system

Abstract

We provide the system. [Solution] A means of receiving user attribute information and collecting information about the learning program, Means for generating an optimized learning program based on the attribute information and collected information, The optimized learning program is provided to the user, and means are used to monitor the user's progress. A means of evaluating the user's learning results and collecting feedback, A means of interacting with users and providing educational support through physical devices, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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] Existing educational programs are often not individually optimized and do not sufficiently correspond to the attributes and career goals of specific users, so the educational effect is limited. In addition, it is difficult for users to effectively utilize the educational resources obtained from various information sources, and there are problems that the continuity of learning and the evaluation of results are not sufficient.

Means for Solving the Problems

[0006] "User attribute information" refers to information related to the user, such as personal information, interests, skill levels, and career goals.

[0007] "Educational program data" refers to data on educational resources, curriculum information, and materials and training courses necessary for skill development.

[0008] "External information sources" refer to information sources that exist outside the company, such as publicly available databases on the internet or online education platforms.

[0009] "Internal corporate systems" refer to databases and information systems related to education and training managed within a company.

[0010] A "generative AI model" is an AI system that uses machine learning and deep learning technologies to automatically generate educational programs optimized for the user.

[0011] "Progress monitoring" is the process of tracking a user's learning process and evaluating their progress against the plan.

[0012] "Feedback" refers to opinions and suggestions for improvement based on the user's learning experience and results. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] 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.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] The present invention relates to an AI-based system that provides users with individually optimized educational programs, and includes the following components:

[0035] The server first collects the data necessary for the educational program from sources on the internet and within the company. External sources include online educational platforms and academic databases, while internal sources include past training data within the company. By collecting this data, the server builds an information infrastructure to meet the diverse educational needs of users.

[0036] The terminal provides an interface for users to input their attribute information. This information includes the user's current skill level, areas of interest, and career goals. As users input this information from the terminal and send it to the server, the foundational data for a personalized learning program is formed.

[0037] The server utilizes a generative AI model to generate personalized educational programs based on user attribute information and collected educational data. For example, for a user who wants to improve their marketing skills, it selects an online course that covers the necessary skill set and designs a learning plan that takes the user's schedule into consideration.

[0038] Once a learning program is generated, the server notifies the user of its contents. The terminal receives this notification and displays the user the program details, learning progress, evaluation methods, etc. The user then proceeds with their learning based on this information.

[0039] As the user progresses through the learning process, the device tracks their progress. The server collects this information and uses an AI model to analyze the user's learning speed and comprehension. If necessary, the learning program can be adjusted to match the user's pace.

[0040] Ultimately, users provide feedback via their devices after completing the program. This feedback is sent to a server and used to improve future programs. This cycle continuously provides a system that maximizes learning effectiveness and supports users' career development. For example, for users who want to improve their skills in the medical field, providing real-time information on the latest medical technologies and techniques allows them to efficiently acquire immediately applicable skills.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects data related to educational programs from external sources and internal corporate systems. During this process, it regularly updates information on the latest educational resources and training projects.

[0044] Step 2:

[0045] The terminal displays an interface for the user to input attribute information. The user enters information such as areas of interest, current skill level, and career goals, and sends this information to the server.

[0046] Step 3:

[0047] The server inputs the received user attribute information and collected educational program data into an AI model to generate an optimal educational program for the user. The generated AI model identifies the user's skill gaps and selects recommended courses and materials.

[0048] Step 4:

[0049] The server sends the generated educational program to the terminal and notifies the user. The terminal displays the program's details and prompts the user to prepare to begin learning.

[0050] Step 5:

[0051] The user begins learning based on the educational program provided through the device. The device tracks the learning progress in real time and sends the progress data to the server.

[0052] Step 6:

[0053] The server analyzes the received progress data and checks the user's learning status. If necessary, it adjusts the learning program using an AI model and provides the user with optimal learning advice.

[0054] Step 7:

[0055] After completing the learning program, users provide feedback through their device. This feedback is sent to the server and used to improve future educational programs.

[0056] (Example 1)

[0057] 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."

[0058] In today's world, while there is a demand for diverse skill development and education, providing educational programs optimized for individual users' attributes and learning speeds is challenging. Furthermore, existing systems suffer from inefficient information gathering and progress monitoring, hindering their ability to maximize user learning effectiveness.

[0059] 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.

[0060] In this invention, the server includes means for acquiring user attribute information and collecting information related to educational content, means for generating optimized educational content based on the attribute information and collected information, and means for notifying the user of the optimized educational content and tracking the user's progress. This enables the provision of individually optimized educational programs and flexible program adjustments according to the user's progress.

[0061] "User attribute information" refers to individual user information such as skill level, areas of interest, and career goals.

[0062] "Educational content" refers to information such as learning materials, online courses, and teaching materials necessary for implementing an educational program.

[0063] "Optimized educational content" refers to educational material that is structured in a way that is best suited to each individual user, based on user attribute information and collected data.

[0064] "Notification" refers to the methods and means used to inform users of the details of the generated educational content.

[0065] "Means of tracking progress" refers to methods of recording and evaluating a user's learning activities, understanding, and progress as they progress through an educational program.

[0066] A "generative AI model" refers to a computational model that uses machine learning techniques to optimize educational programs and automatically select appropriate content and modify programs.

[0067] This invention relates to an AI-based system for providing users with individually optimized educational programs. This system consists primarily of a server, a terminal, and a user. Specific embodiments are described below.

[0068] The server first gathers information. It retrieves necessary data from sources such as online education platforms and academic databases on the internet, as well as historical educational data within the organization. Technologies such as APIs and scraping may be used for data collection. The collected data is stored in a database and used for subsequent processing.

[0069] The device provides an interface for users to customize educational programs. This interface allows users to input their current skill level, areas of interest, and career goals. This user attribute information is transmitted to the server in real time and used as foundational data to generate individually optimized educational content.

[0070] The server uses a generative AI model to analyze user attribute information and collected educational data to design an optimized educational program. The AI ​​model utilizes machine learning techniques to automatically select educational content deemed most suitable for the user's needs. For example, if the user inputs a desire to improve their marketing skills, the server will provide the most relevant online courses and plans.

[0071] Once a learning program is generated, the server sends its contents to the terminal, which then notifies the user. The user receives the notification and can proceed with their learning by checking the program details. The terminal also simultaneously tracks and records the learning progress.

[0072] Furthermore, when users complete the program, they provide feedback through their device. The server receives this feedback, saves it as data, and uses it to improve the program later. This allows the system to continuously provide users with an appropriate educational experience.

[0073] As a concrete example, for users who want to improve their skills in the medical field, information on the latest medical technologies and techniques may be provided in real time. In this case, a generative AI model compiles the necessary information in that field and designs an efficient learning plan.

[0074] An example of a prompt to input into a generative AI model is, "If the user wants to improve their skills in the field of marketing, please generate a suitable online course and learning plan." This prompt allows the system to suggest a program tailored to the user's specific needs.

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

[0076] Step 1:

[0077] The server collects the data necessary for the educational program. This process retrieves information from online educational platforms on the internet, academic databases, and historical educational data within the organization. Inputs include APIs and scraping techniques, and output is educational content information stored in a database. This information is systematically organized for use in subsequent processes.

[0078] Step 2:

[0079] The terminal provides an interface where users can input attribute information. Users enter their areas of interest, current skill level, career goals, etc. The input data is sent to the server in real time and stored in the database as the user's profile. This profile information serves as the basis for individually optimizing educational programs.

[0080] Step 3:

[0081] The server generates educational programs using a generative AI model. It combines user profile information with educational content information collected in Step 1 and performs optimization. Specifically, it inputs prompt statements into the generative AI model and calculates a learning plan suitable for the user's needs. The output is an optimized educational program that is automatically adjusted to meet the individual user's requirements.

[0082] Step 4:

[0083] The server notifies the terminal of the generated educational program. Based on this notification, the terminal displays the program details to the user. To enable the user to begin learning, it provides a dashboard with access links to educational content and progress tracking. The displayed information is tailored to the user's current learning stage, supporting efficient learning.

[0084] Step 5:

[0085] As the user progresses through the learning process, the device tracks their progress and sends this data to the server. The server analyzes this progress data and provides an evaluation based on the learning speed and level of understanding. If necessary, it manually adjusts the learning program using a generative AI model to optimize it to the user's pace. Based on these output results, the program is automatically updated.

[0086] Step 6:

[0087] After the user completes the program, the device will present a feedback interface, prompting them to provide feedback on their learning experience. This feedback data will be sent to a server and stored as data for improving future educational programs. The collected feedback information will be used to improve the quality of the program and increase user satisfaction.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] Traditional education systems struggle to provide flexible programs tailored to individual learning needs and characteristics, and standardized educational plans fail to effectively support a large number of learners. In particular, when users study at home, it is difficult to receive appropriate feedback and individualized support, making it challenging to maintain effective learning. Therefore, it is necessary to solve these problems to provide educational support optimized for each individual user and to create a more efficient and effective learning environment.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes means for receiving user attribute information and collecting information related to a learning program; means for generating an optimized learning program based on the attribute information and the collected information; and means for providing the optimized learning program to the user and monitoring the user's progress. This makes it possible to interact with the user via a physical device and provide educational support tailored to individual learning needs.

[0093] "User attribute information" refers to personal characteristics of learners, including information such as their current skill level, areas of interest, and career goals.

[0094] "Information regarding learning programs" refers to data necessary for designing and delivering educational programs, including educational content from external sources and past training data within the organization.

[0095] An "optimized learning program" is an educational program designed based on the learner's individual attribute information and collected data, and is individually tailored to achieve the most effective learning for the learner.

[0096] A "physical device" refers to equipment or machinery used to provide educational support, and is a type of device that provides interactive information to users within the home.

[0097] A "server" in an educational support system is the central computer responsible for collecting, processing, and providing data, and for generating and managing learning programs.

[0098] The system that realizes this application example utilizes educational support robots to provide an individually optimized learning experience. The robot functions as a physical device that serves as infrastructure for the user, receiving user attribute information and implementing appropriate educational programs.

[0099] The server receives user attribute information from the terminal and, in conjunction with this information, collects necessary learning program information from external sources and learning data within the organization. It uses speech recognition engines such as Google® Speech API to obtain data from the user's voice. On the server, OpenAI® generative AI models are used to generate optimized learning programs for each individual user. The AI ​​model automatically adjusts the learning plan according to the learner's skill level and learning progress.

[0100] The robot, acting as the terminal, includes an interface that provides the user with a learning program and monitors the user's learning progress. The robot also has the ability to interact with the user via voice and touch controls and provide immediate feedback.

[0101] For example, when a child is learning about the movement of planets, the robot can use an AI-generated model to display a visual representation of the solar system and explain the concept both audibly and visually. If the child asks, "How long does it take for the Earth to rotate once?", the robot can provide an immediate answer.

[0102] Examples of prompts for generative AI models:

[0103] "The user is an elementary school student who is interested in science. Please generate a learning program for them to learn about the solar system."

[0104] This system makes it possible to provide user-optimized educational support.

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] Users operate an educational support robot and input their learning objectives and interests via voice or touch. The input information is sent from the robot to the server as attribute information. In the case of voice input, the Google Speech API is used to convert the voice data into text.

[0108] Step 2:

[0109] The server collects relevant educational content from external sources (online education platforms and academic databases) and internal sources (organizational training databases) based on the user's attribute information received. The collected educational data is stored in the database.

[0110] Step 3:

[0111] The server inputs collected educational data and user attribute information into a generating AI model. The generating AI model analyzes the input data according to the prompts and generates a learning program optimized for the user's learning needs. In this process, the model selects content based on the user's skill level and goals.

[0112] Step 4:

[0113] The generated learning program is sent from the server to the robot terminal. Based on this program, the robot begins interacting with the user and provides learning support through voice guidance and visual content. Depending on the scenario, it monitors the learning progress and provides appropriate feedback to the user.

[0114] Step 5:

[0115] Each time a user asks a question or performs an action, the device sends that information to the server in real time. The server analyzes the user's behavior data and dynamically adjusts the learning program using a generated AI model as needed. This adjustment result is then sent back to the robot, updating the learning content and providing an optimized learning experience.

[0116] 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.

[0117] This invention combines an emotion engine with a system that provides users with individually optimized educational programs, and is implemented in the following form.

[0118] First, the server collects data related to the educational program from external sources and the company's internal systems. Based on this data, and combined with user attribute information, the server generates an optimized educational program. Using a generation AI model, the program is then adjusted to meet the individual needs of the user.

[0119] The user uses a device to input attribute information and begin learning. The device acquires emotional data in real time through the user's voice and facial expressions. This emotional data is sent from the device to a server and analyzed by an emotion engine.

[0120] The emotion engine on the server analyzes the user's emotions and dynamically adjusts the content of the educational program based on that feedback. This process ensures that if the user is feeling stressed, more relaxing content is provided, while if they are highly motivated, challenging tasks are presented.

[0121] For example, if a user shows signs of anxiety or worry while working on a math program, the server will immediately lower the difficulty level of the assignment and deliver supplementary content to aid understanding. This helps prevent users from becoming discouraged during the learning process.

[0122] Furthermore, after the learning program is completed, user feedback is sent back to the server via the device. This feedback is used to improve the program and contribute to improving the overall quality of the educational system, including emotion recognition.

[0123] This form allows the present invention to provide a flexible educational program that takes into account the user's emotions, aiming to improve a wide range of learning outcomes. As a result, learners can enjoy learning that suits their emotional state and acquire skills efficiently.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The server collects data related to educational programs from external sources and internal company databases. This data includes detailed information about various online courses and training sessions.

[0127] Step 2:

[0128] The terminal provides an interface for users to input attribute information. Users input information such as their areas of interest, current skill level, and target career, and send it to the server.

[0129] Step 3:

[0130] The server uses the received user information and pre-processed data to create an optimized educational program using a generative AI model. This program provides specific learning content and steps based on the user's attributes and goals.

[0131] Step 4:

[0132] The device recognizes the user's emotions in real time as they progress through the learning process. Sensors detect the user's facial expressions and voice, generating emotion data.

[0133] Step 5:

[0134] When a user engages with learning content, the device sends collected emotional data to a server. The server's emotion engine analyzes this data to evaluate the user's current emotional state.

[0135] Step 6:

[0136] Based on evaluations from the emotion engine, the server adjusts the content of the educational program as needed. For example, if a user is showing frustration, the server can suggest simpler and more engaging content.

[0137] Step 7:

[0138] When a user completes their learning, feedback about their learning experience is sent to the server via their device. This feedback is used to improve the program in the future. Furthermore, the relationship between sentiment data and learning results is analyzed and considered as data to improve the system's accuracy.

[0139] (Example 2)

[0140] 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".

[0141] Traditional education systems often provided uniform educational programs without considering the individual attributes or emotional states of users. As a result, users experienced decreased learning efficiency and increased emotional stress. This invention aims to meet individual learning needs and achieve efficient learning by providing an educational program optimized for each user and making dynamic adjustments along the way in response to their emotional state.

[0142] 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.

[0143] In this invention, the server includes means for receiving user attribute information and collecting educational information, means for generating an optimized educational plan based on the attribute information and collected information, and means for acquiring and analyzing the user's emotional state in real time. As a result, the user can receive educational content adapted to their own emotional state, improving their understanding of the material and their motivation to learn.

[0144] "User" refers to an individual who utilizes an educational program, and the learning process takes into account their attribute information and emotional state.

[0145] "Attribute information" refers to personal data about a user, including information such as age, learning history, interests, and learning objectives.

[0146] "Information for education" refers to data necessary for building and optimizing educational programs, including teaching materials, reference materials, and information obtained from educational institutions.

[0147] An "optimized educational plan" refers to a personalized learning program that is adjusted by a generative AI model based on the user's attribute information and collected data.

[0148] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to dynamically optimize and update educational programs.

[0149] "Emotional state" refers to the psychological response of a user during learning, including the degree of stress and motivation obtained from voice and facial expressions.

[0150] "Methods for acquiring and analyzing data in real time" refers to the process of instantly capturing voice and facial expression data provided by the user during training and analyzing it using an emotion engine.

[0151] "Dynamic adjustment means" refers to the process by which the server modifies the content of the educational plan based on the results of the user's sentiment analysis, in order to provide the user with the most suitable learning experience.

[0152] This invention is a system for providing users with individually optimized educational programs, employing a configuration that incorporates an emotion engine. This system operates through the coordinated efforts of three elements: a server, a terminal, and the user.

[0153] The server collects educational information from external data sources and the organization's internal information systems. It uses programming languages ​​such as Python and R to retrieve necessary information via APIs. The collected information is combined with user attribute information, and an optimized educational plan is generated using a generative AI model. This generative AI model is built using machine learning frameworks such as TENSORFLOW®.

[0154] The user enters attribute information using a device and begins learning. This device is equipped with a camera and microphone to recognize the user's voice and facial expressions, and acquires sentiment data using software such as Google Cloud Speech-to-Text and OpenCV. This data is sent to a server in real time and analyzed by an emotion engine.

[0155] The device sends collected emotional data to a server, which then dynamically adjusts the learning plan based on this data. For example, if a user is feeling stressed, the server lowers the difficulty level of the tasks and presents more user-friendly content. This allows the user to learn while reducing stress.

[0156] For example, if a user feels unsure while using a math learning program, the server can immediately reduce the number of calculation problems and provide supplementary explanations. An example of a prompt in this case would be, "Please provide a brief explanation of the mathematical concept that the user is having trouble understanding."

[0157] In this way, users can enjoy a flexible educational experience tailored to their own learning process and acquire skills efficiently.

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

[0159] Step 1:

[0160] The server collects educational information from external data sources and the organization's internal information systems. Inputs include external online databases and internal training materials, while output is a dataset integrating this information. The server preprocesses this dataset using a Python script, converting it into a format suitable for training.

[0161] Step 2:

[0162] Users input their attribute information using a terminal. The input is personal data provided by the user, and the output is that data sent to the server and registered as attribute information. The terminal's user interface is designed to be easy to understand, and information is collected through form input.

[0163] Step 3:

[0164] The server generates an optimized educational plan using a generative AI model based on user attribute information and collected educational data. The input is the dataset obtained in step 1 and the user attribute information provided in step 2. The output is an individually tailored educational plan, with the model dynamically generated using TensorFlow.

[0165] Step 4:

[0166] The user begins learning using a device. The device acquires the user's voice and facial expressions in real time and collects emotion data. The input is real-time audio and video information obtained from the user during learning. The output is emotion data formatted for analysis, and the data is acquired using OpenCV or Google Cloud Speech-to-Text.

[0167] Step 5:

[0168] The device sends acquired emotional data to the server, which then analyzes it using an emotion engine. The input is the user's real-time emotional data, and the output is the emotional analysis result. The emotion engine uses natural language processing technology to analyze the data and identify the user's emotional state.

[0169] Step 6:

[0170] The server dynamically adjusts the educational plan based on the analysis results and redistributes learning content tailored to the user. The input is the sentiment analysis results, and the output is the updated educational plan. In this process, the generative AI model automatically adjusts the learning content and provides difficulty levels and supplementary explanations appropriate for the user.

[0171] Step 7:

[0172] After completing the learning process, users provide feedback, which they send to the server via their device. The input is user feedback based on their learning experience, and the output is data stored on the server for future program improvements. This feedback is used to improve the system's learning algorithm and the accuracy of its emotion recognition.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0175] Traditional educational programs tend to offer uniform content without considering individual user characteristics or real-time emotional states. This can lead to learners experiencing stress or, conversely, losing motivation, hindering efficient learning progress and skill acquisition. Therefore, there is a need to develop systems that provide individually optimized learning experiences that reflect the user's emotional state.

[0176] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0177] In this invention, the server includes means for receiving user characteristic information and aggregating information related to the learning program; means for creating a learning program adjusted based on the characteristic information and the aggregated information; and means for analyzing the user's voice and facial expressions to acquire emotional data and dynamically modify the adjusted learning program in real time. This makes it possible to provide an efficient learning experience that is adapted to the user's emotional state at that moment.

[0178] "User characteristic information" refers to attribute data such as the user's age, knowledge level, and learning objectives.

[0179] "Information related to the learning program" refers to data related to educational content, such as curriculum, teaching materials, and teaching methodologies.

[0180] A "tailored learning program" is educational content that is individualized and optimized based on the user's characteristics and relevant information.

[0181] "Emotional data" refers to data that indicates a user's emotional state in real time, obtained through their voice and facial expressions.

[0182] "Dynamic modification" refers to the process of changing the content and difficulty level of educational materials in real time according to the user's emotional state.

[0183] This invention provides a system that offers an individually optimized learning program based on user characteristic information and real-time emotional data. This system dynamically modifies the learning experience by collecting user attribute information, adjusting the program using a generative AI model, and further analyzing it in real time using an emotional engine.

[0184] The server first aggregates the characteristic information entered by the user with related information collected from external sources and the company's internal systems. Next, it uses a deep learning library such as TensorFlow to create an optimized training program for the generated AI model. This program is customized to meet the individual needs of the user.

[0185] The device uses its camera and microphone to capture the user's voice and facial expressions, and sends this data to the server as emotion data. An emotion engine on the server, such as Microsoft® Azure® Emotion API, analyzes this emotion data to evaluate the user's emotional state. This allows the program content to be dynamically adjusted, providing an educational experience tailored to the user's emotional state at that moment.

[0186] For example, when a user is working on a math curriculum, if the server detects signs of anxiety, it can lower the program's difficulty and provide supplementary videos to facilitate understanding. Similarly, when elderly individuals are undergoing rehabilitation programs, relaxing music can be played to alleviate stress.

[0187] An example of a prompt to input into the generation AI model is, "Generate a prompt to EduRobot to order educational content to display when it has a happy expression."

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

[0189] Step 1:

[0190] The user enters characteristic information into the device. The device retrieves this information and sends it to the server as initial setup. The data entered includes the user's age, knowledge level, and learning objectives, and this is used to individually optimize educational content.

[0191] Step 2:

[0192] The server aggregates information related to the learning program from external sources and the organization's internal systems. This includes curriculum data, teaching materials, and educational methodologies. Based on this information, a generative AI model generates an optimized educational program. The information processing process involves using a generative AI model to create individually optimized learning programs.

[0193] Step 3:

[0194] The device uses its camera and microphone to collect user voice and facial expression data in real time. This data represents the user's emotional state and is transmitted from the device to the server. During this intermediate processing, voice recognition and facial expression analysis are performed to convert the data into emotional data.

[0195] Step 4:

[0196] The server uses an emotion engine, such as the Microsoft Azure Emotion API, to analyze the received emotion data and evaluate the user's emotional state. By analyzing the input emotion data and understanding mood and emotional trends, the system uses this information to adjust the program accordingly.

[0197] Step 5:

[0198] The server dynamically modifies the learning program content in real time based on the evaluated emotion data. If the user is experiencing stress, adjustments such as lowering the program's difficulty level are made. The modified program is optimized for the user's immediate emotional state.

[0199] Step 6:

[0200] The device displays a modified learning program to the user, and the user progresses through the learning process. Through the interface on the device, the user provides feedback while learning, and this information is sent back to the system. This feedback data is accumulated for future program improvements.

[0201] 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.

[0202] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0203] 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.

[0204] [Second Embodiment]

[0205] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0206] 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.

[0207] 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).

[0208] 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.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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".

[0217] The present invention relates to an AI-based system that provides users with individually optimized educational programs, and includes the following components:

[0218] The server first collects the data necessary for the educational program from sources on the internet and within the company. External sources include online educational platforms and academic databases, while internal sources include past training data within the company. By collecting this data, the server builds an information infrastructure to meet the diverse educational needs of users.

[0219] The terminal provides an interface for users to input their attribute information. This information includes the user's current skill level, areas of interest, and career goals. As users input this information from the terminal and send it to the server, the foundational data for a personalized learning program is formed.

[0220] The server utilizes a generative AI model to generate personalized educational programs based on user attribute information and collected educational data. For example, for a user who wants to improve their marketing skills, it selects an online course that covers the necessary skill set and designs a learning plan that takes the user's schedule into consideration.

[0221] Once a learning program is generated, the server notifies the user of its contents. The terminal receives this notification and displays the user the program details, learning progress, evaluation methods, etc. The user then proceeds with their learning based on this information.

[0222] As the user progresses through the learning process, the device tracks their progress. The server collects this information and uses an AI model to analyze the user's learning speed and comprehension. If necessary, the learning program can be adjusted to match the user's pace.

[0223] Ultimately, users provide feedback via their devices after completing the program. This feedback is sent to a server and used to improve future programs. This cycle continuously provides a system that maximizes learning effectiveness and supports users' career development. For example, for users who want to improve their skills in the medical field, providing real-time information on the latest medical technologies and techniques allows them to efficiently acquire immediately applicable skills.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] The server collects data related to educational programs from external sources and internal corporate systems. During this process, it regularly updates information on the latest educational resources and training projects.

[0227] Step 2:

[0228] The terminal displays an interface for the user to input attribute information. The user enters information such as areas of interest, current skill level, and career goals, and sends this information to the server.

[0229] Step 3:

[0230] The server inputs the received user attribute information and collected educational program data into an AI model to generate an optimal educational program for the user. The generated AI model identifies the user's skill gaps and selects recommended courses and materials.

[0231] Step 4:

[0232] The server sends the generated educational program to the terminal and notifies the user. The terminal displays the program's details and prompts the user to prepare to begin learning.

[0233] Step 5:

[0234] The user begins learning based on the educational program provided through the device. The device tracks the learning progress in real time and sends the progress data to the server.

[0235] Step 6:

[0236] The server analyzes the received progress data and checks the user's learning status. If necessary, it adjusts the learning program using an AI model and provides the user with optimal learning advice.

[0237] Step 7:

[0238] After completing the learning program, users provide feedback through their device. This feedback is sent to the server and used to improve future educational programs.

[0239] (Example 1)

[0240] 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".

[0241] In today's world, while there is a demand for diverse skill development and education, providing educational programs optimized for individual users' attributes and learning speeds is challenging. Furthermore, existing systems suffer from inefficient information gathering and progress monitoring, hindering their ability to maximize user learning effectiveness.

[0242] 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.

[0243] In this invention, the server includes means for acquiring user attribute information and collecting information related to educational content, means for generating optimized educational content based on the attribute information and collected information, and means for notifying the user of the optimized educational content and tracking the user's progress. This enables the provision of individually optimized educational programs and flexible program adjustments according to the user's progress.

[0244] "User attribute information" refers to individual user information such as skill level, areas of interest, and career goals.

[0245] "Educational content" refers to information such as learning materials, online courses, and teaching materials necessary for implementing an educational program.

[0246] "Optimized educational content" refers to educational material that is structured in a way that is best suited to each individual user, based on user attribute information and collected data.

[0247] "Notification" refers to the methods and means used to inform users of the details of the generated educational content.

[0248] "Means of tracking progress" refers to methods of recording and evaluating a user's learning activities, understanding, and progress as they progress through an educational program.

[0249] A "generative AI model" refers to a computational model that uses machine learning techniques to optimize educational programs and automatically select appropriate content and modify programs.

[0250] This invention relates to an AI-based system for providing users with individually optimized educational programs. This system consists primarily of a server, a terminal, and a user. Specific embodiments are described below.

[0251] The server first gathers information. It retrieves necessary data from sources such as online education platforms and academic databases on the internet, as well as historical educational data within the organization. Technologies such as APIs and scraping may be used for data collection. The collected data is stored in a database and used for subsequent processing.

[0252] The device provides an interface for users to customize educational programs. This interface allows users to input their current skill level, areas of interest, and career goals. This user attribute information is transmitted to the server in real time and used as foundational data to generate individually optimized educational content.

[0253] The server uses a generative AI model to analyze user attribute information and collected educational data to design an optimized educational program. The AI ​​model utilizes machine learning techniques to automatically select educational content deemed most suitable for the user's needs. For example, if the user inputs a desire to improve their marketing skills, the server will provide the most relevant online courses and plans.

[0254] Once a learning program is generated, the server sends its contents to the terminal, which then notifies the user. The user receives the notification and can proceed with their learning by checking the program details. The terminal also simultaneously tracks and records the learning progress.

[0255] Furthermore, when users complete the program, they provide feedback through their device. The server receives this feedback, saves it as data, and uses it to improve the program later. This allows the system to continuously provide users with an appropriate educational experience.

[0256] As a concrete example, for users who want to improve their skills in the medical field, information on the latest medical technologies and techniques may be provided in real time. In this case, a generative AI model compiles the necessary information in that field and designs an efficient learning plan.

[0257] An example of a prompt to input into a generative AI model is, "If the user wants to improve their skills in the field of marketing, please generate a suitable online course and learning plan." This prompt allows the system to suggest a program tailored to the user's specific needs.

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

[0259] Step 1:

[0260] The server collects the data necessary for the educational program. This process retrieves information from online educational platforms on the internet, academic databases, and historical educational data within the organization. Inputs include APIs and scraping techniques, and output is educational content information stored in a database. This information is systematically organized for use in subsequent processes.

[0261] Step 2:

[0262] The terminal provides an interface where users can input attribute information. Users enter their areas of interest, current skill level, career goals, etc. The input data is sent to the server in real time and stored in the database as the user's profile. This profile information serves as the basis for individually optimizing educational programs.

[0263] Step 3:

[0264] The server generates educational programs using a generative AI model. It combines user profile information with educational content information collected in Step 1 and performs optimization. Specifically, it inputs prompt statements into the generative AI model and calculates a learning plan suitable for the user's needs. The output is an optimized educational program that is automatically adjusted to meet the individual user's requirements.

[0265] Step 4:

[0266] The server notifies the terminal of the generated educational program. Based on this notification, the terminal displays the program details to the user. To enable the user to begin learning, it provides a dashboard with access links to educational content and progress tracking. The displayed information is tailored to the user's current learning stage, supporting efficient learning.

[0267] Step 5:

[0268] As the user progresses through the learning process, the device tracks their progress and sends this data to the server. The server analyzes this progress data and provides an evaluation based on the learning speed and level of understanding. If necessary, it manually adjusts the learning program using a generative AI model to optimize it to the user's pace. Based on these output results, the program is automatically updated.

[0269] Step 6:

[0270] After the user completes the program, the device will present a feedback interface, prompting them to provide feedback on their learning experience. This feedback data will be sent to a server and stored as data for improving future educational programs. The collected feedback information will be used to improve the quality of the program and increase user satisfaction.

[0271] (Application Example 1)

[0272] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] Traditional education systems struggle to provide flexible programs tailored to individual learning needs and characteristics, and standardized educational plans fail to effectively support a large number of learners. In particular, when users study at home, it is difficult to receive appropriate feedback and individualized support, making it challenging to maintain effective learning. Therefore, it is necessary to solve these problems to provide educational support optimized for each individual user and to create a more efficient and effective learning environment.

[0274] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0275] In this invention, the server includes means for receiving user attribute information and collecting information related to a learning program; means for generating an optimized learning program based on the attribute information and the collected information; and means for providing the optimized learning program to the user and monitoring the user's progress. This makes it possible to interact with the user via a physical device and provide educational support tailored to individual learning needs.

[0276] "User attribute information" refers to personal characteristics of learners, including information such as their current skill level, areas of interest, and career goals.

[0277] "Information regarding learning programs" refers to data necessary for designing and delivering educational programs, including educational content from external sources and past training data within the organization.

[0278] An "optimized learning program" is an educational program designed based on the learner's individual attribute information and collected data, and is individually tailored to achieve the most effective learning for the learner.

[0279] A "physical device" refers to equipment or machinery used to provide educational support, and is a type of device that provides interactive information to users within the home.

[0280] A "server" in an educational support system is the central computer responsible for collecting, processing, and providing data, and for generating and managing learning programs.

[0281] The system that realizes this application example utilizes educational support robots to provide an individually optimized learning experience. The robot functions as a physical device that serves as infrastructure for the user, receiving user attribute information and implementing appropriate educational programs.

[0282] The server receives the user's attribute information from the terminal and collects the necessary learning program information from external information sources and learning data within the organization in cooperation with this information. It obtains data from the user's voice using a speech recognition engine such as the Google Speech API. On the server, an optimized learning program is generated for each individual user using OpenAI's generative AI model. The AI model automatically adjusts the learning plan according to the learner's skill level and learning progress.

[0283] The robot, which is the terminal, includes an interface for providing the learning program to the user and monitors the user's learning progress. The robot also has the function of interacting with the user via voice and touch operations and providing immediate feedback.

[0284] As a specific example, when a child is learning about the movement of planets, the robot uses the AI generation model to display a visualization of the solar system and explains the concepts both audibly and visually. When the child asks, "How long does it take for the Earth to rotate once?", the robot can immediately provide an answer accordingly.

[0285] Prompt example for the generative AI model:

[0286] "The user is an elementary school student and is interested in science. Please generate a learning program for learning about the solar system."

[0287] This system makes it possible to provide educational support optimized for the user.

[0288] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] Users operate an educational support robot and input their learning objectives and interests via voice or touch. The input information is sent from the robot to the server as attribute information. In the case of voice input, the Google Speech API is used to convert the voice data into text.

[0291] Step 2:

[0292] The server collects relevant educational content from external sources (online education platforms and academic databases) and internal sources (organizational training databases) based on the user's attribute information received. The collected educational data is stored in the database.

[0293] Step 3:

[0294] The server inputs collected educational data and user attribute information into a generating AI model. The generating AI model analyzes the input data according to the prompts and generates a learning program optimized for the user's learning needs. In this process, the model selects content based on the user's skill level and goals.

[0295] Step 4:

[0296] The generated learning program is sent from the server to the robot terminal. Based on this program, the robot begins interacting with the user and provides learning support through voice guidance and visual content. Depending on the scenario, it monitors the learning progress and provides appropriate feedback to the user.

[0297] Step 5:

[0298] Each time a user asks a question or performs an action, the device sends that information to the server in real time. The server analyzes the user's behavior data and dynamically adjusts the learning program using a generated AI model as needed. This adjustment result is then sent back to the robot, updating the learning content and providing an optimized learning experience.

[0299] 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.

[0300] This invention combines an emotion engine with a system that provides users with individually optimized educational programs, and is implemented in the following form.

[0301] First, the server collects data related to the educational program from external sources and the company's internal systems. Based on this data, and combined with user attribute information, the server generates an optimized educational program. Using a generation AI model, the program is then adjusted to meet the individual needs of the user.

[0302] The user uses a device to input attribute information and begin learning. The device acquires emotional data in real time through the user's voice and facial expressions. This emotional data is sent from the device to a server and analyzed by an emotion engine.

[0303] The emotion engine on the server analyzes the user's emotions and dynamically adjusts the content of the educational program based on that feedback. This process ensures that if the user is feeling stressed, more relaxing content is provided, while if they are highly motivated, challenging tasks are presented.

[0304] For example, if a user shows signs of anxiety or worry while working on a math program, the server will immediately lower the difficulty level of the assignment and deliver supplementary content to aid understanding. This helps prevent users from becoming discouraged during the learning process.

[0305] Furthermore, after the learning program ends, the user's feedback is returned to the server through the terminal. This feedback is utilized for the following program improvements and contributes to the overall quality improvement of the education system incorporating emotion recognition.

[0306] In this form, the present invention provides a flexible education program considering the user's emotions, aiming to improve a wide range of learning effects. As a result, learners can enjoy learning that suits their emotional state, enabling efficient skill acquisition.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] The server collects data related to the education program from external information sources and the enterprise's internal database. This data includes details of various online courses and training sessions.

[0310] Step 2:

[0311] The terminal provides an interface for the user to input attribute information. The user inputs information such as the fields of interest, current skill level, and target career, and transmits it to the server.

[0312] Step 3:

[0313] The server creates an education program optimized by the generative AI model using the received user information and the data collected in the preprocessing. This program provides specific learning content and steps based on the user's attributes and goals.

[0314] Step 4:

[0315] The terminal recognizes the user's emotions in real time when the user progresses in learning. At this time, the user's expression and voice are detected by sensors to generate emotion data.

[0316] Step 5:

[0317] When a user engages with learning content, the device sends collected emotional data to a server. The server's emotion engine analyzes this data to evaluate the user's current emotional state.

[0318] Step 6:

[0319] Based on evaluations from the emotion engine, the server adjusts the content of the educational program as needed. For example, if a user is showing frustration, the server can suggest simpler and more engaging content.

[0320] Step 7:

[0321] When a user completes their learning, feedback about their learning experience is sent to the server via their device. This feedback is used to improve the program in the future. Furthermore, the relationship between sentiment data and learning results is analyzed and considered as data to improve the system's accuracy.

[0322] (Example 2)

[0323] 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".

[0324] Traditional education systems often provided uniform educational programs without considering the individual attributes or emotional states of users. As a result, users experienced decreased learning efficiency and increased emotional stress. This invention aims to meet individual learning needs and achieve efficient learning by providing an educational program optimized for each user and making dynamic adjustments along the way in response to their emotional state.

[0325] 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.

[0326] In this invention, the server includes means for receiving user attribute information and collecting educational information, means for generating an optimized educational plan based on the attribute information and collected information, and means for acquiring and analyzing the user's emotional state in real time. As a result, the user can receive educational content adapted to their own emotional state, improving their understanding of the material and their motivation to learn.

[0327] "User" refers to an individual who utilizes an educational program, and the learning process takes into account their attribute information and emotional state.

[0328] "Attribute information" refers to personal data about a user, including information such as age, learning history, interests, and learning objectives.

[0329] "Information for education" refers to data necessary for building and optimizing educational programs, including teaching materials, reference materials, and information obtained from educational institutions.

[0330] An "optimized educational plan" refers to a personalized learning program that is adjusted by a generative AI model based on the user's attribute information and collected data.

[0331] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to dynamically optimize and update educational programs.

[0332] "Emotional state" refers to the psychological response of a user during learning, including the degree of stress and motivation obtained from voice and facial expressions.

[0333] "Methods for acquiring and analyzing data in real time" refers to the process of instantly capturing voice and facial expression data provided by the user during training and analyzing it using an emotion engine.

[0334] "Dynamic adjustment means" refers to the process by which the server modifies the content of the educational plan based on the results of the user's sentiment analysis, in order to provide the user with the most suitable learning experience.

[0335] This invention is a system for providing users with individually optimized educational programs, employing a configuration that incorporates an emotion engine. This system operates through the coordinated efforts of three elements: a server, a terminal, and the user.

[0336] The server collects educational information from external data sources and the organization's internal information systems. It retrieves the necessary information via APIs using programming languages ​​such as Python and R. The collected information is combined with user attribute information, and an optimized educational plan is generated using a generative AI model. This generative AI model is built using machine learning frameworks such as TensorFlow.

[0337] The user enters attribute information using a device and begins learning. This device is equipped with a camera and microphone to recognize the user's voice and facial expressions, and acquires sentiment data using software such as Google Cloud Speech-to-Text and OpenCV. This data is sent to a server in real time and analyzed by an emotion engine.

[0338] The device sends collected emotional data to a server, which then dynamically adjusts the learning plan based on this data. For example, if a user is feeling stressed, the server lowers the difficulty level of the tasks and presents more user-friendly content. This allows the user to learn while reducing stress.

[0339] For example, if a user feels unsure while using a math learning program, the server can immediately reduce the number of calculation problems and provide supplementary explanations. An example of a prompt in this case would be, "Please provide a brief explanation of the mathematical concept that the user is having trouble understanding."

[0340] In this way, users can enjoy a flexible educational experience tailored to their own learning process and acquire skills efficiently.

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

[0342] Step 1:

[0343] The server collects educational information from external data sources and the organization's internal information systems. Inputs include external online databases and internal training materials, while output is a dataset integrating this information. The server preprocesses this dataset using a Python script, converting it into a format suitable for training.

[0344] Step 2:

[0345] Users input their attribute information using a terminal. The input is personal data provided by the user, and the output is that data sent to the server and registered as attribute information. The terminal's user interface is designed to be easy to understand, and information is collected through form input.

[0346] Step 3:

[0347] The server generates an optimized educational plan using a generative AI model based on user attribute information and collected educational data. The input is the dataset obtained in step 1 and the user attribute information provided in step 2. The output is an individually tailored educational plan, with the model dynamically generated using TensorFlow.

[0348] Step 4:

[0349] The user begins learning using a device. The device acquires the user's voice and facial expressions in real time and collects emotion data. The input is real-time audio and video information obtained from the user during learning. The output is emotion data formatted for analysis, and the data is acquired using OpenCV or Google Cloud Speech-to-Text.

[0350] Step 5:

[0351] The device sends acquired emotional data to the server, which then analyzes it using an emotion engine. The input is the user's real-time emotional data, and the output is the emotional analysis result. The emotion engine uses natural language processing technology to analyze the data and identify the user's emotional state.

[0352] Step 6:

[0353] The server dynamically adjusts the educational plan based on the analysis results and redistributes learning content tailored to the user. The input is the sentiment analysis results, and the output is the updated educational plan. In this process, the generative AI model automatically adjusts the learning content and provides difficulty levels and supplementary explanations appropriate for the user.

[0354] Step 7:

[0355] After completing the learning process, users provide feedback, which they send to the server via their device. The input is user feedback based on their learning experience, and the output is data stored on the server for future program improvements. This feedback is used to improve the system's learning algorithm and the accuracy of its emotion recognition.

[0356] (Application Example 2)

[0357] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0358] Traditional educational programs tend to offer uniform content without considering individual user characteristics or real-time emotional states. This can lead to learners experiencing stress or, conversely, losing motivation, hindering efficient learning progress and skill acquisition. Therefore, there is a need to develop systems that provide individually optimized learning experiences that reflect the user's emotional state.

[0359] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0360] In this invention, the server includes means for receiving user characteristic information and aggregating information related to the learning program; means for creating a learning program adjusted based on the characteristic information and the aggregated information; and means for analyzing the user's voice and facial expressions to acquire emotional data and dynamically modify the adjusted learning program in real time. This makes it possible to provide an efficient learning experience that is adapted to the user's emotional state at that moment.

[0361] "User characteristic information" refers to attribute data such as the user's age, knowledge level, and learning objectives.

[0362] "Information related to the learning program" refers to data related to educational content, such as curriculum, teaching materials, and teaching methodologies.

[0363] A "tailored learning program" is educational content that is individualized and optimized based on the user's characteristics and relevant information.

[0364] "Emotional data" refers to data that indicates a user's emotional state in real time, obtained through their voice and facial expressions.

[0365] "Dynamic modification" refers to the process of changing the content and difficulty level of educational materials in real time according to the user's emotional state.

[0366] This invention provides a system that offers an individually optimized learning program based on user characteristic information and real-time emotional data. This system dynamically modifies the learning experience by collecting user attribute information, adjusting the program using a generative AI model, and further analyzing it in real time using an emotional engine.

[0367] The server first aggregates the characteristic information entered by the user with related information collected from external sources and the company's internal systems. Next, it uses a deep learning library such as TensorFlow to create an optimized training program for the generated AI model. This program is customized to meet the individual needs of the user.

[0368] The device uses its camera and microphone to capture the user's voice and facial expressions, and sends this data to the server as emotion data. An emotion engine on the server, such as the Microsoft Azure Emotion API, analyzes this emotion data to evaluate the user's emotional state. This allows the program content to be dynamically adjusted, providing an educational experience tailored to the user's emotional state at that moment.

[0369] For example, when a user is working on a math curriculum, if the server detects signs of anxiety, it can lower the program's difficulty and provide supplementary videos to facilitate understanding. Similarly, when elderly individuals are undergoing rehabilitation programs, relaxing music can be played to alleviate stress.

[0370] An example of a prompt to input into the generation AI model is, "Generate a prompt to EduRobot to order educational content to display when it has a happy expression."

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

[0372] Step 1:

[0373] The user enters characteristic information into the device. The device retrieves this information and sends it to the server as initial setup. The data entered includes the user's age, knowledge level, and learning objectives, and this is used to individually optimize educational content.

[0374] Step 2:

[0375] The server aggregates information related to the learning program from external sources and the organization's internal systems. This includes curriculum data, teaching materials, and educational methodologies. Based on this information, a generative AI model generates an optimized educational program. The information processing process involves using a generative AI model to create individually optimized learning programs.

[0376] Step 3:

[0377] The device uses its camera and microphone to collect user voice and facial expression data in real time. This data represents the user's emotional state and is transmitted from the device to the server. During this intermediate processing, voice recognition and facial expression analysis are performed to convert the data into emotional data.

[0378] Step 4:

[0379] The server uses an emotion engine, such as the Microsoft Azure Emotion API, to analyze the received emotion data and evaluate the user's emotional state. By analyzing the input emotion data and understanding mood and emotional trends, the system uses this information to adjust the program accordingly.

[0380] Step 5:

[0381] The server dynamically modifies the learning program content in real time based on the evaluated emotion data. If the user is experiencing stress, adjustments such as lowering the program's difficulty level are made. The modified program is optimized for the user's immediate emotional state.

[0382] Step 6:

[0383] The device displays a modified learning program to the user, and the user progresses through the learning process. Through the interface on the device, the user provides feedback while learning, and this information is sent back to the system. This feedback data is accumulated for future program improvements.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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".

[0400] The present invention relates to an AI-based system that provides users with individually optimized educational programs, and includes the following components:

[0401] The server first collects the data necessary for the educational program from sources on the internet and within the company. External sources include online educational platforms and academic databases, while internal sources include past training data within the company. By collecting this data, the server builds an information infrastructure to meet the diverse educational needs of users.

[0402] The terminal provides an interface for users to input their attribute information. This information includes the user's current skill level, areas of interest, and career goals. As users input this information from the terminal and send it to the server, the foundational data for a personalized learning program is formed.

[0403] The server utilizes a generative AI model to generate personalized educational programs based on user attribute information and collected educational data. For example, for a user who wants to improve their marketing skills, it selects an online course that covers the necessary skill set and designs a learning plan that takes the user's schedule into consideration.

[0404] Once a learning program is generated, the server notifies the user of its contents. The terminal receives this notification and displays the user the program details, learning progress, evaluation methods, etc. The user then proceeds with their learning based on this information.

[0405] As the user progresses through the learning process, the device tracks their progress. The server collects this information and uses an AI model to analyze the user's learning speed and comprehension. If necessary, the learning program can be adjusted to match the user's pace.

[0406] Ultimately, users provide feedback via their devices after completing the program. This feedback is sent to a server and used to improve future programs. This cycle continuously provides a system that maximizes learning effectiveness and supports users' career development. For example, for users who want to improve their skills in the medical field, providing real-time information on the latest medical technologies and techniques allows them to efficiently acquire immediately applicable skills.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] The server collects data related to educational programs from external sources and internal corporate systems. During this process, it regularly updates information on the latest educational resources and training projects.

[0410] Step 2:

[0411] The terminal displays an interface for the user to input attribute information. The user enters information such as areas of interest, current skill level, and career goals, and sends this information to the server.

[0412] Step 3:

[0413] The server inputs the received user attribute information and collected educational program data into an AI model to generate an optimal educational program for the user. The generated AI model identifies the user's skill gaps and selects recommended courses and materials.

[0414] Step 4:

[0415] The server sends the generated educational program to the terminal and notifies the user. The terminal displays the program's details and prompts the user to prepare to begin learning.

[0416] Step 5:

[0417] The user begins learning based on the educational program provided through the device. The device tracks the learning progress in real time and sends the progress data to the server.

[0418] Step 6:

[0419] The server analyzes the received progress data and checks the user's learning status. If necessary, it adjusts the learning program using an AI model and provides the user with optimal learning advice.

[0420] Step 7:

[0421] After completing the learning program, users provide feedback through their device. This feedback is sent to the server and used to improve future educational programs.

[0422] (Example 1)

[0423] 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."

[0424] In today's world, while there is a demand for diverse skill development and education, providing educational programs optimized for individual users' attributes and learning speeds is challenging. Furthermore, existing systems suffer from inefficient information gathering and progress monitoring, hindering their ability to maximize user learning effectiveness.

[0425] 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.

[0426] In this invention, the server includes means for acquiring user attribute information and collecting information related to educational content, means for generating optimized educational content based on the attribute information and collected information, and means for notifying the user of the optimized educational content and tracking the user's progress. This enables the provision of individually optimized educational programs and flexible program adjustments according to the user's progress.

[0427] "User attribute information" refers to individual user information such as skill level, areas of interest, and career goals.

[0428] "Educational content" refers to information such as learning materials, online courses, and teaching materials necessary for implementing an educational program.

[0429] "Optimized educational content" refers to educational material that is structured in a way that is best suited to each individual user, based on user attribute information and collected data.

[0430] "Notification" refers to the methods and means used to inform users of the details of the generated educational content.

[0431] "Means of tracking progress" refers to methods of recording and evaluating a user's learning activities, understanding, and progress as they progress through an educational program.

[0432] A "generative AI model" refers to a computational model that uses machine learning techniques to optimize educational programs and automatically select appropriate content and modify programs.

[0433] This invention relates to an AI-based system for providing users with individually optimized educational programs. This system consists primarily of a server, a terminal, and a user. Specific embodiments are described below.

[0434] The server first gathers information. It retrieves necessary data from sources such as online education platforms and academic databases on the internet, as well as historical educational data within the organization. Technologies such as APIs and scraping may be used for data collection. The collected data is stored in a database and used for subsequent processing.

[0435] The device provides an interface for users to customize educational programs. This interface allows users to input their current skill level, areas of interest, and career goals. This user attribute information is transmitted to the server in real time and used as foundational data to generate individually optimized educational content.

[0436] The server uses a generative AI model to analyze user attribute information and collected educational data to design an optimized educational program. The AI ​​model utilizes machine learning techniques to automatically select educational content deemed most suitable for the user's needs. For example, if the user inputs a desire to improve their marketing skills, the server will provide the most relevant online courses and plans.

[0437] Once a learning program is generated, the server sends its contents to the terminal, which then notifies the user. The user receives the notification and can proceed with their learning by checking the program details. The terminal also simultaneously tracks and records the learning progress.

[0438] Furthermore, when users complete the program, they provide feedback through their device. The server receives this feedback, saves it as data, and uses it to improve the program later. This allows the system to continuously provide users with an appropriate educational experience.

[0439] As a concrete example, for users who want to improve their skills in the medical field, information on the latest medical technologies and techniques may be provided in real time. In this case, a generative AI model compiles the necessary information in that field and designs an efficient learning plan.

[0440] An example of a prompt to input into a generative AI model is, "If the user wants to improve their skills in the field of marketing, please generate a suitable online course and learning plan." This prompt allows the system to suggest a program tailored to the user's specific needs.

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

[0442] Step 1:

[0443] The server collects the data necessary for the educational program. This process retrieves information from online educational platforms on the internet, academic databases, and historical educational data within the organization. Inputs include APIs and scraping techniques, and output is educational content information stored in a database. This information is systematically organized for use in subsequent processes.

[0444] Step 2:

[0445] The terminal provides an interface where users can input attribute information. Users enter their areas of interest, current skill level, career goals, etc. The input data is sent to the server in real time and stored in the database as the user's profile. This profile information serves as the basis for individually optimizing educational programs.

[0446] Step 3:

[0447] The server generates educational programs using a generative AI model. It combines user profile information with educational content information collected in Step 1 and performs optimization. Specifically, it inputs prompt statements into the generative AI model and calculates a learning plan suitable for the user's needs. The output is an optimized educational program that is automatically adjusted to meet the individual user's requirements.

[0448] Step 4:

[0449] The server notifies the terminal of the generated educational program. Based on this notification, the terminal displays the program details to the user. To enable the user to begin learning, it provides a dashboard with access links to educational content and progress tracking. The displayed information is tailored to the user's current learning stage, supporting efficient learning.

[0450] Step 5:

[0451] As the user progresses through the learning process, the device tracks their progress and sends this data to the server. The server analyzes this progress data and provides an evaluation based on the learning speed and level of understanding. If necessary, it manually adjusts the learning program using a generative AI model to optimize it to the user's pace. Based on these output results, the program is automatically updated.

[0452] Step 6:

[0453] After the user completes the program, the device will present a feedback interface, prompting them to provide feedback on their learning experience. This feedback data will be sent to a server and stored as data for improving future educational programs. The collected feedback information will be used to improve the quality of the program and increase user satisfaction.

[0454] (Application Example 1)

[0455] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0456] Traditional education systems struggle to provide flexible programs tailored to individual learning needs and characteristics, and standardized educational plans fail to effectively support a large number of learners. In particular, when users study at home, it is difficult to receive appropriate feedback and individualized support, making it challenging to maintain effective learning. Therefore, it is necessary to solve these problems to provide educational support optimized for each individual user and to create a more efficient and effective learning environment.

[0457] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0458] In this invention, the server includes means for receiving user attribute information and collecting information related to a learning program; means for generating an optimized learning program based on the attribute information and the collected information; and means for providing the optimized learning program to the user and monitoring the user's progress. This makes it possible to interact with the user via a physical device and provide educational support tailored to individual learning needs.

[0459] "User attribute information" refers to personal characteristics of learners, including information such as their current skill level, areas of interest, and career goals.

[0460] "Information regarding learning programs" refers to data necessary for designing and delivering educational programs, including educational content from external sources and past training data within the organization.

[0461] An "optimized learning program" is an educational program designed based on the learner's individual attribute information and collected data, and is individually tailored to achieve the most effective learning for the learner.

[0462] A "physical device" refers to equipment or machinery used to provide educational support, and is a type of device that provides interactive information to users within the home.

[0463] A "server" in an educational support system is the central computer responsible for collecting, processing, and providing data, and for generating and managing learning programs.

[0464] The system that realizes this application example utilizes educational support robots to provide an individually optimized learning experience. The robot functions as a physical device that serves as infrastructure for the user, receiving user attribute information and implementing appropriate educational programs.

[0465] The server receives user attribute information from the terminal and, in conjunction with this information, collects necessary learning program information from external sources and internal learning data within the organization. It uses speech recognition engines such as the Google Speech API to obtain data from the user's voice. On the server, OpenAI's generative AI model is used to generate optimized learning programs for each individual user. The AI ​​model automatically adjusts the learning plan according to the learner's skill level and learning progress.

[0466] The robot, acting as the terminal, includes an interface that provides the user with a learning program and monitors the user's learning progress. The robot also has the ability to interact with the user via voice and touch controls and provide immediate feedback.

[0467] For example, when a child is learning about the movement of planets, the robot can use an AI-generated model to display a visual representation of the solar system and explain the concept both audibly and visually. If the child asks, "How long does it take for the Earth to rotate once?", the robot can provide an immediate answer.

[0468] Examples of prompts for generative AI models:

[0469] "The user is an elementary school student who is interested in science. Please generate a learning program for them to learn about the solar system."

[0470] This system makes it possible to provide user-optimized educational support.

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] Users operate an educational support robot and input their learning objectives and interests via voice or touch. The input information is sent from the robot to the server as attribute information. In the case of voice input, the Google Speech API is used to convert the voice data into text.

[0474] Step 2:

[0475] The server collects relevant educational content from external sources (online education platforms and academic databases) and internal sources (organizational training databases) based on the user's attribute information received. The collected educational data is stored in the database.

[0476] Step 3:

[0477] The server inputs collected educational data and user attribute information into a generating AI model. The generating AI model analyzes the input data according to the prompts and generates a learning program optimized for the user's learning needs. In this process, the model selects content based on the user's skill level and goals.

[0478] Step 4:

[0479] The generated learning program is sent from the server to the robot terminal. Based on this program, the robot begins interacting with the user and provides learning support through voice guidance and visual content. Depending on the scenario, it monitors the learning progress and provides appropriate feedback to the user.

[0480] Step 5:

[0481] Each time a user asks a question or performs an action, the device sends that information to the server in real time. The server analyzes the user's behavior data and dynamically adjusts the learning program using a generated AI model as needed. This adjustment result is then sent back to the robot, updating the learning content and providing an optimized learning experience.

[0482] 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.

[0483] This invention combines an emotion engine with a system that provides users with individually optimized educational programs, and is implemented in the following form.

[0484] First, the server collects data related to the educational program from external sources and the company's internal systems. Based on this data, and combined with user attribute information, the server generates an optimized educational program. Using a generation AI model, the program is then adjusted to meet the individual needs of the user.

[0485] The user uses a device to input attribute information and begin learning. The device acquires emotional data in real time through the user's voice and facial expressions. This emotional data is sent from the device to a server and analyzed by an emotion engine.

[0486] The emotion engine on the server analyzes the user's emotions and dynamically adjusts the content of the educational program based on that feedback. This process ensures that if the user is feeling stressed, more relaxing content is provided, while if they are highly motivated, challenging tasks are presented.

[0487] For example, if a user shows signs of anxiety or worry while working on a math program, the server will immediately lower the difficulty level of the assignment and deliver supplementary content to aid understanding. This helps prevent users from becoming discouraged during the learning process.

[0488] Furthermore, after the learning program is completed, user feedback is sent back to the server via the device. This feedback is used to improve the program and contribute to improving the overall quality of the educational system, including emotion recognition.

[0489] This form allows the present invention to provide a flexible educational program that takes into account the user's emotions, aiming to improve a wide range of learning outcomes. As a result, learners can enjoy learning that suits their emotional state and acquire skills efficiently.

[0490] The following describes the processing flow.

[0491] Step 1:

[0492] The server collects data related to educational programs from external sources and internal company databases. This data includes detailed information about various online courses and training sessions.

[0493] Step 2:

[0494] The terminal provides an interface for users to input attribute information. Users input information such as their areas of interest, current skill level, and target career, and send it to the server.

[0495] Step 3:

[0496] The server uses the received user information and pre-processed data to create an optimized educational program using a generative AI model. This program provides specific learning content and steps based on the user's attributes and goals.

[0497] Step 4:

[0498] The device recognizes the user's emotions in real time as they progress through the learning process. Sensors detect the user's facial expressions and voice, generating emotion data.

[0499] Step 5:

[0500] When a user engages with learning content, the device sends collected emotional data to a server. The server's emotion engine analyzes this data to evaluate the user's current emotional state.

[0501] Step 6:

[0502] Based on evaluations from the emotion engine, the server adjusts the content of the educational program as needed. For example, if a user is showing frustration, the server can suggest simpler and more engaging content.

[0503] Step 7:

[0504] When a user completes their learning, feedback about their learning experience is sent to the server via their device. This feedback is used to improve the program in the future. Furthermore, the relationship between sentiment data and learning results is analyzed and considered as data to improve the system's accuracy.

[0505] (Example 2)

[0506] 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."

[0507] Traditional education systems often provided uniform educational programs without considering the individual attributes or emotional states of users. As a result, users experienced decreased learning efficiency and increased emotional stress. This invention aims to meet individual learning needs and achieve efficient learning by providing an educational program optimized for each user and making dynamic adjustments along the way in response to their emotional state.

[0508] 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.

[0509] In this invention, the server includes means for receiving user attribute information and collecting educational information, means for generating an optimized educational plan based on the attribute information and collected information, and means for acquiring and analyzing the user's emotional state in real time. As a result, the user can receive educational content adapted to their own emotional state, improving their understanding of the material and their motivation to learn.

[0510] "User" refers to an individual who utilizes an educational program, and the learning process takes into account their attribute information and emotional state.

[0511] "Attribute information" refers to personal data about a user, including information such as age, learning history, interests, and learning objectives.

[0512] "Information for education" refers to data necessary for building and optimizing educational programs, including teaching materials, reference materials, and information obtained from educational institutions.

[0513] An "optimized educational plan" refers to a personalized learning program that is adjusted by a generative AI model based on the user's attribute information and collected data.

[0514] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to dynamically optimize and update educational programs.

[0515] "Emotional state" refers to the psychological response of a user during learning, including the degree of stress and motivation obtained from voice and facial expressions.

[0516] "Methods for acquiring and analyzing data in real time" refers to the process of instantly capturing voice and facial expression data provided by the user during training and analyzing it using an emotion engine.

[0517] "Dynamic adjustment means" refers to the process by which the server modifies the content of the educational plan based on the results of the user's sentiment analysis, in order to provide the user with the most suitable learning experience.

[0518] This invention is a system for providing users with individually optimized educational programs, employing a configuration that incorporates an emotion engine. This system operates through the coordinated efforts of three elements: a server, a terminal, and the user.

[0519] The server collects educational information from external data sources and the organization's internal information systems. It retrieves the necessary information via APIs using programming languages ​​such as Python and R. The collected information is combined with user attribute information, and an optimized educational plan is generated using a generative AI model. This generative AI model is built using machine learning frameworks such as TensorFlow.

[0520] The user enters attribute information using a device and begins learning. This device is equipped with a camera and microphone to recognize the user's voice and facial expressions, and acquires sentiment data using software such as Google Cloud Speech-to-Text and OpenCV. This data is sent to a server in real time and analyzed by an emotion engine.

[0521] The device sends collected emotional data to a server, which then dynamically adjusts the learning plan based on this data. For example, if a user is feeling stressed, the server lowers the difficulty level of the tasks and presents more user-friendly content. This allows the user to learn while reducing stress.

[0522] For example, if a user feels unsure while using a math learning program, the server can immediately reduce the number of calculation problems and provide supplementary explanations. An example of a prompt in this case would be, "Please provide a brief explanation of the mathematical concept that the user is having trouble understanding."

[0523] In this way, users can enjoy a flexible educational experience tailored to their own learning process and acquire skills efficiently.

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

[0525] Step 1:

[0526] The server collects educational information from external data sources and the organization's internal information systems. Inputs include external online databases and internal training materials, while output is a dataset integrating this information. The server preprocesses this dataset using a Python script, converting it into a format suitable for training.

[0527] Step 2:

[0528] Users input their attribute information using a terminal. The input is personal data provided by the user, and the output is that data sent to the server and registered as attribute information. The terminal's user interface is designed to be easy to understand, and information is collected through form input.

[0529] Step 3:

[0530] The server generates an optimized educational plan using a generative AI model based on user attribute information and collected educational data. The input is the dataset obtained in step 1 and the user attribute information provided in step 2. The output is an individually tailored educational plan, with the model dynamically generated using TensorFlow.

[0531] Step 4:

[0532] The user begins learning using a device. The device acquires the user's voice and facial expressions in real time and collects emotion data. The input is real-time audio and video information obtained from the user during learning. The output is emotion data formatted for analysis, and the data is acquired using OpenCV or Google Cloud Speech-to-Text.

[0533] Step 5:

[0534] The device sends acquired emotional data to the server, which then analyzes it using an emotion engine. The input is the user's real-time emotional data, and the output is the emotional analysis result. The emotion engine uses natural language processing technology to analyze the data and identify the user's emotional state.

[0535] Step 6:

[0536] The server dynamically adjusts the educational plan based on the analysis results and redistributes learning content tailored to the user. The input is the sentiment analysis results, and the output is the updated educational plan. In this process, the generative AI model automatically adjusts the learning content and provides difficulty levels and supplementary explanations appropriate for the user.

[0537] Step 7:

[0538] After completing the learning process, users provide feedback, which they send to the server via their device. The input is user feedback based on their learning experience, and the output is data stored on the server for future program improvements. This feedback is used to improve the system's learning algorithm and the accuracy of its emotion recognition.

[0539] (Application Example 2)

[0540] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0541] Traditional educational programs tend to offer uniform content without considering individual user characteristics or real-time emotional states. This can lead to learners experiencing stress or, conversely, losing motivation, hindering efficient learning progress and skill acquisition. Therefore, there is a need to develop systems that provide individually optimized learning experiences that reflect the user's emotional state.

[0542] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0543] In this invention, the server includes means for receiving user characteristic information and aggregating information related to the learning program; means for creating a learning program adjusted based on the characteristic information and the aggregated information; and means for analyzing the user's voice and facial expressions to acquire emotional data and dynamically modify the adjusted learning program in real time. This makes it possible to provide an efficient learning experience that is adapted to the user's emotional state at that moment.

[0544] "User characteristic information" refers to attribute data such as the user's age, knowledge level, and learning objectives.

[0545] "Information related to the learning program" refers to data related to educational content, such as curriculum, teaching materials, and teaching methodologies.

[0546] A "tailored learning program" is educational content that is individualized and optimized based on the user's characteristics and relevant information.

[0547] "Emotional data" refers to data that indicates a user's emotional state in real time, obtained through their voice and facial expressions.

[0548] "Dynamic modification" refers to the process of changing the content and difficulty level of educational materials in real time according to the user's emotional state.

[0549] This invention provides a system that offers an individually optimized learning program based on user characteristic information and real-time emotional data. This system dynamically modifies the learning experience by collecting user attribute information, adjusting the program using a generative AI model, and further analyzing it in real time using an emotional engine.

[0550] The server first aggregates the characteristic information entered by the user with related information collected from external sources and the company's internal systems. Next, it uses a deep learning library such as TensorFlow to create an optimized training program for the generated AI model. This program is customized to meet the individual needs of the user.

[0551] The device uses its camera and microphone to capture the user's voice and facial expressions, and sends this data to the server as emotion data. An emotion engine on the server, such as the Microsoft Azure Emotion API, analyzes this emotion data to evaluate the user's emotional state. This allows the program content to be dynamically adjusted, providing an educational experience tailored to the user's emotional state at that moment.

[0552] For example, when a user is working on a math curriculum, if the server detects signs of anxiety, it can lower the program's difficulty and provide supplementary videos to facilitate understanding. Similarly, when elderly individuals are undergoing rehabilitation programs, relaxing music can be played to alleviate stress.

[0553] An example of a prompt to input into the generation AI model is, "Generate a prompt to EduRobot to order educational content to display when it has a happy expression."

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

[0555] Step 1:

[0556] The user enters characteristic information into the device. The device retrieves this information and sends it to the server as initial setup. The data entered includes the user's age, knowledge level, and learning objectives, and this is used to individually optimize educational content.

[0557] Step 2:

[0558] The server aggregates information related to the learning program from external sources and the organization's internal systems. This includes curriculum data, teaching materials, and educational methodologies. Based on this information, a generative AI model generates an optimized educational program. The information processing process involves using a generative AI model to create individually optimized learning programs.

[0559] Step 3:

[0560] The device uses its camera and microphone to collect user voice and facial expression data in real time. This data represents the user's emotional state and is transmitted from the device to the server. During this intermediate processing, voice recognition and facial expression analysis are performed to convert the data into emotional data.

[0561] Step 4:

[0562] The server uses an emotion engine, such as the Microsoft Azure Emotion API, to analyze the received emotion data and evaluate the user's emotional state. By analyzing the input emotion data and understanding mood and emotional trends, the system uses this information to adjust the program accordingly.

[0563] Step 5:

[0564] The server dynamically modifies the learning program content in real time based on the evaluated emotion data. If the user is experiencing stress, adjustments such as lowering the program's difficulty level are made. The modified program is optimized for the user's immediate emotional state.

[0565] Step 6:

[0566] The device displays a modified learning program to the user, and the user progresses through the learning process. Through the interface on the device, the user provides feedback while learning, and this information is sent back to the system. This feedback data is accumulated for future program improvements.

[0567] 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.

[0568] 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.

[0569] 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.

[0570] [Fourth Embodiment]

[0571] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0572] 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.

[0573] 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).

[0574] 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.

[0575] 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.

[0576] 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).

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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".

[0584] The present invention relates to an AI-based system that provides users with individually optimized educational programs, and includes the following components:

[0585] The server first collects the data necessary for the educational program from sources on the internet and within the company. External sources include online educational platforms and academic databases, while internal sources include past training data within the company. By collecting this data, the server builds an information infrastructure to meet the diverse educational needs of users.

[0586] The terminal provides an interface for users to input their attribute information. This information includes the user's current skill level, areas of interest, and career goals. As users input this information from the terminal and send it to the server, the foundational data for a personalized learning program is formed.

[0587] The server utilizes a generative AI model to generate personalized educational programs based on user attribute information and collected educational data. For example, for a user who wants to improve their marketing skills, it selects an online course that covers the necessary skill set and designs a learning plan that takes the user's schedule into consideration.

[0588] Once a learning program is generated, the server notifies the user of its contents. The terminal receives this notification and displays the user the program details, learning progress, evaluation methods, etc. The user then proceeds with their learning based on this information.

[0589] As the user progresses through the learning process, the device tracks their progress. The server collects this information and uses an AI model to analyze the user's learning speed and comprehension. If necessary, the learning program can be adjusted to match the user's pace.

[0590] Ultimately, users provide feedback via their devices after completing the program. This feedback is sent to a server and used to improve future programs. This cycle continuously provides a system that maximizes learning effectiveness and supports users' career development. For example, for users who want to improve their skills in the medical field, providing real-time information on the latest medical technologies and techniques allows them to efficiently acquire immediately applicable skills.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The server collects data related to educational programs from external sources and internal corporate systems. During this process, it regularly updates information on the latest educational resources and training projects.

[0594] Step 2:

[0595] The terminal displays an interface for the user to input attribute information. The user enters information such as areas of interest, current skill level, and career goals, and sends this information to the server.

[0596] Step 3:

[0597] The server inputs the received user attribute information and collected educational program data into an AI model to generate an optimal educational program for the user. The generated AI model identifies the user's skill gaps and selects recommended courses and materials.

[0598] Step 4:

[0599] The server sends the generated educational program to the terminal and notifies the user. The terminal displays the program's details and prompts the user to prepare to begin learning.

[0600] Step 5:

[0601] The user begins learning based on the educational program provided through the device. The device tracks the learning progress in real time and sends the progress data to the server.

[0602] Step 6:

[0603] The server analyzes the received progress data and checks the user's learning status. If necessary, it adjusts the learning program using an AI model and provides the user with optimal learning advice.

[0604] Step 7:

[0605] After completing the learning program, users provide feedback through their device. This feedback is sent to the server and used to improve future educational programs.

[0606] (Example 1)

[0607] 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".

[0608] In today's world, while there is a demand for diverse skill development and education, providing educational programs optimized for individual users' attributes and learning speeds is challenging. Furthermore, existing systems suffer from inefficient information gathering and progress monitoring, hindering their ability to maximize user learning effectiveness.

[0609] 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.

[0610] In this invention, the server includes means for acquiring user attribute information and collecting information related to educational content, means for generating optimized educational content based on the attribute information and collected information, and means for notifying the user of the optimized educational content and tracking the user's progress. This enables the provision of individually optimized educational programs and flexible program adjustments according to the user's progress.

[0611] "User attribute information" refers to individual user information such as skill level, areas of interest, and career goals.

[0612] "Educational content" refers to information such as learning materials, online courses, and teaching materials necessary for implementing an educational program.

[0613] "Optimized educational content" refers to educational material that is structured in a way that is best suited to each individual user, based on user attribute information and collected data.

[0614] "Notification" refers to the methods and means used to inform users of the details of the generated educational content.

[0615] "Means of tracking progress" refers to methods of recording and evaluating a user's learning activities, understanding, and progress as they progress through an educational program.

[0616] A "generative AI model" refers to a computational model that uses machine learning techniques to optimize educational programs and automatically select appropriate content and modify programs.

[0617] This invention relates to an AI-based system for providing users with individually optimized educational programs. This system consists primarily of a server, a terminal, and a user. Specific embodiments are described below.

[0618] The server first gathers information. It retrieves necessary data from sources such as online education platforms and academic databases on the internet, as well as historical educational data within the organization. Technologies such as APIs and scraping may be used for data collection. The collected data is stored in a database and used for subsequent processing.

[0619] The device provides an interface for users to customize educational programs. This interface allows users to input their current skill level, areas of interest, and career goals. This user attribute information is transmitted to the server in real time and used as foundational data to generate individually optimized educational content.

[0620] The server uses a generative AI model to analyze user attribute information and collected educational data to design an optimized educational program. The AI ​​model utilizes machine learning techniques to automatically select educational content deemed most suitable for the user's needs. For example, if the user inputs a desire to improve their marketing skills, the server will provide the most relevant online courses and plans.

[0621] Once a learning program is generated, the server sends its contents to the terminal, which then notifies the user. The user receives the notification and can proceed with their learning by checking the program details. The terminal also simultaneously tracks and records the learning progress.

[0622] Furthermore, when users complete the program, they provide feedback through their device. The server receives this feedback, saves it as data, and uses it to improve the program later. This allows the system to continuously provide users with an appropriate educational experience.

[0623] As a concrete example, for users who want to improve their skills in the medical field, information on the latest medical technologies and techniques may be provided in real time. In this case, a generative AI model compiles the necessary information in that field and designs an efficient learning plan.

[0624] An example of a prompt to input into a generative AI model is, "If the user wants to improve their skills in the field of marketing, please generate a suitable online course and learning plan." This prompt allows the system to suggest a program tailored to the user's specific needs.

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

[0626] Step 1:

[0627] The server collects the data necessary for the educational program. This process retrieves information from online educational platforms on the internet, academic databases, and historical educational data within the organization. Inputs include APIs and scraping techniques, and output is educational content information stored in a database. This information is systematically organized for use in subsequent processes.

[0628] Step 2:

[0629] The terminal provides an interface where users can input attribute information. Users enter their areas of interest, current skill level, career goals, etc. The input data is sent to the server in real time and stored in the database as the user's profile. This profile information serves as the basis for individually optimizing educational programs.

[0630] Step 3:

[0631] The server generates educational programs using a generative AI model. It combines user profile information with educational content information collected in Step 1 and performs optimization. Specifically, it inputs prompt statements into the generative AI model and calculates a learning plan suitable for the user's needs. The output is an optimized educational program that is automatically adjusted to meet the individual user's requirements.

[0632] Step 4:

[0633] The server notifies the terminal of the generated educational program. Based on this notification, the terminal displays the program details to the user. To enable the user to begin learning, it provides a dashboard with access links to educational content and progress tracking. The displayed information is tailored to the user's current learning stage, supporting efficient learning.

[0634] Step 5:

[0635] As the user progresses through the learning process, the device tracks their progress and sends this data to the server. The server analyzes this progress data and provides an evaluation based on the learning speed and level of understanding. If necessary, it manually adjusts the learning program using a generative AI model to optimize it to the user's pace. Based on these output results, the program is automatically updated.

[0636] Step 6:

[0637] After the user completes the program, the device will present a feedback interface, prompting them to provide feedback on their learning experience. This feedback data will be sent to a server and stored as data for improving future educational programs. The collected feedback information will be used to improve the quality of the program and increase user satisfaction.

[0638] (Application Example 1)

[0639] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0640] Traditional education systems struggle to provide flexible programs tailored to individual learning needs and characteristics, and standardized educational plans fail to effectively support a large number of learners. In particular, when users study at home, it is difficult to receive appropriate feedback and individualized support, making it challenging to maintain effective learning. Therefore, it is necessary to solve these problems to provide educational support optimized for each individual user and to create a more efficient and effective learning environment.

[0641] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0642] In this invention, the server includes means for receiving user attribute information and collecting information related to a learning program; means for generating an optimized learning program based on the attribute information and the collected information; and means for providing the optimized learning program to the user and monitoring the user's progress. This makes it possible to interact with the user via a physical device and provide educational support tailored to individual learning needs.

[0643] "User attribute information" refers to personal characteristics of learners, including information such as their current skill level, areas of interest, and career goals.

[0644] "Information regarding learning programs" refers to data necessary for designing and delivering educational programs, including educational content from external sources and past training data within the organization.

[0645] An "optimized learning program" is an educational program designed based on the learner's individual attribute information and collected data, and is individually tailored to achieve the most effective learning for the learner.

[0646] A "physical device" refers to equipment or machinery used to provide educational support, and is a type of device that provides interactive information to users within the home.

[0647] A "server" in an educational support system is the central computer responsible for collecting, processing, and providing data, and for generating and managing learning programs.

[0648] The system that realizes this application example utilizes educational support robots to provide an individually optimized learning experience. The robot functions as a physical device that serves as infrastructure for the user, receiving user attribute information and implementing appropriate educational programs.

[0649] The server receives user attribute information from the terminal and, in conjunction with this information, collects necessary learning program information from external sources and internal learning data within the organization. It uses speech recognition engines such as the Google Speech API to obtain data from the user's voice. On the server, OpenAI's generative AI model is used to generate optimized learning programs for each individual user. The AI ​​model automatically adjusts the learning plan according to the learner's skill level and learning progress.

[0650] The robot, acting as the terminal, includes an interface that provides the user with a learning program and monitors the user's learning progress. The robot also has the ability to interact with the user via voice and touch controls and provide immediate feedback.

[0651] For example, when a child is learning about the movement of planets, the robot can use an AI-generated model to display a visual representation of the solar system and explain the concept both audibly and visually. If the child asks, "How long does it take for the Earth to rotate once?", the robot can provide an immediate answer.

[0652] Examples of prompts for generative AI models:

[0653] "The user is an elementary school student who is interested in science. Please generate a learning program for them to learn about the solar system."

[0654] This system makes it possible to provide user-optimized educational support.

[0655] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0656] Step 1:

[0657] Users operate an educational support robot and input their learning objectives and interests via voice or touch. The input information is sent from the robot to the server as attribute information. In the case of voice input, the Google Speech API is used to convert the voice data into text.

[0658] Step 2:

[0659] The server collects relevant educational content from external sources (online education platforms and academic databases) and internal sources (organizational training databases) based on the user's attribute information received. The collected educational data is stored in the database.

[0660] Step 3:

[0661] The server inputs collected educational data and user attribute information into a generating AI model. The generating AI model analyzes the input data according to the prompts and generates a learning program optimized for the user's learning needs. In this process, the model selects content based on the user's skill level and goals.

[0662] Step 4:

[0663] The generated learning program is sent from the server to the robot terminal. Based on this program, the robot begins interacting with the user and provides learning support through voice guidance and visual content. Depending on the scenario, it monitors the learning progress and provides appropriate feedback to the user.

[0664] Step 5:

[0665] Each time a user asks a question or performs an action, the device sends that information to the server in real time. The server analyzes the user's behavior data and dynamically adjusts the learning program using a generated AI model as needed. This adjustment result is then sent back to the robot, updating the learning content and providing an optimized learning experience.

[0666] 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.

[0667] This invention combines an emotion engine with a system that provides users with individually optimized educational programs, and is implemented in the following form.

[0668] First, the server collects data related to the educational program from external sources and the company's internal systems. Based on this data, and combined with user attribute information, the server generates an optimized educational program. Using a generation AI model, the program is then adjusted to meet the individual needs of the user.

[0669] The user uses a device to input attribute information and begin learning. The device acquires emotional data in real time through the user's voice and facial expressions. This emotional data is sent from the device to a server and analyzed by an emotion engine.

[0670] The emotion engine on the server analyzes the user's emotions and dynamically adjusts the content of the educational program based on that feedback. This process ensures that if the user is feeling stressed, more relaxing content is provided, while if they are highly motivated, challenging tasks are presented.

[0671] For example, if a user shows signs of anxiety or worry while working on a math program, the server will immediately lower the difficulty level of the assignment and deliver supplementary content to aid understanding. This helps prevent users from becoming discouraged during the learning process.

[0672] Furthermore, after the learning program is completed, user feedback is sent back to the server via the device. This feedback is used to improve the program and contribute to improving the overall quality of the educational system, including emotion recognition.

[0673] This form allows the present invention to provide a flexible educational program that takes into account the user's emotions, aiming to improve a wide range of learning outcomes. As a result, learners can enjoy learning that suits their emotional state and acquire skills efficiently.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] The server collects data related to educational programs from external sources and internal company databases. This data includes detailed information about various online courses and training sessions.

[0677] Step 2:

[0678] The terminal provides an interface for users to input attribute information. Users input information such as their areas of interest, current skill level, and target career, and send it to the server.

[0679] Step 3:

[0680] The server uses the received user information and pre-processed data to create an optimized educational program using a generative AI model. This program provides specific learning content and steps based on the user's attributes and goals.

[0681] Step 4:

[0682] The device recognizes the user's emotions in real time as they progress through the learning process. Sensors detect the user's facial expressions and voice, generating emotion data.

[0683] Step 5:

[0684] When a user engages with learning content, the device sends collected emotional data to a server. The server's emotion engine analyzes this data to evaluate the user's current emotional state.

[0685] Step 6:

[0686] Based on evaluations from the emotion engine, the server adjusts the content of the educational program as needed. For example, if a user is showing frustration, the server can suggest simpler and more engaging content.

[0687] Step 7:

[0688] When a user completes their learning, feedback about their learning experience is sent to the server via their device. This feedback is used to improve the program in the future. Furthermore, the relationship between sentiment data and learning results is analyzed and considered as data to improve the system's accuracy.

[0689] (Example 2)

[0690] 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".

[0691] Traditional education systems often provided uniform educational programs without considering the individual attributes or emotional states of users. As a result, users experienced decreased learning efficiency and increased emotional stress. This invention aims to meet individual learning needs and achieve efficient learning by providing an educational program optimized for each user and making dynamic adjustments along the way in response to their emotional state.

[0692] 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.

[0693] In this invention, the server includes means for receiving user attribute information and collecting educational information, means for generating an optimized educational plan based on the attribute information and collected information, and means for acquiring and analyzing the user's emotional state in real time. As a result, the user can receive educational content adapted to their own emotional state, improving their understanding of the material and their motivation to learn.

[0694] "User" refers to an individual who utilizes an educational program, and the learning process takes into account their attribute information and emotional state.

[0695] "Attribute information" refers to personal data about a user, including information such as age, learning history, interests, and learning objectives.

[0696] "Information for education" refers to data necessary for building and optimizing educational programs, including teaching materials, reference materials, and information obtained from educational institutions.

[0697] An "optimized educational plan" refers to a personalized learning program that is adjusted by a generative AI model based on the user's attribute information and collected data.

[0698] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to dynamically optimize and update educational programs.

[0699] "Emotional state" refers to the psychological response of a user during learning, including the degree of stress and motivation obtained from voice and facial expressions.

[0700] "Methods for acquiring and analyzing data in real time" refers to the process of instantly capturing voice and facial expression data provided by the user during training and analyzing it using an emotion engine.

[0701] "Dynamic adjustment means" refers to the process by which the server modifies the content of the educational plan based on the results of the user's sentiment analysis, in order to provide the user with the most suitable learning experience.

[0702] This invention is a system for providing users with individually optimized educational programs, employing a configuration that incorporates an emotion engine. This system operates through the coordinated efforts of three elements: a server, a terminal, and the user.

[0703] The server collects educational information from external data sources and the organization's internal information systems. It retrieves the necessary information via APIs using programming languages ​​such as Python and R. The collected information is combined with user attribute information, and an optimized educational plan is generated using a generative AI model. This generative AI model is built using machine learning frameworks such as TensorFlow.

[0704] The user enters attribute information using a device and begins learning. This device is equipped with a camera and microphone to recognize the user's voice and facial expressions, and acquires sentiment data using software such as Google Cloud Speech-to-Text and OpenCV. This data is sent to a server in real time and analyzed by an emotion engine.

[0705] The device sends collected emotional data to a server, which then dynamically adjusts the learning plan based on this data. For example, if a user is feeling stressed, the server lowers the difficulty level of the tasks and presents more user-friendly content. This allows the user to learn while reducing stress.

[0706] For example, if a user feels unsure while using a math learning program, the server can immediately reduce the number of calculation problems and provide supplementary explanations. An example of a prompt in this case would be, "Please provide a brief explanation of the mathematical concept that the user is having trouble understanding."

[0707] In this way, users can enjoy a flexible educational experience tailored to their own learning process and acquire skills efficiently.

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

[0709] Step 1:

[0710] The server collects educational information from external data sources and the organization's internal information systems. Inputs include external online databases and internal training materials, while output is a dataset integrating this information. The server preprocesses this dataset using a Python script, converting it into a format suitable for training.

[0711] Step 2:

[0712] Users input their attribute information using a terminal. The input is personal data provided by the user, and the output is that data sent to the server and registered as attribute information. The terminal's user interface is designed to be easy to understand, and information is collected through form input.

[0713] Step 3:

[0714] The server generates an optimized educational plan using a generative AI model based on user attribute information and collected educational data. The input is the dataset obtained in step 1 and the user attribute information provided in step 2. The output is an individually tailored educational plan, with the model dynamically generated using TensorFlow.

[0715] Step 4:

[0716] The user begins learning using a device. The device acquires the user's voice and facial expressions in real time and collects emotion data. The input is real-time audio and video information obtained from the user during learning. The output is emotion data formatted for analysis, and the data is acquired using OpenCV or Google Cloud Speech-to-Text.

[0717] Step 5:

[0718] The device sends acquired emotional data to the server, which then analyzes it using an emotion engine. The input is the user's real-time emotional data, and the output is the emotional analysis result. The emotion engine uses natural language processing technology to analyze the data and identify the user's emotional state.

[0719] Step 6:

[0720] The server dynamically adjusts the educational plan based on the analysis results and redistributes learning content tailored to the user. The input is the sentiment analysis results, and the output is the updated educational plan. In this process, the generative AI model automatically adjusts the learning content and provides difficulty levels and supplementary explanations appropriate for the user.

[0721] Step 7:

[0722] After completing the learning process, users provide feedback, which they send to the server via their device. The input is user feedback based on their learning experience, and the output is data stored on the server for future program improvements. This feedback is used to improve the system's learning algorithm and the accuracy of its emotion recognition.

[0723] (Application Example 2)

[0724] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0725] Traditional educational programs tend to offer uniform content without considering individual user characteristics or real-time emotional states. This can lead to learners experiencing stress or, conversely, losing motivation, hindering efficient learning progress and skill acquisition. Therefore, there is a need to develop systems that provide individually optimized learning experiences that reflect the user's emotional state.

[0726] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0727] In this invention, the server includes means for receiving user characteristic information and aggregating information related to the learning program; means for creating a learning program adjusted based on the characteristic information and the aggregated information; and means for analyzing the user's voice and facial expressions to acquire emotional data and dynamically modify the adjusted learning program in real time. This makes it possible to provide an efficient learning experience that is adapted to the user's emotional state at that moment.

[0728] "User characteristic information" refers to attribute data such as the user's age, knowledge level, and learning objectives.

[0729] "Information related to the learning program" refers to data related to educational content, such as curriculum, teaching materials, and teaching methodologies.

[0730] A "tailored learning program" is educational content that is individualized and optimized based on the user's characteristics and relevant information.

[0731] "Emotional data" refers to data that indicates a user's emotional state in real time, obtained through their voice and facial expressions.

[0732] "Dynamic modification" refers to the process of changing the content and difficulty level of educational materials in real time according to the user's emotional state.

[0733] This invention provides a system that offers an individually optimized learning program based on user characteristic information and real-time emotional data. This system dynamically modifies the learning experience by collecting user attribute information, adjusting the program using a generative AI model, and further analyzing it in real time using an emotional engine.

[0734] The server first aggregates the characteristic information entered by the user with related information collected from external sources and the company's internal systems. Next, it uses a deep learning library such as TensorFlow to create an optimized training program for the generated AI model. This program is customized to meet the individual needs of the user.

[0735] The device uses its camera and microphone to capture the user's voice and facial expressions, and sends this data to the server as emotion data. An emotion engine on the server, such as the Microsoft Azure Emotion API, analyzes this emotion data to evaluate the user's emotional state. This allows the program content to be dynamically adjusted, providing an educational experience tailored to the user's emotional state at that moment.

[0736] For example, when a user is working on a math curriculum, if the server detects signs of anxiety, it can lower the program's difficulty and provide supplementary videos to facilitate understanding. Similarly, when elderly individuals are undergoing rehabilitation programs, relaxing music can be played to alleviate stress.

[0737] An example of a prompt to input into the generation AI model is, "Generate a prompt to EduRobot to order educational content to display when it has a happy expression."

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

[0739] Step 1:

[0740] The user enters characteristic information into the device. The device retrieves this information and sends it to the server as initial setup. The data entered includes the user's age, knowledge level, and learning objectives, and this is used to individually optimize educational content.

[0741] Step 2:

[0742] The server aggregates information related to the learning program from external sources and the organization's internal systems. This includes curriculum data, teaching materials, and educational methodologies. Based on this information, a generative AI model generates an optimized educational program. The information processing process involves using a generative AI model to create individually optimized learning programs.

[0743] Step 3:

[0744] The device uses its camera and microphone to collect user voice and facial expression data in real time. This data represents the user's emotional state and is transmitted from the device to the server. During this intermediate processing, voice recognition and facial expression analysis are performed to convert the data into emotional data.

[0745] Step 4:

[0746] The server uses an emotion engine, such as the Microsoft Azure Emotion API, to analyze the received emotion data and evaluate the user's emotional state. By analyzing the input emotion data and understanding mood and emotional trends, the system uses this information to adjust the program accordingly.

[0747] Step 5:

[0748] The server dynamically modifies the learning program content in real time based on the evaluated emotion data. If the user is experiencing stress, adjustments such as lowering the program's difficulty level are made. The modified program is optimized for the user's immediate emotional state.

[0749] Step 6:

[0750] The device displays a modified learning program to the user, and the user progresses through the learning process. Through the interface on the device, the user provides feedback while learning, and this information is sent back to the system. This feedback data is accumulated for future program improvements.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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."

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] The following is further disclosed regarding the embodiments described above.

[0773] (Claim 1)

[0774] A means of receiving user attribute information and collecting data related to educational programs,

[0775] Means for generating an optimized educational program based on the attribute information and collected data,

[0776] The means for providing the optimized educational program to the user and monitoring the user's progress,

[0777] A means of evaluating the user's learning results and collecting feedback,

[0778] A system that includes this.

[0779] (Claim 2)

[0780] The system according to claim 1, wherein the collected data is obtained from external sources and internal systems of a company.

[0781] (Claim 3)

[0782] The system according to claim 1, wherein the optimized educational program is automatically adjusted and updated using a generative AI model.

[0783] "Example 1"

[0784] (Claim 1)

[0785] A means of obtaining user attribute information and collecting information about educational content,

[0786] A means for generating optimized educational content based on the attribute information and collected information,

[0787] Means for notifying users of the optimized educational content and tracking users' progress,

[0788] A means of analyzing users' learning outcomes and collecting their opinions,

[0789] A device that includes this.

[0790] (Claim 2)

[0791] The apparatus according to claim 1, wherein the collected information is obtained from external sources and internal devices of the organization.

[0792] (Claim 3)

[0793] The apparatus according to claim 1, wherein the optimized educational content is automatically modified using a generative AI model.

[0794] "Application Example 1"

[0795] (Claim 1)

[0796] A means of receiving user attribute information and collecting information about the learning program,

[0797] Means for generating an optimized learning program based on the attribute information and collected information,

[0798] The optimized learning program is provided to the user, and means are used to monitor the user's progress.

[0799] A means of evaluating the user's learning results and collecting feedback,

[0800] A means of interacting with users and providing educational support through physical devices,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the collected information is obtained from external sources and the organization's internal platform.

[0804] (Claim 3)

[0805] The system according to claim 1, wherein the optimized learning program is automatically adjusted and updated using a generative artificial intelligence model.

[0806] "Example 2 of combining an emotion engine"

[0807] (Claim 1)

[0808] A means of receiving user attribute information and collecting information for educational purposes,

[0809] Means for generating an optimized educational plan based on the attribute information and collected information,

[0810] A means for providing the user with the optimized educational plan and monitoring the user's progress,

[0811] A means of acquiring and analyzing the user's emotional state in real time,

[0812] A means of dynamically adjusting the content of the educational plan based on the analysis results,

[0813] A means of evaluating the user's learning results and collecting feedback,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, wherein the collected information is obtained from external data sources and the organization's internal information systems.

[0817] (Claim 3)

[0818] The system according to claim 1, wherein the optimized educational plan is automatically adjusted and updated using a generative AI model.

[0819] "Application example 2 when combining with an emotional engine"

[0820] (Claim 1)

[0821] A means of receiving user characteristic information and aggregating information related to the learning program,

[0822] Means for creating a learning program adjusted based on the aforementioned characteristic information and aggregated information,

[0823] A means for analyzing the user's voice and facial expressions to acquire emotional data and dynamically modifying the adjusted learning program in real time,

[0824] A means of providing the modified learning program to the user and monitoring their progress,

[0825] A means of evaluating users' learning results and aggregating their opinions,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, wherein the aggregated information is obtained from external information sources and the internal systems of the corporation.

[0829] (Claim 3)

[0830] The system according to claim 1, wherein the adjusted learning program is automatically modified and updated using a generative AI model. [Explanation of symbols]

[0831] 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 receiving user attribute information and collecting information about the learning program, Means for generating an optimized learning program based on the attribute information and collected information, The optimized learning program is provided to the user, and means are used to monitor the user's progress. A means of evaluating the user's learning results and collecting feedback, A means of interacting with users and providing educational support through physical devices, A system that includes this.

2. The system according to claim 1, wherein the collected information is obtained from external sources and the organization's internal platform.

3. The system according to claim 1, wherein the optimized learning program is automatically adjusted and updated using a generative artificial intelligence model.

Images