system

Abstract

We provide the system. [Solution] An artificial intelligence method that proposes the optimal educational curriculum based on the user's learning history and career information, Means of providing education remotely using generated educational resources, A means of tracking learning progress and providing personalized learning support to users, A means of generating test questions and automatically evaluating user responses, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, with the advancement of technology, working people are required to continuously improve their skills. However, it is difficult for many working people to cultivate new expertise without interrupting their current careers. Therefore, there is a need for a mechanism that effectively utilizes resources and time to provide specialized education remotely. In conventional educational institutions, a flexible learning environment, especially for working people, is not sufficiently established, and there is a problem that it is difficult for working people to smoothly improve their skills or change careers while continuing their occupations.

Means for Solving the Problems

[0005] This invention provides a means for proposing an optimal educational curriculum using artificial intelligence based on a user's learning history and career information. It also delivers the generated educational resources via an online platform, creating a learning environment that enables remote learning. Furthermore, it improves user learning efficiency by tracking learning progress and providing real-time, personalized learning support. In addition, by incorporating a means for generating test questions using artificial intelligence and automatically evaluating the answers, it ensures educational quality while enabling flexible learning. This provides a system that allows working adults to effectively acquire specialized skills without interrupting their careers.

[0006] "Artificial intelligence means" refers to programs and algorithms in computer systems that propose the optimal educational curriculum based on the user's learning history and career information.

[0007] "Educational resources" is a general term for various learning content and support information provided to complete a specific curriculum, such as textbooks, lecture videos, and practice problems.

[0008] "Methods for providing education remotely" refer to technologies and systems that deliver learning content to users from a distance via the internet, without relying on physical educational facilities.

[0009] "Means of tracking learning progress" refers to systems and methods for recording and monitoring how far a user has progressed in their learning activities.

[0010] "Personalized learning support" refers to a method that supports efficient learning by providing optimal learning materials and advice based on the user's individual learning history and progress information.

[0011] "Means for generating exam questions" refers to algorithms or programs that automatically create exam questions tailored to the user's learning progress.

[0012] "Automated evaluation methods" refer to technologies in which a computer program evaluates and scores a user's answers to exam questions. [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]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, a 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, a 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, a 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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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 system implementing this invention will be implemented as an online platform for users to efficiently improve their skills remotely. The system will consist of various servers and user terminals, which will interact with each other via the internet.

[0035] The server first uses artificial intelligence to propose the most suitable educational curriculum based on the user's learning history and career information. For example, if a user is interested in "data science," the server analyzes their past learning content and skill level to recommend introductory courses in Python programming and statistics.

[0036] Based on the course selected by the user, the server generates educational resources such as learning materials and lecture videos and delivers them to the user's device. The user's device efficiently displays the received data, allowing the user to access it at any time.

[0037] During learning, the server consistently tracks the user's learning progress and uses generative AI to provide personalized learning support. For example, if a user is falling behind, it may suggest supplementary materials or provide additional practice problems to support their understanding.

[0038] During the testing phase, the server automatically generates test questions and provides them to the user online. The user's device sends their answers to the server. The server's AI grades the answers and provides the results to the user as feedback. This allows the user to self-assess and use the results to inform their next learning activities.

[0039] For example, in the data science course exam, a Python coding problem is given, and the server executes and evaluates the submitted code, showing areas for improvement and successful examples. This allows users to understand their weaknesses in real time and use that information to further improve their skills.

[0040] Through these features, the system provides an environment where working professionals can deepen their learning regardless of time or location, and enhance their skills without interrupting their careers.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives registration information when a user accesses the portal site and creates an account. It then prompts the user to enter their past learning history and career information, which is then stored in the database.

[0044] Step 2:

[0045] After logging in, the user selects a course they wish to take from the list of available courses displayed by the server. The server registers the selected course in its database and sends a confirmation notification to the user.

[0046] Step 3:

[0047] The server uses a generative AI to generate optimal educational resources (textbooks, lecture videos, etc.) based on the course selected by the user. The generated content is then delivered to the user's device.

[0048] Step 4:

[0049] The terminal displays educational resources sent from the server to the user, making them freely accessible. Users can then use these materials to learn at their own pace.

[0050] Step 5:

[0051] The server continuously tracks the user's learning progress, and the generative AI provides personalized learning support. Supplementary materials and additional practice problems are presented to the user as needed.

[0052] Step 6:

[0053] Once the user completes a learning unit, the server uses a generation AI to generate test questions to measure the user's understanding. These questions are then sent to the user's device.

[0054] Step 7:

[0055] The user's device displays the test questions and prepares the user to enter their answers. Once the user completes the test, they submit their answers to the server.

[0056] Step 8:

[0057] The server automatically evaluates the submitted responses using a generation AI, generating a score and feedback. The results are sent to the user's device, providing the user with information to plan their next learning steps.

[0058] Step 9:

[0059] Based on feedback from the server, users can check their progress and decide on their next course and learning strategy. The server then registers them for a new learning phase and suggests courses.

[0060] (Example 1)

[0061] 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."

[0062] In modern society, people are required to continuously improve their skills without being constrained by time or place. However, traditional learning systems have struggled to propose optimal learning programs tailored to individual learning situations and skill levels, and have also found it difficult to provide appropriate support in real time as learning progresses. This has hindered the efficient realization of skill improvement.

[0063] 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.

[0064] In this invention, the server includes artificial intelligence means for suggesting an optimal educational program based on the user's learning history and work experience, means for remotely providing education using the generated educational content, and means for tracking learning progress and providing personalized learning support to the user. This enables customized learning content and real-time learning support for each individual user.

[0065] A "user" refers to anyone who accesses an online platform, enters their learning history and work experience, and participates in educational programs.

[0066] "Learning history" refers to information about the courses a user has taken and the skills they have acquired in the past.

[0067] "Work history" refers to information about a user's professional experience and career.

[0068] An "educational program" is a set of learning materials suggested based on a user's learning history and work experience, designed to help them acquire specific goals and skills.

[0069] "Artificial intelligence tools" refer to algorithms and models that automatically generate optimal educational programs for users based on given data.

[0070] "Educational content" refers to resources such as learning materials and lecture videos included in an educational program.

[0071] "Remote education" refers to the act of enabling users to learn via the internet, regardless of their physical location.

[0072] "Learning status" refers to real-time information regarding the user's progress and level of understanding.

[0073] "Personalized learning support" refers to providing learning advice and assistance that addresses specific needs based on the user's learning progress.

[0074] "Exam questions" refer to questions generated to evaluate a user's learning achievements.

[0075] "Automatic analysis" refers to the automatic evaluation of user-submitted answers by a generating AI model, followed by the provision of results.

[0076] "Feedback" refers to evaluations and advice generated based on the user's submitted answers and learning progress.

[0077] "Supplementary materials" refer to learning resources provided to support the user's understanding and practice.

[0078] This invention is a system implemented as an online platform for users to efficiently improve their skills remotely. This system operates via a server, terminals, and an internet connection.

[0079] Hardware and software

[0080] The server runs on a high-performance computer and uses artificial intelligence to provide users with optimal educational programs. In particular, a generative AI model is used to generate programs, creating the most suitable content based on data such as the user's learning history and work experience. The terminal is the device used by the user to receive educational content, and includes personal computers, tablets, and smartphones. It displays the content sent from the server through a browser or dedicated application.

[0081] Data processing and calculations

[0082] The server analyzes data acquired from users, and a generative AI model automatically generates educational programs using that data. Machine learning algorithms and natural language processing techniques are used for the analysis. The generated programs are customized according to the user's skill level and learning speed.

[0083] Specific example

[0084] For example, if a user is interested in data science, the server will suggest introductory courses in Python programming and statistics based on their past learning history. Depending on the course the user selects, relevant learning materials and video lectures will be delivered from the server. The user can then view this content on their device and proceed with their learning.

[0085] Example of a prompt

[0086] Examples of prompt statements include the following:

[0087] "User's learning history: Introduction to Python, Basic Statistics / Area of ​​Interest: Data Science / Please suggest the optimal educational curriculum for skill development."

[0088] Through this system, users are provided with an environment where they can efficiently improve their skills regardless of time or location.

[0089] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0090] Step 1:

[0091] Users access an online platform using their devices. Here, users input their learning and work history. This input information serves as foundational data for future educational program proposals. Users enter the necessary information into a dedicated online form and press the submit button to send the data to the server.

[0092] Step 2:

[0093] The server generates an optimal educational program using a generative AI model based on the user's learning and work history. The user data received as input is passed to the generative AI model and analyzed using data analysis and machine learning algorithms. As output, the server generates and presents a list of courses suitable for the user's learning goals.

[0094] Step 3:

[0095] The user reviews a list of educational programs presented by the server and selects the course they wish to take. This selection is performed on the user's device, and the selection information is sent back to the server. This allows for the creation of personalized learning content tailored to the user's learning motivation and goals.

[0096] Step 4:

[0097] The server generates and prepares for distribution relevant educational content (such as textbooks and lecture videos) based on the course selected by the user. The server searches for necessary content from the course database and arranges for efficient distribution to the user's terminal. The output consists of links and data files sent to the user's terminal.

[0098] Step 5:

[0099] The user's device receives educational content delivered from the server and displays it in a format that the user can learn from. The device's application presents the received data to the user in an appropriate format and initiates downloads or streaming as needed. The output is an interactive content display to support the user's learning.

[0100] Step 6:

[0101] The server periodically tracks the user's learning progress and analyzes the progress data using a generative AI model. Based on the user's learning speed and comprehension level, it provides necessary support and supplementary materials. The input is the user's learning log, and the output includes additional practice problems and advice as personalized learning support.

[0102] Step 7:

[0103] When a user completes a course, the server generates exam questions and delivers them to the user's device. The generation AI model automatically generates appropriate and challenging exam questions based on the learned content. The user answers these questions, and the results are sent back to the server.

[0104] Step 8:

[0105] The server receives test answers submitted by the user and automatically evaluates them using a generative AI model. The server analyzes the accuracy rate and learning comprehension level and provides feedback to the user. The output is an evaluation and advice to help the user progress to the next learning step.

[0106] (Application Example 1)

[0107] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0108] In modern society, there is a lack of appropriate learning environments and materials for workers who aim to advance their careers while continuing their individual jobs. Traditional education systems only provide uniform educational content, and do not adequately offer personalized educational support based on individual learning histories and job information. As a result, users have difficulty efficiently accessing educational programs that suit their interests and skills. In addition, the lack of management of learning progress and appropriate feedback is also a challenge.

[0109] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0110] In this invention, the server includes an intelligent algorithm that proposes an optimal educational program based on the user's learning history and job information, a device that provides education remotely using the generated educational content, and a device that monitors the progress of learning and provides personalized learning support to the user. This makes it possible to efficiently provide an optimal educational program according to each user's learning history and abilities.

[0111] An "intelligent algorithm" is a computational method that analyzes a user's learning history and job information to automatically suggest the optimal educational program.

[0112] "Educational content" refers to educational resources such as textbooks, lecture videos, and practice problems that are provided based on the user's learning progress.

[0113] A "device for providing education remotely" is a system that uses communication technology to allow users to receive and learn educational content even when they are physically separated from their homes.

[0114] A "device that monitors learning progress and provides personalized learning support" is a system that tracks the user's learning progress and provides optimal support based on the analysis results.

[0115] "Communication terminal equipment" refers to devices that users use to receive and utilize educational content provided remotely, and includes smartphones and computers.

[0116] The system that implements this application starts when the user inputs their learning history and job information using their communication terminal device, and the server receives this information. The server analyzes the user's information using intelligent algorithms and generates an optimal educational program. In this process, a "general cloud platform" is used as a cloud service, and "TENSORFLOW®" and "PyTorch" are used as "AI libraries."

[0117] Educational content generated from the server is delivered to the user's communication terminal device. This educational content takes the form of learning materials and lecture videos, and is available on demand according to the user's preferences. The terminal efficiently displays the received data and provides an interface that enhances user convenience as they progress through their learning.

[0118] To monitor learning progress, the server periodically retrieves learning data from users and analyzes it to personalize learning support. If learning progress is slow, the server delivers additional supplementary materials to support improved understanding. It also automatically generates and provides test questions, and after receiving the user's answers, automatically grades them using an intelligent algorithm.

[0119] For example, if a user expresses interest in "marketing analytics," the server will analyze this and suggest educational programs related to digital marketing and data analysis. Supplementary materials such as additional explanatory videos and practice problems will be provided. During examinations, it is possible to evaluate the user's submitted marketing data analysis scripts in real time and provide feedback on the results.

[0120] An example of a prompt statement for a generative AI model can be shown as follows:

[0121] "Based on the user's past learning data and area of ​​interest, 'Marketing Analytics,' please recommend appropriate learning content. Specifically, prioritize courses related to digital marketing and data analysis, and provide supplementary materials if needed."

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] Users input their learning history and job information into the system via a communication terminal device. This information is used as input data sent to the server. Users manually enter the necessary information using the screen interface, confirm it, and then press the submit button.

[0125] Step 2:

[0126] The server analyzes the received user learning history and job information using intelligent algorithms. During the analysis, it utilizes generative AI models to process the data and propose educational programs best suited to the user's interests and skills. The output is a list of optimized educational programs for the user.

[0127] Step 3:

[0128] The server selects appropriate educational content for the user based on the generated educational program and distributes it to the communication terminal device. This includes digital content such as educational materials and lecture videos. Data compression and encryption technologies are expected to be used during distribution. The output is the educational content delivered to the user's terminal.

[0129] Step 4:

[0130] The communication terminal visually displays the received educational content to the user. The terminal launches the appropriate application depending on the type of content (video, text, practice exercises, etc.) and plays or displays the data. The user can control the learning progress through the screen.

[0131] Step 5:

[0132] As a user progresses through their learning, their progress data is sent back to the server. The server analyzes this data to optimize learning support. For example, it might suggest supplementary materials to users who are falling behind. The input is progress data, and the output is the suggested support content.

[0133] Step 6:

[0134] The server generates test questions and sends them to the user's communication terminal. In this process, a generation AI model is used to dynamically generate questions, providing different questions for each user. The input is the user's learning history and progress, and the output is the test questions.

[0135] Step 7:

[0136] The user solves the problem on their device and sends their answer to the server. The server automatically scores the received answer using an intelligent algorithm and sends the result as feedback to the user. The server determines the correctness of the answer through data calculation and calculates a score. The output is the scoring result.

[0137] 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.

[0138] This invention enhances the learning experience by incorporating an emotion engine into an online education system that allows users to efficiently improve their skills in a remote environment. The system is configured as a complex system including a server, user terminals, and the emotion engine.

[0139] The server collects learning history and career information provided by the user and uses artificial intelligence to propose an optimal, personalized educational curriculum. It also remotely delivers the generated educational resources to the user's terminal, enabling continuous learning. The terminal appropriately displays the delivered materials, providing the user with a learning environment they can access at their own pace.

[0140] The server constantly tracks the user's learning progress, and the generating AI provides personalized learning support tailored to the user. This includes providing learning materials according to the user's progress and suggesting supplementary materials based on their level of understanding. At key learning milestones, test questions are generated and delivered via the user's device. The device sends the user's answers back to the server, which uses AI to score and evaluate the answers, providing feedback.

[0141] Furthermore, the server utilizes an emotion engine to recognize the user's emotional state in real time. The emotion engine can determine stress levels, concentration levels, and satisfaction levels through facial expression and voice analysis. Based on this emotional recognition, the learning support content is dynamically adjusted. Specifically, if the user shows signs of fatigue, the system automatically takes measures such as recommending a break or providing simple review materials.

[0142] For example, when a user is working on an advanced data science course, the server monitors the user's progress and emotional state, and adjusts the intensity of the practice exercises to improve learning efficiency. If the server detects that the user is becoming impatient, it simplifies the interface and provides hints to deepen the user's understanding.

[0143] As described above, the present invention provides a system that enables working adults to efficiently improve their skills without interrupting their careers, and furthermore, by utilizing an emotional engine, to realize a high-quality learning experience.

[0144] The following describes the processing flow.

[0145] Step 1:

[0146] The user accesses the learning portal and enters the required registration information. The server receives this information and creates a user account in the database.

[0147] Step 2:

[0148] The server analyzes the user's input learning history and career information, and uses artificial intelligence to generate an optimal curriculum. A list of the generated curriculum is then displayed on the user's device.

[0149] Step 3:

[0150] The user selects their desired course from the displayed curriculum. After selection, the server generates the corresponding educational resources and delivers them remotely to the user's terminal.

[0151] Step 4:

[0152] The device visually displays the received educational resources to the user, providing access to lecture videos and learning materials. The user then begins learning accordingly.

[0153] Step 5:

[0154] During learning, the server constantly monitors the user's progress and applies personalized learning support generated by AI. This includes highlighting learned content and suggesting new practice problems.

[0155] Step 6:

[0156] The server activates the emotion engine and recognizes the user's emotional state. It analyzes the user's facial expressions and voice data to evaluate their concentration level and stress level.

[0157] Step 7:

[0158] Based on the emotion engine's evaluation, the server adjusts the learning pace and difficulty to improve the user's experience. If the server determines that the user is fatigued, it sends a notification to the device recommending a short break.

[0159] Step 8:

[0160] When a user completes a learning unit, the server generates test questions and sends them to the user's device. The user takes the test and sends their answers back to the server via their device.

[0161] Step 9:

[0162] The server uses AI to automatically evaluate responses, scores them, and generates feedback. It presents the results to the user in real time and clearly indicates the next learning task.

[0163] Step 10:

[0164] Based on the feedback, users revise their learning plans and decide which courses and content to move on to next. The server supports this process and provides guidance for the new learning phase.

[0165] (Example 2)

[0166] 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 will be referred to as the "terminal."

[0167] In today's educational environment, enabling users to learn sustainably and effectively in a remote setting remains a significant challenge. In particular, uniform educational programs often fail to adequately consider individual users' learning progress and emotional states, potentially leading to decreased learning efficiency. Furthermore, there is a lack of mechanisms to prevent users from being forced to interrupt their learning due to their emotional state. Under these circumstances, it is necessary to provide educational services optimized for individual users and to offer learning support that responds to their emotional state.

[0168] 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.

[0169] In this invention, the server includes intelligent processing means for presenting an optimal educational curriculum based on the user's learning history and occupational information, means for remotely conducting education using the generated educational resources, means for monitoring learning progress and providing personalized learning support to the user, and emotion recognition means for analyzing the user's emotional state in real time and adjusting the content of learning support. This enables the provision of a learning experience optimized for each individual user and dynamic learning support based on emotional state.

[0170] A "user" is an individual who uses an educational system to learn or improve their skills.

[0171] "Learning history" refers to data that records the courses a user has taken, the content they have learned, and their progress.

[0172] "Occupational information" refers to information about a user's career, including data that shows their work experience and skill set.

[0173] An "educational curriculum" refers to a learning program optimized based on the user's needs and skill level.

[0174] "Intelligent processing means" refers to the process of analyzing data using artificial intelligence and proposing the most suitable educational curriculum to the user.

[0175] "Providing education remotely" means offering educational resources to users in physically distant locations via the internet.

[0176] "Monitoring learning progress" refers to the activity of tracking how much a user has learned and recording their learning history.

[0177] "Personalized learning support" refers to the provision of support and learning materials tailored to each user.

[0178] "Emotion recognition means" refers to technology that analyzes a user's emotional state from their facial expressions, voice, etc., and responds accordingly.

[0179] "Educational resources" refer to content such as textbooks, videos, and materials that users utilize during their learning process.

[0180] "Adjusting the content of learning support" means optimizing the educational content provided and offering appropriate support according to the user's emotional state.

[0181] This invention is an online education system that enables users to efficiently improve their skills in a remote environment. It combines a server, terminal, and emotion engine to provide an education service optimized for the user.

[0182] The server receives and collects the user's learning history and occupational information. Based on this data, it uses a generative AI model to generate an optimal learning curriculum for the user. Intelligent processing is used to generate the curriculum. For example, if a user wants to improve their data science skills, relevant courses and materials will be recommended.

[0183] The generated educational resources are delivered to the user's device via the internet. The device displays these materials appropriately, providing a learning environment that the user can access at their own convenience. The delivered materials include video lectures and interactive exercises.

[0184] The server constantly monitors the user's progress during learning. This allows it to track how far the user has progressed and record it as a history. Based on this information, the generating AI provides individually optimized learning support. If the user is stuck on a particular topic, it can provide additional explanatory videos or supplementary materials.

[0185] Furthermore, the server uses an emotion engine to analyze the user's emotional state in real time. By performing facial expression and voice analysis, it can understand the user's stress levels and concentration, and adjust the learning support content accordingly. For example, if the user shows signs of fatigue, the system will automatically suggest a break.

[0186] A concrete example of a prompt is, "Consider the user's current progress and emotional state, and generate a learning plan for the next week." Based on such prompts, the AI ​​model presents the most suitable approach to the user.

[0187] This system allows users to learn flexibly and efficiently without interrupting their careers, and to improve their learning experience with personalized support.

[0188] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0189] Step 1:

[0190] The server receives the user's learning history and occupational information as input. Based on this information, it performs analysis using intelligent processing tools. Specifically, it analyzes the user's past learning data and skill set and proposes an educational curriculum that suits the user's needs. The output of this step is the optimal educational curriculum based on each user's needs.

[0191] Step 2:

[0192] The server uses a generative AI model to construct learning materials based on the curriculum obtained in Step 1. The curriculum identified in the previous step is used as input. Specific data calculations include selecting course content and optimizing learning resource resources. The output of this step is user-optimized learning resources (textbooks, video lectures, practice problems, etc.).

[0193] Step 3:

[0194] The server distributes the obtained educational resources to the user's terminal via the internet. The terminal receives the distributed educational resources and organizes them so that the user can use them. Specifically, this involves downloading the learning materials and displaying them on the interface. The input is the educational resources generated in step 2, and the output is the state in which they have been prepared for the user to use for learning.

[0195] Step 4:

[0196] Users progress through their learning using learning materials provided via their devices. The server tracks the user's learning progress in real time. Learning progress information is used as input, and the server records this information in a database as learning history. The output is updated learning progress information.

[0197] Step 5:

[0198] The server uses a generative AI model to provide personalized learning support based on the user's progress information. The input is learning progress data, which is used to analyze areas where the user is lacking and areas that need further improvement. The output is additional learning materials and explanatory information provided to the user.

[0199] Step 6:

[0200] The server utilizes an emotion engine to analyze the user's emotional state. Using sensors and cameras, it receives user facial expressions and voice information as input and evaluates emotions in real time. The output is data indicating the user's current emotional state, and learning support is adjusted based on this data.

[0201] Step 7:

[0202] The device dynamically adjusts the user interface based on emotional data received from the server. If the user is stressed, it switches to a more intuitive and simpler interface or displays an alert prompting them to take a break. The input is emotional state data from the server, and the output is the adjusted interface and support functions.

[0203] (Application Example 2)

[0204] 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."

[0205] Modern learners demand flexibility and individualization in their learning, and also need support to overcome emotional stress and decreased motivation. Traditional online education systems have lacked the means to address the individual emotional states of learners, making it difficult to maximize learning effectiveness. Furthermore, while there is a demand for continuous, real-time learning support, these systems lacked the flexibility to adapt to diverse learning environments.

[0206] 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.

[0207] In this invention, the server includes information processing means for proposing an appropriate educational curriculum based on the user's learning history and work history information; means for providing education remotely using the generated educational resources; means for tracking learning progress and providing personalized learning support to the user; means for generating test questions and automatically evaluating the user's answers; and emotion analysis means for recognizing the user's emotional state in real time and dynamically adjusting the educational support content. This makes it possible to maximize the learning effectiveness of learners while providing learning support tailored to their individual emotional states in real time.

[0208] A "user" is an individual or legal entity that uses the system to learn.

[0209] "Learning history" refers to a record of the educational resources a user has used to date and the results of those efforts.

[0210] "Work history information" refers to data related to the user's professional experience and career.

[0211] "Information processing means" refers to methods and devices for collecting, analyzing, and processing information.

[0212] "Educational resources" refer to teaching materials and tools provided to support learning activities.

[0213] "Means of providing education remotely" refer to methods and technologies for transmitting learning content regardless of physical distance.

[0214] "Learning progress" refers to the user's level of achievement in the process of completing the learning curriculum.

[0215] "Personalized learning support" means providing learning support tailored to each individual user.

[0216] "Exam questions" are questions designed to evaluate learning and measure understanding.

[0217] "Methods for automated evaluation" refer to methods or devices that have the function of independently analyzing user responses and providing scores or feedback.

[0218] "Emotional state" is a concept that represents a user's psychological feelings and mood.

[0219] "Emotional analysis tools" refer to methods and technologies for recognizing and interpreting a user's emotional state.

[0220] "Dynamically adjusting educational support content" means instantly changing educational methods and materials according to the user's status and progress.

[0221] This invention is a composite system that incorporates an emotion engine into an online education system to enable users to efficiently improve their skills. This system includes a server, a user's mobile device (e.g., smart glasses), and the emotion engine.

[0222] The server uses information processing tools to formulate the optimal learning process based on the input learning history and work history information. This process employs data analysis and machine learning techniques, specifically utilizing AI modules such as TensorFlow and AWS® Lambda. The server also delivers the generated educational resources to the user's terminal via cloud storage such as Amazon S3.

[0223] The user terminal is equipped with a display for showing educational resources and a camera and microphone for detecting emotional states. The emotion engine uses Google® Cloud Vision API and Google Cloud Speech-to-Text to analyze the user's facial expressions and voice in real time, determining emotional states such as concentration levels and stress. Based on this analysis, educational support content is dynamically adjusted. Specifically, generated materials are modified based on the emotional state, and breaks are recommended.

[0224] For example, suppose a user is using smart glasses on a train to study a data science course. The server tracks the user's progress and uses a generative AI model to formulate the optimal answer to the prompt "What learning method is best when the user is not concentrating?" and displays it on the glasses, providing a personalized learning experience. An example of a prompt might be, "What type of content should be recommended when the user is tired?"

[0225] In this way, the present invention provides a system that realizes a flexible and personalized learning experience that takes into account the user's emotional state.

[0226] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0227] Step 1:

[0228] The server receives the user's learning history and work history information. Based on this input data, it uses AI-powered information processing tools to analyze the data and generate an optimal educational curriculum. As output, personalized educational curriculum data is obtained. A machine learning model using TensorFlow is utilized in this analysis process.

[0229] Step 2:

[0230] The server delivers the generated curriculum to the user's device via cloud storage (e.g., Amazon S3). The delivered data is received on the user's device and becomes available as an educational resource. The output is an educational resource file stored on the user's device's storage.

[0231] Step 3:

[0232] The user terminal uses a display device (e.g., smart glasses display) to present the received educational curriculum to the user. Learning activities are conducted through user input. Users can access and interact with the learning materials through intuitive operation.

[0233] Step 4:

[0234] The user device uses an emotion engine to acquire user facial expressions and voice data from the camera and microphone. This input data is analyzed using the Google Cloud Vision API and Google Cloud Speech-to-Text to evaluate the user's emotional state in real time. The output is metadata indicating the emotional state.

[0235] Step 5:

[0236] The server receives metadata about the user's emotional state and, along with learning progress data, generates the next learning support content using a prompt message powered by a generative AI model: "If the user is not focused, which learning method is best?". The output is the next educational support content provided, which includes dynamically adjusted learning materials.

[0237] Step 6:

[0238] The user terminal displays the adjusted educational support content received from the server to the user again, improving learning effectiveness. This process continuously supports the user's learning cycle. The output is a new, customized learning experience that reflects the user's next learning action.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] [Second Embodiment]

[0243] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0244] 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.

[0245] 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).

[0246] 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.

[0247] 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.

[0248] 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).

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] 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".

[0255] The system implementing this invention will be implemented as an online platform for users to efficiently improve their skills remotely. The system will consist of various servers and user terminals, which will interact with each other via the internet.

[0256] The server first uses artificial intelligence to propose the most suitable educational curriculum based on the user's learning history and career information. For example, if a user is interested in "data science," the server analyzes their past learning content and skill level to recommend introductory courses in Python programming and statistics.

[0257] Based on the course selected by the user, the server generates educational resources such as learning materials and lecture videos and delivers them to the user's device. The user's device efficiently displays the received data, allowing the user to access it at any time.

[0258] During learning, the server consistently tracks the user's learning progress and uses generative AI to provide personalized learning support. For example, if a user is falling behind, it may suggest supplementary materials or provide additional practice problems to support their understanding.

[0259] During the testing phase, the server automatically generates test questions and provides them to the user online. The user's device sends their answers to the server. The server's AI grades the answers and provides the results to the user as feedback. This allows the user to self-assess and use the results to inform their next learning activities.

[0260] For example, in the data science course exam, a Python coding problem is given, and the server executes and evaluates the submitted code, showing areas for improvement and successful examples. This allows users to understand their weaknesses in real time and use that information to further improve their skills.

[0261] Through these features, the system provides an environment where working professionals can deepen their learning regardless of time or location, and enhance their skills without interrupting their careers.

[0262] The following describes the processing flow.

[0263] Step 1:

[0264] The server receives registration information when a user accesses the portal site and creates an account. It then prompts the user to enter their past learning history and career information, which is then stored in the database.

[0265] Step 2:

[0266] After logging in, the user selects a course they wish to take from the list of available courses displayed by the server. The server registers the selected course in its database and sends a confirmation notification to the user.

[0267] Step 3:

[0268] The server uses a generative AI to generate optimal educational resources (textbooks, lecture videos, etc.) based on the course selected by the user. The generated content is then delivered to the user's device.

[0269] Step 4:

[0270] The terminal displays educational resources sent from the server to the user, making them freely accessible. Users can then use these materials to learn at their own pace.

[0271] Step 5:

[0272] The server continuously tracks the user's learning progress, and the generative AI provides personalized learning support. Supplementary materials and additional practice problems are presented to the user as needed.

[0273] Step 6:

[0274] Once the user completes a learning unit, the server uses a generation AI to generate test questions to measure the user's understanding. These questions are then sent to the user's device.

[0275] Step 7:

[0276] The user's device displays the test questions and prepares the user to enter their answers. Once the user completes the test, they submit their answers to the server.

[0277] Step 8:

[0278] The server automatically evaluates the transmitted answers using generative AI, generates scoring results and feedback, and sends the results to the user's terminal, providing the user with materials for planning the next learning step.

[0279] Step 9:

[0280] Based on the feedback from the server, the user checks their progress and determines the courses to retake and the learning guidelines for the next step. The server registers for a new learning phase and proposes courses.

[0281] (Example 1)

[0282] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0283] In modern society, people are required to continuously improve their skills without being restricted by time or location. However, in conventional learning systems, it has been difficult to propose an optimal learning program corresponding to individual learning situations and skill levels, and it has also been difficult to provide appropriate support in real time as learning progresses. This has hindered the realization of efficient skill improvement.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0285] In this invention, the server includes artificial intelligence means for proposing an optimal education program based on the user's learning history and work experience, means for conducting education remotely using the generated educational content, and means for tracking the learning situation and providing individualized learning support to the user. This enables customized learning content and real-time learning support for individual users.

[0286] The "user" refers to a person who accesses an online platform, inputs their learning history and work experience, and takes an education program.

[0287] The "learning history" refers to information on the courses the user has taken and the skills acquired in the past.

[0288] The "work history" refers to information regarding the user's professional experiences and career.

[0289] The "education program" refers to a series of learning contents proposed based on the user's learning history and work history for acquiring specific objectives and skills.

[0290] The "artificial intelligence means" refers to algorithms and models for automatically generating the optimal education program for the user based on the given data.

[0291] The "education content" refers to resources such as learning materials and lecture videos included in the education program.

[0292] "Conducting education remotely" refers to an act that enables the user to learn via the Internet without depending on a physical location.

[0293] The "learning situation" refers to real-time information regarding the user's progress and comprehension level.

[0294] "Individualized learning support" refers to providing learning advice and assistance corresponding to specific needs according to the user's learning situation.

[0295] The "test questions" refer to questions generated to evaluate the user's learning outcomes.

[0296] "Automatically analyzing" refers to automatically evaluating the answers submitted by the user using a generative AI model and providing the results.

[0297] "Feedback" refers to evaluations and advice generated based on the answers submitted by the user and the progress of learning.

[0298] "Supplementary materials" refer to learning resources provided to support the user's understanding and practice.

[0299] This invention is a system implemented as an online platform for users to efficiently improve their skills remotely. This system operates via a server, terminals, and an internet connection.

[0300] Hardware and software

[0301] The server runs on a high-performance computer and uses artificial intelligence to provide users with optimal educational programs. In particular, a generative AI model is used to generate programs, creating the most suitable content based on data such as the user's learning history and work experience. The terminal is the device used by the user to receive educational content, and includes personal computers, tablets, and smartphones. It displays the content sent from the server through a browser or dedicated application.

[0302] Data processing and calculations

[0303] The server analyzes data acquired from users, and a generative AI model automatically generates educational programs using that data. Machine learning algorithms and natural language processing techniques are used for the analysis. The generated programs are customized according to the user's skill level and learning speed.

[0304] Specific example

[0305] For example, if a user is interested in data science, the server will suggest introductory courses in Python programming and statistics based on their past learning history. Depending on the course the user selects, relevant learning materials and video lectures will be delivered from the server. The user can then view this content on their device and proceed with their learning.

[0306] Example of a prompt

[0307] Examples of prompt texts may include the following:

[0308] "User's learning history: Introduction to Python, Basic Statistics / Areas of interest: Data Science / Please propose an optimal educational program for skill improvement."

[0309] Through this system, users are provided with an environment where they can efficiently improve their skills regardless of time and location.

[0310] The flow of specific processing in Example 1 will be described using FIG. 11.

[0311] Step 1:

[0312] The user uses the terminal to access the online platform. Here, the user inputs their learning history and job history. This input information is the basic data used for future educational program proposals. The user inputs the necessary information into a dedicated online form and presses the send button to send the data to the server.

[0313] Step 2:

[0314] Based on the learning history and job history received from the user, the server uses a generative AI model to generate an optimal educational program. The user data received as input is passed to the generative AI model and analyzed by data analysis and machine learning algorithms. As output, the server generates and presents a list of courses suitable for the user's learning goals.

[0315] Step 3:

[0316] The user checks the list of educational programs presented by the server and selects the course they want to take. This selection operation is performed on the terminal, and the selection information is sent back to the server. Thereby, individual learning content is set according to the user's learning motivation and direction.

[0317] Step 4:

[0318] The server generates and prepares for distribution relevant educational content (such as textbooks and lecture videos) based on the course selected by the user. The server searches for necessary content from the course database and arranges for efficient distribution to the user's terminal. The output consists of links and data files sent to the user's terminal.

[0319] Step 5:

[0320] The user's device receives educational content delivered from the server and displays it in a format that the user can learn from. The device's application presents the received data to the user in an appropriate format and initiates downloads or streaming as needed. The output is an interactive content display to support the user's learning.

[0321] Step 6:

[0322] The server periodically tracks the user's learning progress and analyzes the progress data using a generative AI model. Based on the user's learning speed and comprehension level, it provides necessary support and supplementary materials. The input is the user's learning log, and the output includes additional practice problems and advice as personalized learning support.

[0323] Step 7:

[0324] When a user completes a course, the server generates exam questions and delivers them to the user's device. The generation AI model automatically generates appropriate and challenging exam questions based on the learned content. The user answers these questions, and the results are sent back to the server.

[0325] Step 8:

[0326] The server receives test answers submitted by the user and automatically evaluates them using a generative AI model. The server analyzes the accuracy rate and learning comprehension level and provides feedback to the user. The output is an evaluation and advice to help the user progress to the next learning step.

[0327] (Application Example 1)

[0328] 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."

[0329] In modern society, there is a lack of appropriate learning environments and materials for workers who aim to advance their careers while continuing their individual jobs. Traditional education systems only provide uniform educational content, and do not adequately offer personalized educational support based on individual learning histories and job information. As a result, users have difficulty efficiently accessing educational programs that suit their interests and skills. In addition, the lack of management of learning progress and appropriate feedback is also a challenge.

[0330] 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.

[0331] In this invention, the server includes an intelligent algorithm that proposes an optimal educational program based on the user's learning history and job information, a device that provides education remotely using the generated educational content, and a device that monitors the progress of learning and provides personalized learning support to the user. This makes it possible to efficiently provide an optimal educational program according to each user's learning history and abilities.

[0332] An "intelligent algorithm" is a computational method that analyzes a user's learning history and job information to automatically suggest the optimal educational program.

[0333] "Educational content" refers to educational resources such as textbooks, lecture videos, and practice problems that are provided based on the user's learning progress.

[0334] A "device for providing education remotely" is a system that uses communication technology to allow users to receive and learn educational content even when they are physically separated from their homes.

[0335] A "device that monitors learning progress and provides personalized learning support" is a system that tracks the user's learning progress and provides optimal support based on the analysis results.

[0336] "Communication terminal equipment" refers to devices that users use to receive and utilize educational content provided remotely, and includes smartphones and computers.

[0337] The system that implements this application starts when the user inputs their learning history and job information using their communication terminal device, and the server receives this information. The server analyzes the user's information using intelligent algorithms and generates an optimal educational program. In this process, a "general cloud platform" is used as a cloud service, and "TensorFlow" and "PyTorch" are used as "AI libraries".

[0338] Educational content generated from the server is delivered to the user's communication terminal device. This educational content takes the form of learning materials and lecture videos, and is available on demand according to the user's preferences. The terminal efficiently displays the received data and provides an interface that enhances user convenience as they progress through their learning.

[0339] To monitor learning progress, the server periodically retrieves learning data from users and analyzes it to personalize learning support. If learning progress is slow, the server delivers additional supplementary materials to support improved understanding. It also automatically generates and provides test questions, and after receiving the user's answers, automatically grades them using an intelligent algorithm.

[0340] For example, if a user expresses interest in "marketing analytics," the server will analyze this and suggest educational programs related to digital marketing and data analysis. Supplementary materials such as additional explanatory videos and practice problems will be provided. During examinations, it is possible to evaluate the user's submitted marketing data analysis scripts in real time and provide feedback on the results.

[0341] An example of a prompt statement for a generative AI model can be shown as follows:

[0342] "Based on the user's past learning data and area of ​​interest, 'Marketing Analytics,' please recommend appropriate learning content. Specifically, prioritize courses related to digital marketing and data analysis, and provide supplementary materials if needed."

[0343] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0344] Step 1:

[0345] Users input their learning history and job information into the system via a communication terminal device. This information is used as input data sent to the server. Users manually enter the necessary information using the screen interface, confirm it, and then press the submit button.

[0346] Step 2:

[0347] The server analyzes the received user learning history and job information using intelligent algorithms. During the analysis, it utilizes generative AI models to process the data and propose educational programs best suited to the user's interests and skills. The output is a list of optimized educational programs for the user.

[0348] Step 3:

[0349] The server selects appropriate educational content for the user based on the generated educational program and distributes it to the communication terminal device. This includes digital content such as educational materials and lecture videos. Data compression and encryption technologies are expected to be used during distribution. The output is the educational content delivered to the user's terminal.

[0350] Step 4:

[0351] The communication terminal visually displays the received educational content to the user. The terminal launches the appropriate application depending on the type of content (video, text, practice exercises, etc.) and plays or displays the data. The user can control the learning progress through the screen.

[0352] Step 5:

[0353] As a user progresses through their learning, their progress data is sent back to the server. The server analyzes this data to optimize learning support. For example, it might suggest supplementary materials to users who are falling behind. The input is progress data, and the output is the suggested support content.

[0354] Step 6:

[0355] The server generates test questions and sends them to the user's communication terminal. In this process, a generation AI model is used to dynamically generate questions, providing different questions for each user. The input is the user's learning history and progress, and the output is the test questions.

[0356] Step 7:

[0357] The user solves the problem on their device and sends their answer to the server. The server automatically scores the received answer using an intelligent algorithm and sends the result as feedback to the user. The server determines the correctness of the answer through data calculation and calculates a score. The output is the scoring result.

[0358] 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.

[0359] This invention enhances the learning experience by incorporating an emotion engine into an online education system that allows users to efficiently improve their skills in a remote environment. The system is configured as a complex system including a server, user terminals, and the emotion engine.

[0360] The server collects learning history and career information provided by the user and uses artificial intelligence to propose an optimal, personalized educational curriculum. It also remotely delivers the generated educational resources to the user's terminal, enabling continuous learning. The terminal appropriately displays the delivered materials, providing the user with a learning environment they can access at their own pace.

[0361] The server constantly tracks the user's learning progress, and the generating AI provides personalized learning support tailored to the user. This includes providing learning materials according to the user's progress and suggesting supplementary materials based on their level of understanding. At key learning milestones, test questions are generated and delivered via the user's device. The device sends the user's answers back to the server, which uses AI to score and evaluate the answers, providing feedback.

[0362] Furthermore, the server utilizes an emotion engine to recognize the user's emotional state in real time. The emotion engine can determine stress levels, concentration levels, and satisfaction levels through facial expression and voice analysis. Based on this emotional recognition, the learning support content is dynamically adjusted. Specifically, if the user shows signs of fatigue, the system automatically takes measures such as recommending a break or providing simple review materials.

[0363] For example, when a user is working on an advanced data science course, the server monitors the user's progress and emotional state, and adjusts the intensity of the practice exercises to improve learning efficiency. If the server detects that the user is becoming impatient, it simplifies the interface and provides hints to deepen the user's understanding.

[0364] As described above, the present invention provides a system that enables working adults to efficiently improve their skills without interrupting their careers, and furthermore, by utilizing an emotional engine, to realize a high-quality learning experience.

[0365] The following describes the processing flow.

[0366] Step 1:

[0367] The user accesses the learning portal and enters the required registration information. The server receives this information and creates a user account in the database.

[0368] Step 2:

[0369] The server analyzes the user's input learning history and career information, and uses artificial intelligence to generate an optimal curriculum. A list of the generated curriculum is then displayed on the user's device.

[0370] Step 3:

[0371] The user selects their desired course from the displayed curriculum. After selection, the server generates the corresponding educational resources and delivers them remotely to the user's terminal.

[0372] Step 4:

[0373] The device visually displays the received educational resources to the user, providing access to lecture videos and learning materials. The user then begins learning accordingly.

[0374] Step 5:

[0375] During learning, the server constantly monitors the user's progress and applies personalized learning support generated by AI. This includes highlighting learned content and suggesting new practice problems.

[0376] Step 6:

[0377] The server activates the emotion engine and recognizes the user's emotional state. It analyzes the user's facial expressions and voice data to evaluate their concentration level and stress level.

[0378] Step 7:

[0379] Based on the emotion engine's evaluation, the server adjusts the learning pace and difficulty to improve the user's experience. If the server determines that the user is fatigued, it sends a notification to the device recommending a short break.

[0380] Step 8:

[0381] When a user completes a learning unit, the server generates test questions and sends them to the user's device. The user takes the test and sends their answers back to the server via their device.

[0382] Step 9:

[0383] The server uses AI to automatically evaluate responses, scores them, and generates feedback. It presents the results to the user in real time and clearly indicates the next learning task.

[0384] Step 10:

[0385] Based on the feedback, users revise their learning plans and decide which courses and content to move on to next. The server supports this process and provides guidance for the new learning phase.

[0386] (Example 2)

[0387] 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".

[0388] In today's educational environment, enabling users to learn sustainably and effectively in a remote setting remains a significant challenge. In particular, uniform educational programs often fail to adequately consider individual users' learning progress and emotional states, potentially leading to decreased learning efficiency. Furthermore, there is a lack of mechanisms to prevent users from being forced to interrupt their learning due to their emotional state. Under these circumstances, it is necessary to provide educational services optimized for individual users and to offer learning support that responds to their emotional state.

[0389] 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.

[0390] In this invention, the server includes intelligent processing means for presenting an optimal educational curriculum based on the user's learning history and occupational information, means for remotely conducting education using the generated educational resources, means for monitoring learning progress and providing personalized learning support to the user, and emotion recognition means for analyzing the user's emotional state in real time and adjusting the content of learning support. This enables the provision of a learning experience optimized for each individual user and dynamic learning support based on emotional state.

[0391] A "user" is an individual who uses an educational system to learn or improve their skills.

[0392] "Learning history" refers to data that records the courses a user has taken, the content they have learned, and their progress.

[0393] "Occupational information" refers to information about a user's career, including data that shows their work experience and skill set.

[0394] An "educational curriculum" refers to a learning program optimized based on the user's needs and skill level.

[0395] "Intelligent processing means" refers to the process of analyzing data using artificial intelligence and proposing the most suitable educational curriculum to the user.

[0396] "Providing education remotely" means offering educational resources to users in physically distant locations via the internet.

[0397] "Monitoring learning progress" refers to the activity of tracking how much a user has learned and recording their learning history.

[0398] "Personalized learning support" refers to the provision of support and learning materials tailored to each user.

[0399] "Emotion recognition means" refers to technology that analyzes a user's emotional state from their facial expressions, voice, etc., and responds accordingly.

[0400] "Educational resources" refer to content such as textbooks, videos, and materials that users utilize during their learning process.

[0401] "Adjusting the content of learning support" means optimizing the educational content provided and offering appropriate support according to the user's emotional state.

[0402] This invention is an online education system that enables users to efficiently improve their skills in a remote environment. It combines a server, terminal, and emotion engine to provide an education service optimized for the user.

[0403] The server receives and collects the user's learning history and occupational information. Based on this data, it uses a generative AI model to generate an optimal learning curriculum for the user. Intelligent processing is used to generate the curriculum. For example, if a user wants to improve their data science skills, relevant courses and materials will be recommended.

[0404] The generated educational resources are delivered to the user's device via the internet. The device displays these materials appropriately, providing a learning environment that the user can access at their own convenience. The delivered materials include video lectures and interactive exercises.

[0405] The server constantly monitors the user's progress during learning. This allows it to track how far the user has progressed and record it as a history. Based on this information, the generating AI provides individually optimized learning support. If the user is stuck on a particular topic, it can provide additional explanatory videos or supplementary materials.

[0406] Furthermore, the server uses an emotion engine to analyze the user's emotional state in real time. By performing facial expression and voice analysis, it can understand the user's stress levels and concentration, and adjust the learning support content accordingly. For example, if the user shows signs of fatigue, the system will automatically suggest a break.

[0407] A concrete example of a prompt is, "Consider the user's current progress and emotional state, and generate a learning plan for the next week." Based on such prompts, the AI ​​model presents the most suitable approach to the user.

[0408] This system allows users to learn flexibly and efficiently without interrupting their careers, and to improve their learning experience with personalized support.

[0409] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0410] Step 1:

[0411] The server receives the user's learning history and occupational information as input. Based on this information, it performs analysis using intelligent processing tools. Specifically, it analyzes the user's past learning data and skill set and proposes an educational curriculum that suits the user's needs. The output of this step is the optimal educational curriculum based on each user's needs.

[0412] Step 2:

[0413] The server uses a generative AI model to construct learning materials based on the curriculum obtained in Step 1. The curriculum identified in the previous step is used as input. Specific data calculations include selecting course content and optimizing learning resource resources. The output of this step is user-optimized learning resources (textbooks, video lectures, practice problems, etc.).

[0414] Step 3:

[0415] The server distributes the obtained educational resources to the user's terminal via the internet. The terminal receives the distributed educational resources and organizes them so that the user can use them. Specifically, this involves downloading the learning materials and displaying them on the interface. The input is the educational resources generated in step 2, and the output is the state in which they have been prepared for the user to use for learning.

[0416] Step 4:

[0417] Users progress through their learning using learning materials provided via their devices. The server tracks the user's learning progress in real time. Learning progress information is used as input, and the server records this information in a database as learning history. The output is updated learning progress information.

[0418] Step 5:

[0419] The server uses a generative AI model to provide personalized learning support based on the user's progress information. The input is learning progress data, which is used to analyze areas where the user is lacking and areas that need further improvement. The output is additional learning materials and explanatory information provided to the user.

[0420] Step 6:

[0421] The server utilizes an emotion engine to analyze the user's emotional state. Using sensors and cameras, it receives user facial expressions and voice information as input and evaluates emotions in real time. The output is data indicating the user's current emotional state, and learning support is adjusted based on this data.

[0422] Step 7:

[0423] The device dynamically adjusts the user interface based on emotional data received from the server. If the user is stressed, it switches to a more intuitive and simpler interface or displays an alert prompting them to take a break. The input is emotional state data from the server, and the output is the adjusted interface and support functions.

[0424] (Application Example 2)

[0425] 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."

[0426] Modern learners demand flexibility and individualization in their learning, and also need support to overcome emotional stress and decreased motivation. Traditional online education systems have lacked the means to address the individual emotional states of learners, making it difficult to maximize learning effectiveness. Furthermore, while there is a demand for continuous, real-time learning support, these systems lacked the flexibility to adapt to diverse learning environments.

[0427] 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.

[0428] In this invention, the server includes information processing means for proposing an appropriate educational curriculum based on the user's learning history and work history information; means for providing education remotely using the generated educational resources; means for tracking learning progress and providing personalized learning support to the user; means for generating test questions and automatically evaluating the user's answers; and emotion analysis means for recognizing the user's emotional state in real time and dynamically adjusting the educational support content. This makes it possible to maximize the learning effectiveness of learners while providing learning support tailored to their individual emotional states in real time.

[0429] A "user" is an individual or legal entity that uses the system to learn.

[0430] "Learning history" refers to a record of the educational resources a user has used to date and the results of those efforts.

[0431] "Work history information" refers to data related to the user's professional experience and career.

[0432] "Information processing means" refers to methods and devices for collecting, analyzing, and processing information.

[0433] "Educational resources" refer to teaching materials and tools provided to support learning activities.

[0434] "Means of providing education remotely" refer to methods and technologies for transmitting learning content regardless of physical distance.

[0435] "Learning progress" refers to the user's level of achievement in the process of completing the learning curriculum.

[0436] "Personalized learning support" means providing learning support tailored to each individual user.

[0437] "Exam questions" are questions designed to evaluate learning and measure understanding.

[0438] "Methods for automated evaluation" refer to methods or devices that have the function of independently analyzing user responses and providing scores or feedback.

[0439] "Emotional state" is a concept that represents a user's psychological feelings and mood.

[0440] "Emotional analysis tools" refer to methods and technologies for recognizing and interpreting a user's emotional state.

[0441] "Dynamically adjusting educational support content" means instantly changing educational methods and materials according to the user's status and progress.

[0442] This invention is a composite system that incorporates an emotion engine into an online education system to enable users to efficiently improve their skills. This system includes a server, a user's mobile device (e.g., smart glasses), and the emotion engine.

[0443] The server uses information processing tools to formulate the optimal learning process based on the input learning history and work history information. This process employs data analysis and machine learning techniques, specifically utilizing AI modules such as TensorFlow and AWS Lambda. The server also delivers the generated educational resources to the user's device via cloud storage such as Amazon S3.

[0444] The user terminal is equipped with a display for showing educational resources and a camera and microphone for detecting emotional states. The emotion engine uses the Google Cloud Vision API and Google Cloud Speech-to-Text to analyze the user's facial expressions and voice in real time, determining emotional states such as concentration levels and stress. Based on this analysis, educational support content is dynamically adjusted. Specifically, generated materials are modified based on the emotional state, and breaks are recommended.

[0445] For example, suppose a user is using smart glasses on a train to study a data science course. The server tracks the user's progress and uses a generative AI model to formulate the optimal answer to the prompt "What learning method is best when the user is not concentrating?" and displays it on the glasses, providing a personalized learning experience. An example of a prompt might be, "What type of content should be recommended when the user is tired?"

[0446] In this way, the present invention provides a system that realizes a flexible and personalized learning experience that takes into account the user's emotional state.

[0447] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0448] Step 1:

[0449] The server receives the user's learning history and work history information. Based on this input data, it uses AI-powered information processing tools to analyze the data and generate an optimal educational curriculum. As output, personalized educational curriculum data is obtained. A machine learning model using TensorFlow is utilized in this analysis process.

[0450] Step 2:

[0451] The server delivers the generated curriculum to the user's device via cloud storage (e.g., Amazon S3). The delivered data is received on the user's device and becomes available as an educational resource. The output is an educational resource file stored on the user's device's storage.

[0452] Step 3:

[0453] The user terminal uses a display device (e.g., smart glasses display) to present the received educational curriculum to the user. Learning activities are conducted through user input. Users can access and interact with the learning materials through intuitive operation.

[0454] Step 4:

[0455] The user device uses an emotion engine to acquire user facial expressions and voice data from the camera and microphone. This input data is analyzed using the Google Cloud Vision API and Google Cloud Speech-to-Text to evaluate the user's emotional state in real time. The output is metadata indicating the emotional state.

[0456] Step 5:

[0457] The server receives metadata about the user's emotional state and, along with learning progress data, generates the next learning support content using a prompt message powered by a generative AI model: "If the user is not focused, which learning method is best?". The output is the next educational support content provided, which includes dynamically adjusted learning materials.

[0458] Step 6:

[0459] The user terminal displays the adjusted educational support content received from the server to the user again, improving learning effectiveness. This process continuously supports the user's learning cycle. The output is a new, customized learning experience that reflects the user's next learning action.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] [Third Embodiment]

[0464] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0465] 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.

[0466] 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).

[0467] 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.

[0468] 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.

[0469] 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).

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] 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.

[0475] 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".

[0476] The system implementing this invention will be implemented as an online platform for users to efficiently improve their skills remotely. The system will consist of various servers and user terminals, which will interact with each other via the internet.

[0477] The server first uses artificial intelligence to propose the most suitable educational curriculum based on the user's learning history and career information. For example, if a user is interested in "data science," the server analyzes their past learning content and skill level to recommend introductory courses in Python programming and statistics.

[0478] Based on the course selected by the user, the server generates educational resources such as learning materials and lecture videos and delivers them to the user's device. The user's device efficiently displays the received data, allowing the user to access it at any time.

[0479] During learning, the server consistently tracks the user's learning progress and uses generative AI to provide personalized learning support. For example, if a user is falling behind, it may suggest supplementary materials or provide additional practice problems to support their understanding.

[0480] During the testing phase, the server automatically generates test questions and provides them to the user online. The user's device sends their answers to the server. The server's AI grades the answers and provides the results to the user as feedback. This allows the user to self-assess and use the results to inform their next learning activities.

[0481] For example, in the data science course exam, a Python coding problem is given, and the server executes and evaluates the submitted code, showing areas for improvement and successful examples. This allows users to understand their weaknesses in real time and use that information to further improve their skills.

[0482] Through these features, the system provides an environment where working professionals can deepen their learning regardless of time or location, and enhance their skills without interrupting their careers.

[0483] The following describes the processing flow.

[0484] Step 1:

[0485] The server receives registration information when a user accesses the portal site and creates an account. It then prompts the user to enter their past learning history and career information, which is then stored in the database.

[0486] Step 2:

[0487] After logging in, the user selects a course they wish to take from the list of available courses displayed by the server. The server registers the selected course in its database and sends a confirmation notification to the user.

[0488] Step 3:

[0489] The server uses a generative AI to generate optimal educational resources (textbooks, lecture videos, etc.) based on the course selected by the user. The generated content is then delivered to the user's device.

[0490] Step 4:

[0491] The terminal displays educational resources sent from the server to the user, making them freely accessible. Users can then use these materials to learn at their own pace.

[0492] Step 5:

[0493] The server continuously tracks the user's learning progress, and the generative AI provides personalized learning support. Supplementary materials and additional practice problems are presented to the user as needed.

[0494] Step 6:

[0495] Once the user completes a learning unit, the server uses a generation AI to generate test questions to measure the user's understanding. These questions are then sent to the user's device.

[0496] Step 7:

[0497] The user's device displays the test questions and prepares the user to enter their answers. Once the user completes the test, they submit their answers to the server.

[0498] Step 8:

[0499] The server automatically evaluates the submitted responses using a generation AI, generating a score and feedback. The results are sent to the user's device, providing the user with information to plan their next learning steps.

[0500] Step 9:

[0501] Based on feedback from the server, users can check their progress and decide on their next course and learning strategy. The server then registers them for a new learning phase and suggests courses.

[0502] (Example 1)

[0503] 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."

[0504] In modern society, people are required to continuously improve their skills without being constrained by time or place. However, traditional learning systems have struggled to propose optimal learning programs tailored to individual learning situations and skill levels, and have also found it difficult to provide appropriate support in real time as learning progresses. This has hindered the efficient realization of skill improvement.

[0505] 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.

[0506] In this invention, the server includes artificial intelligence means for suggesting an optimal educational program based on the user's learning history and work experience, means for remotely providing education using the generated educational content, and means for tracking learning progress and providing personalized learning support to the user. This enables customized learning content and real-time learning support for each individual user.

[0507] A "user" refers to anyone who accesses an online platform, enters their learning history and work experience, and participates in educational programs.

[0508] "Learning history" refers to information about the courses a user has taken and the skills they have acquired in the past.

[0509] "Work history" refers to information about a user's professional experience and career.

[0510] An "educational program" is a set of learning materials suggested based on a user's learning history and work experience, designed to help them acquire specific goals and skills.

[0511] "Artificial intelligence tools" refer to algorithms and models that automatically generate optimal educational programs for users based on given data.

[0512] "Educational content" refers to resources such as learning materials and lecture videos included in an educational program.

[0513] "Remote education" refers to the act of enabling users to learn via the internet, regardless of their physical location.

[0514] "Learning status" refers to real-time information regarding the user's progress and level of understanding.

[0515] "Personalized learning support" refers to providing learning advice and assistance that addresses specific needs based on the user's learning progress.

[0516] "Exam questions" refer to questions generated to evaluate a user's learning achievements.

[0517] "Automatic analysis" refers to the automatic evaluation of user-submitted answers by a generating AI model, followed by the provision of results.

[0518] "Feedback" refers to evaluations and advice generated based on the user's submitted answers and learning progress.

[0519] "Supplementary materials" refer to learning resources provided to support the user's understanding and practice.

[0520] This invention is a system implemented as an online platform for users to efficiently improve their skills remotely. This system operates via a server, terminals, and an internet connection.

[0521] Hardware and software

[0522] The server runs on a high-performance computer and uses artificial intelligence to provide users with optimal educational programs. In particular, a generative AI model is used to generate programs, creating the most suitable content based on data such as the user's learning history and work experience. The terminal is the device used by the user to receive educational content, and includes personal computers, tablets, and smartphones. It displays the content sent from the server through a browser or dedicated application.

[0523] Data processing and calculations

[0524] The server analyzes data acquired from users, and a generative AI model automatically generates educational programs using that data. Machine learning algorithms and natural language processing techniques are used for the analysis. The generated programs are customized according to the user's skill level and learning speed.

[0525] Specific example

[0526] For example, if a user is interested in data science, the server will suggest introductory courses in Python programming and statistics based on their past learning history. Depending on the course the user selects, relevant learning materials and video lectures will be delivered from the server. The user can then view this content on their device and proceed with their learning.

[0527] Example of a prompt

[0528] Examples of prompt statements include the following:

[0529] "User's learning history: Introduction to Python, Basic Statistics / Area of ​​Interest: Data Science / Please suggest the optimal educational curriculum for skill development."

[0530] Through this system, users are provided with an environment where they can efficiently improve their skills regardless of time or location.

[0531] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0532] Step 1:

[0533] Users access an online platform using their devices. Here, users input their learning and work history. This input information serves as foundational data for future educational program proposals. Users enter the necessary information into a dedicated online form and press the submit button to send the data to the server.

[0534] Step 2:

[0535] The server generates an optimal educational program using a generative AI model based on the user's learning and work history. The user data received as input is passed to the generative AI model and analyzed using data analysis and machine learning algorithms. As output, the server generates and presents a list of courses suitable for the user's learning goals.

[0536] Step 3:

[0537] The user reviews a list of educational programs presented by the server and selects the course they wish to take. This selection is performed on the user's device, and the selection information is sent back to the server. This allows for the creation of personalized learning content tailored to the user's learning motivation and goals.

[0538] Step 4:

[0539] The server generates and prepares for distribution relevant educational content (such as textbooks and lecture videos) based on the course selected by the user. The server searches for necessary content from the course database and arranges for efficient distribution to the user's terminal. The output consists of links and data files sent to the user's terminal.

[0540] Step 5:

[0541] The user's device receives educational content delivered from the server and displays it in a format that the user can learn from. The device's application presents the received data to the user in an appropriate format and initiates downloads or streaming as needed. The output is an interactive content display to support the user's learning.

[0542] Step 6:

[0543] The server periodically tracks the user's learning progress and analyzes the progress data using a generative AI model. Based on the user's learning speed and comprehension level, it provides necessary support and supplementary materials. The input is the user's learning log, and the output includes additional practice problems and advice as personalized learning support.

[0544] Step 7:

[0545] When a user completes a course, the server generates exam questions and delivers them to the user's device. The generation AI model automatically generates appropriate and challenging exam questions based on the learned content. The user answers these questions, and the results are sent back to the server.

[0546] Step 8:

[0547] The server receives test answers submitted by the user and automatically evaluates them using a generative AI model. The server analyzes the accuracy rate and learning comprehension level and provides feedback to the user. The output is an evaluation and advice to help the user progress to the next learning step.

[0548] (Application Example 1)

[0549] 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."

[0550] In modern society, there is a lack of appropriate learning environments and materials for workers who aim to advance their careers while continuing their individual jobs. Traditional education systems only provide uniform educational content, and do not adequately offer personalized educational support based on individual learning histories and job information. As a result, users have difficulty efficiently accessing educational programs that suit their interests and skills. In addition, the lack of management of learning progress and appropriate feedback is also a challenge.

[0551] 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.

[0552] In this invention, the server includes an intelligent algorithm that proposes an optimal educational program based on the user's learning history and job information, a device that provides education remotely using the generated educational content, and a device that monitors the progress of learning and provides personalized learning support to the user. This makes it possible to efficiently provide an optimal educational program according to each user's learning history and abilities.

[0553] An "intelligent algorithm" is a computational method that analyzes a user's learning history and job information to automatically suggest the optimal educational program.

[0554] "Educational content" refers to educational resources such as textbooks, lecture videos, and practice problems that are provided based on the user's learning progress.

[0555] A "device for providing education remotely" is a system that uses communication technology to allow users to receive and learn educational content even when they are physically separated from their homes.

[0556] A "device that monitors learning progress and provides personalized learning support" is a system that tracks the user's learning progress and provides optimal support based on the analysis results.

[0557] "Communication terminal equipment" refers to devices that users use to receive and utilize educational content provided remotely, and includes smartphones and computers.

[0558] The system that implements this application starts when the user inputs their learning history and job information using their communication terminal device, and the server receives this information. The server analyzes the user's information using intelligent algorithms and generates an optimal educational program. In this process, a "general cloud platform" is used as a cloud service, and "TensorFlow" and "PyTorch" are used as "AI libraries".

[0559] Educational content generated from the server is delivered to the user's communication terminal device. This educational content takes the form of learning materials and lecture videos, and is available on demand according to the user's preferences. The terminal efficiently displays the received data and provides an interface that enhances user convenience as they progress through their learning.

[0560] To monitor learning progress, the server periodically retrieves learning data from users and analyzes it to personalize learning support. If learning progress is slow, the server delivers additional supplementary materials to support improved understanding. It also automatically generates and provides test questions, and after receiving the user's answers, automatically grades them using an intelligent algorithm.

[0561] For example, if a user expresses interest in "marketing analytics," the server will analyze this and suggest educational programs related to digital marketing and data analysis. Supplementary materials such as additional explanatory videos and practice problems will be provided. During examinations, it is possible to evaluate the user's submitted marketing data analysis scripts in real time and provide feedback on the results.

[0562] An example of a prompt statement for a generative AI model can be shown as follows:

[0563] "Based on the user's past learning data and area of ​​interest, 'Marketing Analytics,' please recommend appropriate learning content. Specifically, prioritize courses related to digital marketing and data analysis, and provide supplementary materials if needed."

[0564] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0565] Step 1:

[0566] Users input their learning history and job information into the system via a communication terminal device. This information is used as input data sent to the server. Users manually enter the necessary information using the screen interface, confirm it, and then press the submit button.

[0567] Step 2:

[0568] The server analyzes the received user learning history and job information using intelligent algorithms. During the analysis, it utilizes generative AI models to process the data and propose educational programs best suited to the user's interests and skills. The output is a list of optimized educational programs for the user.

[0569] Step 3:

[0570] The server selects appropriate educational content for the user based on the generated educational program and distributes it to the communication terminal device. This includes digital content such as educational materials and lecture videos. Data compression and encryption technologies are expected to be used during distribution. The output is the educational content delivered to the user's terminal.

[0571] Step 4:

[0572] The communication terminal visually displays the received educational content to the user. The terminal launches the appropriate application depending on the type of content (video, text, practice exercises, etc.) and plays or displays the data. The user can control the learning progress through the screen.

[0573] Step 5:

[0574] As a user progresses through their learning, their progress data is sent back to the server. The server analyzes this data to optimize learning support. For example, it might suggest supplementary materials to users who are falling behind. The input is progress data, and the output is the suggested support content.

[0575] Step 6:

[0576] The server generates test questions and sends them to the user's communication terminal. In this process, a generation AI model is used to dynamically generate questions, providing different questions for each user. The input is the user's learning history and progress, and the output is the test questions.

[0577] Step 7:

[0578] The user solves the problem on their device and sends their answer to the server. The server automatically scores the received answer using an intelligent algorithm and sends the result as feedback to the user. The server determines the correctness of the answer through data calculation and calculates a score. The output is the scoring result.

[0579] 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.

[0580] This invention enhances the learning experience by incorporating an emotion engine into an online education system that allows users to efficiently improve their skills in a remote environment. The system is configured as a complex system including a server, user terminals, and the emotion engine.

[0581] The server collects learning history and career information provided by the user and uses artificial intelligence to propose an optimal, personalized educational curriculum. It also remotely delivers the generated educational resources to the user's terminal, enabling continuous learning. The terminal appropriately displays the delivered materials, providing the user with a learning environment they can access at their own pace.

[0582] The server constantly tracks the user's learning progress, and the generating AI provides personalized learning support tailored to the user. This includes providing learning materials according to the user's progress and suggesting supplementary materials based on their level of understanding. At key learning milestones, test questions are generated and delivered via the user's device. The device sends the user's answers back to the server, which uses AI to score and evaluate the answers, providing feedback.

[0583] Furthermore, the server utilizes an emotion engine to recognize the user's emotional state in real time. The emotion engine can determine stress levels, concentration levels, and satisfaction levels through facial expression and voice analysis. Based on this emotional recognition, the learning support content is dynamically adjusted. Specifically, if the user shows signs of fatigue, the system automatically takes measures such as recommending a break or providing simple review materials.

[0584] For example, when a user is working on an advanced data science course, the server monitors the user's progress and emotional state, and adjusts the intensity of the practice exercises to improve learning efficiency. If the server detects that the user is becoming impatient, it simplifies the interface and provides hints to deepen the user's understanding.

[0585] As described above, the present invention provides a system that enables working adults to efficiently improve their skills without interrupting their careers, and furthermore, by utilizing an emotional engine, to realize a high-quality learning experience.

[0586] The following describes the processing flow.

[0587] Step 1:

[0588] The user accesses the learning portal and enters the required registration information. The server receives this information and creates a user account in the database.

[0589] Step 2:

[0590] The server analyzes the user's input learning history and career information, and uses artificial intelligence to generate an optimal curriculum. A list of the generated curriculum is then displayed on the user's device.

[0591] Step 3:

[0592] The user selects their desired course from the displayed curriculum. After selection, the server generates the corresponding educational resources and delivers them remotely to the user's terminal.

[0593] Step 4:

[0594] The device visually displays the received educational resources to the user, providing access to lecture videos and learning materials. The user then begins learning accordingly.

[0595] Step 5:

[0596] During learning, the server constantly monitors the user's progress and applies personalized learning support generated by AI. This includes highlighting learned content and suggesting new practice problems.

[0597] Step 6:

[0598] The server activates the emotion engine and recognizes the user's emotional state. It analyzes the user's facial expressions and voice data to evaluate their concentration level and stress level.

[0599] Step 7:

[0600] Based on the emotion engine's evaluation, the server adjusts the learning pace and difficulty to improve the user's experience. If the server determines that the user is fatigued, it sends a notification to the device recommending a short break.

[0601] Step 8:

[0602] When a user completes a learning unit, the server generates test questions and sends them to the user's device. The user takes the test and sends their answers back to the server via their device.

[0603] Step 9:

[0604] The server uses AI to automatically evaluate responses, scores them, and generates feedback. It presents the results to the user in real time and clearly indicates the next learning task.

[0605] Step 10:

[0606] Based on the feedback, users revise their learning plans and decide which courses and content to move on to next. The server supports this process and provides guidance for the new learning phase.

[0607] (Example 2)

[0608] 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."

[0609] In today's educational environment, enabling users to learn sustainably and effectively in a remote setting remains a significant challenge. In particular, uniform educational programs often fail to adequately consider individual users' learning progress and emotional states, potentially leading to decreased learning efficiency. Furthermore, there is a lack of mechanisms to prevent users from being forced to interrupt their learning due to their emotional state. Under these circumstances, it is necessary to provide educational services optimized for individual users and to offer learning support that responds to their emotional state.

[0610] 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.

[0611] In this invention, the server includes intelligent processing means for presenting an optimal educational curriculum based on the user's learning history and occupational information, means for remotely conducting education using the generated educational resources, means for monitoring learning progress and providing personalized learning support to the user, and emotion recognition means for analyzing the user's emotional state in real time and adjusting the content of learning support. This enables the provision of a learning experience optimized for each individual user and dynamic learning support based on emotional state.

[0612] A "user" is an individual who uses an educational system to learn or improve their skills.

[0613] "Learning history" refers to data that records the courses a user has taken, the content they have learned, and their progress.

[0614] "Occupational information" refers to information about a user's career, including data that shows their work experience and skill set.

[0615] An "educational curriculum" refers to a learning program optimized based on the user's needs and skill level.

[0616] "Intelligent processing means" refers to the process of analyzing data using artificial intelligence and proposing the most suitable educational curriculum to the user.

[0617] "Providing education remotely" means offering educational resources to users in physically distant locations via the internet.

[0618] "Monitoring learning progress" refers to the activity of tracking how much a user has learned and recording their learning history.

[0619] "Personalized learning support" refers to the provision of support and learning materials tailored to each user.

[0620] "Emotion recognition means" refers to technology that analyzes a user's emotional state from their facial expressions, voice, etc., and responds accordingly.

[0621] "Educational resources" refer to content such as textbooks, videos, and materials that users utilize during their learning process.

[0622] "Adjusting the content of learning support" means optimizing the educational content provided and offering appropriate support according to the user's emotional state.

[0623] This invention is an online education system that enables users to efficiently improve their skills in a remote environment. It combines a server, terminal, and emotion engine to provide an education service optimized for the user.

[0624] The server receives and collects the user's learning history and occupational information. Based on this data, it uses a generative AI model to generate an optimal learning curriculum for the user. Intelligent processing is used to generate the curriculum. For example, if a user wants to improve their data science skills, relevant courses and materials will be recommended.

[0625] The generated educational resources are delivered to the user's device via the internet. The device displays these materials appropriately, providing a learning environment that the user can access at their own convenience. The delivered materials include video lectures and interactive exercises.

[0626] The server constantly monitors the user's progress during learning. This allows it to track how far the user has progressed and record it as a history. Based on this information, the generating AI provides individually optimized learning support. If the user is stuck on a particular topic, it can provide additional explanatory videos or supplementary materials.

[0627] Furthermore, the server uses an emotion engine to analyze the user's emotional state in real time. By performing facial expression and voice analysis, it can understand the user's stress levels and concentration, and adjust the learning support content accordingly. For example, if the user shows signs of fatigue, the system will automatically suggest a break.

[0628] A concrete example of a prompt is, "Consider the user's current progress and emotional state, and generate a learning plan for the next week." Based on such prompts, the AI ​​model presents the most suitable approach to the user.

[0629] This system allows users to learn flexibly and efficiently without interrupting their careers, and to improve their learning experience with personalized support.

[0630] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0631] Step 1:

[0632] The server receives the user's learning history and occupational information as input. Based on this information, it performs analysis using intelligent processing tools. Specifically, it analyzes the user's past learning data and skill set and proposes an educational curriculum that suits the user's needs. The output of this step is the optimal educational curriculum based on each user's needs.

[0633] Step 2:

[0634] The server uses a generative AI model to construct learning materials based on the curriculum obtained in Step 1. The curriculum identified in the previous step is used as input. Specific data calculations include selecting course content and optimizing learning resource resources. The output of this step is user-optimized learning resources (textbooks, video lectures, practice problems, etc.).

[0635] Step 3:

[0636] The server distributes the obtained educational resources to the user's terminal via the internet. The terminal receives the distributed educational resources and organizes them so that the user can use them. Specifically, this involves downloading the learning materials and displaying them on the interface. The input is the educational resources generated in step 2, and the output is the state in which they have been prepared for the user to use for learning.

[0637] Step 4:

[0638] Users progress through their learning using learning materials provided via their devices. The server tracks the user's learning progress in real time. Learning progress information is used as input, and the server records this information in a database as learning history. The output is updated learning progress information.

[0639] Step 5:

[0640] The server uses a generative AI model to provide personalized learning support based on the user's progress information. The input is learning progress data, which is used to analyze areas where the user is lacking and areas that need further improvement. The output is additional learning materials and explanatory information provided to the user.

[0641] Step 6:

[0642] The server utilizes an emotion engine to analyze the user's emotional state. Using sensors and cameras, it receives user facial expressions and voice information as input and evaluates emotions in real time. The output is data indicating the user's current emotional state, and learning support is adjusted based on this data.

[0643] Step 7:

[0644] The device dynamically adjusts the user interface based on emotional data received from the server. If the user is stressed, it switches to a more intuitive and simpler interface or displays an alert prompting them to take a break. The input is emotional state data from the server, and the output is the adjusted interface and support functions.

[0645] (Application Example 2)

[0646] 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."

[0647] Modern learners demand flexibility and individualization in their learning, and also need support to overcome emotional stress and decreased motivation. Traditional online education systems have lacked the means to address the individual emotional states of learners, making it difficult to maximize learning effectiveness. Furthermore, while there is a demand for continuous, real-time learning support, these systems lacked the flexibility to adapt to diverse learning environments.

[0648] 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.

[0649] In this invention, the server includes information processing means for proposing an appropriate educational curriculum based on the user's learning history and work history information; means for providing education remotely using the generated educational resources; means for tracking learning progress and providing personalized learning support to the user; means for generating test questions and automatically evaluating the user's answers; and emotion analysis means for recognizing the user's emotional state in real time and dynamically adjusting the educational support content. This makes it possible to maximize the learning effectiveness of learners while providing learning support tailored to their individual emotional states in real time.

[0650] A "user" is an individual or legal entity that uses the system to learn.

[0651] "Learning history" refers to a record of the educational resources a user has used to date and the results of those efforts.

[0652] "Work history information" refers to data related to the user's professional experience and career.

[0653] "Information processing means" refers to methods and devices for collecting, analyzing, and processing information.

[0654] "Educational resources" refer to teaching materials and tools provided to support learning activities.

[0655] "Means of providing education remotely" refer to methods and technologies for transmitting learning content regardless of physical distance.

[0656] "Learning progress" refers to the user's level of achievement in the process of completing the learning curriculum.

[0657] "Personalized learning support" means providing learning support tailored to each individual user.

[0658] "Exam questions" are questions designed to evaluate learning and measure understanding.

[0659] "Methods for automated evaluation" refer to methods or devices that have the function of independently analyzing user responses and providing scores or feedback.

[0660] "Emotional state" is a concept that represents a user's psychological feelings and mood.

[0661] "Emotional analysis tools" refer to methods and technologies for recognizing and interpreting a user's emotional state.

[0662] "Dynamically adjusting educational support content" means instantly changing educational methods and materials according to the user's status and progress.

[0663] This invention is a composite system that incorporates an emotion engine into an online education system to enable users to efficiently improve their skills. This system includes a server, a user's mobile device (e.g., smart glasses), and the emotion engine.

[0664] The server uses information processing tools to formulate the optimal learning process based on the input learning history and work history information. This process employs data analysis and machine learning techniques, specifically utilizing AI modules such as TensorFlow and AWS Lambda. The server also delivers the generated educational resources to the user's device via cloud storage such as Amazon S3.

[0665] The user terminal is equipped with a display for showing educational resources and a camera and microphone for detecting emotional states. The emotion engine uses the Google Cloud Vision API and Google Cloud Speech-to-Text to analyze the user's facial expressions and voice in real time, determining emotional states such as concentration levels and stress. Based on this analysis, educational support content is dynamically adjusted. Specifically, generated materials are modified based on the emotional state, and breaks are recommended.

[0666] For example, suppose a user is using smart glasses on a train to study a data science course. The server tracks the user's progress and uses a generative AI model to formulate the optimal answer to the prompt "What learning method is best when the user is not concentrating?" and displays it on the glasses, providing a personalized learning experience. An example of a prompt might be, "What type of content should be recommended when the user is tired?"

[0667] In this way, the present invention provides a system that realizes a flexible and personalized learning experience that takes into account the user's emotional state.

[0668] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0669] Step 1:

[0670] The server receives the user's learning history and work history information. Based on this input data, it uses AI-powered information processing tools to analyze the data and generate an optimal educational curriculum. As output, personalized educational curriculum data is obtained. A machine learning model using TensorFlow is utilized in this analysis process.

[0671] Step 2:

[0672] The server delivers the generated curriculum to the user's device via cloud storage (e.g., Amazon S3). The delivered data is received on the user's device and becomes available as an educational resource. The output is an educational resource file stored on the user's device's storage.

[0673] Step 3:

[0674] The user terminal uses a display device (e.g., smart glasses display) to present the received educational curriculum to the user. Learning activities are conducted through user input. Users can access and interact with the learning materials through intuitive operation.

[0675] Step 4:

[0676] The user device uses an emotion engine to acquire user facial expressions and voice data from the camera and microphone. This input data is analyzed using the Google Cloud Vision API and Google Cloud Speech-to-Text to evaluate the user's emotional state in real time. The output is metadata indicating the emotional state.

[0677] Step 5:

[0678] The server receives metadata about the user's emotional state and, along with learning progress data, generates the next learning support content using a prompt message powered by a generative AI model: "If the user is not focused, which learning method is best?". The output is the next educational support content provided, which includes dynamically adjusted learning materials.

[0679] Step 6:

[0680] The user terminal displays the adjusted educational support content received from the server to the user again, improving learning effectiveness. This process continuously supports the user's learning cycle. The output is a new, customized learning experience that reflects the user's next learning action.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] [Fourth Embodiment]

[0685] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0686] 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.

[0687] 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).

[0688] 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.

[0689] 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.

[0690] 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).

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] 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.

[0697] 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".

[0698] The system implementing this invention will be implemented as an online platform for users to efficiently improve their skills remotely. The system will consist of various servers and user terminals, which will interact with each other via the internet.

[0699] The server first uses artificial intelligence to propose the most suitable educational curriculum based on the user's learning history and career information. For example, if a user is interested in "data science," the server analyzes their past learning content and skill level to recommend introductory courses in Python programming and statistics.

[0700] Based on the course selected by the user, the server generates educational resources such as learning materials and lecture videos and delivers them to the user's device. The user's device efficiently displays the received data, allowing the user to access it at any time.

[0701] During learning, the server consistently tracks the user's learning progress and uses generative AI to provide personalized learning support. For example, if a user is falling behind, it may suggest supplementary materials or provide additional practice problems to support their understanding.

[0702] During the testing phase, the server automatically generates test questions and provides them to the user online. The user's device sends their answers to the server. The server's AI grades the answers and provides the results to the user as feedback. This allows the user to self-assess and use the results to inform their next learning activities.

[0703] For example, in the data science course exam, a Python coding problem is given, and the server executes and evaluates the submitted code, showing areas for improvement and successful examples. This allows users to understand their weaknesses in real time and use that information to further improve their skills.

[0704] Through these features, the system provides an environment where working professionals can deepen their learning regardless of time or location, and enhance their skills without interrupting their careers.

[0705] The following describes the processing flow.

[0706] Step 1:

[0707] The server receives registration information when a user accesses the portal site and creates an account. It then prompts the user to enter their past learning history and career information, which is then stored in the database.

[0708] Step 2:

[0709] After logging in, the user selects a course they wish to take from the list of available courses displayed by the server. The server registers the selected course in its database and sends a confirmation notification to the user.

[0710] Step 3:

[0711] The server uses a generative AI to generate optimal educational resources (textbooks, lecture videos, etc.) based on the course selected by the user. The generated content is then delivered to the user's device.

[0712] Step 4:

[0713] The terminal displays educational resources sent from the server to the user, making them freely accessible. Users can then use these materials to learn at their own pace.

[0714] Step 5:

[0715] The server continuously tracks the user's learning progress, and the generative AI provides personalized learning support. Supplementary materials and additional practice problems are presented to the user as needed.

[0716] Step 6:

[0717] Once the user completes a learning unit, the server uses a generation AI to generate test questions to measure the user's understanding. These questions are then sent to the user's device.

[0718] Step 7:

[0719] The user's device displays the test questions and prepares the user to enter their answers. Once the user completes the test, they submit their answers to the server.

[0720] Step 8:

[0721] The server automatically evaluates the submitted responses using a generation AI, generating a score and feedback. The results are sent to the user's device, providing the user with information to plan their next learning steps.

[0722] Step 9:

[0723] Based on feedback from the server, users can check their progress and decide on their next course and learning strategy. The server then registers them for a new learning phase and suggests courses.

[0724] (Example 1)

[0725] 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".

[0726] In modern society, people are required to continuously improve their skills without being constrained by time or place. However, traditional learning systems have struggled to propose optimal learning programs tailored to individual learning situations and skill levels, and have also found it difficult to provide appropriate support in real time as learning progresses. This has hindered the efficient realization of skill improvement.

[0727] 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.

[0728] In this invention, the server includes artificial intelligence means for suggesting an optimal educational program based on the user's learning history and work experience, means for remotely providing education using the generated educational content, and means for tracking learning progress and providing personalized learning support to the user. This enables customized learning content and real-time learning support for each individual user.

[0729] A "user" refers to anyone who accesses an online platform, enters their learning history and work experience, and participates in educational programs.

[0730] "Learning history" refers to information about the courses a user has taken and the skills they have acquired in the past.

[0731] "Work history" refers to information about a user's professional experience and career.

[0732] An "educational program" is a set of learning materials suggested based on a user's learning history and work experience, designed to help them acquire specific goals and skills.

[0733] "Artificial intelligence tools" refer to algorithms and models that automatically generate optimal educational programs for users based on given data.

[0734] "Educational content" refers to resources such as learning materials and lecture videos included in an educational program.

[0735] "Remote education" refers to the act of enabling users to learn via the internet, regardless of their physical location.

[0736] "Learning status" refers to real-time information regarding the user's progress and level of understanding.

[0737] "Personalized learning support" refers to providing learning advice and assistance that addresses specific needs based on the user's learning progress.

[0738] "Exam questions" refer to questions generated to evaluate a user's learning achievements.

[0739] "Automatic analysis" refers to the automatic evaluation of user-submitted answers by a generating AI model, followed by the provision of results.

[0740] "Feedback" refers to evaluations and advice generated based on the user's submitted answers and learning progress.

[0741] "Supplementary materials" refer to learning resources provided to support the user's understanding and practice.

[0742] This invention is a system implemented as an online platform for users to efficiently improve their skills remotely. This system operates via a server, terminals, and an internet connection.

[0743] Hardware and software

[0744] The server runs on a high-performance computer and uses artificial intelligence to provide users with optimal educational programs. In particular, a generative AI model is used to generate programs, creating the most suitable content based on data such as the user's learning history and work experience. The terminal is the device used by the user to receive educational content, and includes personal computers, tablets, and smartphones. It displays the content sent from the server through a browser or dedicated application.

[0745] Data processing and calculations

[0746] The server analyzes data acquired from users, and a generative AI model automatically generates educational programs using that data. Machine learning algorithms and natural language processing techniques are used for the analysis. The generated programs are customized according to the user's skill level and learning speed.

[0747] Specific example

[0748] For example, if a user is interested in data science, the server will suggest introductory courses in Python programming and statistics based on their past learning history. Depending on the course the user selects, relevant learning materials and video lectures will be delivered from the server. The user can then view this content on their device and proceed with their learning.

[0749] Example of a prompt

[0750] Examples of prompt statements include the following:

[0751] "User's learning history: Introduction to Python, Basic Statistics / Area of ​​Interest: Data Science / Please suggest the optimal educational curriculum for skill development."

[0752] Through this system, users are provided with an environment where they can efficiently improve their skills regardless of time or location.

[0753] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0754] Step 1:

[0755] Users access an online platform using their devices. Here, users input their learning and work history. This input information serves as foundational data for future educational program proposals. Users enter the necessary information into a dedicated online form and press the submit button to send the data to the server.

[0756] Step 2:

[0757] The server generates an optimal educational program using a generative AI model based on the user's learning and work history. The user data received as input is passed to the generative AI model and analyzed using data analysis and machine learning algorithms. As output, the server generates and presents a list of courses suitable for the user's learning goals.

[0758] Step 3:

[0759] The user reviews a list of educational programs presented by the server and selects the course they wish to take. This selection is performed on the user's device, and the selection information is sent back to the server. This allows for the creation of personalized learning content tailored to the user's learning motivation and goals.

[0760] Step 4:

[0761] The server generates and prepares for distribution relevant educational content (such as textbooks and lecture videos) based on the course selected by the user. The server searches for necessary content from the course database and arranges for efficient distribution to the user's terminal. The output consists of links and data files sent to the user's terminal.

[0762] Step 5:

[0763] The user's device receives educational content delivered from the server and displays it in a format that the user can learn from. The device's application presents the received data to the user in an appropriate format and initiates downloads or streaming as needed. The output is an interactive content display to support the user's learning.

[0764] Step 6:

[0765] The server periodically tracks the user's learning progress and analyzes the progress data using a generative AI model. Based on the user's learning speed and comprehension level, it provides necessary support and supplementary materials. The input is the user's learning log, and the output includes additional practice problems and advice as personalized learning support.

[0766] Step 7:

[0767] When a user completes a course, the server generates exam questions and delivers them to the user's device. The generation AI model automatically generates appropriate and challenging exam questions based on the learned content. The user answers these questions, and the results are sent back to the server.

[0768] Step 8:

[0769] The server receives test answers submitted by the user and automatically evaluates them using a generative AI model. The server analyzes the accuracy rate and learning comprehension level and provides feedback to the user. The output is an evaluation and advice to help the user progress to the next learning step.

[0770] (Application Example 1)

[0771] 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".

[0772] In modern society, there is a lack of appropriate learning environments and materials for workers who aim to advance their careers while continuing their individual jobs. Traditional education systems only provide uniform educational content, and do not adequately offer personalized educational support based on individual learning histories and job information. As a result, users have difficulty efficiently accessing educational programs that suit their interests and skills. In addition, the lack of management of learning progress and appropriate feedback is also a challenge.

[0773] 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.

[0774] In this invention, the server includes an intelligent algorithm that proposes an optimal educational program based on the user's learning history and job information, a device that provides education remotely using the generated educational content, and a device that monitors the progress of learning and provides personalized learning support to the user. This makes it possible to efficiently provide an optimal educational program according to each user's learning history and abilities.

[0775] An "intelligent algorithm" is a computational method that analyzes a user's learning history and job information to automatically suggest the optimal educational program.

[0776] "Educational content" refers to educational resources such as textbooks, lecture videos, and practice problems that are provided based on the user's learning progress.

[0777] A "device for providing education remotely" is a system that uses communication technology to allow users to receive and learn educational content even when they are physically separated from their homes.

[0778] A "device that monitors learning progress and provides personalized learning support" is a system that tracks the user's learning progress and provides optimal support based on the analysis results.

[0779] "Communication terminal equipment" refers to devices that users use to receive and utilize educational content provided remotely, and includes smartphones and computers.

[0780] The system that implements this application starts when the user inputs their learning history and job information using their communication terminal device, and the server receives this information. The server analyzes the user's information using intelligent algorithms and generates an optimal educational program. In this process, a "general cloud platform" is used as a cloud service, and "TensorFlow" and "PyTorch" are used as "AI libraries".

[0781] Educational content generated from the server is delivered to the user's communication terminal device. This educational content takes the form of learning materials and lecture videos, and is available on demand according to the user's preferences. The terminal efficiently displays the received data and provides an interface that enhances user convenience as they progress through their learning.

[0782] To monitor learning progress, the server periodically retrieves learning data from users and analyzes it to personalize learning support. If learning progress is slow, the server delivers additional supplementary materials to support improved understanding. It also automatically generates and provides test questions, and after receiving the user's answers, automatically grades them using an intelligent algorithm.

[0783] For example, if a user expresses interest in "marketing analytics," the server will analyze this and suggest educational programs related to digital marketing and data analysis. Supplementary materials such as additional explanatory videos and practice problems will be provided. During examinations, it is possible to evaluate the user's submitted marketing data analysis scripts in real time and provide feedback on the results.

[0784] An example of a prompt statement for a generative AI model can be shown as follows:

[0785] "Based on the user's past learning data and area of ​​interest, 'Marketing Analytics,' please recommend appropriate learning content. Specifically, prioritize courses related to digital marketing and data analysis, and provide supplementary materials if needed."

[0786] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0787] Step 1:

[0788] Users input their learning history and job information into the system via a communication terminal device. This information is used as input data sent to the server. Users manually enter the necessary information using the screen interface, confirm it, and then press the submit button.

[0789] Step 2:

[0790] The server analyzes the received user learning history and job information using intelligent algorithms. During the analysis, it utilizes generative AI models to process the data and propose educational programs best suited to the user's interests and skills. The output is a list of optimized educational programs for the user.

[0791] Step 3:

[0792] The server selects appropriate educational content for the user based on the generated educational program and distributes it to the communication terminal device. This includes digital content such as educational materials and lecture videos. Data compression and encryption technologies are expected to be used during distribution. The output is the educational content delivered to the user's terminal.

[0793] Step 4:

[0794] The communication terminal visually displays the received educational content to the user. The terminal launches the appropriate application depending on the type of content (video, text, practice exercises, etc.) and plays or displays the data. The user can control the learning progress through the screen.

[0795] Step 5:

[0796] As a user progresses through their learning, their progress data is sent back to the server. The server analyzes this data to optimize learning support. For example, it might suggest supplementary materials to users who are falling behind. The input is progress data, and the output is the suggested support content.

[0797] Step 6:

[0798] The server generates test questions and sends them to the user's communication terminal. In this process, a generation AI model is used to dynamically generate questions, providing different questions for each user. The input is the user's learning history and progress, and the output is the test questions.

[0799] Step 7:

[0800] The user solves the problem on their device and sends their answer to the server. The server automatically scores the received answer using an intelligent algorithm and sends the result as feedback to the user. The server determines the correctness of the answer through data calculation and calculates a score. The output is the scoring result.

[0801] 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.

[0802] This invention enhances the learning experience by incorporating an emotion engine into an online education system that allows users to efficiently improve their skills in a remote environment. The system is configured as a complex system including a server, user terminals, and the emotion engine.

[0803] The server collects learning history and career information provided by the user and uses artificial intelligence to propose an optimal, personalized educational curriculum. It also remotely delivers the generated educational resources to the user's terminal, enabling continuous learning. The terminal appropriately displays the delivered materials, providing the user with a learning environment they can access at their own pace.

[0804] The server constantly tracks the user's learning progress, and the generating AI provides personalized learning support tailored to the user. This includes providing learning materials according to the user's progress and suggesting supplementary materials based on their level of understanding. At key learning milestones, test questions are generated and delivered via the user's device. The device sends the user's answers back to the server, which uses AI to score and evaluate the answers, providing feedback.

[0805] Furthermore, the server utilizes an emotion engine to recognize the user's emotional state in real time. The emotion engine can determine stress levels, concentration levels, and satisfaction levels through facial expression and voice analysis. Based on this emotional recognition, the learning support content is dynamically adjusted. Specifically, if the user shows signs of fatigue, the system automatically takes measures such as recommending a break or providing simple review materials.

[0806] For example, when a user is working on an advanced data science course, the server monitors the user's progress and emotional state, and adjusts the intensity of the practice exercises to improve learning efficiency. If the server detects that the user is becoming impatient, it simplifies the interface and provides hints to deepen the user's understanding.

[0807] As described above, the present invention provides a system that enables working adults to efficiently improve their skills without interrupting their careers, and furthermore, by utilizing an emotional engine, to realize a high-quality learning experience.

[0808] The following describes the processing flow.

[0809] Step 1:

[0810] The user accesses the learning portal and enters the required registration information. The server receives this information and creates a user account in the database.

[0811] Step 2:

[0812] The server analyzes the user's input learning history and career information, and uses artificial intelligence to generate an optimal curriculum. A list of the generated curriculum is then displayed on the user's device.

[0813] Step 3:

[0814] The user selects their desired course from the displayed curriculum. After selection, the server generates the corresponding educational resources and delivers them remotely to the user's terminal.

[0815] Step 4:

[0816] The device visually displays the received educational resources to the user, providing access to lecture videos and learning materials. The user then begins learning accordingly.

[0817] Step 5:

[0818] During learning, the server constantly monitors the user's progress and applies personalized learning support generated by AI. This includes highlighting learned content and suggesting new practice problems.

[0819] Step 6:

[0820] The server activates the emotion engine and recognizes the user's emotional state. It analyzes the user's facial expressions and voice data to evaluate their concentration level and stress level.

[0821] Step 7:

[0822] Based on the emotion engine's evaluation, the server adjusts the learning pace and difficulty to improve the user's experience. If the server determines that the user is fatigued, it sends a notification to the device recommending a short break.

[0823] Step 8:

[0824] When a user completes a learning unit, the server generates test questions and sends them to the user's device. The user takes the test and sends their answers back to the server via their device.

[0825] Step 9:

[0826] The server uses AI to automatically evaluate responses, scores them, and generates feedback. It presents the results to the user in real time and clearly indicates the next learning task.

[0827] Step 10:

[0828] Based on the feedback, users revise their learning plans and decide which courses and content to move on to next. The server supports this process and provides guidance for the new learning phase.

[0829] (Example 2)

[0830] 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".

[0831] In today's educational environment, enabling users to learn sustainably and effectively in a remote setting remains a significant challenge. In particular, uniform educational programs often fail to adequately consider individual users' learning progress and emotional states, potentially leading to decreased learning efficiency. Furthermore, there is a lack of mechanisms to prevent users from being forced to interrupt their learning due to their emotional state. Under these circumstances, it is necessary to provide educational services optimized for individual users and to offer learning support that responds to their emotional state.

[0832] 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.

[0833] In this invention, the server includes intelligent processing means for presenting an optimal educational curriculum based on the user's learning history and occupational information, means for remotely conducting education using the generated educational resources, means for monitoring learning progress and providing personalized learning support to the user, and emotion recognition means for analyzing the user's emotional state in real time and adjusting the content of learning support. This enables the provision of a learning experience optimized for each individual user and dynamic learning support based on emotional state.

[0834] A "user" is an individual who uses an educational system to learn or improve their skills.

[0835] "Learning history" refers to data that records the courses a user has taken, the content they have learned, and their progress.

[0836] "Occupational information" refers to information about a user's career, including data that shows their work experience and skill set.

[0837] An "educational curriculum" refers to a learning program optimized based on the user's needs and skill level.

[0838] "Intelligent processing means" refers to the process of analyzing data using artificial intelligence and proposing the most suitable educational curriculum to the user.

[0839] "Providing education remotely" means offering educational resources to users in physically distant locations via the internet.

[0840] "Monitoring learning progress" refers to the activity of tracking how much a user has learned and recording their learning history.

[0841] "Personalized learning support" refers to the provision of support and learning materials tailored to each user.

[0842] "Emotion recognition means" refers to technology that analyzes a user's emotional state from their facial expressions, voice, etc., and responds accordingly.

[0843] "Educational resources" refer to content such as textbooks, videos, and materials that users utilize during their learning process.

[0844] "Adjusting the content of learning support" means optimizing the educational content provided and offering appropriate support according to the user's emotional state.

[0845] This invention is an online education system that enables users to efficiently improve their skills in a remote environment. It combines a server, terminal, and emotion engine to provide an education service optimized for the user.

[0846] The server receives and collects the user's learning history and occupational information. Based on this data, it uses a generative AI model to generate an optimal learning curriculum for the user. Intelligent processing is used to generate the curriculum. For example, if a user wants to improve their data science skills, relevant courses and materials will be recommended.

[0847] The generated educational resources are delivered to the user's device via the internet. The device displays these materials appropriately, providing a learning environment that the user can access at their own convenience. The delivered materials include video lectures and interactive exercises.

[0848] The server constantly monitors the user's progress during learning. This allows it to track how far the user has progressed and record it as a history. Based on this information, the generating AI provides individually optimized learning support. If the user is stuck on a particular topic, it can provide additional explanatory videos or supplementary materials.

[0849] Furthermore, the server uses an emotion engine to analyze the user's emotional state in real time. By performing facial expression and voice analysis, it can understand the user's stress levels and concentration, and adjust the learning support content accordingly. For example, if the user shows signs of fatigue, the system will automatically suggest a break.

[0850] A concrete example of a prompt is, "Consider the user's current progress and emotional state, and generate a learning plan for the next week." Based on such prompts, the AI ​​model presents the most suitable approach to the user.

[0851] This system allows users to learn flexibly and efficiently without interrupting their careers, and to improve their learning experience with personalized support.

[0852] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0853] Step 1:

[0854] The server receives the user's learning history and occupational information as input. Based on this information, it performs analysis using intelligent processing tools. Specifically, it analyzes the user's past learning data and skill set and proposes an educational curriculum that suits the user's needs. The output of this step is the optimal educational curriculum based on each user's needs.

[0855] Step 2:

[0856] The server uses a generative AI model to construct learning materials based on the curriculum obtained in Step 1. The curriculum identified in the previous step is used as input. Specific data calculations include selecting course content and optimizing learning resource resources. The output of this step is user-optimized learning resources (textbooks, video lectures, practice problems, etc.).

[0857] Step 3:

[0858] The server distributes the obtained educational resources to the user's terminal via the internet. The terminal receives the distributed educational resources and organizes them so that the user can use them. Specifically, this involves downloading the learning materials and displaying them on the interface. The input is the educational resources generated in step 2, and the output is the state in which they have been prepared for the user to use for learning.

[0859] Step 4:

[0860] Users progress through their learning using learning materials provided via their devices. The server tracks the user's learning progress in real time. Learning progress information is used as input, and the server records this information in a database as learning history. The output is updated learning progress information.

[0861] Step 5:

[0862] The server uses a generative AI model to provide personalized learning support based on the user's progress information. The input is learning progress data, which is used to analyze areas where the user is lacking and areas that need further improvement. The output is additional learning materials and explanatory information provided to the user.

[0863] Step 6:

[0864] The server utilizes an emotion engine to analyze the user's emotional state. Using sensors and cameras, it receives user facial expressions and voice information as input and evaluates emotions in real time. The output is data indicating the user's current emotional state, and learning support is adjusted based on this data.

[0865] Step 7:

[0866] The device dynamically adjusts the user interface based on emotional data received from the server. If the user is stressed, it switches to a more intuitive and simpler interface or displays an alert prompting them to take a break. The input is emotional state data from the server, and the output is the adjusted interface and support functions.

[0867] (Application Example 2)

[0868] 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".

[0869] Modern learners demand flexibility and individualization in their learning, and also need support to overcome emotional stress and decreased motivation. Traditional online education systems have lacked the means to address the individual emotional states of learners, making it difficult to maximize learning effectiveness. Furthermore, while there is a demand for continuous, real-time learning support, these systems lacked the flexibility to adapt to diverse learning environments.

[0870] 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.

[0871] In this invention, the server includes information processing means for proposing an appropriate educational curriculum based on the user's learning history and work history information; means for providing education remotely using the generated educational resources; means for tracking learning progress and providing personalized learning support to the user; means for generating test questions and automatically evaluating the user's answers; and emotion analysis means for recognizing the user's emotional state in real time and dynamically adjusting the educational support content. This makes it possible to maximize the learning effectiveness of learners while providing learning support tailored to their individual emotional states in real time.

[0872] A "user" is an individual or legal entity that uses the system to learn.

[0873] "Learning history" refers to a record of the educational resources a user has used to date and the results of those efforts.

[0874] "Work history information" refers to data related to the user's professional experience and career.

[0875] "Information processing means" refers to methods and devices for collecting, analyzing, and processing information.

[0876] "Educational resources" refer to teaching materials and tools provided to support learning activities.

[0877] "Means of providing education remotely" refer to methods and technologies for transmitting learning content regardless of physical distance.

[0878] "Learning progress" refers to the user's level of achievement in the process of completing the learning curriculum.

[0879] "Personalized learning support" means providing learning support tailored to each individual user.

[0880] "Exam questions" are questions designed to evaluate learning and measure understanding.

[0881] "Methods for automated evaluation" refer to methods or devices that have the function of independently analyzing user responses and providing scores or feedback.

[0882] "Emotional state" is a concept that represents a user's psychological feelings and mood.

[0883] "Emotional analysis tools" refer to methods and technologies for recognizing and interpreting a user's emotional state.

[0884] "Dynamically adjusting educational support content" means instantly changing educational methods and materials according to the user's status and progress.

[0885] This invention is a composite system that incorporates an emotion engine into an online education system to enable users to efficiently improve their skills. This system includes a server, a user's mobile device (e.g., smart glasses), and the emotion engine.

[0886] The server uses information processing tools to formulate the optimal learning process based on the input learning history and work history information. This process employs data analysis and machine learning techniques, specifically utilizing AI modules such as TensorFlow and AWS Lambda. The server also delivers the generated educational resources to the user's device via cloud storage such as Amazon S3.

[0887] The user terminal is equipped with a display for showing educational resources and a camera and microphone for detecting emotional states. The emotion engine uses the Google Cloud Vision API and Google Cloud Speech-to-Text to analyze the user's facial expressions and voice in real time, determining emotional states such as concentration levels and stress. Based on this analysis, educational support content is dynamically adjusted. Specifically, generated materials are modified based on the emotional state, and breaks are recommended.

[0888] For example, suppose a user is using smart glasses on a train to study a data science course. The server tracks the user's progress and uses a generative AI model to formulate the optimal answer to the prompt "What learning method is best when the user is not concentrating?" and displays it on the glasses, providing a personalized learning experience. An example of a prompt might be, "What type of content should be recommended when the user is tired?"

[0889] In this way, the present invention provides a system that realizes a flexible and personalized learning experience that takes into account the user's emotional state.

[0890] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0891] Step 1:

[0892] The server receives the user's learning history and work history information. Based on this input data, it uses AI-powered information processing tools to analyze the data and generate an optimal educational curriculum. As output, personalized educational curriculum data is obtained. A machine learning model using TensorFlow is utilized in this analysis process.

[0893] Step 2:

[0894] The server delivers the generated curriculum to the user's device via cloud storage (e.g., Amazon S3). The delivered data is received on the user's device and becomes available as an educational resource. The output is an educational resource file stored on the user's device's storage.

[0895] Step 3:

[0896] The user terminal uses a display device (e.g., smart glasses display) to present the received educational curriculum to the user. Learning activities are conducted through user input. Users can access and interact with the learning materials through intuitive operation.

[0897] Step 4:

[0898] The user device uses an emotion engine to acquire user facial expressions and voice data from the camera and microphone. This input data is analyzed using the Google Cloud Vision API and Google Cloud Speech-to-Text to evaluate the user's emotional state in real time. The output is metadata indicating the emotional state.

[0899] Step 5:

[0900] The server receives metadata about the user's emotional state and, along with learning progress data, generates the next learning support content using a prompt message powered by a generative AI model: "If the user is not focused, which learning method is best?". The output is the next educational support content provided, which includes dynamically adjusted learning materials.

[0901] Step 6:

[0902] The user terminal displays the adjusted educational support content received from the server to the user again, improving learning effectiveness. This process continuously supports the user's learning cycle. The output is a new, customized learning experience that reflects the user's next learning action.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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."

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] The following is further disclosed regarding the embodiments described above.

[0925] (Claim 1)

[0926] An artificial intelligence method that proposes the optimal educational curriculum based on the user's learning history and career information,

[0927] Means of providing education remotely using generated educational resources,

[0928] A means of tracking learning progress and providing personalized learning support to users,

[0929] A means of generating test questions and automatically evaluating user responses,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, which optimizes user learning using generated learning feedback.

[0933] (Claim 3)

[0934] The system according to claim 1, further comprising means for suggesting the next educational phase based on the learning results.

[0935] "Example 1"

[0936] (Claim 1)

[0937] An artificial intelligence method that proposes the optimal educational program based on the user's learning history and work experience,

[0938] A means of conducting remote education using generated educational content,

[0939] A means of tracking learning progress and providing personalized learning support to users,

[0940] A means for generating test questions and automatically analyzing user answers,

[0941] A means of providing supplementary materials and practice exercises adaptively in real time based on the user's progress,

[0942] A means of generating and providing learning feedback to the user,

[0943] A system that includes this.

[0944] (Claim 2)

[0945] The system according to claim 1, which enhances user learning based on the generated feedback.

[0946] (Claim 3)

[0947] The system according to claim 1, further comprising means for recommending the next educational stage based on learning results.

[0948] "Application Example 1"

[0949] (Claim 1)

[0950] An intelligent algorithm that proposes the optimal educational program based on the user's learning history and job information,

[0951] A device that provides remote education using generated educational content,

[0952] A device that monitors learning progress and provides personalized learning support to the user,

[0953] A device that generates test questions and automatically evaluates user responses,

[0954] A device that delivers user-optimized educational content to communication terminal devices using intelligent algorithms,

[0955] A system that includes this.

[0956] (Claim 2)

[0957] The system according to claim 1, which optimizes user learning using generated learning feedback.

[0958] (Claim 3)

[0959] The system according to claim 1, further comprising a device that suggests the next educational stage based on the learning results.

[0960] "Example 2 of combining an emotion engine"

[0961] (Claim 1)

[0962] An intelligent processing means that presents an optimal educational curriculum based on the user's learning history and occupational information,

[0963] Means for conducting remote education using generated educational resources,

[0964] A means of monitoring learning progress and providing personalized learning support to users,

[0965] A means for generating test questions and automatically analyzing user answers,

[0966] An emotion recognition means that analyzes the user's emotional state in real time and adjusts the content of learning support accordingly,

[0967] A system that includes this.

[0968] (Claim 2)

[0969] The system according to claim 1, which optimizes user learning based on generated learning feedback and emotional states.

[0970] (Claim 3)

[0971] The system according to claim 1, further comprising means for suggesting the next educational stage based on learning results and emotion analysis results.

[0972] "Application example 2 when combining with an emotional engine"

[0973] (Claim 1)

[0974] An information processing means that proposes an appropriate educational curriculum based on the user's learning history and work history information,

[0975] Means of providing remote education using generated educational resources,

[0976] A means of tracking learning progress and providing personalized learning support to users,

[0977] A means of generating test questions and automatically evaluating user responses,

[0978] A sentiment analysis method that recognizes the user's emotional state in real time and dynamically adjusts educational support content,

[0979] A system that includes this.

[0980] (Claim 2)

[0981] The system according to claim 1, which optimizes user learning using generated learning feedback and emotional state data.

[0982] (Claim 3)

[0983] The system according to claim 1, further comprising means for suggesting the next educational stage based on learning results and emotional state. [Explanation of symbols]

[0984] 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. An artificial intelligence method that proposes the optimal educational curriculum based on the user's learning history and career information, Means of providing education remotely using generated educational resources, A means of tracking learning progress and providing personalized learning support to users, A means of generating test questions and automatically evaluating user responses, A system that includes this.

2. The system according to claim 1, which optimizes user learning using generated learning feedback.

3. The system according to claim 1, further comprising means for suggesting the next educational phase based on the learning results.

Images