's emotional state using text analysis and image recognition technology and adapting the learning plan based on the analysis results. This makes it possible to optimize the learning experience based on the individual emotional state of the user and to provide learning content that matches the user's preferences and interests.

[0325] "Learning progress information" refers to data that shows the degree of achievement and progress a user has made during their learning activities.

[0326] "Learning history" refers to the accumulation of information about the learning activities a user has undertaken in the past and the results of those activities.

[0327] "Analysis results" refer to the conclusions and insights derived from the analyzed data.

[0328] A "learning plan" is a plan that includes the learning process and content optimized for each individual user.

[0329] "Learning materials" refer to educational materials and resources provided to users, and are sources of information to support learning.

[0330] "Response" refers to feedback provided to the user, such as evaluations and advice.

[0331] "Text analysis" is a technique that analyzes written text data and extracts useful information from it.

[0332] "Image recognition technology" is a technology that analyzes images and recognizes the information and features they contain.

[0333] "Emotional state" refers to the user's mental state or emotional response.

[0334] "Preferences" refer to characteristics that indicate a user's likes and tendencies.

[0335] This invention is an online learning system designed to individually optimize the user's learning experience. The system mainly consists of a server, user terminals, and a network.

[0336] The server plays a central role, performing authentication when a user logs in. Upon successful login, the server retrieves the user's learning history from the database. A relational database management system (RDBMS) is used here. The database stores the user's learning progress and past learning history.

[0337] The server utilizes text analysis and image recognition technologies to analyze the user's emotional state. For text analysis, a natural language processing library is used to extract emotions from text data such as user comments and notes. If the device has a camera, image recognition technology is used to analyze emotions from the user's facial expressions. Open-source computer vision libraries are generally used for image analysis.

[0338] Users are provided with an optimized learning plan based on prompts generated by an AI model. For example, the prompt "Suggest the most effective learning plan for the next hour" is input to the AI ​​model based on the user's current learning progress and emotional data. In this way, the generated learning plan is customized to take into account the user's learning style, interests, and emotional state.

[0339] The user terminal visually displays learning materials and assignments according to the learning plan and records the user's performance and emotional changes during learning. The terminal's software is operated via a graphical user interface, providing the user with an interactive learning experience.

[0340] Thus, the present invention enables real-time sentiment analysis and the provision of optimized learning plans to individual users. This improves learning efficiency and enhances user motivation to learn.

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] The server receives login information provided by the user and performs authentication. The input consists of a username and password, and this information is compared against registered records in the database using database queries. If authentication is successful, the server starts the user's session and prepares to retrieve their learning history.

[0344] Step 2:

[0345] The server retrieves the user's learning history data from the database. The input is the user ID, which is used to search for relevant information in the database. The output is a set of data from past learning sessions, including completed assignments and performance information. This data forms the basis for subsequent analysis.

[0346] Step 3:

[0347] The terminal receives text input from the user and sends it to the server. This input consists of user comments and learning notes, and the server uses natural language processing technology to perform sentiment analysis. Through this analysis, emotional states such as positive, negative, and neutral are extracted. This allows the emotional state to be output from the text.

[0348] Step 4:

[0349] The device uses its built-in camera to capture the user's facial expressions and sends the data to the server. The input is a real-time image of the facial expression, which the server analyzes using an image recognition algorithm. Based on the analysis, the user's emotional state is determined and output as display data.

[0350] Step 5:

[0351] The server uses the sentiment analysis data obtained in steps 3 and 4 to prompt the generating AI model and generate a learning plan optimized for the user. The input consists of analyzed sentiment data and learning history, and the AI ​​model uses this to recommend learning styles and content. The output is a personalized learning plan.

[0352] Step 6:

[0353] The device receives the learning plan sent from the server and displays it visually to the user. The input is the generated learning plan, and the device provides learning materials and assignments based on that plan. It also continuously records the user's progress and responses and sends this information to the server.

[0354] Step 7:

[0355] The server updates the sentiment data and learning history collected at the end of each user's learning session. The input is the data accumulated during the session, which is then reflected in the database. The output is the latest learning history, which is used to optimize the next session. This ensures continuous improvement of the learning experience.

[0356] (Application Example 2)

[0357] 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."

[0358] Traditional learning platforms have struggled to accurately grasp users' emotional states and provide individually optimized experiences. This has led to problems such as decreased learning effectiveness and motivation. Furthermore, in commercial facilities and other settings, there has been a demand for customer service solutions that can analyze customer emotions in real time and respond individually. This is a crucial issue for improving customer satisfaction and increasing purchasing intent.

[0359] 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.

[0360] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information, means for generating a learning plan optimized for the user based on the generated analysis results, and means for providing learning materials and assignments to the user terminal according to the learning plan. This enables detailed learning support that takes into account each user's emotional state and effective communication with customers.

[0361] "User learning progress information" refers to information that shows the learning goals and activities that a learner achieved over a specific period of time.

[0362] "Means for analyzing learning history" refers to methods or devices for analyzing learning trends and patterns based on learner data accumulated in the past.

[0363] An "optimized learning plan" refers to a learning plan that is customized based on the individual learner's progress and interests.

[0364] "User terminal" refers to electronic devices such as computers, smartphones, and tablets used by learners.

[0365] "A means of monitoring and providing feedback in real time" refers to a system that continuously tracks the current learning progress and provides appropriate guidance and advice to learners on the spot.

[0366] "A means of analyzing facial expressions and voice in real time and displaying the results on staff terminals" refers to a method of instantly evaluating a customer's facial expressions and voice tone, and displaying the analysis results on a device for staff.

[0367] The system for realizing this invention is built to analyze the user's emotional state and provide optimized learning and customer experiences. Specifically, for emotion analysis, the server receives and analyzes the user's learning history, text data, and real-time facial expression information. Face recognition software such as OpenCV and Dlib, and cloud-based machine learning models such as Google Cloud AI are used for the analysis. The server processes this data and generates learning plans and customer service plans optimized for the user.

[0368] The devices, such as smart glasses or smartphones, perform real-time sentiment analysis during interactions with users or staff and display the analysis results. This allows users and staff to respond adaptively. Additionally, a generated learning plan is sent to the user's device, and learning materials and assignments are provided via a GUI. Users can then use these resources to progress through their learning.

[0369] As a concrete example, consider a scenario in an electronics store where a customer picks up a new smartphone. In this case, the device analyzes the customer's facial expressions to determine their feelings of interest and anxiety, and presents this information visually to the staff. Based on this information, the staff can provide more detailed product explanations and suggestions, thereby improving the customer experience.

[0370] An example of a prompt for a generative AI model is: "Analyze the customer's current emotional state based on their facial expression when they pick up the product. Generate and display an action sign indicating interest."

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The server receives user learning progress information and facial expression data. The data sent from the user's device includes the history of the learning content being used and the current progress. The server stores this information in a database in preparation for future analysis.

[0374] Step 2:

[0375] The server performs emotion analysis based on the received facial expression data. Specifically, it extracts facial features using OpenCV and Dlib, and then estimates the emotional state from those features using Google Cloud AI. The input is facial image data, and the output is the type and intensity of the emotion.

[0376] Step 3:

[0377] The server generates an optimized learning plan based on the results of sentiment analysis and learning progress information. This process involves selecting learning materials and adjusting the learning pace according to the user's emotional state. Analysis results are used as input, and a customized learning plan is created as output.

[0378] Step 4:

[0379] The generated learning plan is sent to the user's device, and learning materials and assignments are displayed on the screen. The user then proceeds with their learning based on this. The input is the plan from the server, and the output is the content presented to the user.

[0380] Step 5:

[0381] During the learning process, the device sends facial expression data back to the server, tracking emotional changes in real time. This allows the server to adjust the learning plan as needed. In a retail setting, the customer's emotional state is displayed on a staff terminal, helping staff to respond appropriately.

[0382] In this way, continuous optimization based on emotions is performed, making it possible to provide users and customers with a highly adaptable experience.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] [Third Embodiment]

[0387] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0388] 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.

[0389] 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).

[0390] 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.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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".

[0399] This invention is applied to an online learning platform to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0400] When a user first logs into the learning platform, the server verifies the user's authentication information and retrieves the user's learning history data from the database. The retrieved data is then analyzed by a generating AI to identify the user's learning style, learning speed, and level of comprehension.

[0401] Based on identified learning characteristics, the server generates a personalized learning plan for the user. This plan includes appropriate learning materials, assignments, and a learning pace, which the generating AI adjusts to be optimal considering the user's past learning history and current progress. The learning plan is sent from the server to the user's device, and the user can access the learning content through their device.

[0402] As a concrete example, let's assume a user is taking a mathematics course. Through analysis, the server determines that this user is strong in computational problems and needs theoretical explanations. Therefore, the server generates a plan that combines advanced practice problems tailored to the user's skill level with video materials to complement their theoretical learning.

[0403] During the learning process, the server continuously monitors the user's progress and immediately provides temporary hints and additional explanations to the device when the user encounters difficulties. This real-time feedback allows the user to smoothly overcome learning obstacles. When the user completes a learning session, the server aggregates the progress data obtained and updates the database. This allows for more efficient adjustment of the next learning plan.

[0404] This invention can provide a flexible and effective individualized learning experience, thereby improving users' motivation and learning outcomes.

[0405] The following describes the processing flow.

[0406] Step 1:

[0407] A user accesses an online learning platform and sends their login information to the server. The server authenticates the user based on the received information and connects to a database where their learning history is stored.

[0408] Step 2:

[0409] The server retrieves the user's learning history data from the database. This data includes past learning activities, test results, and the history of learning materials used. The server then inputs this information into the generating AI for analysis.

[0410] Step 3:

[0411] Based on the analysis results, the server generates a personalized learning plan for the user. The generating AI takes into account the user's learning style and progress, adjusting the selection of learning materials, the difficulty level of assignments, and the learning pace. This learning plan is optimized to meet the user's needs.

[0412] Step 4:

[0413] The server sends the generated learning plan to the user's terminal. The user's terminal has the functionality to display the corresponding learning materials and assignments based on the received plan. The user starts a learning session and uses the content through the terminal.

[0414] Step 5:

[0415] While the user is learning, the server collects progress data in real time and monitors the user's learning activity. This progress data includes the user's frequency of using learning materials, assignment completion status, and accuracy of answers.

[0416] Step 6:

[0417] Based on the collected progress data, the server analyzes the areas where the user is experiencing problems and generates real-time feedback. This feedback, including additional hints and explanations, is immediately sent to the user's device.

[0418] Step 7:

[0419] When a learning session ends, the user terminates the session via their device and notifies the server. The server then updates the progress data obtained during the session in the learning history database, preparing it for use in generating future learning plans.

[0420] (Example 1)

[0421] 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."

[0422] Online learning platforms face the challenge of providing a learning experience that is appropriately optimized for each individual user. Specifically, it is difficult to provide effective learning plans tailored to each user's learning style and progress, and real-time feedback is required. However, existing systems have lacked the means to efficiently achieve these goals.

[0423] 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.

[0424] In this invention, the server includes means for verifying user identification information and obtaining user progress information, means for performing learning history analysis using a generated AI model with the progress information, and means for creating a user-specific learning plan based on the analysis results. This enables the provision of individually optimized learning plans to users and appropriate real-time feedback.

[0425] "Identification information" refers to information used to identify a user, and is data used for login authentication and verification of access rights.

[0426] A "generative AI model" refers to an artificial intelligence algorithm that analyzes user data to identify characteristics such as learning style and level of understanding.

[0427] "Learning history analysis" refers to the process of understanding a user's learning tendencies by analyzing past learning data, and then creating an optimal learning plan based on that understanding.

[0428] A "learning plan" refers to a plan that includes optimized learning materials, assignments, and a learning pace tailored to the user's learning style and progress.

[0429] "Feedback" refers to information, including advice, hints, and correction instructions, that are provided in real time regarding the user's learning progress.

[0430] A "database" refers to a system that serves as an information infrastructure for managing and storing users' learning history and progress information.

[0431] This invention is a system for providing an optimized educational experience for individual users on an online learning platform. Its components include a server, user terminals, and a network. The role of each component is described below.

[0432] server

[0433] The server first verifies the user's identity when they log in. The software used for this verification includes authentication protocols and secure communication methods. The server also accesses a database to retrieve the user's learning history data. This data is then analyzed using a generative AI model. The generative AI model executes algorithms to evaluate the user's learning style, speed, and comprehension. Based on this analysis, the server creates an individually optimized learning plan. This plan includes learning materials, assignments, and a learning pace selected by the AI.

[0434] User terminal

[0435] The learning plan, sent from the server, is configured to be received on the user's device. The user's device displays content based on this learning plan, making it accessible to the user. As the user progresses through the learning process, the device provides an interactive interface and receives new feedback and hints in real time.

[0436] Specific example

[0437] As a concrete example, let's assume a user is taking a mathematics course. The server uses an AI model to analyze the user and determine that they are strong at calculation problems but need more theoretical explanations. Based on these results, the server suggests advanced practice problems and supplementary video materials to the user.

[0438] Example of a prompt

[0439] An example of a prompt message to be input to a generative AI model is: "Based on the user's learning history data, identify their learning style and generate the most suitable learning materials."

[0440] In this way, users can effectively progress in their learning using materials and methods that are truly suited to their own learning style and progress.

[0441] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0442] Step 1:

[0443] When a user accesses and logs into the online learning platform, the server receives identification information as input. Based on this information, the server activates an authentication protocol to verify that the user is authenticated, and if authentication is successful, outputs a user ID. Next, the server uses the user ID to retrieve the corresponding user's learning history data from the database.

[0444] Step 2:

[0445] The server inputs the acquired learning history data into the generating AI model. During this process, the data is processed to convert the user's past performance, preferences, and progress into an analyzable format. The generating AI model performs the analysis and outputs results regarding the user's learning style, speed, and comprehension. These analysis results are temporarily stored for use in the next step.

[0446] Step 3:

[0447] The server creates a user-specific learning plan based on the analysis results. This process includes learning materials, assignments, and a learning pace optimized by the AI ​​model. For example, it incorporates more challenging problems in areas where the user has a high level of understanding, and provides ample foundational materials in areas where their understanding is weaker. The output is a learning plan tailored to the user.

[0448] Step 4:

[0449] The generated learning plan is sent from the server to the user's terminal. The user's terminal receives this plan as input and displays learning materials and assignments to the user according to the plan. The user accesses learning content according to their progress, and the terminal adjusts the user interface as needed.

[0450] Step 5:

[0451] While the user is learning, the server receives the user's progress data in real time. The server analyzes this progress data as input and uses a generative AI model to instantly generate feedback. For example, if the user is stuck on a particular problem, it outputs hints or additional explanations. The generated feedback is sent to the user's device, which then displays it.

[0452] Step 6:

[0453] Once a learning session ends, the server aggregates the progress data generated by the user during their learning. This data is used to update the database and create the next learning plan. This allows for a more effective optimization of the user's next learning experience.

[0454] (Application Example 1)

[0455] 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."

[0456] The present invention aims to provide personalized learning and shopping experiences by analyzing users' historical information and real-time behavioral data, thereby offering plans and suggestions optimized for each individual user. Such an adaptive system aims to improve understanding and engagement in learning, as well as satisfaction in purchasing.

[0457] 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.

[0458] In this invention, the server includes means for receiving user history information from a computer device and analyzing the history data based on that information; means for generating a plan optimized for the user based on the generated analysis results; and means for providing materials and tests corresponding to the plan to the user's information terminal. This enables individual optimization tailored to the user's needs.

[0459] A "computer device" is an electronic device that collects and transmits user history information and real-time behavioral data.

[0460] "History information" refers to data that records the actions, browsing, and purchases a user has made in the past.

[0461] "Historical data" refers to a collection of data that accumulates information about a user's past behavior, and it forms the basis for analysis.

[0462] "Analysis results" refer to information that shows insights and trends derived from historical data.

[0463] "Planning" refers to action guidelines and suggestions optimized for the user, providing personalized support in learning and purchasing activities.

[0464] An "information terminal" is an electronic device owned by a user that receives and displays information from a server.

[0465] "Materials" refer to documents and media files that include learning content and product information provided to users.

[0466] A "test" refers to questions or tasks designed to assess a user's understanding and skills.

[0467] The system implementing this invention consists of a server, a user-carried information terminal, and a network. The server has the function of receiving historical information transmitted from the user and analyzing the historical data based on that information. Specifically, the server operates on a cloud environment (e.g., AWS), and a deep learning framework (e.g., TensorFlow) is used for data analysis. In addition, a database management system (e.g., MySQL) is used to store historical data and use it to generate future plans.

[0468] The user's information terminal receives learning materials and product information in real time based on a personalized plan sent from the server. Based on this information, the user can proceed with learning and purchasing activities. Information terminals include smart glasses and smartphones, allowing users to receive real-time feedback and decide on their next actions as needed.

[0469] As a concrete example, suppose a user is wearing smart glasses in a shopping mall. Based on the user's past purchase history and current in-store behavior data, the server generates optimal product suggestions and displays them on the glasses' screen. In this case, a generative AI model is used, and prompts are used to select the suggested products. An example of a prompt is, "Please enter a request to the generative AI model to develop an algorithm that recommends relevant products in real time based on the customer's purchase history."

[0470] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0471] Step 1:

[0472] The server receives historical information sent from the user. The input is the user's past behavior and purchase history, and the output is historical data. This data is stored in a database and used in the next analysis step.

[0473] Step 2:

[0474] The server performs analysis based on the received historical data. It uses a generative AI model (e.g., TensorFlow) to extract user preferences and patterns from the data. The input is the accumulated historical data, and the output is the analysis result. This analysis reveals elements that require individual optimization.

[0475] Step 3:

[0476] The server generates a plan optimized for the user based on the analysis results. Utilizing prompts, the AI ​​generates personalized suggestions and plans for each individual user. The input is the analysis results, and the output is an optimized plan for each user.

[0477] Step 4:

[0478] The server sends the generated plan to the user's information terminal. The terminal (e.g., smart glasses) receives this information and provides the user with visual feedback. The input is the user's optimized plan, and the output is information provided to the user. This allows the user to carry out activities based on the plan.

[0479] Step 5:

[0480] The terminal presents the user with materials and tests corresponding to the received plan. This involves using a device to visually present information (e.g., smart glasses). The input is the materials and information sent from the server, and the output is the user's use of that information. Based on this information, the user decides on their next action.

[0481] 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.

[0482] This invention relates to an online learning platform that incorporates an emotion engine to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0483] The server first authenticates the user when they log into the platform and retrieves their learning history from the database. Using an emotion engine, the server analyzes the user's emotional state based on the learning history data and real-time learning progress information. This analysis utilizes text analysis and facial recognition technology.

[0484] The analysis results form the basis of the learning plan, and the server uses this information to generate a customized learning plan specifically for the user. The learning plan takes into account the user's learning style, interests, and emotional state, and adjusts the selection of learning materials, assignment content, and learning pace accordingly. In particular, based on the user's emotions, the plan includes elements aimed at reducing stress and improving motivation.

[0485] The generated learning plan is sent to the user's device, and the user begins learning through it. The device displays learning materials, assignments, and feedback to the user via a graphical user interface, and continuously records changes in their emotional state.

[0486] As a concrete example, let's assume a user is conducting an English learning session. If this user shows signs of fatigue during the session, the emotion engine will detect this. The server will immediately adjust the plan and provide interactive, relaxing learning tools. This helps maintain the user's motivation and relieve stress.

[0487] When a user's learning session ends, the server updates the collected sentiment data and learning history, enabling further optimization for subsequent sessions. In this way, the present invention makes it possible to provide users with detailed learning support through the introduction of an emotion engine.

[0488] The following describes the processing flow.

[0489] Step 1:

[0490] A user accesses an online learning platform and sends their login information to the server. The server verifies the user's authentication information and retrieves the user's learning history data from the database. Simultaneously, the server prepares to activate the emotion engine.

[0491] Step 2:

[0492] The server passes the user's learning history and current learning progress information to the emotion engine, which then analyzes it. The emotion engine uses text data, visual data, and other information to analyze the user's emotional state and evaluate the user's stress level and motivation.

[0493] Step 3:

[0494] The server generates a personalized learning plan for each user based on the analysis results from the emotion engine. This plan includes learning materials and assignments optimized to take into account the user's learning style, areas of interest, and emotional state.

[0495] Step 4:

[0496] The server sends a learning plan to the user's terminal. The user's terminal provides the user with the learning content received from the server through its interface. The user begins learning on the terminal's interface.

[0497] Step 5:

[0498] During user learning, the device collects user reactions and facial expression data through sensors or camera functions and sends it to the server. The server then uses an emotion engine to re-analyze this data and monitor changes in the user's emotional state in real time.

[0499] Step 6:

[0500] The server generates immediate feedback based on the real-time data it collects and adjusts the learning plan as needed. For example, if the emotion engine detects user fatigue, the server will suggest a break or make adjustments such as changing the learning content.

[0501] Step 7:

[0502] Once a learning session ends, the user logs out of their device. The server records the sentiment data and learning progress data obtained during that session in a database and uses it to generate future learning plans. In this way, the next session becomes more efficient and personalized.

[0503] (Example 2)

[0504] 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."

[0505] Existing online learning systems fail to adequately optimize the user's learning experience based on their individual emotional state, leading to challenges such as decreased learning efficiency and reduced user motivation. Furthermore, providing learning content that fully reflects users' preferences and interests is not easy, which can impair learning continuity.

[0506] 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.

[0507] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information; means for generating a learning plan optimized for the user based on the generated analysis results; and means for analyzing the user's emotional state using text analysis and image recognition technology and adapting the learning plan based on the analysis results. This makes it possible to optimize the learning experience based on the individual emotional state of the user and to provide learning content that matches the user's preferences and interests.

[0508] "Learning progress information" refers to data that shows the degree of achievement and progress a user has made during their learning activities.

[0509] "Learning history" refers to the accumulation of information about the learning activities a user has undertaken in the past and the results of those activities.

[0510] "Analysis results" refer to the conclusions and insights derived from the analyzed data.

[0511] A "learning plan" is a plan that includes the learning process and content optimized for each individual user.

[0512] "Learning materials" refer to educational materials and resources provided to users, and are sources of information to support learning.

[0513] "Response" refers to feedback provided to the user, such as evaluations and advice.

[0514] "Text analysis" is a technique that analyzes written text data and extracts useful information from it.

[0515] "Image recognition technology" is a technology that analyzes images and recognizes the information and features they contain.

[0516] "Emotional state" refers to the user's mental state or emotional response.

[0517] "Preferences" refer to characteristics that indicate a user's likes and tendencies.

[0518] This invention is an online learning system designed to individually optimize the user's learning experience. The system mainly consists of a server, user terminals, and a network.

[0519] The server plays a central role, performing authentication when a user logs in. Upon successful login, the server retrieves the user's learning history from the database. A relational database management system (RDBMS) is used here. The database stores the user's learning progress and past learning history.

[0520] The server utilizes text analysis and image recognition technologies to analyze the user's emotional state. For text analysis, a natural language processing library is used to extract emotions from text data such as user comments and notes. If the device has a camera, image recognition technology is used to analyze emotions from the user's facial expressions. Open-source computer vision libraries are generally used for image analysis.

[0521] Users are provided with an optimized learning plan based on prompts generated by an AI model. For example, the prompt "Suggest the most effective learning plan for the next hour" is input to the AI ​​model based on the user's current learning progress and emotional data. In this way, the generated learning plan is customized to take into account the user's learning style, interests, and emotional state.

[0522] The user terminal visually displays learning materials and assignments according to the learning plan and records the user's performance and emotional changes during learning. The terminal's software is operated via a graphical user interface, providing the user with an interactive learning experience.

[0523] Thus, the present invention enables real-time sentiment analysis and the provision of optimized learning plans to individual users. This improves learning efficiency and enhances user motivation to learn.

[0524] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0525] Step 1:

[0526] The server receives login information provided by the user and performs authentication. The input consists of a username and password, and this information is compared against registered records in the database using database queries. If authentication is successful, the server starts the user's session and prepares to retrieve their learning history.

[0527] Step 2:

[0528] The server retrieves the user's learning history data from the database. The input is the user ID, which is used to search for relevant information in the database. The output is a set of data from past learning sessions, including completed assignments and performance information. This data forms the basis for subsequent analysis.

[0529] Step 3:

[0530] The terminal receives text input from the user and sends it to the server. This input consists of user comments and learning notes, and the server uses natural language processing technology to perform sentiment analysis. Through this analysis, emotional states such as positive, negative, and neutral are extracted. This allows the emotional state to be output from the text.

[0531] Step 4:

[0532] The device uses its built-in camera to capture the user's facial expressions and sends the data to the server. The input is a real-time image of the facial expression, which the server analyzes using an image recognition algorithm. Based on the analysis, the user's emotional state is determined and output as display data.

[0533] Step 5:

[0534] The server uses the sentiment analysis data obtained in steps 3 and 4 to prompt the generating AI model and generate a learning plan optimized for the user. The input consists of analyzed sentiment data and learning history, and the AI ​​model uses this to recommend learning styles and content. The output is a personalized learning plan.

[0535] Step 6:

[0536] The device receives the learning plan sent from the server and displays it visually to the user. The input is the generated learning plan, and the device provides learning materials and assignments based on that plan. It also continuously records the user's progress and responses and sends this information to the server.

[0537] Step 7:

[0538] The server updates the sentiment data and learning history collected at the end of each user's learning session. The input is the data accumulated during the session, which is then reflected in the database. The output is the latest learning history, which is used to optimize the next session. This ensures continuous improvement of the learning experience.

[0539] (Application Example 2)

[0540] 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."

[0541] Traditional learning platforms have struggled to accurately grasp users' emotional states and provide individually optimized experiences. This has led to problems such as decreased learning effectiveness and motivation. Furthermore, in commercial facilities and other settings, there has been a demand for customer service solutions that can analyze customer emotions in real time and respond individually. This is a crucial issue for improving customer satisfaction and increasing purchasing intent.

[0542] 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.

[0543] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information, means for generating a learning plan optimized for the user based on the generated analysis results, and means for providing learning materials and assignments to the user terminal according to the learning plan. This enables detailed learning support that takes into account each user's emotional state and effective communication with customers.

[0544] "User learning progress information" refers to information that shows the learning goals and activities that a learner achieved over a specific period of time.

[0545] "Means for analyzing learning history" refers to methods or devices for analyzing learning trends and patterns based on learner data accumulated in the past.

[0546] An "optimized learning plan" refers to a learning plan that is customized based on the individual learner's progress and interests.

[0547] "User terminal" refers to electronic devices such as computers, smartphones, and tablets used by learners.

[0548] "A means of monitoring and providing feedback in real time" refers to a system that continuously tracks the current learning progress and provides appropriate guidance and advice to learners on the spot.

[0549] "A means of analyzing facial expressions and voice in real time and displaying the results on staff terminals" refers to a method of instantly evaluating a customer's facial expressions and voice tone, and displaying the analysis results on a device for staff.

[0550] The system for realizing this invention is built to analyze the user's emotional state and provide optimized learning and customer experiences. Specifically, for emotion analysis, the server receives and analyzes the user's learning history, text data, and real-time facial expression information. Face recognition software such as OpenCV and Dlib, and cloud-based machine learning models such as Google Cloud AI are used for the analysis. The server processes this data and generates learning plans and customer service plans optimized for the user.

[0551] The devices, such as smart glasses or smartphones, perform real-time sentiment analysis during interactions with users or staff and display the analysis results. This allows users and staff to respond adaptively. Additionally, a generated learning plan is sent to the user's device, and learning materials and assignments are provided via a GUI. Users can then use these resources to progress through their learning.

[0552] As a concrete example, consider a scenario in an electronics store where a customer picks up a new smartphone. In this case, the device analyzes the customer's facial expressions to determine their feelings of interest and anxiety, and presents this information visually to the staff. Based on this information, the staff can provide more detailed product explanations and suggestions, thereby improving the customer experience.

[0553] An example of a prompt for a generative AI model is: "Analyze the customer's current emotional state based on their facial expression when they pick up the product. Generate and display an action sign indicating interest."

[0554] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0555] Step 1:

[0556] The server receives user learning progress information and facial expression data. The data sent from the user's device includes the history of the learning content being used and the current progress. The server stores this information in a database in preparation for future analysis.

[0557] Step 2:

[0558] The server performs emotion analysis based on the received facial expression data. Specifically, it extracts facial features using OpenCV and Dlib, and then estimates the emotional state from those features using Google Cloud AI. The input is facial image data, and the output is the type and intensity of the emotion.

[0559] Step 3:

[0560] The server generates an optimized learning plan based on the results of sentiment analysis and learning progress information. This process involves selecting learning materials and adjusting the learning pace according to the user's emotional state. Analysis results are used as input, and a customized learning plan is created as output.

[0561] Step 4:

[0562] The generated learning plan is sent to the user's device, and learning materials and assignments are displayed on the screen. The user then proceeds with their learning based on this. The input is the plan from the server, and the output is the content presented to the user.

[0563] Step 5:

[0564] During the learning process, the device sends facial expression data back to the server, tracking emotional changes in real time. This allows the server to adjust the learning plan as needed. In a retail setting, the customer's emotional state is displayed on a staff terminal, helping staff to respond appropriately.

[0565] In this way, continuous optimization based on emotions is performed, making it possible to provide users and customers with a highly adaptable experience.

[0566] 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.

[0567] 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.

[0568] 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.

[0569] [Fourth Embodiment]

[0570] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0571] 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.

[0572] 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).

[0573] 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.

[0574] 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.

[0575] 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).

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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".

[0583] This invention is applied to an online learning platform to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0584] When a user first logs into the learning platform, the server verifies the user's authentication information and retrieves the user's learning history data from the database. The retrieved data is then analyzed by a generating AI to identify the user's learning style, learning speed, and level of comprehension.

[0585] Based on identified learning characteristics, the server generates a personalized learning plan for the user. This plan includes appropriate learning materials, assignments, and a learning pace, which the generating AI adjusts to be optimal considering the user's past learning history and current progress. The learning plan is sent from the server to the user's device, and the user can access the learning content through their device.

[0586] As a concrete example, let's assume a user is taking a mathematics course. Through analysis, the server determines that this user is strong in computational problems and needs theoretical explanations. Therefore, the server generates a plan that combines advanced practice problems tailored to the user's skill level with video materials to complement their theoretical learning.

[0587] During the learning process, the server continuously monitors the user's progress and immediately provides temporary hints and additional explanations to the device when the user encounters difficulties. This real-time feedback allows the user to smoothly overcome learning obstacles. When the user completes a learning session, the server aggregates the progress data obtained and updates the database. This allows for more efficient adjustment of the next learning plan.

[0588] This invention can provide a flexible and effective individualized learning experience, thereby improving users' motivation and learning outcomes.

[0589] The following describes the processing flow.

[0590] Step 1:

[0591] A user accesses an online learning platform and sends their login information to the server. The server authenticates the user based on the received information and connects to a database where their learning history is stored.

[0592] Step 2:

[0593] The server retrieves the user's learning history data from the database. This data includes past learning activities, test results, and the history of learning materials used. The server then inputs this information into the generating AI for analysis.

[0594] Step 3:

[0595] Based on the analysis results, the server generates a personalized learning plan for the user. The generating AI takes into account the user's learning style and progress, adjusting the selection of learning materials, the difficulty level of assignments, and the learning pace. This learning plan is optimized to meet the user's needs.

[0596] Step 4:

[0597] The server sends the generated learning plan to the user's terminal. The user's terminal has the functionality to display the corresponding learning materials and assignments based on the received plan. The user starts a learning session and uses the content through the terminal.

[0598] Step 5:

[0599] While the user is learning, the server collects progress data in real time and monitors the user's learning activity. This progress data includes the user's frequency of using learning materials, assignment completion status, and accuracy of answers.

[0600] Step 6:

[0601] Based on the collected progress data, the server analyzes the areas where the user is experiencing problems and generates real-time feedback. This feedback, including additional hints and explanations, is immediately sent to the user's device.

[0602] Step 7:

[0603] When a learning session ends, the user terminates the session via their device and notifies the server. The server then updates the progress data obtained during the session in the learning history database, preparing it for use in generating future learning plans.

[0604] (Example 1)

[0605] 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".

[0606] Online learning platforms face the challenge of providing a learning experience that is appropriately optimized for each individual user. Specifically, it is difficult to provide effective learning plans tailored to each user's learning style and progress, and real-time feedback is required. However, existing systems have lacked the means to efficiently achieve these goals.

[0607] 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.

[0608] In this invention, the server includes means for verifying user identification information and obtaining user progress information, means for performing learning history analysis using a generated AI model with the progress information, and means for creating a user-specific learning plan based on the analysis results. This enables the provision of individually optimized learning plans to users and appropriate real-time feedback.

[0609] "Identification information" refers to information used to identify a user, and is data used for login authentication and verification of access rights.

[0610] A "generative AI model" refers to an artificial intelligence algorithm that analyzes user data to identify characteristics such as learning style and level of understanding.

[0611] "Learning history analysis" refers to the process of understanding a user's learning tendencies by analyzing past learning data, and then creating an optimal learning plan based on that understanding.

[0612] A "learning plan" refers to a plan that includes optimized learning materials, assignments, and a learning pace tailored to the user's learning style and progress.

[0613] "Feedback" refers to information, including advice, hints, and correction instructions, that are provided in real time regarding the user's learning progress.

[0614] A "database" refers to a system that serves as an information infrastructure for managing and storing users' learning history and progress information.

[0615] This invention is a system for providing an optimized educational experience for individual users on an online learning platform. Its components include a server, user terminals, and a network. The role of each component is described below.

[0616] server

[0617] The server first verifies the user's identity when they log in. The software used for this verification includes authentication protocols and secure communication methods. The server also accesses a database to retrieve the user's learning history data. This data is then analyzed using a generative AI model. The generative AI model executes algorithms to evaluate the user's learning style, speed, and comprehension. Based on this analysis, the server creates an individually optimized learning plan. This plan includes learning materials, assignments, and a learning pace selected by the AI.

[0618] User terminal

[0619] The learning plan, sent from the server, is configured to be received on the user's device. The user's device displays content based on this learning plan, making it accessible to the user. As the user progresses through the learning process, the device provides an interactive interface and receives new feedback and hints in real time.

[0620] Specific example

[0621] As a concrete example, let's assume a user is taking a mathematics course. The server uses an AI model to analyze the user and determine that they are strong at calculation problems but need more theoretical explanations. Based on these results, the server suggests advanced practice problems and supplementary video materials to the user.

[0622] Example of a prompt

[0623] An example of a prompt message to be input to a generative AI model is: "Based on the user's learning history data, identify their learning style and generate the most suitable learning materials."

[0624] In this way, users can effectively progress in their learning using materials and methods that are truly suited to their own learning style and progress.

[0625] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0626] Step 1:

[0627] When a user accesses and logs into the online learning platform, the server receives identification information as input. Based on this information, the server activates an authentication protocol to verify that the user is authenticated, and if authentication is successful, outputs a user ID. Next, the server uses the user ID to retrieve the corresponding user's learning history data from the database.

[0628] Step 2:

[0629] The server inputs the acquired learning history data into the generating AI model. During this process, the data is processed to convert the user's past performance, preferences, and progress into an analyzable format. The generating AI model performs the analysis and outputs results regarding the user's learning style, speed, and comprehension. These analysis results are temporarily stored for use in the next step.

[0630] Step 3:

[0631] The server creates a user-specific learning plan based on the analysis results. This process includes learning materials, assignments, and a learning pace optimized by the AI ​​model. For example, it incorporates more challenging problems in areas where the user has a high level of understanding, and provides ample foundational materials in areas where their understanding is weaker. The output is a learning plan tailored to the user.

[0632] Step 4:

[0633] The generated learning plan is sent from the server to the user's terminal. The user's terminal receives this plan as input and displays learning materials and assignments to the user according to the plan. The user accesses learning content according to their progress, and the terminal adjusts the user interface as needed.

[0634] Step 5:

[0635] While the user is learning, the server receives the user's progress data in real time. The server analyzes this progress data as input and uses a generative AI model to instantly generate feedback. For example, if the user is stuck on a particular problem, it outputs hints or additional explanations. The generated feedback is sent to the user's device, which then displays it.

[0636] Step 6:

[0637] Once a learning session ends, the server aggregates the progress data generated by the user during their learning. This data is used to update the database and create the next learning plan. This allows for a more effective optimization of the user's next learning experience.

[0638] (Application Example 1)

[0639] 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".

[0640] The present invention aims to provide personalized learning and shopping experiences by analyzing users' historical information and real-time behavioral data, thereby offering plans and suggestions optimized for each individual user. Such an adaptive system aims to improve understanding and engagement in learning, as well as satisfaction in purchasing.

[0641] 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.

[0642] In this invention, the server includes means for receiving user history information from a computer device and analyzing the history data based on that information; means for generating a plan optimized for the user based on the generated analysis results; and means for providing materials and tests corresponding to the plan to the user's information terminal. This enables individual optimization tailored to the user's needs.

[0643] A "computer device" is an electronic device that collects and transmits user history information and real-time behavioral data.

[0644] "History information" refers to data that records the actions, browsing, and purchases a user has made in the past.

[0645] "Historical data" refers to a collection of data that accumulates information about a user's past behavior, and it forms the basis for analysis.

[0646] "Analysis results" refer to information that shows insights and trends derived from historical data.

[0647] "Planning" refers to action guidelines and suggestions optimized for the user, providing personalized support in learning and purchasing activities.

[0648] An "information terminal" is an electronic device owned by a user that receives and displays information from a server.

[0649] "Materials" refer to documents and media files that include learning content and product information provided to users.

[0650] A "test" refers to questions or tasks designed to assess a user's understanding and skills.

[0651] The system implementing this invention consists of a server, a user-carried information terminal, and a network. The server has the function of receiving historical information transmitted from the user and analyzing the historical data based on that information. Specifically, the server operates on a cloud environment (e.g., AWS), and a deep learning framework (e.g., TensorFlow) is used for data analysis. In addition, a database management system (e.g., MySQL) is used to store historical data and use it to generate future plans.

[0652] The user's information terminal receives learning materials and product information in real time based on a personalized plan sent from the server. Based on this information, the user can proceed with learning and purchasing activities. Information terminals include smart glasses and smartphones, allowing users to receive real-time feedback and decide on their next actions as needed.

[0653] As a concrete example, suppose a user is wearing smart glasses in a shopping mall. Based on the user's past purchase history and current in-store behavior data, the server generates optimal product suggestions and displays them on the glasses' screen. In this case, a generative AI model is used, and prompts are used to select the suggested products. An example of a prompt is, "Please enter a request to the generative AI model to develop an algorithm that recommends relevant products in real time based on the customer's purchase history."

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] The server receives historical information sent from the user. The input is the user's past behavior and purchase history, and the output is historical data. This data is stored in a database and used in the next analysis step.

[0657] Step 2:

[0658] The server performs analysis based on the received historical data. It uses a generative AI model (e.g., TensorFlow) to extract user preferences and patterns from the data. The input is the accumulated historical data, and the output is the analysis result. This analysis reveals elements that require individual optimization.

[0659] Step 3:

[0660] The server generates a plan optimized for the user based on the analysis results. Utilizing prompts, the AI ​​generates personalized suggestions and plans for each individual user. The input is the analysis results, and the output is an optimized plan for each user.

[0661] Step 4:

[0662] The server sends the generated plan to the user's information terminal. The terminal (e.g., smart glasses) receives this information and provides the user with visual feedback. The input is the user's optimized plan, and the output is information provided to the user. This allows the user to carry out activities based on the plan.

[0663] Step 5:

[0664] The terminal presents the user with materials and tests corresponding to the received plan. This involves using a device to visually present information (e.g., smart glasses). The input is the materials and information sent from the server, and the output is the user's use of that information. Based on this information, the user decides on their next action.

[0665] 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.

[0666] This invention relates to an online learning platform that incorporates an emotion engine to individually optimize the user's learning experience. This platform consists of a server, user terminals, and a network.

[0667] The server first authenticates the user when they log into the platform and retrieves their learning history from the database. Using an emotion engine, the server analyzes the user's emotional state based on the learning history data and real-time learning progress information. This analysis utilizes text analysis and facial recognition technology.

[0668] The analysis results form the basis of the learning plan, and the server uses this information to generate a customized learning plan specifically for the user. The learning plan takes into account the user's learning style, interests, and emotional state, and adjusts the selection of learning materials, assignment content, and learning pace accordingly. In particular, based on the user's emotions, the plan includes elements aimed at reducing stress and improving motivation.

[0669] The generated learning plan is sent to the user's device, and the user begins learning through it. The device displays learning materials, assignments, and feedback to the user via a graphical user interface, and continuously records changes in their emotional state.

[0670] As a concrete example, let's assume a user is conducting an English learning session. If this user shows signs of fatigue during the session, the emotion engine will detect this. The server will immediately adjust the plan and provide interactive, relaxing learning tools. This helps maintain the user's motivation and relieve stress.

[0671] When a user's learning session ends, the server updates the collected sentiment data and learning history, enabling further optimization for subsequent sessions. In this way, the present invention makes it possible to provide users with detailed learning support through the introduction of an emotion engine.

[0672] The following describes the processing flow.

[0673] Step 1:

[0674] A user accesses an online learning platform and sends their login information to the server. The server verifies the user's authentication information and retrieves the user's learning history data from the database. Simultaneously, the server prepares to activate the emotion engine.

[0675] Step 2:

[0676] The server passes the user's learning history and current learning progress information to the emotion engine, which then analyzes it. The emotion engine uses text data, visual data, and other information to analyze the user's emotional state and evaluate the user's stress level and motivation.

[0677] Step 3:

[0678] The server generates a personalized learning plan for each user based on the analysis results from the emotion engine. This plan includes learning materials and assignments optimized to take into account the user's learning style, areas of interest, and emotional state.

[0679] Step 4:

[0680] The server sends a learning plan to the user's terminal. The user's terminal provides the user with the learning content received from the server through its interface. The user begins learning on the terminal's interface.

[0681] Step 5:

[0682] During user learning, the device collects user reactions and facial expression data through sensors or camera functions and sends it to the server. The server then uses an emotion engine to re-analyze this data and monitor changes in the user's emotional state in real time.

[0683] Step 6:

[0684] The server generates immediate feedback based on the real-time data it collects and adjusts the learning plan as needed. For example, if the emotion engine detects user fatigue, the server will suggest a break or make adjustments such as changing the learning content.

[0685] Step 7:

[0686] Once a learning session ends, the user logs out of their device. The server records the sentiment data and learning progress data obtained during that session in a database and uses it to generate future learning plans. In this way, the next session becomes more efficient and personalized.

[0687] (Example 2)

[0688] 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".

[0689] Existing online learning systems fail to adequately optimize the user's learning experience based on their individual emotional state, leading to challenges such as decreased learning efficiency and reduced user motivation. Furthermore, providing learning content that fully reflects users' preferences and interests is not easy, which can impair learning continuity.

[0690] 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.

[0691] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information; means for generating a learning plan optimized for the user based on the generated analysis results; and means for analyzing the user's emotional state using text analysis and image recognition technology and adapting the learning plan based on the analysis results. This makes it possible to optimize the learning experience based on the individual emotional state of the user and to provide learning content that matches the user's preferences and interests.

[0692] "Learning progress information" refers to data that shows the degree of achievement and progress a user has made during their learning activities.

[0693] "Learning history" refers to the accumulation of information about the learning activities a user has undertaken in the past and the results of those activities.

[0694] "Analysis results" refer to the conclusions and insights derived from the analyzed data.

[0695] A "learning plan" is a plan that includes the learning process and content optimized for each individual user.

[0696] "Learning materials" refer to educational materials and resources provided to users, and are sources of information to support learning.

[0697] "Response" refers to feedback provided to the user, such as evaluations and advice.

[0698] "Text analysis" is a technique that analyzes written text data and extracts useful information from it.

[0699] "Image recognition technology" is a technology that analyzes images and recognizes the information and features they contain.

[0700] "Emotional state" refers to the user's mental state or emotional response.

[0701] "Preferences" refer to characteristics that indicate a user's likes and tendencies.

[0702] This invention is an online learning system designed to individually optimize the user's learning experience. The system mainly consists of a server, user terminals, and a network.

[0703] The server plays a central role, performing authentication when a user logs in. Upon successful login, the server retrieves the user's learning history from the database. A relational database management system (RDBMS) is used here. The database stores the user's learning progress and past learning history.

[0704] The server utilizes text analysis and image recognition technologies to analyze the user's emotional state. For text analysis, a natural language processing library is used to extract emotions from text data such as user comments and notes. If the device has a camera, image recognition technology is used to analyze emotions from the user's facial expressions. Open-source computer vision libraries are generally used for image analysis.

[0705] Users are provided with an optimized learning plan based on prompts generated by an AI model. For example, the prompt "Suggest the most effective learning plan for the next hour" is input to the AI ​​model based on the user's current learning progress and emotional data. In this way, the generated learning plan is customized to take into account the user's learning style, interests, and emotional state.

[0706] The user terminal visually displays learning materials and assignments according to the learning plan and records the user's performance and emotional changes during learning. The terminal's software is operated via a graphical user interface, providing the user with an interactive learning experience.

[0707] Thus, the present invention enables real-time sentiment analysis and the provision of optimized learning plans to individual users. This improves learning efficiency and enhances user motivation to learn.

[0708] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0709] Step 1:

[0710] The server receives login information provided by the user and performs authentication. The input consists of a username and password, and this information is compared against registered records in the database using database queries. If authentication is successful, the server starts the user's session and prepares to retrieve their learning history.

[0711] Step 2:

[0712] The server retrieves the user's learning history data from the database. The input is the user ID, which is used to search for relevant information in the database. The output is a set of data from past learning sessions, including completed assignments and performance information. This data forms the basis for subsequent analysis.

[0713] Step 3:

[0714] The terminal receives text input from the user and sends it to the server. This input consists of user comments and learning notes, and the server uses natural language processing technology to perform sentiment analysis. Through this analysis, emotional states such as positive, negative, and neutral are extracted. This allows the emotional state to be output from the text.

[0715] Step 4:

[0716] The device uses its built-in camera to capture the user's facial expressions and sends the data to the server. The input is a real-time image of the facial expression, which the server analyzes using an image recognition algorithm. Based on the analysis, the user's emotional state is determined and output as display data.

[0717] Step 5:

[0718] The server uses the sentiment analysis data obtained in steps 3 and 4 to prompt the generating AI model and generate a learning plan optimized for the user. The input consists of analyzed sentiment data and learning history, and the AI ​​model uses this to recommend learning styles and content. The output is a personalized learning plan.

[0719] Step 6:

[0720] The device receives the learning plan sent from the server and displays it visually to the user. The input is the generated learning plan, and the device provides learning materials and assignments based on that plan. It also continuously records the user's progress and responses and sends this information to the server.

[0721] Step 7:

[0722] The server updates the sentiment data and learning history collected at the end of each user's learning session. The input is the data accumulated during the session, which is then reflected in the database. The output is the latest learning history, which is used to optimize the next session. This ensures continuous improvement of the learning experience.

[0723] (Application Example 2)

[0724] 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".

[0725] Traditional learning platforms have struggled to accurately grasp users' emotional states and provide individually optimized experiences. This has led to problems such as decreased learning effectiveness and motivation. Furthermore, in commercial facilities and other settings, there has been a demand for customer service solutions that can analyze customer emotions in real time and respond individually. This is a crucial issue for improving customer satisfaction and increasing purchasing intent.

[0726] 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.

[0727] In this invention, the server includes means for receiving user learning progress information and analyzing the learning history based on said information, means for generating a learning plan optimized for the user based on the generated analysis results, and means for providing learning materials and assignments to the user terminal according to the learning plan. This enables detailed learning support that takes into account each user's emotional state and effective communication with customers.

[0728] "User learning progress information" refers to information that shows the learning goals and activities that a learner achieved over a specific period of time.

[0729] "Means for analyzing learning history" refers to methods or devices for analyzing learning trends and patterns based on learner data accumulated in the past.

[0730] An "optimized learning plan" refers to a learning plan that is customized based on the individual learner's progress and interests.

[0731] "User terminal" refers to electronic devices such as computers, smartphones, and tablets used by learners.

[0732] "A means of monitoring and providing feedback in real time" refers to a system that continuously tracks the current learning progress and provides appropriate guidance and advice to learners on the spot.

[0733] "A means of analyzing facial expressions and voice in real time and displaying the results on staff terminals" refers to a method of instantly evaluating a customer's facial expressions and voice tone, and displaying the analysis results on a device for staff.

[0734] The system for realizing this invention is built to analyze the user's emotional state and provide optimized learning and customer experiences. Specifically, for emotion analysis, the server receives and analyzes the user's learning history, text data, and real-time facial expression information. Face recognition software such as OpenCV and Dlib, and cloud-based machine learning models such as Google Cloud AI are used for the analysis. The server processes this data and generates learning plans and customer service plans optimized for the user.

[0735] The devices, such as smart glasses or smartphones, perform real-time sentiment analysis during interactions with users or staff and display the analysis results. This allows users and staff to respond adaptively. Additionally, a generated learning plan is sent to the user's device, and learning materials and assignments are provided via a GUI. Users can then use these resources to progress through their learning.

[0736] As a concrete example, consider a scenario in an electronics store where a customer picks up a new smartphone. In this case, the device analyzes the customer's facial expressions to determine their feelings of interest and anxiety, and presents this information visually to the staff. Based on this information, the staff can provide more detailed product explanations and suggestions, thereby improving the customer experience.

[0737] An example of a prompt for a generative AI model is: "Analyze the customer's current emotional state based on their facial expression when they pick up the product. Generate and display an action sign indicating interest."

[0738] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0739] Step 1:

[0740] The server receives user learning progress information and facial expression data. The data sent from the user's device includes the history of the learning content being used and the current progress. The server stores this information in a database in preparation for future analysis.

[0741] Step 2:

[0742] The server performs emotion analysis based on the received facial expression data. Specifically, it extracts facial features using OpenCV and Dlib, and then estimates the emotional state from those features using Google Cloud AI. The input is facial image data, and the output is the type and intensity of the emotion.

[0743] Step 3:

[0744] The server generates an optimized learning plan based on the results of sentiment analysis and learning progress information. This process involves selecting learning materials and adjusting the learning pace according to the user's emotional state. Analysis results are used as input, and a customized learning plan is created as output.

[0745] Step 4:

[0746] The generated learning plan is sent to the user's device, and learning materials and assignments are displayed on the screen. The user then proceeds with their learning based on this. The input is the plan from the server, and the output is the content presented to the user.

[0747] Step 5:

[0748] During the learning process, the device sends facial expression data back to the server, tracking emotional changes in real time. This allows the server to adjust the learning plan as needed. In a retail setting, the customer's emotional state is displayed on a staff terminal, helping staff to respond appropriately.

[0749] In this way, continuous optimization based on emotions is performed, making it possible to provide users and customers with a highly adaptable experience.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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."

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] The following is further disclosed regarding the embodiments described above.

[0772] (Claim 1)

[0773] A means for receiving user learning progress information and analyzing the learning history based on that information,

[0774] A means for generating a user-optimized learning plan based on the generated analysis results,

[0775] A means of providing learning materials and assignments to the user terminal according to the learning plan,

[0776] A means of monitoring users' learning progress in real time and providing feedback,

[0777] Means for adjusting the learning plan based on the aforementioned feedback,

[0778] A system that includes this.

[0779] (Claim 2)

[0780] The system according to claim 1, characterized in that it takes into account the user's interests and areas of concern when providing learning content to the user.

[0781] (Claim 3)

[0782] The system according to claim 1, characterized in that it updates the learning history database in order to use the user's learning history data for generating the next learning plan.

[0783] "Example 1"

[0784] (Claim 1)

[0785] A means for verifying user identification information and obtaining progress information of the said user,

[0786] A means for performing learning history analysis by a generative AI model using the progress information,

[0787] A means of creating a user-specific learning plan based on the analysis results,

[0788] A means for transmitting the learning materials and assignments included in the learning plan to the user's terminal,

[0789] A means to monitor the user's learning progress in real time and provide immediate feedback,

[0790] A means for dynamically adjusting the learning plan based on the feedback,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, characterized in that it selects learning content taking into consideration the user's interests and preferences.

[0794] (Claim 3)

[0795] The system according to claim 1, characterized in that it analyzes user progress data and updates the database for use in generating the next learning plan.

[0796] "Application Example 1"

[0797] (Claim 1)

[0798] A means for receiving user history information from a computer device and analyzing the history data based on said information,

[0799] A means for generating a user-optimized plan based on the generated analysis results,

[0800] A means of providing the user's information terminal with materials and tests according to the plan,

[0801] A means of monitoring user progress in real time and providing information,

[0802] Based on the aforementioned information, means for adjusting the plan,

[0803] A means of collecting user location information and purchase history to provide personalized recommendations in real time,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, characterized in that it takes into account the user's interests and preferred fields in the information provided to the user.

[0807] (Claim 3)

[0808] The system according to claim 1, characterized in that it updates the history database in order to use the history data for generating the next plan.

[0809] "Example 2 of combining an emotion engine"

[0810] (Claim 1)

[0811] A means for receiving user learning progress information and analyzing the learning history based on that information,

[0812] A means for generating a user-optimized learning plan based on the generated analysis results,

[0813] A means of providing learning materials and assignments to a user terminal according to the learning plan,

[0814] A means of monitoring the user's learning progress in real time and providing responses,

[0815] Means for adjusting the learning plan based on the above response,

[0816] A means for analyzing a user's emotional state using text analysis and image recognition technologies, and for adapting a learning plan based on the analysis results,

[0817] A system that includes this.

[0818] (Claim 2)

[0819] The system according to claim 1, characterized in that it takes into account the user's preferences and areas of interest when providing learning content to the user.

[0820] (Claim 3)

[0821] The system according to claim 1, characterized in that it updates the learning history database in order to use the user's learning history data for generating the next learning plan.

[0822] "Application example 2 when combining with an emotional engine"

[0823] (Claim 1)

[0824] A means for receiving user learning progress information and analyzing the learning history based on that information,

[0825] A means for generating a user-optimized learning plan based on the generated analysis results,

[0826] A means of providing learning materials and assignments to the user terminal according to the learning plan,

[0827] A means of monitoring users' learning progress in real time and providing feedback,

[0828] Means for adjusting the learning plan based on the aforementioned feedback,

[0829] Analyzing human interactions with the aim of improving the individually optimized customer experience,

[0830] A means of analyzing customer facial expressions and voice in real time and displaying the results on staff terminals,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, characterized in that it takes into account the user's interests and areas of concern when providing learning content to the user.

[0834] (Claim 3)

[0835] The system according to claim 1, characterized in that it updates the learning history database in order to use the user's learning history data for generating the next learning plan. [Explanation of Symbols]

[0836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving user learning progress information and analyzing the learning history based on that information, A means for generating a user-optimized learning plan based on the generated analysis results, A means of providing learning materials and assignments to the user terminal according to the learning plan, A means of monitoring users' learning progress in real time and providing feedback, Means for adjusting the learning plan based on the aforementioned feedback, A system that includes this.

2. The system according to claim 1, characterized in that it takes into account the user's interests and areas of concern when providing learning content to the user.

3. The system according to claim 1, characterized in that it updates the learning history database in order to use the user's learning history data for generating the next learning plan.

Images