system

Abstract

We provide the system. [Solution] A means of collecting the user's learning history, A means of generating customized learning content using natural language generation technology based on collected learning history, A means of providing the generated learning content to the user, A means of monitoring user responses to provided learning content and evaluating user understanding and progress based on those responses, A means of generating and providing additional learning content and advice to users based on evaluation results, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional learning support systems often provide the same learning content to all learners, and cannot provide optimal learning support according to the needs and comprehension levels of individual learners. As a result, some learners may continue learning without progress in understanding, or conversely, the learning efficiency may decrease by repeatedly learning the same content. In addition, it has been difficult to appropriately grasp the individual weaknesses and progress of learners and perform reinforcement learning based on them. The object of this invention is to provide a new learning support system that provides learning content optimized for learners through the collection and analysis of learning histories, and improves learning efficiency and effects.

Means for Solving the Problems

[0005] The present invention comprises means for collecting a user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, and means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response. It also includes means for generating and providing additional learning content and advice to the user based on the evaluation results. Furthermore, it includes means for receiving the user's initial settings information and generating an initial learning plan, and means for collecting user feedback and improving the next learning plan and learning content based on the feedback. This makes it possible to provide a learning experience that is individually optimized for each learner and promote efficient and effective learning.

[0006] "User" refers to individual learners who utilize the learning support AI system.

[0007] "Learning history" refers to a collection of data related to the content a user has studied, their study time, their answer results, and other learning activities.

[0008] "Natural language generation technology" refers to the technology that uses artificial intelligence to automatically generate text using natural language.

[0009] "Customized learning content" refers to learning materials such as specific questions, explanations, and resources that are generated based on each user's learning history and needs.

[0010] "Evaluation" refers to measuring and analyzing users' responses to and understanding of the learning material.

[0011] "Advice" refers to suggestions and guidelines provided by the system to improve the user's learning efficiency and effectiveness.

[0012] "Initial setup information" refers to the basic information (such as name, grade level, subjects of interest, and learning goals) that users enter when registering with the system.

[0013] A "learning plan" refers to the specific learning content and schedule that is built based on the user's current situation and goals.

[0014] "Feedback" refers to the act of a user communicating their level of understanding, satisfaction, and opinions on the learning content to the system after completing a course.

[0015] A "database" refers to a system component that stores and manages learning history, user information, generated learning content, and other related data. [Brief explanation of the drawing]

[0016] [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 the data processing device and 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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. [[ID=]19]

[0018] First, the terms used in the following description will be explained. [[ID=]22]

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] As an embodiment for carrying out the present invention, the specific program processing of the learning support AI system is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[0038] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their own learning goals and schedule, and this information is also sent to the server via the terminal.

[0039] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as the learning history.

[0040] The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. The generated learning content is provided to the user via the device. The user then uses the provided content to continue their learning.

[0041] The device monitors the user's responses, recording, for example, the answer result and time taken for each question. This data is sent to a server, which evaluates the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[0042] After completing a lesson, users can enter self-assessments and feedback. The feedback data is sent to a server via the device, which analyzes it to improve future learning plans and content.

[0043] As a concrete example, consider the case of user B, a second-year high school student, studying mathematics. After logging in, user B begins studying "quadratic equations." The system identifies that user B struggles with "quadratic equations" based on past learning history data. The server provides user B with specific practice problems and explanations via the terminal. When user B solves the problems, the terminal records the answer and sends it to the server. The server evaluates user B's answer and time taken, and provides additional practice problems or explanatory videos as needed.

[0044] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The user accesses the AI ​​learning support system and registers. Specifically, the user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in a database.

[0048] Step 2:

[0049] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[0050] Step 3:

[0051] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[0052] Step 4:

[0053] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[0054] Step 5:

[0055] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[0056] Step 6:

[0057] The device monitors the user's responses, recording, for example, the answer result and time taken for each question. This data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[0058] Step 7:

[0059] Based on the evaluation results, the server generates additional learning content and advice to reinforce the user's weaknesses. For example, it might generate additional practice problems or detailed explanations for specific areas. The generated content and advice are sent from the server to the terminal, which then provides it to the user.

[0060] Step 8:

[0061] After a user completes a learning session, they enter a self-assessment and feedback. This feedback data is sent from the device to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[0062] Step 9:

[0063] The server generates an improved learning plan and saves it to the database. In the next learning session, the device provides this new learning plan to the user, thus repeating the learning cycle.

[0064] (Example 1)

[0065] 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."

[0066] Conventional learning support systems have struggled to appropriately reflect users' learning history and comprehension levels, and to provide individually optimized learning content. Furthermore, they lacked the functionality to effectively utilize user feedback and continuously improve learning plans. As a result, learning effectiveness was limited, and it was difficult to maintain users' motivation to learn.

[0067] 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.

[0068] In this invention, the server includes means for receiving user initial setup information and generating an initial learning plan; means for collecting the user's learning history; means for generating customized learning content using natural language generation technology based on the collected learning history; means for providing the generated learning content to the user; means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response; means for generating and providing additional learning content and advice based on the evaluation results; means for collecting user feedback and improving the next learning plan and learning content based on the feedback; means for tracking learning activities in real time when the user starts learning activities and collecting that data; and means for generating prompt sentences for a generation AI model and generating customized learning content based on the collected user learning history data. This makes it possible to provide a learning experience that is individually optimized for each user, continuously improve learning plans and content, and maximize learning effectiveness.

[0069] "User initial information" refers to the information a user enters when they first access the system, and includes personal information and basic learning-related information such as name, grade level, subjects of interest, and learning goals.

[0070] An "initial learning plan" refers to a plan generated by the server based on the user's initial settings, designed to help the user efficiently begin learning.

[0071] "Learning history" refers to data collected when a user engages in learning activities using the system, such as records of activities, learning progress, and grades.

[0072] "Natural language generation technology" refers to the technology of generating natural language using artificial intelligence. Specifically, it refers to the technology of generating texts, explanations, questions, etc., using AI models.

[0073] "Customized learning content" refers to learning materials, questions, and explanations that are optimized for a specific user based on their learning history and level of understanding.

[0074] "User response" refers to the results of user actions and inputs regarding learning content, specifically data such as answer results, response time, and operation logs.

[0075] "Comprehension level" refers to an indicator that evaluates how well a user understands a particular learning topic.

[0076] "Progress" refers to an indicator that shows how far a user has progressed according to their learning plan.

[0077] "Feedback" refers to information provided by users, such as evaluations, opinions, and suggestions for improvement regarding learning content and the system as a whole.

[0078] "Real-time tracking" refers to the process of instantly recording a user's learning activities and sending the data to the server in real time as they occur.

[0079] A "generative AI model" refers to an algorithm or software that uses an artificial intelligence model to generate learning content and prompt sentences.

[0080] A "prompt sentence" refers to an instruction or question given to a generative AI model, which serves as the basis for the AI ​​to generate output.

[0081] As an embodiment of the present invention, a learning support AI system is provided to enable users to learn efficiently and effectively. The learning support AI system mainly consists of a server, a terminal, and a user.

[0082] First, the user accesses the system via a terminal and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal, and the terminal sends this information to the server. The server stores the received information in a database and generates an initial learning plan. In this process, the database and server can use commonly used computer and server-related software (e.g., MySQL, Apache).

[0083] Next, the user logs back into the system and sets their learning goals and schedule. The terminal sends the entered data to the server, which then stores it in the database.

[0084] When a user starts a learning session, the device tracks their learning activity in real time and sends that data to the server. The server then records the user's learning history in a database.

[0085] Based on learning history data, the server generates customized learning content using natural language generation technology. For example, the GPT-4 AI model is used for generation. The generated learning content is provided to the user via a terminal. While the user progresses through the learning process, the terminal monitors the user's responses (e.g., answers to each question and response time) and sends this data to the server.

[0086] The server evaluates the user's understanding and progress based on user response data. Based on the evaluation results, the server further generates additional learning content and advice using natural language generation technology and provides it to the user via the device.

[0087] Furthermore, after completing a lesson, users input self-assessments and feedback into their device, and the device sends this feedback data to a server. The server analyzes the feedback and uses it to improve future learning plans and learning content.

[0088] As a concrete example, consider the case of User B, a second-year high school student, who is studying "quadratic equations" in mathematics. After logging in, User B begins learning. The server identifies User B's weaknesses from their past learning history and uses a generative AI model (e.g., GPT-4) to generate specific practice problems and explanations. This generated content is provided to User B through their device. When User B solves a problem, the device records the answer and sends it to the server. The server evaluates this data and provides additional practice problems or explanatory videos as needed.

[0089] An example of a prompt message would be: "When user B, a second-year high school student, is solving practice problems on quadratic equations, identify user B's weak areas and generate customized practice problems based on those areas."

[0090] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[0091] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0092] Step 1:

[0093] The user accesses the system and registers. The terminal receives initial information from the user, such as name, grade level, and subjects of interest. The terminal sends this information to the server. The server stores the received information in its database. Specifically, when the user clicks the "Register" button, an HTTP POST request is sent from the terminal to the server, which receives it and stores it in the database.

[0094] Step 2:

[0095] The user logs into the system and sets their learning goals and schedule. The terminal receives the user's input (learning goals and schedule) and sends it to the server. The server saves this data to a database. Specifically, when the user clicks the "Save" button, data in JSON format is sent from the terminal to the server, which parses it and saves it to the database.

[0096] Step 3:

[0097] The user starts a learning session. The device records the start time of the learning session and sends activity data during the learning session (such as answers to questions and typing speed) to the server in real time. The server receives the learning start signal and activity data during the learning session as input from the device and continuously records this in its database. Specifically, when the user clicks the "Start Learning" button, the device records the current time and periodically sends activity data to the server.

[0098] Step 4:

[0099] The server generates customized learning content based on the collected learning history. Using the collected learning history data as input, the server sends prompts to a generative AI model (e.g., GPT-4) to generate content. The generated content is sent to the terminal and provided to the user. Specifically, the server periodically checks the database, and if there is any unprocessed learning history data, it uses the generative AI model to generate custom content and sends it to the terminal.

[0100] Step 5:

[0101] The device monitors the user's responses and records the answer and response time for each question. It receives user response data as input and sends it to the server. The server evaluates the user's understanding and progress based on this data. Specifically, each time the user answers a question, the device records the result and response time and sends it to the server. The server analyzes this data and stores the evaluation results in a database.

[0102] Step 6:

[0103] The server generates additional learning content and advice based on the evaluation results. Using the evaluation results as input, the server sends prompts to the generating AI model, which then generates customized content and advice. The generated content is sent to the terminal and provided to the user. Specifically, the server sends new prompts to the generating AI model based on the evaluation results, generates additional content, and sends it to the terminal for the user to receive.

[0104] Step 7:

[0105] After completing a lesson, the user enters their self-assessment and feedback into the device. The device sends the entered data to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content. Specifically, when the user fills out and submits the feedback form, the data is sent from the device to the server, which analyzes the feedback and makes updates to reflect it in the next learning session.

[0106] (Application Example 1)

[0107] 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."

[0108] Traditional shopping experiences often fail to provide appropriate recommendations to increase user purchasing intent, and finding products in stores is inconvenient. On the other hand, there is no system that accurately understands user preferences and purchasing behavior and provides optimal recommendations and navigation based on that information. This results in a lack of personalized shopping experiences and hinders efficient purchasing.

[0109] 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.

[0110] In this invention, the server includes means for collecting user behavior history, means for generating customized recommendation content using a generation AI model based on the collected behavior history, means for providing the generated recommendation content to the user, means for monitoring the user's reaction to the provided recommendation content and evaluating the user's level of interest and purchase intent based on the reaction, and means for generating and providing additional recommendation content and advice to the user based on the evaluation results. This enables a shopping experience that is individually optimized for each user.

[0111] "User behavior history" refers to data about a user's series of purchasing activities, their movement within a store, and the products they viewed.

[0112] A "generative AI model" is an algorithm or program that uses machine learning and deep learning techniques to generate appropriate recommendation content from data.

[0113] "Customized recommendation content" refers to recommendations for products and services that are optimized for a user based on their individual preferences and behavioral history.

[0114] "User responses to recommended content" refer to actions and evaluations that users show towards the recommended products or services, such as click-through rates and purchase behavior.

[0115] "Methods for evaluating user interest and purchasing intent" refer to technologies and methods for analyzing collected user response data and quantitatively evaluating how interested a user is in a product or service.

[0116] "Initial setup information" refers to basic information that users enter when they start using the system, such as name, age, gender, and product categories of interest.

[0117] "Feedback" refers to evaluations and opinions that users provide to the system, such as comments on the shopping experience or reactions to recommended content.

[0118] "Additional recommended content and advice" refers to recommendations for products and services created based on user interest and purchase intent evaluations, as well as suggestions and advice given to users.

[0119] As an embodiment of this invention, a system for improving the shopping experience in physical stores will be specifically described. This system consists of a server, a terminal (mainly a smartphone), and a user.

[0120] Program operation

[0121] Means of collecting user behavior history

[0122] Once a user installs the application and begins browsing within a store, location data is collected using the smartphone's GPS and Wi-Fi information. The products the user views and purchases are also automatically tracked. This data is transmitted to a server in real time and stored in a database.

[0123] Means for generating customized recommendation content

[0124] The server uses a generative AI model to analyze the collected behavioral history data. The data is processed using machine learning frameworks such as TensorFlow, and optimal product recommendation content is created based on the user's preferences.

[0125] Means of providing recommended content to users

[0126] The generated recommendation content is notified to the user via their smartphone. The user can then open the application to view individually customized product recommendations.

[0127] A means of monitoring and evaluating user reactions.

[0128] All actions users take regarding recommended content (e.g., clicks and purchases) are sent from their devices to the server. This data is aggregated and analyzed on the server and used as an indicator to evaluate the user's level of interest and purchase intent.

[0129] A means of generating and providing additional recommended content and advice.

[0130] Based on the evaluation results, the server generates newly created recommendation content and advice. This additional information is also provided to the user via smartphone, further enhancing the shopping experience.

[0131] Hardware and software used for implementation

[0132] Hardware: Smartphones (Android / iOS), Servers

[0133] Software: Firebase (database management), TensorFlow (machine learning models), Google Maps API (in-store navigation)

[0134] Examples of specific cases and prompt statements

[0135] For example, if a user types "Tell me today's recommended products" on their smartphone while in a store, the application will notify them based on their purchase history, saying, "Today we recommend wireless earphones, which are on sale. They are located in area B of the store." Also, if a user types "Direct me to the battery section," detailed navigation from their current location to the battery section will be provided.

[0136] Examples of prompt statements:

[0137] Based on the user's purchase history, generate a list of recommended products for today.

[0138] Please guide the user through the store, from their current location to the shelf of the specified product.

[0139] As described above, this embodiment of the invention provides a system that enhances the user's shopping experience by offering personalized recommendation content in real time based on the user's daily behavior history.

[0140] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0141] Step 1:

[0142] The user installs the application and enters initial setup information. Initial setup information such as the user's name, age, gender, and product categories of interest is collected and sent from the device to the server. The server stores this initial setup information in a database and generates an initial recommendation plan.

[0143] Input: User's name, age, gender, product categories of interest

[0144] Data processing: The server receives this data and saves it to the database.

[0145] Output: Initial Recommended Plan

[0146] Step 2:

[0147] When a user visits a store and launches the application, the device tracks the user's current location. It obtains location information from the smartphone's GPS or Wi-Fi and sends that data to the server in real time.

[0148] Input: Smartphone GPS information, Wi-Fi information

[0149] Data processing: Collection and real-time transmission of location data.

[0150] Output: Location data stored on the server

[0151] Step 3:

[0152] The server generates customized recommendation content using an AI model based on user behavior history data. The collected behavior history data is analyzed using TensorFlow, and optimal product recommendations are created through a machine learning model.

[0153] Input: User activity history data

[0154] Data processing: Data analysis using machine learning models

[0155] Output: Customized recommendation content

[0156] Step 4:

[0157] The generated recommendation content is sent to the device and provided to the user through a smartphone application. The user reviews the recommendation content within the app and makes a purchasing decision.

[0158] Input: Customized recommendation content

[0159] Output: Recommended content notified to your smartphone

[0160] Step 5:

[0161] User responses (for example, the number of clicks on recommended products and actual purchase behavior) are sent from the device to the server. The server collects and stores this response data to evaluate the user's level of interest and purchase intent.

[0162] Input: User response data

[0163] Data processing: Collection and storage of reaction data

[0164] Output: Evaluation results of interest level and purchase intent

[0165] Step 6:

[0166] Based on the evaluation results, the server generates additional recommended content and advice. This is again done using a generative AI model and machine learning algorithm to produce the most optimal content.

[0167] Input: Evaluation result

[0168] Data processing: Generate new recommendation content based on evaluation results.

[0169] Output: Additional recommended content and advice

[0170] Step 7:

[0171] The newly generated additional recommendation content and advice are sent to the device and provided to the user via their smartphone. The user can then review this and take further purchasing action.

[0172] Input: Additional recommended content or advice

[0173] Output: Additional recommended content notified to your smartphone

[0174] As described above, this system collects, analyzes, and notifies data between users, devices, and servers to provide a personalized shopping experience.

[0175] 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.

[0176] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[0177] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[0178] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as learning history. The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is sent from the server to the device.

[0179] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress with their learning. For example, the device displays specific practice problems or explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[0180] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust the presentation method and content of learning materials.

[0181] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, advice is also generated to maintain and improve the user's motivation. For example, if the user is tired, a short break may be suggested, while if they are highly engaged, additional challenges may be offered.

[0182] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[0183] The following describes the processing flow.

[0184] Step 1:

[0185] The user accesses the AI ​​learning support system and registers. The user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in its database.

[0186] Step 2:

[0187] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[0188] Step 3:

[0189] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[0190] Step 4:

[0191] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. Data analysis is performed to identify the user's strengths and weaknesses, and the generated learning content is sent from the server to the terminal.

[0192] Step 5:

[0193] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[0194] Step 6:

[0195] The device monitors the user's responses. For example, it records the answer result and time taken to answer each question, and this data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[0196] Step 7:

[0197] During learning, the device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state. For example, it can determine whether the user is having fun or feeling stressed.

[0198] Step 8:

[0199] The server receives the results of the emotion engine's analysis and adjusts how and what learning content is presented. For example, if the user is feeling stressed, the server may lower the difficulty level or display encouraging messages.

[0200] Step 9:

[0201] Based on the evaluation results and the emotion engine's output, the server generates additional learning content and advice to reinforce the user's weaknesses. The generated content and advice are sent from the server to the device, which then provides it to the user.

[0202] Step 10:

[0203] After a user completes a learning session, they input a self-assessment and feedback. This feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. The server also generates advice to maintain and improve motivation based on the output of the emotion engine. For example, if the user is tired, it might suggest a short break.

[0204] Step 11:

[0205] The server generates an improved learning plan and saves it to the database. In the next learning session, the device provides this new learning plan to the user, thus repeating the learning cycle.

[0206] (Example 2)

[0207] 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".

[0208] In modern learning systems, providing learning content optimized for individual users is crucial, but many systems fail to take into account the user's emotional state. As a result, they cannot adequately manage the stress and fatigue users experience during learning, which can reduce learning effectiveness. Furthermore, they lack the ability to provide real-time, customized learning content based on the user's learning history and responses.

[0209] 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.

[0210] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice to the user based on the evaluation results, and means for detecting the user's emotional state from their facial expressions and voice and adjusting the learning content based on the detection results. This makes it possible to maximize the user's learning effectiveness and appropriately manage stress and fatigue during learning.

[0211] A "user" refers to an individual user who uses the system to learn.

[0212] "Learning history" refers to a record of the learning activities a user has undertaken so far.

[0213] "Natural language generation technology" refers to artificial intelligence technology used to generate human language.

[0214] "Learning content" refers to information such as learning materials, problems, and explanations provided to users for learning purposes.

[0215] "Reactions" refer to the answers, actions, and facial expressions that users show in response to learning content.

[0216] "Comprehension level" refers to an indicator that evaluates how well a user understands the learning material.

[0217] "Progress" refers to an indicator that shows the degree to which a user's learning is progressing.

[0218] "Additional learning content" refers to learning materials that are newly provided based on the user's understanding and progress.

[0219] "Advice" refers to suggestions and suggestions for effectively advancing a user's learning.

[0220] "Facial expressions" refer to the expressions on the user's face. It is one way of understanding the emotional state during the learning process.

[0221] "Voice data" refers to data collected from the user's speech and voice. This is also one way to understand the user's emotional state.

[0222] An "emotion engine" refers to artificial intelligence technology that analyzes facial expressions and voice data to identify a user's emotional state.

[0223] A "database" refers to a system for storing collected information.

[0224] As an embodiment for carrying out the present invention, a specific program processing that combines an emotion engine with a learning support AI system will be described. This system supports users in efficiently and effectively advancing their learning, and consists of a server, a terminal, and a user.

[0225] Hardware and software usage

[0226] server

[0227] Database management systems (e.g., MySQL, PostgreSQL)

[0228] Natural language generation technology (e.g. GPT-3)

[0229] Emotion engine (e.g., Affectiva's SDK)

[0230] terminal

[0231] A web browser or mobile app to retrieve your learning history.

[0232] Camera and microphone

[0233] Display for showing learning content

[0234] User

[0235] PCs and mobile devices with an internet connection

[0236] Program processing

[0237] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. Subsequently, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[0238] When a user logs in and starts a learning session, the device tracks the user's learning activity in real time and sends learning history data to the server. The server uses the data stored in the database to perform analysis and generates individually customized learning content using natural language generation technology.

[0239] The generated learning content is sent from the server to the device, and the device provides that content to the user. As the user progresses through the learning process using the provided content, the device monitors the user's responses, recording, for example, the results of each question and the time taken to answer them. This data is also sent to the server and evaluated. The server analyzes the user's understanding and progress, and generates additional learning content or advice as needed, providing it to the user via the device.

[0240] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state (for example, whether they are enjoying themselves or feeling stressed). This information is sent to the server and used to adjust the pace and content of the learning material.

[0241] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, it generates advice to maintain and improve the user's motivation; for example, it suggests a short break if the user is tired, or offers additional challenges if they are focused.

[0242] Specific example

[0243] For example, consider a case where User C, a second-year high school student, is studying quadratic equations in mathematics. After User C logs in, they start a learning session, and the system identifies their weaknesses from their past learning history data. The server generates specific practice problems and explanations and provides them to User C via the terminal. When User C solves the problems, the terminal records the solution and the time taken to solve them and sends it to the server. The server evaluates the data and provides additional practice problems or explanatory videos. In the process, an emotion engine identifies User C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks.

[0244] Example of a prompt

[0245] "A user starts a learning session. Explain how the user's device tracks their learning activity in real time and sends learning history data to the server."

[0246] By inputting this prompt into the generating AI model, it explains how the system tracks the user's learning activity and sends data to the server.

[0247] Based on the above explanation, you should be able to understand the specific programming processes of the learning support AI system and the emotion engine.

[0248] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0249] Step 1:

[0250] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal.

[0251] Input: Name, grade level, subjects of interest

[0252] Terminal: Sends input information to the server.

[0253] Output: Sending initial setup information

[0254] Step 2:

[0255] The server saves the initial configuration information it receives to the database.

[0256] Input: Initial setup information

[0257] Server: Performs data processing to store information in a database.

[0258] Output: Saving information to the database

[0259] Step 3:

[0260] Users set their learning goals and schedules from their devices.

[0261] Input: Learning objectives, schedule

[0262] Terminal: Sends configuration information to the server.

[0263] Output: Submit learning goals and schedule

[0264] Step 4:

[0265] The server generates an initial learning plan based on the information it receives.

[0266] Input: Learning objectives, schedule

[0267] Server: Performs data calculations to generate learning plans and saves them to the database.

[0268] Output: Generation and saving of the initial training plan

[0269] Step 5:

[0270] The user logs in and starts a learning session.

[0271] Input: Login information (ID, password)

[0272] Terminal: Displays the learning screen and monitors user actions in real time.

[0273] Output: Start of learning session

[0274] Step 6:

[0275] The device tracks the user's learning activity in real time and sends learning history data to the server.

[0276] Input: Learning activity data (answer results, operation history, etc.)

[0277] Terminal: Collects data and sends it to the server.

[0278] Output: Sending learning history data

[0279] Step 7:

[0280] The server saves the learning history data in the database and analyzes the strengths and weaknesses of the user.

[0281] Input: Learning history data

[0282] Server: Save in the database and perform data analysis.

[0283] Output: Identification of strengths and weaknesses

[0284] Step 8:

[0285] The server generates customized learning content using natural language generation technology.

[0286] Input: Analysis results (strengths and weaknesses)

[0287] Server: Generate learning content using natural language generation technology.

[0288] Output: Generation of customized learning content

[0289] Step 9:

[0290] The terminal provides the generated learning content to the user.

[0291] Input: Learning content

[0292] Terminal: Display the learning content.

[0293] Output: Provision of learning content

[0294] Step 10:

[0295] The user proceeds with learning using the content.

[0296] Input: Learning content

[0297] User: Proceed with learning.

[0298] Output: Progress of learning

[0299] Step 11:

[0300] The terminal monitors the user's reaction and records the answer result and answer time.

[0301] Input: User's reaction (answer result, answer time)

[0302] Terminal: Record the data and send it to the server.

[0303] Output: Transmission of reaction data

[0304] Step 12:

[0305] The server evaluates the user's understanding level and progress based on the data.

[0306] Input: Reaction data

[0307] Server: Perform data analysis and evaluate the understanding level and progress.

[0308] Output: Evaluation result

[0309] Step 13:

[0310] The server generates additional learning content and advice as needed and provides them to the user via the terminal.

[0311] Input: Evaluation result

[0312] Server: Generate additional learning content and advice.

[0313] Output: Additional learning content and advice

[0314] Step 14:

[0315] The device provides users with additional content and advice that it generates.

[0316] Input: Additional learning content or advice

[0317] Terminal: Display it.

[0318] Output: Providing additional content and advice

[0319] Step 15:

[0320] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[0321] Input: Facial expressions and voice data

[0322] Terminal: Acquires data and sends it to the emotion engine.

[0323] Output: Sending emotion data

[0324] Step 16:

[0325] The emotion engine analyzes the data and identifies the user's emotional state.

[0326] Input: Facial expressions and voice data

[0327] Emotion Engine: Performs data analysis.

[0328] Output: Analysis results of emotional state

[0329] Step 17:

[0330] The emotion engine sends the analysis results to the server.

[0331] Input: Analysis results of emotional state

[0332] Emotion engine: Sends results to the server.

[0333] Output: Sending results to the server

[0334] Step 18:

[0335] The server adjusts the learning content according to the user's emotional state and sends it to the device.

[0336] Input: Analysis results of emotional state

[0337] Server: Adjusts learning content.

[0338] Output: Sending adjusted learning content

[0339] Step 19:

[0340] The device provides users with optimized learning content.

[0341] Input: Adjusted learning content

[0342] Terminal: Display it.

[0343] Output: Provision of tailored learning content

[0344] Step 20:

[0345] Users enter their self-assessments and feedback.

[0346] Input: Self-assessment, feedback

[0347] User: Enter that.

[0348] Output: Self-assessment, feedback input

[0349] Step 21:

[0350] The device sends feedback data to the server.

[0351] Input: Self-assessment, feedback

[0352] Terminal: Sends it to the server.

[0353] Output: Sending feedback data

[0354] Step 22:

[0355] The server analyzes the feedback it receives and incorporates it into the next learning plan.

[0356] Input: Feedback data

[0357] Server: Performs data analysis.

[0358] Output: How to incorporate this into the next learning plan.

[0359] Step 23:

[0360] The server generates and sends advice to the terminal based on the output of the emotion engine, aiming to maintain and improve the user's motivation.

[0361] Input: Emotion Engine Output

[0362] Server: Generates advice.

[0363] Output: Send advice

[0364] Step 24:

[0365] The device presents the generated advice to the user.

[0366] Input: Advice

[0367] Terminal: Display it.

[0368] Output: Providing advice

[0369] (Application Example 2)

[0370] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0371] Traditional learning support systems offer customization based on users' learning history and comprehension levels, but they lack support that considers the user's emotional state. Therefore, when users experience stress or decreased motivation, appropriate support is not provided, resulting in a failure to maximize learning effectiveness. Similarly, in factory settings, there is a lack of real-time support that considers the emotional state of workers, hindering sufficient improvements in work efficiency.

[0372] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0373] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice based on the evaluation results, means for detecting the user's emotional state and adjusting the presentation method and content of the learning content based on the emotional state, and means for generating advice for maintaining and improving the user's motivation based on an emotion engine. This enables the provision of individually optimized learning experiences and support that take into account the user's emotional state and motivation, maximizing learning effectiveness and improving work efficiency.

[0374] "Learning history" refers to a record of the learning activities a user has undertaken so far, and includes data such as the content of specific learning sessions, study time, and the results of answering questions.

[0375] "Natural language generation technology" is a technology that automatically generates personalized text based on collected data, and it is a technology that uses AI models to create text.

[0376] "Learning content" refers to a series of digital information provided to users for learning purposes, such as textbooks, workbooks, and explanatory videos.

[0377] "User response" refers to performance data such as user behavior, answer results, and answer time in relation to learning content, and can also include emotional data such as facial expressions and voice.

[0378] An "emotion engine" is an artificial intelligence technology that analyzes biometric data such as a user's facial expressions and voice to detect their emotional state.

[0379] "Advice for maintaining and improving motivation" refers to specific suggestions and instructions that provide motivation and encouragement for users to continue learning or working.

[0380] A "learning plan" is a schedule that outlines the learning methods and content recommended by the system, based on the learning goals and schedule set by the user.

[0381] "Feedback" refers to opinions and evaluations provided by users to a system, including opinions on the quality of learning content and user experience.

[0382] "User emotional state" refers to data that represents the type and intensity of emotions a user experiences while learning or working, and includes emotions such as joy, sadness, stress, and concentration.

[0383] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[0384] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[0385] Next, the user logs in and starts a learning session. The device tracks the user's learning activity and emotional state in real time and sends learning history data and emotional data to the server. The server stores this data in a database and records it as learning history. The server also analyzes the collected learning history data and generates customized learning content using a generative AI model. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[0386] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress through the learning process. For example, the device displays specific practice problems and explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[0387] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device uses its camera to capture the user's facial expressions and voice data, which are then sent to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust how learning content is presented and what it entails. For example, if the user is feeling stressed, a short break may be suggested, while if they are focused, additional challenges may be offered.

[0388] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Furthermore, based on the emotion engine's output, advice is generated to maintain and improve the user's motivation. For example, the following are examples of prompt messages:

[0389] "Worker ID: 12345

[0390] Stress level detection: 90%

[0391] Proposed action: Take a 10-minute break.

[0392] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The user accesses the system and registers a new account.

[0396] Input: Initial information such as user name, grade level, and subjects of interest.

[0397] Specific operation: The user enters initial setup information via the terminal and sends it to the server.

[0398] Data processing: The server saves the received initial configuration information to the database.

[0399] Output: Saved user default settings information

[0400] Step 2:

[0401] Users set their learning goals and schedules.

[0402] Input: Learning objectives, learning schedule

[0403] Specific operation: The user inputs learning goals and study schedules via their device and sends them to the server.

[0404] Data processing: The server stores this information in a database and generates an initial training plan.

[0405] Output: Generated initial training plan

[0406] Step 3:

[0407] The user logs in and starts a learning session.

[0408] Input: Login information, instructions for starting the learning program.

[0409] Specific operation: The user logs in via their device and starts a learning session.

[0410] Data processing: The server tracks the user's learning history and emotional state in real time.

[0411] Output: Collected learning history data and sentiment data

[0412] Step 4:

[0413] The collected learning history and sentiment data are sent to the server.

[0414] Input: Learning history data, sentiment data

[0415] Specific operation: The device sends learning history data and sentiment data collected in real time to the server.

[0416] Data processing: The server receives this data and stores it in the database.

[0417] Output: Saved learning history data and sentiment data

[0418] Step 5:

[0419] The server generates customized learning content using the generated AI model.

[0420] Input: Stored learning history data and sentiment data

[0421] Specific operation: The server retrieves learning history data and sentiment data from the database and generates optimized learning content using a generative AI model.

[0422] Data processing: Based on this data, the server creates learning content using natural language generation technology.

[0423] Output: Generated customized learning content

[0424] Step 6:

[0425] Provide the generated learning content to the user.

[0426] Input: Generated learning content

[0427] Specific operation: The server sends the generated learning content to the device, and the device displays it to the user.

[0428] Data output: Learning content provided to the user

[0429] Step 7:

[0430] Monitor user responses and evaluate user understanding and progress based on those responses.

[0431] Input: User's answer result, answer time, facial expression, audio data

[0432] Specific operation: The device records the user's responses in real time and sends that data to the server.

[0433] Data processing: The server analyzes the received data and evaluates the user's understanding and progress.

[0434] Output: Evaluation results

[0435] Step 8:

[0436] Based on the evaluation results, additional learning content and advice are generated and provided to the user.

[0437] Input: Evaluation result

[0438] Specific operation: Based on the evaluation results, the server generates additional learning content and appropriate advice and sends it to the terminal. The terminal then displays this to the user.

[0439] Output: Additional learning content, advice

[0440] Step 9:

[0441] The system detects the user's emotional state and adjusts the presentation method and content of learning materials based on that state.

[0442] Input: User facial expression data, voice data

[0443] Specific operation: The device uses its camera and microphone to capture facial expressions and voice, and sends them to the emotion engine. The server adjusts how the learning content is presented based on the results obtained from the emotion engine.

[0444] Data processing: The emotion engine analyzes facial expressions and voice data to identify the emotional state.

[0445] Output: Adjusted learning content presentation method

[0446] Step 10:

[0447] We collect user feedback to improve future learning plans and content.

[0448] Input: User feedback

[0449] Specific operation: After the learning session ends, the user enters a self-assessment and feedback, and the device sends this data to the server.

[0450] Data processing: The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[0451] Output: Improved learning plan and learning content

[0452] 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.

[0453] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0454] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0455] [Second Embodiment]

[0456] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0457] 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.

[0458] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0459] The 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.

[0460] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0461] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0462] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0463] Figure 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.

[0464] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0465] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0466] In the 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.

[0467] 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".

[0468] As an embodiment for carrying out the present invention, the specific program processing of the learning support AI system is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[0469] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their own learning goals and schedule, and this information is also sent to the server via the terminal.

[0470] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as the learning history.

[0471] The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. The generated learning content is provided to the user via the device. The user then uses the provided content to proceed with their learning.

[0472] The device monitors the user's responses, recording, for example, the answer result and time taken for each question. This data is sent to a server, which evaluates the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[0473] After completing a lesson, users can enter self-assessments and feedback. The feedback data is sent to a server via the device, which analyzes it to improve future learning plans and content.

[0474] As a concrete example, consider the case of user B, a second-year high school student, studying mathematics. After logging in, user B begins studying "quadratic equations." The system identifies that user B struggles with "quadratic equations" based on past learning history data. The server provides user B with specific practice problems and explanations via the terminal. When user B solves the problems, the terminal records the answer and sends it to the server. The server evaluates user B's answer and time taken, and provides additional practice problems or explanatory videos as needed.

[0475] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[0476] The following describes the processing flow.

[0477] Step 1:

[0478] The user accesses the AI ​​learning support system and registers. Specifically, the user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in a database.

[0479] Step 2:

[0480] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[0481] Step 3:

[0482] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[0483] Step 4:

[0484] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[0485] Step 5:

[0486] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[0487] Step 6:

[0488] The device monitors the user's responses, recording, for example, the answer result and the time taken to answer each question. This data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[0489] Step 7:

[0490] Based on the evaluation results, the server generates additional learning content and advice to reinforce the user's weaknesses. For example, it might generate additional practice problems or detailed explanations for specific areas. The generated content and advice are sent from the server to the terminal, which then provides it to the user.

[0491] Step 8:

[0492] After a user completes a learning session, they enter a self-assessment and feedback. This feedback data is sent from the device to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[0493] Step 9:

[0494] The server generates an improved learning plan and saves it to the database. In the next learning session, the terminal provides this new learning plan to the user, thus repeating the learning cycle.

[0495] (Example 1)

[0496] 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."

[0497] Conventional learning support systems have struggled to appropriately reflect users' learning history and comprehension levels, and to provide individually optimized learning content. Furthermore, they lacked the functionality to effectively utilize user feedback and continuously improve learning plans. As a result, learning effectiveness was limited, and it was difficult to maintain users' motivation to learn.

[0498] 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.

[0499] In this invention, the server includes means for receiving user initial setup information and generating an initial learning plan; means for collecting the user's learning history; means for generating customized learning content using natural language generation technology based on the collected learning history; means for providing the generated learning content to the user; means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response; means for generating and providing additional learning content and advice based on the evaluation results; means for collecting user feedback and improving the next learning plan and learning content based on the feedback; means for tracking learning activities in real time when the user starts learning activities and collecting that data; and means for generating prompt sentences for a generation AI model and generating customized learning content based on the collected user learning history data. This makes it possible to provide a learning experience that is individually optimized for each user, continuously improve learning plans and content, and maximize learning effectiveness.

[0500] "User initial information" refers to the information a user enters when they first access the system, and includes personal information and basic learning-related information such as name, grade level, subjects of interest, and learning goals.

[0501] An "initial learning plan" refers to a plan generated by the server based on the user's initial settings, designed to help the user efficiently begin learning.

[0502] "Learning history" refers to data collected when a user engages in learning activities using the system, such as records of activities, learning progress, and grades.

[0503] "Natural language generation technology" refers to the technology of generating natural language using artificial intelligence. Specifically, it refers to the technology of generating texts, explanations, questions, etc., using AI models.

[0504] "Customized learning content" refers to learning materials, questions, and explanations that are optimized for a specific user based on their learning history and level of understanding.

[0505] "User response" refers to the results of user actions and inputs regarding learning content, specifically data such as answer results, response time, and operation logs.

[0506] "Comprehension level" refers to an indicator that evaluates how well a user understands a particular learning topic.

[0507] "Progress" refers to an indicator that shows how far a user has progressed according to their learning plan.

[0508] "Feedback" refers to information provided by users, such as evaluations, opinions, and suggestions for improvement regarding learning content and the system as a whole.

[0509] "Real-time tracking" refers to the process of instantly recording a user's learning activities and sending the data to the server in real time as they occur.

[0510] A "generative AI model" refers to an algorithm or software that uses an artificial intelligence model to generate learning content and prompt sentences.

[0511] A "prompt sentence" refers to an instruction or question given to a generative AI model, which serves as the basis for the AI ​​to generate output.

[0512] As an embodiment of the present invention, a learning support AI system is provided to enable users to learn efficiently and effectively. The learning support AI system mainly consists of a server, a terminal, and a user.

[0513] First, the user accesses the system via a terminal and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal, and the terminal sends this information to the server. The server stores the received information in a database and generates an initial learning plan. In this process, the database and server can use commonly used computer and server-related software (e.g., MySQL, Apache).

[0514] Next, the user logs back into the system and sets their learning goals and schedule. The terminal sends the entered data to the server, which then stores it in the database.

[0515] When a user starts a learning session, the device tracks their learning activity in real time and sends that data to the server. The server then records the user's learning history in a database.

[0516] Based on learning history data, the server generates customized learning content using natural language generation technology. For example, the GPT-4 AI model is used for generation. The generated learning content is provided to the user via a terminal. While the user progresses through the learning process, the terminal monitors the user's responses (e.g., answers to each question and response time) and sends this data to the server.

[0517] The server evaluates the user's understanding and progress based on user response data. Based on the evaluation results, the server further generates additional learning content and advice using natural language generation technology and provides it to the user via the device.

[0518] Furthermore, after completing a lesson, users input self-assessments and feedback into their device, and the device sends this feedback data to a server. The server analyzes the feedback and uses it to improve future learning plans and learning content.

[0519] As a concrete example, consider the case of User B, a second-year high school student, who is studying "quadratic equations" in mathematics. After logging in, User B begins learning. The server identifies User B's weaknesses from their past learning history and uses a generative AI model (e.g., GPT-4) to generate specific practice problems and explanations. This generated content is provided to User B through their device. When User B solves a problem, the device records the answer and sends it to the server. The server evaluates this data and provides additional practice problems or explanatory videos as needed.

[0520] An example of a prompt message would be: "When user B, a second-year high school student, is solving practice problems on quadratic equations, identify user B's weak areas and generate customized practice problems based on those areas."

[0521] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[0522] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0523] Step 1:

[0524] The user accesses the system and registers. The terminal receives initial information from the user, such as name, grade level, and subjects of interest. The terminal sends this information to the server. The server stores the received information in its database. Specifically, when the user clicks the "Register" button, an HTTP POST request is sent from the terminal to the server, which receives it and stores it in the database.

[0525] Step 2:

[0526] The user logs into the system and sets their learning goals and schedule. The terminal receives the user's input (learning goals and schedule) and sends it to the server. The server saves this data to a database. Specifically, when the user clicks the "Save" button, data in JSON format is sent from the terminal to the server, which parses it and saves it to the database.

[0527] Step 3:

[0528] The user starts a learning session. The device records the start time of the learning session and sends activity data during the learning session (such as answers to questions and typing speed) to the server in real time. The server receives the learning start signal and activity data during the learning session as input from the device and continuously records this in its database. Specifically, when the user clicks the "Start Learning" button, the device records the current time and periodically sends activity data to the server.

[0529] Step 4:

[0530] The server generates customized learning content based on the collected learning history. Using the collected learning history data as input, the server sends prompts to a generative AI model (e.g., GPT-4) to generate content. The generated content is sent to the terminal and provided to the user. Specifically, the server periodically checks the database, and if there is any unprocessed learning history data, it uses the generative AI model to generate custom content and sends it to the terminal.

[0531] Step 5:

[0532] The device monitors the user's responses and records the answer and response time for each question. It receives user response data as input and sends it to the server. The server evaluates the user's understanding and progress based on this data. Specifically, each time the user answers a question, the device records the result and response time and sends it to the server. The server analyzes this data and stores the evaluation results in a database.

[0533] Step 6:

[0534] The server generates additional learning content and advice based on the evaluation results. Using the evaluation results as input, the server sends prompts to the generating AI model, which then generates customized content and advice. The generated content is sent to the terminal and provided to the user. Specifically, the server sends new prompts to the generating AI model based on the evaluation results, generates additional content, and sends it to the terminal for the user to receive.

[0535] Step 7:

[0536] After completing a lesson, the user enters their self-assessment and feedback into the device. The device sends the entered data to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content. Specifically, when the user fills out and submits the feedback form, the data is sent from the device to the server, which analyzes the feedback and makes updates to reflect it in the next learning session.

[0537] (Application Example 1)

[0538] 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."

[0539] Traditional shopping experiences often fail to provide appropriate recommendations to increase user purchasing intent, and finding products in stores is inconvenient. On the other hand, there is no system that accurately understands user preferences and purchasing behavior and provides optimal recommendations and navigation based on that information. This results in a lack of personalized shopping experiences and hinders efficient purchasing.

[0540] 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.

[0541] In this invention, the server includes means for collecting user behavior history, means for generating customized recommendation content using a generation AI model based on the collected behavior history, means for providing the generated recommendation content to the user, means for monitoring the user's reaction to the provided recommendation content and evaluating the user's level of interest and purchase intent based on the reaction, and means for generating and providing additional recommendation content and advice to the user based on the evaluation results. This enables a shopping experience that is individually optimized for each user.

[0542] "User behavior history" refers to data about a user's series of purchasing activities, their movement within a store, and the products they viewed.

[0543] A "generative AI model" is an algorithm or program that uses machine learning and deep learning techniques to generate appropriate recommendation content from data.

[0544] "Customized recommendation content" refers to recommendations for products and services that are optimized for a user based on their individual preferences and behavioral history.

[0545] "User responses to recommended content" refer to actions and evaluations that users show towards the recommended products or services, such as click-through rates and purchase behavior.

[0546] "Methods for evaluating user interest and purchasing intent" refer to technologies and methods for analyzing collected user response data and quantitatively evaluating how interested a user is in a product or service.

[0547] "Initial setup information" refers to basic information that users enter when they start using the system, such as name, age, gender, and product categories of interest.

[0548] "Feedback" refers to evaluations and opinions that users provide to the system, such as comments on the shopping experience or reactions to recommended content.

[0549] "Additional recommended content and advice" refers to recommendations for products and services created based on user interest and purchase intent evaluations, as well as suggestions and advice given to users.

[0550] As an embodiment of this invention, a system for improving the shopping experience in physical stores will be specifically described. This system consists of a server, a terminal (mainly a smartphone), and a user.

[0551] Program operation

[0552] Means of collecting user behavior history

[0553] Once a user installs the application and begins browsing within a store, location data is collected using the smartphone's GPS and Wi-Fi information. The products the user views and purchases are also automatically tracked. This data is transmitted to a server in real time and stored in a database.

[0554] Means for generating customized recommendation content

[0555] The server uses a generative AI model to analyze the collected behavioral history data. The data is processed using machine learning frameworks such as TensorFlow, and optimal product recommendation content is created based on the user's preferences.

[0556] Means of providing recommended content to users

[0557] The generated recommendation content is notified to the user via their smartphone. The user can then open the application to view individually customized product recommendations.

[0558] A means of monitoring and evaluating user reactions.

[0559] All actions users take with recommended content (e.g., clicks and purchases) are sent from their devices to the server. This data is aggregated and analyzed on the server and used as an indicator to evaluate the user's level of interest and purchase intent.

[0560] A means of generating and providing additional recommended content and advice.

[0561] Based on the evaluation results, the server generates newly created recommendation content and advice. This additional information is also provided to the user via smartphone, further enhancing the shopping experience.

[0562] Hardware and software used for implementation

[0563] Hardware: Smartphones (Android / iOS), Servers

[0564] Software: Firebase (database management), TensorFlow (machine learning models), Google Maps API (in-store navigation)

[0565] Examples of specific cases and prompt statements

[0566] For example, if a user types "Tell me today's recommended products" on their smartphone while in a store, the application will notify them based on their purchase history, saying, "Today we recommend wireless earphones, which are on sale. They are located in area B of the store." Also, if a user types "Direct me to the battery section," detailed navigation from their current location to the battery section will be provided.

[0567] Examples of prompt statements:

[0568] Based on the user's purchase history, generate a list of recommended products for today.

[0569] Please guide the user through the store, from their current location to the shelf of the specified product.

[0570] As described above, this embodiment of the invention provides a system that enhances the user's shopping experience by offering personalized recommendation content in real time based on the user's daily behavior history.

[0571] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0572] Step 1:

[0573] The user installs the application and enters initial setup information. Initial setup information such as the user's name, age, gender, and product categories of interest is collected and sent from the device to the server. The server stores this initial setup information in a database and generates an initial recommendation plan.

[0574] Input: User's name, age, gender, product categories of interest

[0575] Data processing: The server receives this data and saves it to the database.

[0576] Output: Initial Recommended Plan

[0577] Step 2:

[0578] When a user visits a store and launches the application, the device tracks the user's current location. It obtains location information from the smartphone's GPS or Wi-Fi and sends that data to the server in real time.

[0579] Input: Smartphone GPS information, Wi-Fi information

[0580] Data processing: Collection and real-time transmission of location data.

[0581] Output: Location data stored on the server

[0582] Step 3:

[0583] The server generates customized recommendation content using an AI model based on user behavior history data. The collected behavior history data is analyzed using TensorFlow, and optimal product recommendations are created through a machine learning model.

[0584] Input: User activity history data

[0585] Data processing: Data analysis using machine learning models

[0586] Output: Customized recommendation content

[0587] Step 4:

[0588] The generated recommendation content is sent to the device and provided to the user through a smartphone application. The user reviews the recommendation content within the app and makes a purchasing decision.

[0589] Input: Customized recommendation content

[0590] Output: Recommended content notified to your smartphone

[0591] Step 5:

[0592] User responses (for example, the number of clicks on recommended products and actual purchase behavior) are sent from the device to the server. The server collects and stores this response data to evaluate the user's level of interest and purchase intent.

[0593] Input: User response data

[0594] Data processing: Collection and storage of reaction data

[0595] Output: Evaluation results of interest level and purchase intent

[0596] Step 6:

[0597] Based on the evaluation results, the server generates additional recommended content and advice. This is again done using a generative AI model and machine learning algorithm to produce the most optimal content.

[0598] Input: Evaluation result

[0599] Data processing: Generate new recommendation content based on evaluation results.

[0600] Output: Additional recommended content and advice

[0601] Step 7:

[0602] The newly generated additional recommendation content and advice are sent to the device and provided to the user via their smartphone. The user can then review this and take further purchasing action.

[0603] Input: Additional recommended content or advice

[0604] Output: Additional recommended content notified to your smartphone

[0605] As described above, this system collects, analyzes, and notifies data between users, devices, and servers to provide a personalized shopping experience.

[0606] 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.

[0607] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[0608] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[0609] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as learning history. The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is sent from the server to the device.

[0610] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress with their learning. For example, the device displays specific practice problems or explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[0611] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust the presentation method and content of learning materials.

[0612] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, advice is also generated to maintain and improve the user's motivation. For example, if the user is tired, a short break may be suggested, while if they are highly engaged, additional challenges may be offered.

[0613] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[0614] The following describes the processing flow.

[0615] Step 1:

[0616] The user accesses the AI ​​learning support system and registers. The user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in its database.

[0617] Step 2:

[0618] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[0619] Step 3:

[0620] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[0621] Step 4:

[0622] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. Data analysis is performed to identify the user's strengths and weaknesses, and the generated learning content is sent from the server to the terminal.

[0623] Step 5:

[0624] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[0625] Step 6:

[0626] The device monitors the user's responses. For example, it records the answer result and time taken to answer each question, and this data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[0627] Step 7:

[0628] During learning, the device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state. For example, it can determine whether the user is having fun or feeling stressed.

[0629] Step 8:

[0630] The server receives the results of the emotion engine's analysis and adjusts how and what learning content is presented. For example, if the user is feeling stressed, the server may lower the difficulty level or display encouraging messages.

[0631] Step 9:

[0632] Based on the evaluation results and the emotion engine's output, the server generates additional learning content and advice to reinforce the user's weaknesses. The generated content and advice are sent from the server to the device, which then provides it to the user.

[0633] Step 10:

[0634] After a user completes a learning session, they input a self-assessment and feedback. This feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. The server also generates advice to maintain and improve motivation based on the output of the emotion engine. For example, if the user is tired, it might suggest a short break.

[0635] Step 11:

[0636] The server generates an improved learning plan and saves it to the database. In the next learning session, the terminal provides this new learning plan to the user, thus repeating the learning cycle.

[0637] (Example 2)

[0638] 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".

[0639] In modern learning systems, providing learning content optimized for individual users is crucial, but many systems fail to take into account the user's emotional state. As a result, they cannot adequately manage the stress and fatigue users experience during learning, which can reduce learning effectiveness. Furthermore, they lack the ability to provide real-time, customized learning content based on the user's learning history and responses.

[0640] 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.

[0641] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice to the user based on the evaluation results, and means for detecting the user's emotional state from their facial expressions and voice and adjusting the learning content based on the detection results. This makes it possible to maximize the user's learning effectiveness and appropriately manage stress and fatigue during learning.

[0642] A "user" refers to an individual user who uses the system to learn.

[0643] "Learning history" refers to a record of the learning activities a user has undertaken so far.

[0644] "Natural language generation technology" refers to artificial intelligence technology used to generate human language.

[0645] "Learning content" refers to information such as learning materials, problems, and explanations provided to users for learning purposes.

[0646] "Reactions" refer to the answers, actions, and facial expressions that users show in response to learning content.

[0647] "Comprehension level" refers to an indicator that evaluates how well a user understands the learning material.

[0648] "Progress" refers to an indicator that shows the degree to which a user's learning is progressing.

[0649] "Additional learning content" refers to learning materials that are newly provided based on the user's understanding and progress.

[0650] "Advice" refers to suggestions and suggestions for effectively advancing a user's learning.

[0651] "Facial expressions" refer to the expressions on the user's face. It is one way of understanding the emotional state during the learning process.

[0652] "Voice data" refers to data collected from the user's speech and voice. This is also one way to understand the user's emotional state.

[0653] An "emotion engine" refers to artificial intelligence technology that analyzes facial expressions and voice data to identify a user's emotional state.

[0654] A "database" refers to a system for storing collected information.

[0655] As an embodiment for carrying out the present invention, a specific program processing that combines an emotion engine with a learning support AI system will be described. This system supports users in efficiently and effectively advancing their learning, and consists of a server, a terminal, and a user.

[0656] Hardware and software usage

[0657] server

[0658] Database management systems (e.g., MySQL, PostgreSQL)

[0659] Natural language generation technology (e.g. GPT-3)

[0660] Emotion engine (e.g., Affectiva's SDK)

[0661] terminal

[0662] A web browser or mobile app to retrieve your learning history.

[0663] Camera and microphone

[0664] Display for showing learning content

[0665] User

[0666] PCs and mobile devices with an internet connection

[0667] Program processing

[0668] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. Subsequently, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[0669] When a user logs in and starts a learning session, the device tracks the user's learning activity in real time and sends learning history data to the server. The server uses the data stored in the database to perform analysis and generates individually customized learning content using natural language generation technology.

[0670] The generated learning content is sent from the server to the device, and the device provides that content to the user. As the user progresses through the learning process using the provided content, the device monitors the user's responses, recording, for example, the results of each question and the time taken to answer them. This data is also sent to the server and evaluated. The server analyzes the user's understanding and progress, and generates additional learning content or advice as needed, providing it to the user via the device.

[0671] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state (for example, whether they are enjoying themselves or feeling stressed). This information is sent to the server and used to adjust the pace and content of the learning material.

[0672] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, it generates advice to maintain and improve the user's motivation; for example, it suggests a short break if the user is tired, or offers additional challenges if they are focused.

[0673] Specific example

[0674] For example, consider a case where User C, a second-year high school student, is studying quadratic equations in mathematics. After User C logs in, they start a learning session, and the system identifies their weaknesses from their past learning history data. The server generates specific practice problems and explanations and provides them to User C via the terminal. When User C solves the problems, the terminal records the solution and the time taken to solve them and sends it to the server. The server evaluates the data and provides additional practice problems or explanatory videos. In the process, an emotion engine identifies User C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks.

[0675] Example of a prompt

[0676] "A user starts a learning session. Explain how the user's device tracks their learning activity in real time and sends learning history data to the server."

[0677] By inputting this prompt into the generating AI model, it explains how the system tracks the user's learning activity and sends data to the server.

[0678] Based on the above explanation, you should be able to understand the specific programming processes of the learning support AI system and the emotion engine.

[0679] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0680] Step 1:

[0681] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal.

[0682] Input: Name, grade level, subjects of interest

[0683] Terminal: Sends input information to the server.

[0684] Output: Sending initial setup information

[0685] Step 2:

[0686] The server saves the initial configuration information it receives to the database.

[0687] Input: Initial setup information

[0688] Server: Performs data processing to store information in a database.

[0689] Output: Saving information to the database

[0690] Step 3:

[0691] Users set their learning goals and schedules from their devices.

[0692] Input: Learning objectives, schedule

[0693] Terminal: Sends configuration information to the server.

[0694] Output: Submit learning goals and schedule

[0695] Step 4:

[0696] The server generates an initial learning plan based on the information it receives.

[0697] Input: Learning objectives, schedule

[0698] Server: Performs data calculations to generate learning plans and saves them to the database.

[0699] Output: Generation and saving of the initial training plan

[0700] Step 5:

[0701] The user logs in and starts a learning session.

[0702] Input: Login information (ID, password)

[0703] Terminal: Displays the learning screen and monitors user actions in real time.

[0704] Output: Start of learning session

[0705] Step 6:

[0706] The device tracks the user's learning activity in real time and sends learning history data to the server.

[0707] Input: Learning activity data (answer results, operation history, etc.)

[0708] Terminal: Collects data and sends it to the server.

[0709] Output: Sending learning history data

[0710] Step 7:

[0711] The server stores learning history data in a database and analyzes the user's strengths and weaknesses.

[0712] Input: Learning history data

[0713] Server: Stores data in a database and performs data analysis.

[0714] Output: Identifying strengths and weaknesses

[0715] Step 8:

[0716] The server generates customized learning content using natural language generation technology.

[0717] Input: Analysis results (strengths and weaknesses)

[0718] Server: Generates learning content using natural language generation technology.

[0719] Output: Generation of customized learning content

[0720] Step 9:

[0721] The device provides the user with the generated learning content.

[0722] Input: Learning content

[0723] Device: Displays learning content.

[0724] Output: Provision of learning content

[0725] Step 10:

[0726] Users progress through their learning using the content.

[0727] Input: Learning content

[0728] User: Continue learning.

[0729] Output: Learning progress

[0730] Step 11:

[0731] The device monitors the user's responses and records the answer results and response time.

[0732] Input: User response (answer result, answer time)

[0733] Terminal: Records data and sends it to the server.

[0734] Output: Sending reaction data

[0735] Step 12:

[0736] The server evaluates the user's understanding and progress based on the data.

[0737] Input: Reaction data

[0738] Server: Performs data analysis and evaluates understanding and progress.

[0739] Output: Evaluation results

[0740] Step 13:

[0741] The server generates additional learning content and advice as needed and provides it to the user via the terminal.

[0742] Input: Evaluation result

[0743] Server: Generates additional learning content and advice.

[0744] Output: Additional learning content and advice

[0745] Step 14:

[0746] The device provides users with additional content and advice that it generates.

[0747] Input: Additional learning content or advice

[0748] Terminal: Display it.

[0749] Output: Providing additional content and advice

[0750] Step 15:

[0751] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[0752] Input: Facial expressions and voice data

[0753] Terminal: Acquires data and sends it to the emotion engine.

[0754] Output: Sending emotion data

[0755] Step 16:

[0756] The emotion engine analyzes the data and identifies the user's emotional state.

[0757] Input: Facial expressions and voice data

[0758] Emotion Engine: Performs data analysis.

[0759] Output: Analysis results of emotional state

[0760] Step 17:

[0761] The emotion engine sends the analysis results to the server.

[0762] Input: Analysis results of emotional state

[0763] Emotion engine: Sends results to the server.

[0764] Output: Sending results to the server

[0765] Step 18:

[0766] The server adjusts the learning content according to the user's emotional state and sends it to the device.

[0767] Input: Analysis results of emotional state

[0768] Server: Adjusts learning content.

[0769] Output: Sending adjusted learning content

[0770] Step 19:

[0771] The device provides users with optimized learning content.

[0772] Input: Adjusted learning content

[0773] Terminal: Display it.

[0774] Output: Provision of tailored learning content

[0775] Step 20:

[0776] Users enter their self-assessments and feedback.

[0777] Input: Self-assessment, feedback

[0778] User: Enter that.

[0779] Output: Self-assessment, feedback input

[0780] Step 21:

[0781] The device sends feedback data to the server.

[0782] Input: Self-assessment, feedback

[0783] Terminal: Sends it to the server.

[0784] Output: Sending feedback data

[0785] Step 22:

[0786] The server analyzes the feedback it receives and incorporates it into the next learning plan.

[0787] Input: Feedback data

[0788] Server: Performs data analysis.

[0789] Output: How to incorporate this into the next learning plan.

[0790] Step 23:

[0791] The server generates and sends advice to the terminal based on the output of the emotion engine, aiming to maintain and improve the user's motivation.

[0792] Input: Emotion Engine Output

[0793] Server: Generates advice.

[0794] Output: Send advice

[0795] Step 24:

[0796] The device presents the generated advice to the user.

[0797] Input: Advice

[0798] Terminal: Display it.

[0799] Output: Providing advice

[0800] (Application Example 2)

[0801] 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."

[0802] Traditional learning support systems offer customization based on users' learning history and comprehension levels, but they lack support that considers the user's emotional state. Therefore, when users experience stress or decreased motivation, appropriate support is not provided, resulting in a failure to maximize learning effectiveness. Similarly, in factory settings, there is a lack of real-time support that considers the emotional state of workers, hindering sufficient improvements in work efficiency.

[0803] 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.

[0804] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice based on the evaluation results, means for detecting the user's emotional state and adjusting the presentation method and content of the learning content based on the emotional state, and means for generating advice for maintaining and improving the user's motivation based on an emotion engine. This enables the provision of individually optimized learning experiences and support that take into account the user's emotional state and motivation, maximizing learning effectiveness and improving work efficiency.

[0805] "Learning history" refers to a record of the learning activities a user has undertaken so far, and includes data such as the content of specific learning sessions, study time, and the results of answering questions.

[0806] "Natural language generation technology" is a technology that automatically generates personalized text based on collected data, and it is a technology that uses AI models to create text.

[0807] "Learning content" refers to a series of digital information provided to users for learning purposes, such as textbooks, workbooks, and explanatory videos.

[0808] "User response" refers to performance data such as user behavior, answer results, and answer time in relation to learning content, and can also include emotional data such as facial expressions and voice.

[0809] An "emotion engine" is an artificial intelligence technology that analyzes biometric data such as a user's facial expressions and voice to detect their emotional state.

[0810] "Advice for maintaining and improving motivation" refers to specific suggestions and instructions that provide motivation and encouragement for users to continue learning or working.

[0811] A "learning plan" is a schedule that outlines the learning methods and content recommended by the system, based on the learning goals and schedule set by the user.

[0812] "Feedback" refers to opinions and evaluations provided by users to a system, including opinions on the quality of learning content and user experience.

[0813] "User emotional state" refers to data that represents the type and intensity of emotions a user experiences while learning or working, and includes emotions such as joy, sadness, stress, and concentration.

[0814] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[0815] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[0816] Next, the user logs in and starts a learning session. The device tracks the user's learning activity and emotional state in real time and sends learning history data and emotional data to the server. The server stores this data in a database and records it as learning history. The server also analyzes the collected learning history data and generates customized learning content using a generative AI model. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[0817] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress through the learning process. For example, the device displays specific practice problems and explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[0818] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device uses its camera to capture the user's facial expressions and voice data, which are then sent to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust how learning content is presented and what it entails. For example, if the user is feeling stressed, a short break may be suggested, while if they are focused, additional challenges may be offered.

[0819] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Furthermore, based on the emotion engine's output, advice is generated to maintain and improve the user's motivation. For example, the following are examples of prompt messages:

[0820] "Worker ID: 12345

[0821] Stress level detection: 90%

[0822] Proposed action: Take a 10-minute break.

[0823] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[0824] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0825] Step 1:

[0826] The user accesses the system and registers a new account.

[0827] Input: Initial information such as user name, grade level, and subjects of interest.

[0828] Specific operation: The user enters initial setup information via the terminal and sends it to the server.

[0829] Data processing: The server saves the received initial configuration information to the database.

[0830] Output: Saved user default settings information

[0831] Step 2:

[0832] Users set their learning goals and schedules.

[0833] Input: Learning objectives, learning schedule

[0834] Specific operation: The user inputs learning goals and study schedules via their device and sends them to the server.

[0835] Data processing: The server stores this information in a database and generates an initial training plan.

[0836] Output: Generated initial training plan

[0837] Step 3:

[0838] The user logs in and starts a learning session.

[0839] Input: Login information, instructions for starting the learning program.

[0840] Specific operation: The user logs in via their device and starts a learning session.

[0841] Data processing: The server tracks the user's learning history and emotional state in real time.

[0842] Output: Collected learning history data and sentiment data

[0843] Step 4:

[0844] The collected learning history and sentiment data are sent to the server.

[0845] Input: Learning history data, sentiment data

[0846] Specific operation: The device sends learning history data and sentiment data collected in real time to the server.

[0847] Data processing: The server receives this data and stores it in the database.

[0848] Output: Saved learning history data and sentiment data

[0849] Step 5:

[0850] The server generates customized learning content using the generated AI model.

[0851] Input: Stored learning history data and sentiment data

[0852] Specific operation: The server retrieves learning history data and sentiment data from the database and generates optimized learning content using a generative AI model.

[0853] Data processing: Based on this data, the server creates learning content using natural language generation technology.

[0854] Output: Generated customized learning content

[0855] Step 6:

[0856] Provide the generated learning content to the user.

[0857] Input: Generated learning content

[0858] Specific operation: The server sends the generated learning content to the device, and the device displays it to the user.

[0859] Data output: Learning content provided to the user

[0860] Step 7:

[0861] Monitor user responses and evaluate user understanding and progress based on those responses.

[0862] Input: User's answer result, answer time, facial expression, audio data

[0863] Specific operation: The device records the user's responses in real time and sends that data to the server.

[0864] Data processing: The server analyzes the received data and evaluates the user's understanding and progress.

[0865] Output: Evaluation results

[0866] Step 8:

[0867] Based on the evaluation results, additional learning content and advice are generated and provided to the user.

[0868] Input: Evaluation result

[0869] Specific operation: Based on the evaluation results, the server generates additional learning content and appropriate advice and sends it to the terminal. The terminal then displays this to the user.

[0870] Output: Additional learning content, advice

[0871] Step 9:

[0872] The system detects the user's emotional state and adjusts the presentation method and content of learning materials based on that state.

[0873] Input: User facial expression data, voice data

[0874] Specific operation: The device uses its camera and microphone to capture facial expressions and voice, and sends them to the emotion engine. The server adjusts how the learning content is presented based on the results obtained from the emotion engine.

[0875] Data processing: The emotion engine analyzes facial expressions and voice data to identify the emotional state.

[0876] Output: Adjusted learning content presentation method

[0877] Step 10:

[0878] We collect user feedback to improve future learning plans and content.

[0879] Input: User feedback

[0880] Specific operation: After the learning session ends, the user enters a self-assessment and feedback, and the device sends this data to the server.

[0881] Data processing: The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[0882] Output: Improved learning plan and learning content

[0883] 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.

[0884] 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.

[0885] 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.

[0886] [Third Embodiment]

[0887] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0888] 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.

[0889] 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).

[0890] 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.

[0891] 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.

[0892] 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).

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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".

[0899] As an embodiment for carrying out the present invention, the specific program processing of the learning support AI system is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[0900] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their own learning goals and schedule, and this information is also sent to the server via the terminal.

[0901] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as the learning history.

[0902] The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. The generated learning content is provided to the user via the device. The user then uses the provided content to proceed with their learning.

[0903] The device monitors the user's responses, recording, for example, the answer result and time taken for each question. This data is sent to a server, which evaluates the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[0904] After completing a lesson, users can enter self-assessments and feedback. The feedback data is sent to a server via the device, which analyzes it to improve future learning plans and content.

[0905] As a concrete example, consider the case of user B, a second-year high school student, studying mathematics. After logging in, user B begins studying "quadratic equations." The system identifies that user B struggles with "quadratic equations" based on past learning history data. The server provides user B with specific practice problems and explanations via the terminal. When user B solves the problems, the terminal records the answer and sends it to the server. The server evaluates user B's answer and time taken, and provides additional practice problems or explanatory videos as needed.

[0906] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[0907] The following describes the processing flow.

[0908] Step 1:

[0909] The user accesses the AI ​​learning support system and registers. Specifically, the user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in a database.

[0910] Step 2:

[0911] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[0912] Step 3:

[0913] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[0914] Step 4:

[0915] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[0916] Step 5:

[0917] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[0918] Step 6:

[0919] The device monitors the user's responses, recording, for example, the answer result and the time taken to answer each question. This data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[0920] Step 7:

[0921] Based on the evaluation results, the server generates additional learning content and advice to reinforce the user's weaknesses. For example, it might generate additional practice problems or detailed explanations for specific areas. The generated content and advice are sent from the server to the terminal, which then provides it to the user.

[0922] Step 8:

[0923] After a user completes a learning session, they enter a self-assessment and feedback. This feedback data is sent from the device to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[0924] Step 9:

[0925] The server generates an improved learning plan and saves it to the database. In the next learning session, the terminal provides this new learning plan to the user, thus repeating the learning cycle.

[0926] (Example 1)

[0927] 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."

[0928] Conventional learning support systems have struggled to appropriately reflect users' learning history and comprehension levels, and to provide individually optimized learning content. Furthermore, they lacked the functionality to effectively utilize user feedback and continuously improve learning plans. As a result, learning effectiveness was limited, and it was difficult to maintain users' motivation to learn.

[0929] 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.

[0930] In this invention, the server includes means for receiving user initial setup information and generating an initial learning plan; means for collecting the user's learning history; means for generating customized learning content using natural language generation technology based on the collected learning history; means for providing the generated learning content to the user; means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response; means for generating and providing additional learning content and advice based on the evaluation results; means for collecting user feedback and improving the next learning plan and learning content based on the feedback; means for tracking learning activities in real time when the user starts learning activities and collecting that data; and means for generating prompt sentences for a generation AI model and generating customized learning content based on the collected user learning history data. This makes it possible to provide a learning experience that is individually optimized for each user, continuously improve learning plans and content, and maximize learning effectiveness.

[0931] "User initial information" refers to the information a user enters when they first access the system, and includes personal information and basic learning-related information such as name, grade level, subjects of interest, and learning goals.

[0932] An "initial learning plan" refers to a plan generated by the server based on the user's initial settings, designed to help the user efficiently begin learning.

[0933] "Learning history" refers to data collected when a user engages in learning activities using the system, such as records of activities, learning progress, and grades.

[0934] "Natural language generation technology" refers to the technology of generating natural language using artificial intelligence. Specifically, it refers to the technology of generating texts, explanations, questions, etc., using AI models.

[0935] "Customized learning content" refers to learning materials, questions, and explanations that are optimized for a specific user based on their learning history and level of understanding.

[0936] "User response" refers to the results of user actions and inputs regarding learning content, specifically data such as answer results, response time, and operation logs.

[0937] "Comprehension level" refers to an indicator that evaluates how well a user understands a particular learning topic.

[0938] "Progress" refers to an indicator that shows how far a user has progressed according to their learning plan.

[0939] "Feedback" refers to information provided by users, such as evaluations, opinions, and suggestions for improvement regarding learning content and the system as a whole.

[0940] "Real-time tracking" refers to the process of instantly recording a user's learning activities and sending the data to the server in real time as they occur.

[0941] A "generative AI model" refers to an algorithm or software that uses an artificial intelligence model to generate learning content and prompt sentences.

[0942] A "prompt sentence" refers to an instruction or question given to a generative AI model, which serves as the basis for the AI ​​to generate output.

[0943] As an embodiment of the present invention, a learning support AI system is provided to enable users to learn efficiently and effectively. The learning support AI system mainly consists of a server, a terminal, and a user.

[0944] First, the user accesses the system via a terminal and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal, and the terminal sends this information to the server. The server stores the received information in a database and generates an initial learning plan. In this process, the database and server can use commonly used computer and server-related software (e.g., MySQL, Apache).

[0945] Next, the user logs back into the system and sets their learning goals and schedule. The terminal sends the entered data to the server, which then stores it in the database.

[0946] When a user starts a learning session, the device tracks their learning activity in real time and sends that data to the server. The server then records the user's learning history in a database.

[0947] Based on learning history data, the server generates customized learning content using natural language generation technology. For example, the GPT-4 AI model is used for generation. The generated learning content is provided to the user via a terminal. While the user progresses through the learning process, the terminal monitors the user's responses (e.g., answers to each question and response time) and sends this data to the server.

[0948] The server evaluates the user's understanding and progress based on user response data. Based on the evaluation results, the server further generates additional learning content and advice using natural language generation technology and provides it to the user via the device.

[0949] Furthermore, after completing a lesson, users input self-assessments and feedback into their device, and the device sends this feedback data to a server. The server analyzes the feedback and uses it to improve future learning plans and learning content.

[0950] As a concrete example, consider the case of User B, a second-year high school student, who is studying "quadratic equations" in mathematics. After logging in, User B begins learning. The server identifies User B's weaknesses from their past learning history and uses a generative AI model (e.g., GPT-4) to generate specific practice problems and explanations. This generated content is provided to User B through their device. When User B solves a problem, the device records the answer and sends it to the server. The server evaluates this data and provides additional practice problems or explanatory videos as needed.

[0951] An example of a prompt message would be: "When user B, a second-year high school student, is solving practice problems on quadratic equations, identify user B's weak areas and generate customized practice problems based on those areas."

[0952] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[0953] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0954] Step 1:

[0955] The user accesses the system and registers. The terminal receives initial information from the user, such as name, grade level, and subjects of interest. The terminal sends this information to the server. The server stores the received information in its database. Specifically, when the user clicks the "Register" button, an HTTP POST request is sent from the terminal to the server, which receives it and stores it in the database.

[0956] Step 2:

[0957] The user logs into the system and sets their learning goals and schedule. The terminal receives the user's input (learning goals and schedule) and sends it to the server. The server saves this data to a database. Specifically, when the user clicks the "Save" button, data in JSON format is sent from the terminal to the server, which parses it and saves it to the database.

[0958] Step 3:

[0959] The user starts a learning session. The device records the start time of the learning session and sends activity data during the learning session (such as answers to questions and typing speed) to the server in real time. The server receives the learning start signal and activity data during the learning session as input from the device and continuously records this in its database. Specifically, when the user clicks the "Start Learning" button, the device records the current time and periodically sends activity data to the server.

[0960] Step 4:

[0961] The server generates customized learning content based on the collected learning history. Using the collected learning history data as input, the server sends prompts to a generative AI model (e.g., GPT-4) to generate content. The generated content is sent to the terminal and provided to the user. Specifically, the server periodically checks the database, and if there is any unprocessed learning history data, it uses the generative AI model to generate custom content and sends it to the terminal.

[0962] Step 5:

[0963] The device monitors the user's responses and records the answer and response time for each question. It receives user response data as input and sends it to the server. The server evaluates the user's understanding and progress based on this data. Specifically, each time the user answers a question, the device records the result and response time and sends it to the server. The server analyzes this data and stores the evaluation results in a database.

[0964] Step 6:

[0965] The server generates additional learning content and advice based on the evaluation results. Using the evaluation results as input, the server sends prompts to the generating AI model, which then generates customized content and advice. The generated content is sent to the terminal and provided to the user. Specifically, the server sends new prompts to the generating AI model based on the evaluation results, generates additional content, and sends it to the terminal for the user to receive.

[0966] Step 7:

[0967] After completing a lesson, the user enters their self-assessment and feedback into the device. The device sends the entered data to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content. Specifically, when the user fills out and submits the feedback form, the data is sent from the device to the server, which analyzes the feedback and makes updates to reflect it in the next learning session.

[0968] (Application Example 1)

[0969] 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."

[0970] Traditional shopping experiences often fail to provide appropriate recommendations to increase user purchasing intent, and finding products in stores is inconvenient. On the other hand, there is no system that accurately understands user preferences and purchasing behavior and provides optimal recommendations and navigation based on that information. This results in a lack of personalized shopping experiences and hinders efficient purchasing.

[0971] 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.

[0972] In this invention, the server includes means for collecting user behavior history, means for generating customized recommendation content using a generation AI model based on the collected behavior history, means for providing the generated recommendation content to the user, means for monitoring the user's reaction to the provided recommendation content and evaluating the user's level of interest and purchase intent based on the reaction, and means for generating and providing additional recommendation content and advice to the user based on the evaluation results. This enables a shopping experience that is individually optimized for each user.

[0973] "User behavior history" refers to data about a user's series of purchasing activities, their movement within a store, and the products they viewed.

[0974] A "generative AI model" is an algorithm or program that uses machine learning and deep learning techniques to generate appropriate recommendation content from data.

[0975] "Customized recommendation content" refers to recommendations for products and services that are optimized for a user based on their individual preferences and behavioral history.

[0976] "User responses to recommended content" refer to actions and evaluations that users show towards the recommended products or services, such as click-through rates and purchase behavior.

[0977] "Methods for evaluating user interest and purchasing intent" refer to technologies and methods for analyzing collected user response data and quantitatively evaluating how interested a user is in a product or service.

[0978] "Initial setup information" refers to basic information that users enter when they start using the system, such as name, age, gender, and product categories of interest.

[0979] "Feedback" refers to evaluations and opinions that users provide to the system, such as comments on the shopping experience or reactions to recommended content.

[0980] "Additional recommended content and advice" refers to recommendations for products and services created based on user interest and purchase intent evaluations, as well as suggestions and advice given to users.

[0981] As an embodiment of this invention, a system for improving the shopping experience in physical stores will be specifically described. This system consists of a server, a terminal (mainly a smartphone), and a user.

[0982] Program operation

[0983] Means of collecting user behavior history

[0984] Once a user installs the application and begins browsing within a store, location data is collected using the smartphone's GPS and Wi-Fi information. The products the user views and purchases are also automatically tracked. This data is transmitted to a server in real time and stored in a database.

[0985] Means for generating customized recommendation content

[0986] The server uses a generative AI model to analyze the collected behavioral history data. The data is processed using machine learning frameworks such as TensorFlow, and optimal product recommendation content is created based on the user's preferences.

[0987] Means of providing recommended content to users

[0988] The generated recommendation content is notified to the user via their smartphone. The user can then open the application to view individually customized product recommendations.

[0989] A means of monitoring and evaluating user reactions.

[0990] All actions users take with recommended content (e.g., clicks and purchases) are sent from their devices to the server. This data is aggregated and analyzed on the server and used as an indicator to evaluate the user's level of interest and purchase intent.

[0991] A means of generating and providing additional recommended content and advice.

[0992] Based on the evaluation results, the server generates newly created recommendation content and advice. This additional information is also provided to the user via smartphone, further enhancing the shopping experience.

[0993] Hardware and software used for implementation

[0994] Hardware: Smartphones (Android / iOS), Servers

[0995] Software: Firebase (database management), TensorFlow (machine learning models), Google Maps API (in-store navigation)

[0996] Examples of specific cases and prompt statements

[0997] For example, if a user types "Tell me today's recommended products" on their smartphone while in a store, the application will notify them based on their purchase history, saying, "Today we recommend wireless earphones, which are on sale. They are located in area B of the store." Also, if a user types "Direct me to the battery section," detailed navigation from their current location to the battery section will be provided.

[0998] Examples of prompt statements:

[0999] Based on the user's purchase history, generate a list of recommended products for today.

[1000] Please guide the user through the store, from their current location to the shelf of the specified product.

[1001] As described above, this embodiment of the invention provides a system that enhances the user's shopping experience by offering personalized recommendation content in real time based on the user's daily behavior history.

[1002] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1003] Step 1:

[1004] The user installs the application and enters initial setup information. Initial setup information such as the user's name, age, gender, and product categories of interest is collected and sent from the device to the server. The server stores this initial setup information in a database and generates an initial recommendation plan.

[1005] Input: User's name, age, gender, product categories of interest

[1006] Data processing: The server receives this data and saves it to the database.

[1007] Output: Initial Recommended Plan

[1008] Step 2:

[1009] When a user visits a store and launches the application, the device tracks the user's current location. It obtains location information from the smartphone's GPS or Wi-Fi and sends that data to the server in real time.

[1010] Input: Smartphone GPS information, Wi-Fi information

[1011] Data processing: Collection and real-time transmission of location data.

[1012] Output: Location data stored on the server

[1013] Step 3:

[1014] The server generates customized recommendation content using an AI model based on user behavior history data. The collected behavior history data is analyzed using TensorFlow, and optimal product recommendations are created through a machine learning model.

[1015] Input: User activity history data

[1016] Data processing: Data analysis using machine learning models

[1017] Output: Customized recommendation content

[1018] Step 4:

[1019] The generated recommendation content is sent to the device and provided to the user through a smartphone application. The user reviews the recommendation content within the app and makes a purchasing decision.

[1020] Input: Customized recommendation content

[1021] Output: Recommended content notified to your smartphone

[1022] Step 5:

[1023] User responses (for example, the number of clicks on recommended products and actual purchase behavior) are sent from the device to the server. The server collects and stores this response data to evaluate the user's level of interest and purchase intent.

[1024] Input: User response data

[1025] Data processing: Collection and storage of reaction data

[1026] Output: Evaluation results of interest level and purchase intent

[1027] Step 6:

[1028] Based on the evaluation results, the server generates additional recommended content and advice. This is again done using a generative AI model and machine learning algorithm to produce the most optimal content.

[1029] Input: Evaluation result

[1030] Data processing: Generate new recommendation content based on evaluation results.

[1031] Output: Additional recommended content and advice

[1032] Step 7:

[1033] The newly generated additional recommendation content and advice are sent to the device and provided to the user via their smartphone. The user can then review this and take further purchasing action.

[1034] Input: Additional recommended content or advice

[1035] Output: Additional recommended content notified to your smartphone

[1036] As described above, this system collects, analyzes, and notifies data between users, devices, and servers to provide a personalized shopping experience.

[1037] 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.

[1038] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[1039] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[1040] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as learning history. The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is sent from the server to the device.

[1041] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress with their learning. For example, the device displays specific practice problems or explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[1042] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust the presentation method and content of learning materials.

[1043] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, advice is also generated to maintain and improve the user's motivation. For example, if the user is tired, a short break may be suggested, while if they are highly engaged, additional challenges may be offered.

[1044] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[1045] The following describes the processing flow.

[1046] Step 1:

[1047] The user accesses the AI ​​learning support system and registers. The user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in its database.

[1048] Step 2:

[1049] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[1050] Step 3:

[1051] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[1052] Step 4:

[1053] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. Data analysis is performed to identify the user's strengths and weaknesses, and the generated learning content is sent from the server to the terminal.

[1054] Step 5:

[1055] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[1056] Step 6:

[1057] The device monitors the user's responses. For example, it records the answer result and time taken to answer each question, and this data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[1058] Step 7:

[1059] During learning, the device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state. For example, it can determine whether the user is having fun or feeling stressed.

[1060] Step 8:

[1061] The server receives the results of the emotion engine's analysis and adjusts how and what learning content is presented. For example, if the user is feeling stressed, the server may lower the difficulty level or display encouraging messages.

[1062] Step 9:

[1063] Based on the evaluation results and the emotion engine's output, the server generates additional learning content and advice to reinforce the user's weaknesses. The generated content and advice are sent from the server to the device, which then provides it to the user.

[1064] Step 10:

[1065] After a user completes a learning session, they input a self-assessment and feedback. This feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. The server also generates advice to maintain and improve motivation based on the output of the emotion engine. For example, if the user is tired, it might suggest a short break.

[1066] Step 11:

[1067] The server generates an improved learning plan and saves it to the database. In the next learning session, the terminal provides this new learning plan to the user, thus repeating the learning cycle.

[1068] (Example 2)

[1069] 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."

[1070] In modern learning systems, providing learning content optimized for individual users is crucial, but many systems fail to take into account the user's emotional state. As a result, they cannot adequately manage the stress and fatigue users experience during learning, which can reduce learning effectiveness. Furthermore, they lack the ability to provide real-time, customized learning content based on the user's learning history and responses.

[1071] 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.

[1072] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice to the user based on the evaluation results, and means for detecting the user's emotional state from their facial expressions and voice and adjusting the learning content based on the detection results. This makes it possible to maximize the user's learning effectiveness and appropriately manage stress and fatigue during learning.

[1073] A "user" refers to an individual user who uses the system to learn.

[1074] "Learning history" refers to a record of the learning activities a user has undertaken so far.

[1075] "Natural language generation technology" refers to artificial intelligence technology used to generate human language.

[1076] "Learning content" refers to information such as learning materials, problems, and explanations provided to users for learning purposes.

[1077] "Reactions" refer to the answers, actions, and facial expressions that users show in response to learning content.

[1078] "Comprehension level" refers to an indicator that evaluates how well a user understands the learning material.

[1079] "Progress" refers to an indicator that shows the degree to which a user's learning is progressing.

[1080] "Additional learning content" refers to learning materials that are newly provided based on the user's understanding and progress.

[1081] "Advice" refers to suggestions and suggestions for effectively advancing a user's learning.

[1082] "Facial expressions" refer to the expressions on the user's face. It is one way of understanding the emotional state during the learning process.

[1083] "Voice data" refers to data collected from the user's speech and voice. This is also one way to understand the user's emotional state.

[1084] An "emotion engine" refers to artificial intelligence technology that analyzes facial expressions and voice data to identify a user's emotional state.

[1085] A "database" refers to a system for storing collected information.

[1086] As an embodiment for carrying out the present invention, a specific program processing that combines an emotion engine with a learning support AI system will be described. This system supports users in efficiently and effectively advancing their learning, and consists of a server, a terminal, and a user.

[1087] Hardware and software usage

[1088] server

[1089] Database management systems (e.g., MySQL, PostgreSQL)

[1090] Natural language generation technology (e.g. GPT-3)

[1091] Emotion engine (e.g., Affectiva's SDK)

[1092] terminal

[1093] A web browser or mobile app to retrieve your learning history.

[1094] Camera and microphone

[1095] Display for showing learning content

[1096] User

[1097] PCs and mobile devices with an internet connection

[1098] Program processing

[1099] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. Subsequently, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[1100] When a user logs in and starts a learning session, the device tracks the user's learning activity in real time and sends learning history data to the server. The server uses the data stored in the database to perform analysis and generates individually customized learning content using natural language generation technology.

[1101] The generated learning content is sent from the server to the device, and the device provides that content to the user. As the user progresses through the learning process using the provided content, the device monitors the user's responses, recording, for example, the results of each question and the time taken to answer them. This data is also sent to the server and evaluated. The server analyzes the user's understanding and progress, and generates additional learning content or advice as needed, providing it to the user via the device.

[1102] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state (for example, whether they are enjoying themselves or feeling stressed). This information is sent to the server and used to adjust the pace and content of the learning material.

[1103] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, it generates advice to maintain and improve the user's motivation; for example, it suggests a short break if the user is tired, or offers additional challenges if they are focused.

[1104] Specific example

[1105] For example, consider a case where User C, a second-year high school student, is studying quadratic equations in mathematics. After User C logs in, they start a learning session, and the system identifies their weaknesses from their past learning history data. The server generates specific practice problems and explanations and provides them to User C via the terminal. When User C solves the problems, the terminal records the solution and the time taken to solve them and sends it to the server. The server evaluates the data and provides additional practice problems or explanatory videos. In the process, an emotion engine identifies User C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks.

[1106] Example of a prompt

[1107] "A user starts a learning session. Explain how the user's device tracks their learning activity in real time and sends learning history data to the server."

[1108] By inputting this prompt into the generating AI model, it explains how the system tracks the user's learning activity and sends data to the server.

[1109] Based on the above explanation, you should be able to understand the specific programming processes of the learning support AI system and the emotion engine.

[1110] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1111] Step 1:

[1112] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal.

[1113] Input: Name, grade level, subjects of interest

[1114] Terminal: Sends input information to the server.

[1115] Output: Sending initial setup information

[1116] Step 2:

[1117] The server saves the initial configuration information it receives to the database.

[1118] Input: Initial setup information

[1119] Server: Performs data processing to store information in a database.

[1120] Output: Saving information to the database

[1121] Step 3:

[1122] Users set their learning goals and schedules from their devices.

[1123] Input: Learning objectives, schedule

[1124] Terminal: Sends configuration information to the server.

[1125] Output: Submit learning goals and schedule

[1126] Step 4:

[1127] The server generates an initial learning plan based on the information it receives.

[1128] Input: Learning objectives, schedule

[1129] Server: Performs data calculations to generate learning plans and saves them to the database.

[1130] Output: Generation and saving of the initial training plan

[1131] Step 5:

[1132] The user logs in and starts a learning session.

[1133] Input: Login information (ID, password)

[1134] Terminal: Displays the learning screen and monitors user actions in real time.

[1135] Output: Start of learning session

[1136] Step 6:

[1137] The device tracks the user's learning activity in real time and sends learning history data to the server.

[1138] Input: Learning activity data (answer results, operation history, etc.)

[1139] Terminal: Collects data and sends it to the server.

[1140] Output: Sending learning history data

[1141] Step 7:

[1142] The server stores learning history data in a database and analyzes the user's strengths and weaknesses.

[1143] Input: Learning history data

[1144] Server: Stores data in a database and performs data analysis.

[1145] Output: Identifying strengths and weaknesses

[1146] Step 8:

[1147] The server generates customized learning content using natural language generation technology.

[1148] Input: Analysis results (strengths and weaknesses)

[1149] Server: Generates learning content using natural language generation technology.

[1150] Output: Generation of customized learning content

[1151] Step 9:

[1152] The device provides the user with the generated learning content.

[1153] Input: Learning content

[1154] Device: Displays learning content.

[1155] Output: Provision of learning content

[1156] Step 10:

[1157] Users progress through their learning using the content.

[1158] Input: Learning content

[1159] User: Continue learning.

[1160] Output: Learning progress

[1161] Step 11:

[1162] The device monitors the user's responses and records the answer results and response time.

[1163] Input: User response (answer result, answer time)

[1164] Terminal: Records data and sends it to the server.

[1165] Output: Sending reaction data

[1166] Step 12:

[1167] The server evaluates the user's understanding and progress based on the data.

[1168] Input: Reaction data

[1169] Server: Performs data analysis and evaluates understanding and progress.

[1170] Output: Evaluation results

[1171] Step 13:

[1172] The server generates additional learning content and advice as needed and provides it to the user via the terminal.

[1173] Input: Evaluation result

[1174] Server: Generates additional learning content and advice.

[1175] Output: Additional learning content and advice

[1176] Step 14:

[1177] The device provides users with additional content and advice that it generates.

[1178] Input: Additional learning content or advice

[1179] Terminal: Display it.

[1180] Output: Providing additional content and advice

[1181] Step 15:

[1182] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[1183] Input: Facial expressions and voice data

[1184] Terminal: Acquires data and sends it to the emotion engine.

[1185] Output: Sending emotion data

[1186] Step 16:

[1187] The emotion engine analyzes the data and identifies the user's emotional state.

[1188] Input: Facial expressions and voice data

[1189] Emotion Engine: Performs data analysis.

[1190] Output: Analysis results of emotional state

[1191] Step 17:

[1192] The emotion engine sends the analysis results to the server.

[1193] Input: Analysis results of emotional state

[1194] Emotion engine: Sends results to the server.

[1195] Output: Sending results to the server

[1196] Step 18:

[1197] The server adjusts the learning content according to the user's emotional state and sends it to the device.

[1198] Input: Analysis results of emotional state

[1199] Server: Adjusts learning content.

[1200] Output: Sending adjusted learning content

[1201] Step 19:

[1202] The device provides users with optimized learning content.

[1203] Input: Adjusted learning content

[1204] Terminal: Display it.

[1205] Output: Provision of tailored learning content

[1206] Step 20:

[1207] Users enter their self-assessments and feedback.

[1208] Input: Self-assessment, feedback

[1209] User: Enter that.

[1210] Output: Self-assessment, feedback input

[1211] Step 21:

[1212] The device sends feedback data to the server.

[1213] Input: Self-assessment, feedback

[1214] Terminal: Sends it to the server.

[1215] Output: Sending feedback data

[1216] Step 22:

[1217] The server analyzes the feedback it receives and incorporates it into the next learning plan.

[1218] Input: Feedback data

[1219] Server: Performs data analysis.

[1220] Output: How to incorporate this into the next learning plan.

[1221] Step 23:

[1222] The server generates and sends advice to the terminal based on the output of the emotion engine, aiming to maintain and improve the user's motivation.

[1223] Input: Emotion Engine Output

[1224] Server: Generates advice.

[1225] Output: Send advice

[1226] Step 24:

[1227] The device presents the generated advice to the user.

[1228] Input: Advice

[1229] Terminal: Display it.

[1230] Output: Providing advice

[1231] (Application Example 2)

[1232] 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."

[1233] Traditional learning support systems offer customization based on users' learning history and comprehension levels, but they lack support that considers the user's emotional state. Therefore, when users experience stress or decreased motivation, appropriate support is not provided, resulting in a failure to maximize learning effectiveness. Similarly, in factory settings, there is a lack of real-time support that considers the emotional state of workers, hindering sufficient improvements in work efficiency.

[1234] 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.

[1235] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice based on the evaluation results, means for detecting the user's emotional state and adjusting the presentation method and content of the learning content based on the emotional state, and means for generating advice for maintaining and improving the user's motivation based on an emotion engine. This enables the provision of individually optimized learning experiences and support that take into account the user's emotional state and motivation, maximizing learning effectiveness and improving work efficiency.

[1236] "Learning history" refers to a record of the learning activities a user has undertaken so far, and includes data such as the content of specific learning sessions, study time, and the results of answering questions.

[1237] "Natural language generation technology" is a technology that automatically generates personalized text based on collected data, and it is a technology that uses AI models to create text.

[1238] "Learning content" refers to a series of digital information provided to users for learning purposes, such as textbooks, workbooks, and explanatory videos.

[1239] "User response" refers to performance data such as user behavior, answer results, and answer time in relation to learning content, and can also include emotional data such as facial expressions and voice.

[1240] An "emotion engine" is an artificial intelligence technology that analyzes biometric data such as a user's facial expressions and voice to detect their emotional state.

[1241] "Advice for maintaining and improving motivation" refers to specific suggestions and instructions that provide motivation and encouragement for users to continue learning or working.

[1242] A "learning plan" is a schedule that outlines the learning methods and content recommended by the system, based on the learning goals and schedule set by the user.

[1243] "Feedback" refers to opinions and evaluations provided by users to the system, including opinions on the quality of learning content and user experience.

[1244] "User emotional state" refers to data that represents the type and intensity of emotions a user experiences while learning or working, and includes emotions such as joy, sadness, stress, and concentration.

[1245] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[1246] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[1247] Next, the user logs in and starts a learning session. The device tracks the user's learning activity and emotional state in real time and sends learning history data and emotional data to the server. The server stores this data in a database and records it as learning history. The server also analyzes the collected learning history data and generates customized learning content using a generative AI model. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[1248] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress through the learning process. For example, the device displays specific practice problems and explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[1249] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device uses its camera to capture the user's facial expressions and voice data, which are then sent to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust how learning content is presented and what it entails. For example, if the user is feeling stressed, a short break may be suggested, while if they are focused, additional challenges may be offered.

[1250] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Furthermore, based on the emotion engine's output, advice is generated to maintain and improve the user's motivation. For example, the following are examples of prompt messages:

[1251] "Worker ID: 12345

[1252] Stress level detection: 90%

[1253] Proposed action: Take a 10-minute break.

[1254] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[1255] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1256] Step 1:

[1257] The user accesses the system and registers a new account.

[1258] Input: Initial information such as user name, grade level, and subjects of interest.

[1259] Specific operation: The user enters initial setup information via the terminal and sends it to the server.

[1260] Data processing: The server saves the received initial configuration information to the database.

[1261] Output: Saved user default settings information

[1262] Step 2:

[1263] Users set their learning goals and schedules.

[1264] Input: Learning objectives, learning schedule

[1265] Specific operation: The user inputs learning goals and study schedules via their device and sends them to the server.

[1266] Data processing: The server stores this information in a database and generates an initial training plan.

[1267] Output: Generated initial training plan

[1268] Step 3:

[1269] The user logs in and starts a learning session.

[1270] Input: Login information, instructions for starting the learning program.

[1271] Specific operation: The user logs in via their device and starts a learning session.

[1272] Data processing: The server tracks the user's learning history and emotional state in real time.

[1273] Output: Collected learning history data and sentiment data

[1274] Step 4:

[1275] The collected learning history and sentiment data are sent to the server.

[1276] Input: Learning history data, sentiment data

[1277] Specific operation: The device sends learning history data and sentiment data collected in real time to the server.

[1278] Data processing: The server receives this data and stores it in the database.

[1279] Output: Saved learning history data and sentiment data

[1280] Step 5:

[1281] The server generates customized learning content using the generated AI model.

[1282] Input: Stored learning history data and sentiment data

[1283] Specific operation: The server retrieves learning history data and sentiment data from the database and generates optimized learning content using a generative AI model.

[1284] Data processing: Based on this data, the server creates learning content using natural language generation technology.

[1285] Output: Generated customized learning content

[1286] Step 6:

[1287] Provide the generated learning content to the user.

[1288] Input: Generated learning content

[1289] Specific operation: The server sends the generated learning content to the device, and the device displays it to the user.

[1290] Data output: Learning content provided to the user

[1291] Step 7:

[1292] Monitor user responses and evaluate user understanding and progress based on those responses.

[1293] Input: User's answer result, answer time, facial expression, audio data

[1294] Specific operation: The device records the user's responses in real time and sends that data to the server.

[1295] Data processing: The server analyzes the received data and evaluates the user's understanding and progress.

[1296] Output: Evaluation results

[1297] Step 8:

[1298] Based on the evaluation results, additional learning content and advice are generated and provided to the user.

[1299] Input: Evaluation result

[1300] Specific operation: Based on the evaluation results, the server generates additional learning content and appropriate advice and sends it to the terminal. The terminal then displays this to the user.

[1301] Output: Additional learning content, advice

[1302] Step 9:

[1303] The system detects the user's emotional state and adjusts the presentation method and content of learning materials based on that state.

[1304] Input: User facial expression data, voice data

[1305] Specific operation: The device uses its camera and microphone to capture facial expressions and voice, and sends them to the emotion engine. The server adjusts how the learning content is presented based on the results obtained from the emotion engine.

[1306] Data processing: The emotion engine analyzes facial expressions and voice data to identify the emotional state.

[1307] Output: Adjusted learning content presentation method

[1308] Step 10:

[1309] We collect user feedback to improve future learning plans and content.

[1310] Input: User feedback

[1311] Specific operation: After the learning session ends, the user enters a self-assessment and feedback, and the device sends this data to the server.

[1312] Data processing: The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[1313] Output: Improved learning plan and learning content

[1314] 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.

[1315] 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.

[1316] 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.

[1317] [Fourth Embodiment]

[1318] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1319] 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.

[1320] 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).

[1321] 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.

[1322] 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.

[1323] 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).

[1324] 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.

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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".

[1331] As an embodiment for carrying out the present invention, the specific program processing of the learning support AI system is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[1332] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their own learning goals and schedule, and this information is also sent to the server via the terminal.

[1333] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as the learning history.

[1334] The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. The generated learning content is provided to the user via the device. The user then uses the provided content to continue their learning.

[1335] The device monitors the user's responses, recording, for example, the answer result and time taken for each question. This data is sent to a server, which evaluates the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[1336] After completing a lesson, users can enter self-assessments and feedback. The feedback data is sent to a server via the device, which analyzes it to improve future learning plans and content.

[1337] As a concrete example, consider the case of user B, a second-year high school student, studying mathematics. After logging in, user B begins studying "quadratic equations." The system identifies that user B struggles with "quadratic equations" based on past learning history data. The server provides user B with specific practice problems and explanations via the terminal. When user B solves the problems, the terminal records the answer and sends it to the server. The server evaluates user B's answer and time taken, and provides additional practice problems or explanatory videos as needed.

[1338] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[1339] The following describes the processing flow.

[1340] Step 1:

[1341] The user accesses the AI ​​learning support system and registers. Specifically, the user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in a database.

[1342] Step 2:

[1343] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[1344] Step 3:

[1345] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[1346] Step 4:

[1347] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[1348] Step 5:

[1349] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[1350] Step 6:

[1351] The device monitors the user's responses, recording, for example, the answer result and time taken for each question. This data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[1352] Step 7:

[1353] Based on the evaluation results, the server generates additional learning content and advice to reinforce the user's weaknesses. For example, it might generate additional practice problems or detailed explanations for specific areas. The generated content and advice are sent from the server to the terminal, which then provides it to the user.

[1354] Step 8:

[1355] After a user completes a learning session, they enter a self-assessment and feedback. This feedback data is sent from the device to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[1356] Step 9:

[1357] The server generates an improved learning plan and saves it to the database. In the next learning session, the device provides this new learning plan to the user, thus repeating the learning cycle.

[1358] (Example 1)

[1359] 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".

[1360] Conventional learning support systems have struggled to appropriately reflect users' learning history and comprehension levels, and to provide individually optimized learning content. Furthermore, they lacked the functionality to effectively utilize user feedback and continuously improve learning plans. As a result, learning effectiveness was limited, and it was difficult to maintain users' motivation to learn.

[1361] 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.

[1362] In this invention, the server includes means for receiving user initial setup information and generating an initial learning plan; means for collecting the user's learning history; means for generating customized learning content using natural language generation technology based on the collected learning history; means for providing the generated learning content to the user; means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response; means for generating and providing additional learning content and advice based on the evaluation results; means for collecting user feedback and improving the next learning plan and learning content based on the feedback; means for tracking learning activities in real time when the user starts learning activities and collecting that data; and means for generating prompt sentences for a generation AI model and generating customized learning content based on the collected user learning history data. This makes it possible to provide a learning experience that is individually optimized for each user, continuously improve learning plans and content, and maximize learning effectiveness.

[1363] "User initial information" refers to the information a user enters when they first access the system, and includes personal information and basic learning-related information such as name, grade level, subjects of interest, and learning goals.

[1364] An "initial learning plan" refers to a plan generated by the server based on the user's initial settings, designed to help the user efficiently begin learning.

[1365] "Learning history" refers to data collected when a user engages in learning activities using the system, such as records of activities, learning progress, and grades.

[1366] "Natural language generation technology" refers to the technology of generating natural language using artificial intelligence. Specifically, it refers to the technology of generating texts, explanations, questions, etc., using AI models.

[1367] "Customized learning content" refers to learning materials, questions, and explanations that are optimized for a specific user based on their learning history and level of understanding.

[1368] "User response" refers to the results of user actions and inputs regarding learning content, specifically data such as answer results, response time, and operation logs.

[1369] "Comprehension level" refers to an indicator that evaluates how well a user understands a particular learning topic.

[1370] "Progress" refers to an indicator that shows how far a user has progressed according to their learning plan.

[1371] "Feedback" refers to information provided by users, such as evaluations, opinions, and suggestions for improvement regarding learning content and the system as a whole.

[1372] "Real-time tracking" refers to the process of instantly recording a user's learning activities and sending the data to the server in real time as they occur.

[1373] A "generative AI model" refers to an algorithm or software that uses an artificial intelligence model to generate learning content and prompt sentences.

[1374] A "prompt sentence" refers to an instruction or question given to a generative AI model, which serves as the basis for the AI ​​to generate output.

[1375] As an embodiment of the present invention, a learning support AI system is provided to enable users to learn efficiently and effectively. The learning support AI system mainly consists of a server, a terminal, and a user.

[1376] First, the user accesses the system via a terminal and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal, and the terminal sends this information to the server. The server stores the received information in a database and generates an initial learning plan. In this process, the database and server can use commonly used computer and server-related software (e.g., MySQL, Apache).

[1377] Next, the user logs back into the system and sets their learning goals and schedule. The terminal sends the entered data to the server, which then stores it in the database.

[1378] When a user starts a learning session, the device tracks their learning activity in real time and sends that data to the server. The server then records the user's learning history in a database.

[1379] Based on learning history data, the server generates customized learning content using natural language generation technology. For example, the GPT-4 AI model is used for generation. The generated learning content is provided to the user via a terminal. While the user progresses through the learning process, the terminal monitors the user's responses (e.g., answers to each question and response time) and sends this data to the server.

[1380] The server evaluates the user's understanding and progress based on user response data. Based on the evaluation results, the server further generates additional learning content and advice using natural language generation technology and provides it to the user via the device.

[1381] Furthermore, after completing a lesson, users input self-assessments and feedback into their device, and the device sends this feedback data to a server. The server analyzes the feedback and uses it to improve future learning plans and learning content.

[1382] As a concrete example, consider the case of User B, a second-year high school student, who is studying "quadratic equations" in mathematics. After logging in, User B begins learning. The server identifies User B's weaknesses from their past learning history and uses a generative AI model (e.g., GPT-4) to generate specific practice problems and explanations. This generated content is provided to User B through their device. When User B solves a problem, the device records the answer and sends it to the server. The server evaluates this data and provides additional practice problems or explanatory videos as needed.

[1383] An example of a prompt message would be: "When user B, a second-year high school student, is solving practice problems on quadratic equations, identify user B's weak areas and generate customized practice problems based on those areas."

[1384] In this way, the learning support AI system can provide a learning experience that is individually optimized for each user, maximizing the user's learning effectiveness.

[1385] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1386] Step 1:

[1387] The user accesses the system and registers. The terminal receives initial information from the user, such as name, grade level, and subjects of interest. The terminal sends this information to the server. The server stores the received information in its database. Specifically, when the user clicks the "Register" button, an HTTP POST request is sent from the terminal to the server, which receives it and stores it in the database.

[1388] Step 2:

[1389] The user logs into the system and sets their learning goals and schedule. The terminal receives the user's input (learning goals and schedule) and sends it to the server. The server saves this data to a database. Specifically, when the user clicks the "Save" button, data in JSON format is sent from the terminal to the server, which parses it and saves it to the database.

[1390] Step 3:

[1391] The user starts a learning session. The device records the start time of the learning session and sends activity data during the learning session (such as answers to questions and typing speed) to the server in real time. The server receives the learning start signal and activity data during the learning session as input from the device and continuously records this in its database. Specifically, when the user clicks the "Start Learning" button, the device records the current time and periodically sends activity data to the server.

[1392] Step 4:

[1393] The server generates customized learning content based on the collected learning history. Using the collected learning history data as input, the server sends prompts to a generative AI model (e.g., GPT-4) to generate content. The generated content is sent to the terminal and provided to the user. Specifically, the server periodically checks the database, and if there is any unprocessed learning history data, it uses the generative AI model to generate custom content and sends it to the terminal.

[1394] Step 5:

[1395] The device monitors the user's responses and records the answer and response time for each question. It receives user response data as input and sends it to the server. The server evaluates the user's understanding and progress based on this data. Specifically, each time the user answers a question, the device records the result and response time and sends it to the server. The server analyzes this data and stores the evaluation results in a database.

[1396] Step 6:

[1397] The server generates additional learning content and advice based on the evaluation results. Using the evaluation results as input, the server sends prompts to the generating AI model, which then generates customized content and advice. The generated content is sent to the terminal and provided to the user. Specifically, the server sends new prompts to the generating AI model based on the evaluation results, generates additional content, and sends it to the terminal for the user to receive.

[1398] Step 7:

[1399] After completing a lesson, the user enters their self-assessment and feedback into the device. The device sends the entered data to the server. The server analyzes the feedback and uses it to improve the next learning plan and learning content. Specifically, when the user fills out and submits the feedback form, the data is sent from the device to the server, which analyzes the feedback and makes updates to reflect it in the next learning session.

[1400] (Application Example 1)

[1401] 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".

[1402] Traditional shopping experiences often fail to provide appropriate recommendations to increase user purchasing intent, and finding products in stores is inconvenient. On the other hand, there is no system that accurately understands user preferences and purchasing behavior and provides optimal recommendations and navigation based on that information. This results in a lack of personalized shopping experiences and hinders efficient purchasing.

[1403] 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.

[1404] In this invention, the server includes means for collecting user behavior history, means for generating customized recommendation content using a generation AI model based on the collected behavior history, means for providing the generated recommendation content to the user, means for monitoring the user's reaction to the provided recommendation content and evaluating the user's level of interest and purchase intent based on the reaction, and means for generating and providing additional recommendation content and advice to the user based on the evaluation results. This enables a shopping experience that is individually optimized for each user.

[1405] "User behavior history" refers to data about a user's series of purchasing activities, their movement within a store, and the products they viewed.

[1406] A "generative AI model" is an algorithm or program that uses machine learning and deep learning techniques to generate appropriate recommendation content from data.

[1407] "Customized recommendation content" refers to recommendations for products and services that are optimized for a user based on their individual preferences and behavioral history.

[1408] "User responses to recommended content" refer to actions and evaluations that users show towards the recommended products or services, such as click-through rates and purchase behavior.

[1409] "Methods for evaluating user interest and purchasing intent" refer to technologies and methods for analyzing collected user response data and quantitatively evaluating how interested a user is in a product or service.

[1410] "Initial setup information" refers to basic information that users enter when they start using the system, such as name, age, gender, and product categories of interest.

[1411] "Feedback" refers to evaluations and opinions that users provide to the system, such as comments on the shopping experience or reactions to recommended content.

[1412] "Additional recommended content and advice" refers to recommendations for products and services created based on user interest and purchase intent evaluations, as well as suggestions and advice given to users.

[1413] As an embodiment of this invention, a system for improving the shopping experience in physical stores will be specifically described. This system consists of a server, a terminal (mainly a smartphone), and a user.

[1414] Program operation

[1415] Means of collecting user behavior history

[1416] Once a user installs the application and begins browsing within a store, location data is collected using the smartphone's GPS and Wi-Fi information. The products the user views and purchases are also automatically tracked. This data is transmitted to a server in real time and stored in a database.

[1417] Means for generating customized recommendation content

[1418] The server uses a generative AI model to analyze the collected behavioral history data. The data is processed using machine learning frameworks such as TensorFlow, and optimal product recommendation content is created based on the user's preferences.

[1419] Means of providing recommended content to users

[1420] The generated recommendation content is notified to the user via their smartphone. The user can then open the application to view individually customized product recommendations.

[1421] A means of monitoring and evaluating user reactions.

[1422] All actions users take regarding recommended content (e.g., clicks and purchases) are sent from their devices to the server. This data is aggregated and analyzed on the server and used as an indicator to evaluate the user's level of interest and purchase intent.

[1423] A means of generating and providing additional recommended content and advice.

[1424] Based on the evaluation results, the server generates newly created recommendation content and advice. This additional information is also provided to the user via smartphone, further enhancing the shopping experience.

[1425] Hardware and software used for implementation

[1426] Hardware: Smartphones (Android / iOS), Servers

[1427] Software: Firebase (database management), TensorFlow (machine learning models), Google Maps API (in-store navigation)

[1428] Examples of specific cases and prompt statements

[1429] For example, if a user types "Tell me today's recommended products" on their smartphone while in a store, the application will notify them based on their purchase history, saying, "Today we recommend wireless earphones, which are on sale. They are located in area B of the store." Also, if a user types "Direct me to the battery section," detailed navigation from their current location to the battery section will be provided.

[1430] Examples of prompt statements:

[1431] Based on the user's purchase history, generate a list of recommended products for today.

[1432] Please guide the user through the store, from their current location to the shelf of the specified product.

[1433] As described above, this embodiment of the invention provides a system that enhances the user's shopping experience by offering personalized recommendation content in real time based on the user's daily behavior history.

[1434] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1435] Step 1:

[1436] The user installs the application and enters initial setup information. Initial setup information such as the user's name, age, gender, and product categories of interest is collected and sent from the device to the server. The server stores this initial setup information in a database and generates an initial recommendation plan.

[1437] Input: User's name, age, gender, product categories of interest

[1438] Data processing: The server receives this data and saves it to the database.

[1439] Output: Initial Recommended Plan

[1440] Step 2:

[1441] When a user visits a store and launches the application, the device tracks the user's current location. It obtains location information from the smartphone's GPS or Wi-Fi and sends that data to the server in real time.

[1442] Input: Smartphone GPS information, Wi-Fi information

[1443] Data processing: Collection and real-time transmission of location data.

[1444] Output: Location data stored on the server

[1445] Step 3:

[1446] The server generates customized recommendation content using an AI model based on user behavior history data. The collected behavior history data is analyzed using TensorFlow, and optimal product recommendations are created through a machine learning model.

[1447] Input: User activity history data

[1448] Data processing: Data analysis using machine learning models

[1449] Output: Customized recommendation content

[1450] Step 4:

[1451] The generated recommendation content is sent to the device and provided to the user through a smartphone application. The user reviews the recommendation content within the app and makes a purchasing decision.

[1452] Input: Customized recommendation content

[1453] Output: Recommended content notified to your smartphone

[1454] Step 5:

[1455] User responses (for example, the number of clicks on recommended products and actual purchase behavior) are sent from the device to the server. The server collects and stores this response data to evaluate the user's level of interest and purchase intent.

[1456] Input: User response data

[1457] Data processing: Collection and storage of reaction data

[1458] Output: Evaluation results of interest level and purchase intent

[1459] Step 6:

[1460] Based on the evaluation results, the server generates additional recommended content and advice. This is again done using a generative AI model and machine learning algorithm to produce the most optimal content.

[1461] Input: Evaluation result

[1462] Data processing: Generate new recommendation content based on evaluation results.

[1463] Output: Additional recommended content and advice

[1464] Step 7:

[1465] The newly generated additional recommendation content and advice are sent to the device and provided to the user via their smartphone. The user can then review this and take further purchasing action.

[1466] Input: Additional recommended content or advice

[1467] Output: Additional recommended content notified to your smartphone

[1468] As described above, this system collects, analyzes, and notifies data between users, devices, and servers to provide a personalized shopping experience.

[1469] 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.

[1470] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[1471] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[1472] Next, the user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server stores this data in a database and records it as learning history. The server analyzes the collected learning history data and generates customized learning content using natural language generation technology. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is sent from the server to the device.

[1473] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress with their learning. For example, the device displays specific practice problems or explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[1474] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust the presentation method and content of learning materials.

[1475] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, advice is also generated to maintain and improve the user's motivation. For example, if the user is tired, a short break may be suggested, while if they are highly engaged, additional challenges may be offered.

[1476] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[1477] The following describes the processing flow.

[1478] Step 1:

[1479] The user accesses the AI ​​learning support system and registers. The user enters initial information such as their name, grade level, and subjects of interest, and the device sends this information to the server. The server stores this information in its database.

[1480] Step 2:

[1481] The user sets their own learning goals and schedule. This information is sent to the server via the device, and the server stores it in a database. The server then generates an initial learning plan based on this information.

[1482] Step 3:

[1483] The user logs in and starts a learning session. The device tracks the user's learning activity in real time and sends learning history data to the server. The server saves this data to a database and records it as the learning history.

[1484] Step 4:

[1485] The server analyzes collected learning history data and generates customized learning content using natural language generation technology. Data analysis is performed to identify the user's strengths and weaknesses, and the generated learning content is sent from the server to the terminal.

[1486] Step 5:

[1487] The device provides the user with customized learning content received from the server. The user then uses the provided content to proceed with their learning. For example, the device might display specific practice problems or explanatory videos.

[1488] Step 6:

[1489] The device monitors the user's responses. For example, it records the answer result and time taken to answer each question, and this data is sent from the device to the server. The server evaluates this data and analyzes the user's level of understanding and progress.

[1490] Step 7:

[1491] During learning, the device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state. For example, it can determine whether the user is having fun or feeling stressed.

[1492] Step 8:

[1493] The server receives the results of the emotion engine's analysis and adjusts how and what learning content is presented. For example, if the user is feeling stressed, the server may lower the difficulty level or display encouraging messages.

[1494] Step 9:

[1495] Based on the evaluation results and the emotion engine's output, the server generates additional learning content and advice to reinforce the user's weaknesses. The generated content and advice are sent from the server to the device, which then provides it to the user.

[1496] Step 10:

[1497] After a user completes a learning session, they input a self-assessment and feedback. This feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. The server also generates advice to maintain and improve motivation based on the output of the emotion engine. For example, if the user is tired, it might suggest a short break.

[1498] Step 11:

[1499] The server generates an improved learning plan and saves it to the database. In the next learning session, the device provides this new learning plan to the user, thus repeating the learning cycle.

[1500] (Example 2)

[1501] 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".

[1502] In modern learning systems, providing learning content optimized for individual users is crucial, but many systems fail to take into account the user's emotional state. As a result, they cannot adequately manage the stress and fatigue users experience during learning, which can reduce learning effectiveness. Furthermore, they lack the ability to provide real-time, customized learning content based on the user's learning history and responses.

[1503] 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.

[1504] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice to the user based on the evaluation results, and means for detecting the user's emotional state from their facial expressions and voice and adjusting the learning content based on the detection results. This makes it possible to maximize the user's learning effectiveness and appropriately manage stress and fatigue during learning.

[1505] A "user" refers to an individual user who uses the system to learn.

[1506] "Learning history" refers to a record of the learning activities a user has undertaken so far.

[1507] "Natural language generation technology" refers to artificial intelligence technology used to generate human language.

[1508] "Learning content" refers to information such as learning materials, problems, and explanations provided to users for learning purposes.

[1509] "Reactions" refer to the answers, actions, and facial expressions that users show in response to learning content.

[1510] "Comprehension level" refers to an indicator that evaluates how well a user understands the learning material.

[1511] "Progress" refers to an indicator that shows the degree to which a user's learning is progressing.

[1512] "Additional learning content" refers to learning materials that are newly provided based on the user's understanding and progress.

[1513] "Advice" refers to suggestions and suggestions for effectively advancing a user's learning.

[1514] "Facial expressions" refer to the expressions on the user's face. It is one way of understanding the emotional state during the learning process.

[1515] "Voice data" refers to data collected from the user's speech and voice. This is also one way to understand the user's emotional state.

[1516] An "emotion engine" refers to artificial intelligence technology that analyzes facial expressions and voice data to identify a user's emotional state.

[1517] A "database" refers to a system for storing collected information.

[1518] As an embodiment for carrying out the present invention, a specific program processing that combines an emotion engine with a learning support AI system will be described. This system supports users in efficiently and effectively advancing their learning, and consists of a server, a terminal, and a user.

[1519] Hardware and software usage

[1520] server

[1521] Database management systems (e.g., MySQL, PostgreSQL)

[1522] Natural language generation technology (e.g. GPT-3)

[1523] Emotion engine (e.g., Affectiva's SDK)

[1524] terminal

[1525] A web browser or mobile app to retrieve your learning history.

[1526] Camera and microphone

[1527] Display for showing learning content

[1528] User

[1529] PCs and mobile devices with an internet connection

[1530] Program processing

[1531] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. Subsequently, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[1532] When a user logs in and starts a learning session, the device tracks the user's learning activity in real time and sends learning history data to the server. The server uses the data stored in the database to perform analysis and generates individually customized learning content using natural language generation technology.

[1533] The generated learning content is sent from the server to the device, and the device provides that content to the user. As the user progresses through the learning process using the provided content, the device monitors the user's responses, recording, for example, the results of each question and the time taken to answer them. This data is also sent to the server and evaluated. The server analyzes the user's understanding and progress, and generates additional learning content or advice as needed, providing it to the user via the device.

[1534] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device acquires the user's facial expressions and voice data and sends it to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state (for example, whether they are enjoying themselves or feeling stressed). This information is sent to the server and used to adjust the pace and content of the learning material.

[1535] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Based on the output of the emotion engine, it generates advice to maintain and improve the user's motivation; for example, it suggests a short break if the user is tired, or offers additional challenges if they are focused.

[1536] Specific example

[1537] For example, consider a case where User C, a second-year high school student, is studying quadratic equations in mathematics. After User C logs in, they start a learning session, and the system identifies their weaknesses from their past learning history data. The server generates specific practice problems and explanations and provides them to User C via the terminal. When User C solves the problems, the terminal records the solution and the time taken to solve them and sends it to the server. The server evaluates the data and provides additional practice problems or explanatory videos. In the process, an emotion engine identifies User C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks.

[1538] Example of a prompt

[1539] "A user starts a learning session. Explain how the user's device tracks their learning activity in real time and sends learning history data to the server."

[1540] By inputting this prompt into the generating AI model, it explains how the system tracks the user's learning activity and sends data to the server.

[1541] Based on the above explanation, you should be able to understand the specific programming processes of the learning support AI system and the emotion engine.

[1542] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1543] Step 1:

[1544] The user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest into the terminal.

[1545] Input: Name, grade level, subjects of interest

[1546] Terminal: Sends input information to the server.

[1547] Output: Sending initial setup information

[1548] Step 2:

[1549] The server saves the initial configuration information it receives to the database.

[1550] Input: Initial setup information

[1551] Server: Performs data processing to store information in a database.

[1552] Output: Saving information to the database

[1553] Step 3:

[1554] Users set their learning goals and schedules from their devices.

[1555] Input: Learning objectives, schedule

[1556] Terminal: Sends configuration information to the server.

[1557] Output: Submit learning goals and schedule

[1558] Step 4:

[1559] The server generates an initial learning plan based on the information it receives.

[1560] Input: Learning objectives, schedule

[1561] Server: Performs data calculations to generate learning plans and saves them to the database.

[1562] Output: Generation and saving of the initial training plan

[1563] Step 5:

[1564] The user logs in and starts a learning session.

[1565] Input: Login information (ID, password)

[1566] Terminal: Displays the learning screen and monitors user actions in real time.

[1567] Output: Start of learning session

[1568] Step 6:

[1569] The device tracks the user's learning activity in real time and sends learning history data to the server.

[1570] Input: Learning activity data (answer results, operation history, etc.)

[1571] Terminal: Collects data and sends it to the server.

[1572] Output: Sending learning history data

[1573] Step 7:

[1574] The server stores learning history data in a database and analyzes the user's strengths and weaknesses.

[1575] Input: Learning history data

[1576] Server: Stores data in a database and performs data analysis.

[1577] Output: Identifying strengths and weaknesses

[1578] Step 8:

[1579] The server generates customized learning content using natural language generation technology.

[1580] Input: Analysis results (strengths and weaknesses)

[1581] Server: Generates learning content using natural language generation technology.

[1582] Output: Generation of customized learning content

[1583] Step 9:

[1584] The device provides the user with the generated learning content.

[1585] Input: Learning content

[1586] Device: Displays learning content.

[1587] Output: Provision of learning content

[1588] Step 10:

[1589] Users progress through their learning using the content.

[1590] Input: Learning content

[1591] User: Continue learning.

[1592] Output: Learning progress

[1593] Step 11:

[1594] The device monitors the user's responses and records the answer results and response time.

[1595] Input: User response (answer result, answer time)

[1596] Terminal: Records data and sends it to the server.

[1597] Output: Sending reaction data

[1598] Step 12:

[1599] The server evaluates the user's understanding and progress based on the data.

[1600] Input: Reaction data

[1601] Server: Performs data analysis and evaluates understanding and progress.

[1602] Output: Evaluation results

[1603] Step 13:

[1604] The server generates additional learning content and advice as needed and provides it to the user via the terminal.

[1605] Input: Evaluation result

[1606] Server: Generates additional learning content and advice.

[1607] Output: Additional learning content and advice

[1608] Step 14:

[1609] The device provides users with additional content and advice that it generates.

[1610] Input: Additional learning content or advice

[1611] Terminal: Display it.

[1612] Output: Providing additional content and advice

[1613] Step 15:

[1614] The device acquires the user's facial expressions and voice data and sends it to the emotion engine.

[1615] Input: Facial expressions and voice data

[1616] Terminal: Acquires data and sends it to the emotion engine.

[1617] Output: Sending emotion data

[1618] Step 16:

[1619] The emotion engine analyzes the data and identifies the user's emotional state.

[1620] Input: Facial expressions and voice data

[1621] Emotion Engine: Performs data analysis.

[1622] Output: Analysis results of emotional state

[1623] Step 17:

[1624] The emotion engine sends the analysis results to the server.

[1625] Input: Analysis results of emotional state

[1626] Emotion engine: Sends results to the server.

[1627] Output: Sending results to the server

[1628] Step 18:

[1629] The server adjusts the learning content according to the user's emotional state and sends it to the device.

[1630] Input: Analysis results of emotional state

[1631] Server: Adjusts learning content.

[1632] Output: Sending adjusted learning content

[1633] Step 19:

[1634] The device provides users with optimized learning content.

[1635] Input: Adjusted learning content

[1636] Terminal: Display it.

[1637] Output: Provision of tailored learning content

[1638] Step 20:

[1639] Users enter their self-assessments and feedback.

[1640] Input: Self-assessment, feedback

[1641] User: Enter that.

[1642] Output: Self-assessment, feedback input

[1643] Step 21:

[1644] The device sends feedback data to the server.

[1645] Input: Self-assessment, feedback

[1646] Terminal: Sends it to the server.

[1647] Output: Sending feedback data

[1648] Step 22:

[1649] The server analyzes the feedback it receives and incorporates it into the next learning plan.

[1650] Input: Feedback data

[1651] Server: Performs data analysis.

[1652] Output: How to incorporate this into the next learning plan.

[1653] Step 23:

[1654] The server generates and sends advice to the terminal based on the output of the emotion engine, aiming to maintain and improve the user's motivation.

[1655] Input: Emotion Engine Output

[1656] Server: Generates advice.

[1657] Output: Send advice

[1658] Step 24:

[1659] The device presents the generated advice to the user.

[1660] Input: Advice

[1661] Terminal: Display it.

[1662] Output: Providing advice

[1663] (Application Example 2)

[1664] 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".

[1665] Traditional learning support systems offer customization based on users' learning history and comprehension levels, but they lack support that considers the user's emotional state. Therefore, when users experience stress or decreased motivation, appropriate support is not provided, resulting in a failure to maximize learning effectiveness. Similarly, in factory settings, there is a lack of real-time support that considers the emotional state of workers, hindering sufficient improvements in work efficiency.

[1666] 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.

[1667] In this invention, the server includes means for collecting the user's learning history, means for generating customized learning content using natural language generation technology based on the collected learning history, means for providing the generated learning content to the user, means for monitoring the user's response to the provided learning content and evaluating the user's understanding and progress based on the response, means for generating and providing additional learning content and advice based on the evaluation results, means for detecting the user's emotional state and adjusting the presentation method and content of the learning content based on the emotional state, and means for generating advice for maintaining and improving the user's motivation based on an emotion engine. This enables the provision of individually optimized learning experiences and support that take into account the user's emotional state and motivation, maximizing learning effectiveness and improving work efficiency.

[1668] "Learning history" refers to a record of the learning activities a user has undertaken so far, and includes data such as the content of specific learning sessions, study time, and the results of answering questions.

[1669] "Natural language generation technology" is a technology that automatically generates personalized text based on collected data, and it is a technology that uses AI models to create text.

[1670] "Learning content" refers to a series of digital information provided to users for learning purposes, such as textbooks, workbooks, and explanatory videos.

[1671] "User response" refers to performance data such as user behavior, answer results, and answer time in relation to learning content, and can also include emotional data such as facial expressions and voice.

[1672] An "emotion engine" is an artificial intelligence technology that analyzes biometric data such as a user's facial expressions and voice to detect their emotional state.

[1673] "Advice for maintaining and improving motivation" refers to specific suggestions and instructions that provide motivation and encouragement for users to continue learning or working.

[1674] A "learning plan" is a schedule that outlines the learning methods and content recommended by the system, based on the learning goals and schedule set by the user.

[1675] "Feedback" refers to opinions and evaluations provided by users to the system, including opinions on the quality of learning content and user experience.

[1676] "User emotional state" refers to data that represents the type and intensity of emotions a user experiences while learning or working, and includes emotions such as joy, sadness, stress, and concentration.

[1677] As an embodiment for carrying out the present invention, a specific program processing method combining a learning support AI system with an emotion engine is described below. The learning support AI system assists users in efficiently and effectively progressing with their learning, and mainly consists of a server, a terminal, and a user.

[1678] First, the user accesses the system and registers. The user enters initial information such as their name, grade level, and subjects of interest. This information is sent to the server via the terminal, and the server stores it in a database. After that, the user sets their learning goals and schedule, and this information is also sent to the server via the terminal. The server generates an initial learning plan based on this information.

[1679] Next, the user logs in and starts a learning session. The device tracks the user's learning activity and emotional state in real time and sends learning history data and emotional data to the server. The server stores this data in a database and records it as learning history. The server also analyzes the collected learning history data and generates customized learning content using a generative AI model. This process includes data analysis to identify the user's strengths and weaknesses. The generated learning content is then sent from the server to the device.

[1680] The device provides the user with customized learning content received from the server. The user then uses the provided content to progress through the learning process. For example, the device displays specific practice problems and explanatory videos. The device monitors the user's responses, recording, for example, the answer result and time taken for each problem. This data is sent from the device to the server. The server evaluates this data and analyzes the user's understanding and progress. Based on the evaluation, the server generates additional learning content and advice to reinforce the user's weaknesses and provides it to the user via the device.

[1681] Furthermore, an emotion engine is used to detect the user's emotional state during learning. The device uses its camera to capture the user's facial expressions and voice data, which are then sent to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state, such as whether they are enjoying themselves or feeling stressed. This information is sent to a server and used to adjust how learning content is presented and what it entails. For example, if the user is feeling stressed, a short break may be suggested, while if they are focused, additional challenges may be offered.

[1682] After completing a lesson, users can input self-assessments and feedback. The feedback data is sent from the device to the server, which analyzes it to improve future learning plans and content. Furthermore, based on the emotion engine's output, advice is generated to maintain and improve the user's motivation. For example, the following are examples of prompt messages:

[1683] "Worker ID: 12345

[1684] Stress level detection: 90%

[1685] Proposed action: Take a 10-minute break.

[1686] As a concrete example, consider the case of user C, a second-year high school student, studying mathematics. After logging in, user C begins learning "quadratic equations." The system identifies that user C struggles with "quadratic equations" based on past learning history data. The server provides user C with specific practice problems and explanations via the terminal. When user C solves the problems, the terminal records the answer and sends it to the server. The server evaluates user C's answer and time, and provides additional practice problems or explanatory videos as needed. Furthermore, an emotion engine identifies user C's emotional state during learning from their facial expressions and voice, and provides encouraging messages or suggestions for breaks at appropriate times. In this way, the learning support AI system can provide an individually optimized learning experience while also considering the user's emotional state, maximizing the user's learning effectiveness.

[1687] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1688] Step 1:

[1689] The user accesses the system and registers a new account.

[1690] Input: Initial information such as user name, grade level, and subjects of interest.

[1691] Specific operation: The user enters initial setup information via the terminal and sends it to the server.

[1692] Data processing: The server saves the received initial configuration information to the database.

[1693] Output: Saved user default settings information

[1694] Step 2:

[1695] Users set their learning goals and schedules.

[1696] Input: Learning objectives, learning schedule

[1697] Specific operation: The user inputs learning goals and study schedules via their device and sends them to the server.

[1698] Data processing: The server stores this information in a database and generates an initial training plan.

[1699] Output: Generated initial training plan

[1700] Step 3:

[1701] The user logs in and starts a learning session.

[1702] Input: Login information, instructions for starting the learning program.

[1703] Specific operation: The user logs in via their device and starts a learning session.

[1704] Data processing: The server tracks the user's learning history and emotional state in real time.

[1705] Output: Collected learning history data and sentiment data

[1706] Step 4:

[1707] The collected learning history and sentiment data are sent to the server.

[1708] Input: Learning history data, sentiment data

[1709] Specific operation: The device sends learning history data and sentiment data collected in real time to the server.

[1710] Data processing: The server receives this data and stores it in the database.

[1711] Output: Saved learning history data and sentiment data

[1712] Step 5:

[1713] The server generates customized learning content using the generated AI model.

[1714] Input: Stored learning history data and sentiment data

[1715] Specific operation: The server retrieves learning history data and sentiment data from the database and generates optimized learning content using a generative AI model.

[1716] Data processing: Based on this data, the server creates learning content using natural language generation technology.

[1717] Output: Generated customized learning content

[1718] Step 6:

[1719] Provide the generated learning content to the user.

[1720] Input: Generated learning content

[1721] Specific operation: The server sends the generated learning content to the device, and the device displays it to the user.

[1722] Data output: Learning content provided to the user

[1723] Step 7:

[1724] Monitor user responses and evaluate user understanding and progress based on those responses.

[1725] Input: User's answer result, answer time, facial expression, audio data

[1726] Specific operation: The device records the user's responses in real time and sends that data to the server.

[1727] Data processing: The server analyzes the received data and evaluates the user's understanding and progress.

[1728] Output: Evaluation results

[1729] Step 8:

[1730] Based on the evaluation results, additional learning content and advice are generated and provided to the user.

[1731] Input: Evaluation result

[1732] Specific operation: Based on the evaluation results, the server generates additional learning content and appropriate advice and sends it to the terminal. The terminal then displays this to the user.

[1733] Output: Additional learning content, advice

[1734] Step 9:

[1735] The system detects the user's emotional state and adjusts the presentation method and content of learning materials based on that state.

[1736] Input: User facial expression data, voice data

[1737] Specific operation: The device uses its camera and microphone to capture facial expressions and voice, and sends them to the emotion engine. The server adjusts how the learning content is presented based on the results obtained from the emotion engine.

[1738] Data processing: The emotion engine analyzes facial expressions and voice data to identify the emotional state.

[1739] Output: Adjusted learning content presentation method

[1740] Step 10:

[1741] We collect user feedback to improve future learning plans and content.

[1742] Input: User feedback

[1743] Specific operation: After the learning session ends, the user enters a self-assessment and feedback, and the device sends this data to the server.

[1744] Data processing: The server analyzes the feedback and uses it to improve the next learning plan and learning content.

[1745] Output: Improved learning plan and learning content

[1746] 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.

[1747] 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.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] 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.

[1753] 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.

[1754] 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."

[1755] 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.

[1756] 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.

[1757] 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.

[1758] 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.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] 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.

[1767] The following is further disclosed regarding the embodiments described above.

[1768] (Claim 1)

[1769] A means of collecting the user's learning history,

[1770] A means of generating customized learning content using natural language generation technology based on collected learning history,

[1771] A means of providing the generated learning content to the user,

[1772] A means of monitoring user responses to provided learning content and evaluating user understanding and progress based on those responses,

[1773] A means of generating and providing additional learning content and advice to users based on evaluation results,

[1774] A system that includes this.

[1775] (Claim 2)

[1776] The system according to claim 1, comprising means for receiving user initial settings information and generating an initial learning plan.

[1777] (Claim 3)

[1778] The system according to claim 1, comprising means for collecting user feedback and improving the next learning plan or learning content based on the feedback.

[1779]

[1780] "Example 1"

[1781] (Claim 1)

[1782] A means for receiving user initial setup information and generating an initial learning plan,

[1783] A means of collecting the user's learning history,

[1784] A means of generating customized learning content using natural language generation technology based on collected learning history,

[1785] A means of providing the generated learning content to the user,

[1786] A means of monitoring user responses to provided learning content and evaluating user understanding and progress based on those responses,

[1787] A means of generating and providing additional learning content and advice to users based on evaluation results,

[1788] A means of collecting user feedback and improving the next learning plan and learning content based on that feedback,

[1789] A system that includes this.

[1790] (Claim 2)

[1791] The system according to claim 1, comprising means for tracking a user's learning activity in real time when the user begins a learning activity and collecting the data therefrom.

[1792] (Claim 3)

[1793] The system according to claim 1, comprising means for generating prompt sentences for a generative AI model and generating customized learning content based on collected user learning history data.

[1794] "Application Example 1"

[1795] (Claim 1)

[1796] Means for collecting user behavior history,

[1797] A means of generating customized recommendation content using an AI model based on collected behavioral history,

[1798] A means of providing the generated recommendation content to the user,

[1799] A means of monitoring user reactions to provided recommended content and evaluating user interest and purchase intent based on those reactions,

[1800] A means of generating and providing additional recommended content and advice to users based on evaluation results,

[1801] A system that includes this.

[1802] (Claim 2)

[1803] The system according to claim 1, comprising means for receiving user initial settings information and generating an initial recommendation plan.

[1804] (Claim 3)

[1805] The system according to claim 1, comprising means for collecting user feedback and improving the next recommendation plan or recommended content based on the feedback.

[1806] "Example 2 of combining an emotion engine"

[1807] (Claim 1)

[1808] A means of collecting the user's learning history,

[1809] A means of generating customized learning content using natural language generation technology based on collected learning history,

[1810] A means of providing the generated learning content to the user,

[1811] A means of monitoring user responses to provided learning content and evaluating user understanding and progress based on those responses,

[1812] A means of generating and providing additional learning content and advice to users based on evaluation results,

[1813] A means for detecting the user's emotional state from their facial expressions and voice, and adjusting the learning content based on the detection results,

[1814] A system that includes this.

[1815] (Claim 2)

[1816] The system according to claim 1, comprising means for receiving user initial settings information and generating an initial learning plan.

[1817] (Claim 3)

[1818] The system according to claim 1, comprising means for collecting user feedback and improving the next learning plan or learning content based on the feedback.

[1819] "Application example 2 when combining with an emotional engine"

[1820] (Claim 1)

[1821] A means of collecting the user's learning history,

[1822] A means of generating customized learning content using natural language generation technology based on collected learning history,

[1823] A means of providing the generated learning content to the user,

[1824] A means of monitoring user responses to provided learning content and evaluating user understanding and progress based on those responses,

[1825] A means of generating and providing additional learning content and advice to users based on evaluation results,

[1826] A means for detecting the user's emotional state and adjusting the presentation method and content of learning content based on that emotional state,

[1827] A means of generating advice for maintaining and improving user motivation based on an emotion engine,

[1828] A system that includes this.

[1829] (Claim 2)

[1830] The system according to claim 1, comprising means for receiving user initial settings information and generating an initial learning plan.

[1831] (Claim 3)

[1832] The system according to claim 1, comprising means for collecting user feedback and improving the next learning plan or learning content based on the feedback. [Explanation of symbols]

[1833] 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 of collecting the user's learning history, A means of generating customized learning content using natural language generation technology based on collected learning history, A means of providing the generated learning content to the user, A means of monitoring user responses to provided learning content and evaluating user understanding and progress based on those responses, A means of generating and providing additional learning content and advice to users based on evaluation results, A system that includes this.

2. The system according to claim 1, comprising means for receiving user initial settings information and generating an initial learning plan.

3. The system according to claim 1, comprising means for collecting user feedback and improving the next learning plan or learning content based on the feedback.

Images