System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating personalized educational content based on input information of a user using generative artificial intelligence; means for providing the generated educational content to a terminal of the user; and means for collecting and storing feedback of the user on the educational content displayed on the terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Traditional, one-size-fits-all educational models have been unable to fully address the diverse learning needs and learning styles of each learner, resulting in a decline in motivation and inconsistent learning outcomes. Furthermore, limited means of appropriately collecting and utilizing learner feedback during the learning process make it difficult to provide a personalized educational experience. This makes it difficult to effectively support the growth of each individual learner. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means: A system including means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to a user's terminal, and means for collecting and saving user feedback on the educational content displayed on the terminal. Furthermore, by further including means for providing an interface through which the user can input information about learning goals and learning styles, and means for reflecting the feedback information in the generation of the next educational content, the system provides an educational experience optimized for each individual learner.

[0006] "Generative AI" is AI that has the ability to generate new data and information based on training data.

[0007] "User" refers to a learner or educator who uses the system.

[0008] "Input information" refers to the user providing various information to the system, including learning goals, learning style, etc.

[0009] "Personalized educational content" refers to learning materials and learning materials that are individually optimized based on user input.

[0010] "Terminal" refers to a device (e.g., PC, tablet, smartphone) through which a user accesses the system and uses educational content.

[0011] "Feedback" refers to the user providing the system with their opinions and evaluations of the learning content.

[0012] "Interface" refers to a software or hardware element that acts as a window through which a user and a system communicate with each other.

[0013] "Reflection" refers to the process of generating and improving the next educational content based on the collected feedback.

[0014] "Learning objectives" refer to the specific learning goals and outcomes that a user is trying to achieve.

[0015] "Learning style" refers to the method or approach (e.g., visual, auditory, movement) in which a user learns most effectively. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system for providing users with personalized educational content using generative artificial intelligence. This system is implemented as follows, with a server, a terminal, and a user each playing a specific role.

[0038] The system's program begins when a user inputs information about their learning goals and learning style through their device. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the device and provided to the user. The user studies the content and then provides feedback. This feedback is sent back to the server and reflected in the next generation of educational content. This series of steps makes it possible to provide the user with an optimized educational experience.

[0039] Example 1: High school math class

[0040] User Actions

[0041] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "Mathematics" and enters "Solution of Quadratic Equations" as the specific learning goal. The user also selects "Visual Learning" as the preferred learning style.

[0042] Server Operation

[0043] The server receives user input and uses generative artificial intelligence to generate customized educational content on solving quadratic equations, including visual instructional videos and interactive exercises.

[0044] Device behavior

[0045] The terminal receives the educational content sent from the server and displays it to the user, who then watches the content and solves the exercises.

[0046] User behavior (feedback)

[0047] After completing the study, the user inputs feedback on their satisfaction and understanding, which is then sent from the device to the server.

[0048] Server operation (reflecting feedback)

[0049] The server analyzes the user's feedback and reflects it in the next content generation. For example, if the user feels that the explanation is difficult, the generative AI will adjust the next content to provide a more concise and easy-to-understand explanation.

[0050] Example 2: Corporate training programs

[0051] User Actions

[0052] The user (a company's training officer) logs in to the platform using a terminal. After logging in, he / she enters "project management" and "agile methods" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[0053] Server Operation

[0054] The server takes user input and uses generative artificial intelligence to generate customized training materials on agile methods, including hands-on workshops and simulation training.

[0055] Device behavior

[0056] The terminal receives the training materials sent from the server and provides them to the user, who then uses the training materials to provide training to new employees.

[0057] User behavior (feedback)

[0058] After the training is completed, the trainer collects feedback from the new employees and sends it to the server from their devices, including the usefulness of the training and areas for improvement.

[0059] Server operation (reflecting feedback)

[0060] The server analyzes the collected feedback and reflects it in the generation of the next training materials. For example, if a new employee feels that "more practical examples are needed," the generative AI will adjust the next training materials to include more practical examples.

[0061] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user logs in to the platform through the terminal. The user enters the user ID and password for authentication. If the login is successful, the user profile is loaded.

[0065] Step 2:

[0066] The user inputs initial information about their learning goals and learning style into the terminal, including the subject, topic, learning goals, and preferred learning style (visual, auditory, movement, etc.). Once the information is input, the terminal sends it to the server.

[0067] Step 3:

[0068] The server stores the received user information in a database, which creates a personalized learning profile for each user.

[0069] Step 4:

[0070] Users select the specific topic they want to learn about on their device and enter details about it, after which the device sends this information to the server.

[0071] Step 5:

[0072] Based on the received topic information, the server sends a request to the generative AI, which then generates educational content customized to the user's learning goals and learning style.

[0073] Step 6:

[0074] The generative AI returns the generated customized educational content to the server, which receives the content and sends it to the user's device.

[0075] Step 7:

[0076] The device displays educational content received from the server. Users use this content to learn. Examples of content include visual instructional videos, interactive exercises, and simulations.

[0077] Step 8:

[0078] After the user has completed the learning, they can input feedback via the device, including their satisfaction with the learning content, their level of understanding, and areas for improvement.

[0079] Step 9:

[0080] The device sends the user's feedback to the server, which stores the received feedback in a database and reflects it in the generation of the next learning content.

[0081] Step 10:

[0082] The server analyzes the feedback and uses it as data to generate new learning content. The generative AI also uses this feedback to optimize the next content generation process.

[0083] This sequence of steps provides an optimized learning experience for the user.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] Conventional educational content delivery systems have struggled to effectively provide content tailored to individual users' learning goals and learning styles. Furthermore, mechanisms for incorporating feedback into subsequent content generation are inadequate, making it impossible to maximize users' learning effectiveness and satisfaction. Furthermore, systems that effectively utilize generative artificial intelligence to generate personalized educational content require the generation and effective use of prompt sentences. The present invention aims to solve these problems and provide users with educational content optimized for their needs.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes means for generating personalized educational content based on user input information using a generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and saving user feedback on the educational content displayed on the terminal, means for analyzing the feedback and reflecting it in the generation of the next educational content, and means for generating prompt sentences based on the user input information and inputting them into the generative artificial intelligence. This makes it possible to provide highly personalized educational content tailored to the needs of each individual user, thereby improving learning effectiveness and satisfaction.

[0089] "Generative AI" is an AI technology that can generate adaptive and personalized responses and content based on user input.

[0090] "Educational content" means teaching materials, resources, questions, and other learning aids designed to help learners acquire specific knowledge or skills.

[0091] A "terminal" is an electronic device that allows a user to access the system, input learning objectives, display educational content, and provide feedback.

[0092] "Feedback" is information that users provide to the system, such as their opinions on educational content, their level of satisfaction, their level of understanding, and areas for improvement.

[0093] A "prompt sentence" is a sentence that instructs a generative artificial intelligence to produce a specific output, and is generated based on information input by the user.

[0094] "Learning objectives" are specific educational goals or themes that a user wants to achieve.

[0095] "Learning style" refers to the type of teaching method or learning method that a user prefers, including visual learning, hands-on learning, etc.

[0096] "Personalization" means optimizing educational content and services to suit the specific needs and preferences of individual users.

[0097] "Analysis" is the act of digging deep into collected feedback and other data to extract insights.

[0098] This invention is a system that uses generative artificial intelligence to provide users with personalized educational content. In this system, the server, terminal, and user each play specific roles, and the specific process for implementing the invention is as follows:

[0099] First, a user accesses the platform using a terminal and inputs information about their learning goals and learning style. For example, if a user wants to learn how to solve quadratic equations in mathematics, they can input "how to solve quadratic equations" as their learning goal and select "visual learning" as their preferred learning style.

[0100] The device then sends the user's input information to a server, which uses generative artificial intelligence (such as OpenAI's GPT-3) to create a prompt to generate educational content optimized for the user's learning goals and style. An example prompt might be, "Generate educational content that includes visual explanation videos and interactive practice problems on how to solve quadratic equations in mathematics."

[0101] The server inputs the generated prompt sentences into a generative artificial intelligence (AI) to generate educational content customized for the user. This educational content includes visual instruction videos, interactive exercises, etc. The generated educational content is sent from the server to the device, which displays it to the user. The user then views the educational content on the device and works on the exercises.

[0102] After completing the learning process, the user inputs feedback on the educational content into the server from their device. The feedback includes satisfaction, level of understanding, and areas for improvement, and specific comments such as "I found the explanation in this part difficult to understand" can be entered.

[0103] The server receives the feedback sent from the device and analyzes it. Based on the analysis results, it reflects the results in the next educational content generation. Through this process, the generative AI generates prompts that reflect the feedback, and the next time, more personalized content is provided.

[0104] To give a specific example, when a high school student is learning "how to solve quadratic equations" in a mathematics class, the process proceeds as follows: The user (high school student) uses a device to select the "Mathematics" subject, enters "how to solve quadratic equations" as the learning goal, and selects "visual learning" as the preferred learning style. The user's input information is sent to the server, which then sends a prompt to the generative AI such as "Please generate visual educational content on how to solve quadratic equations." The educational content generated by the generative AI is sent to the device, and the user studies it. After completing the study, the feedback entered by the user is reflected in the next content generation.

[0105] This series of steps allows users to receive an optimized educational experience, increasing learning effectiveness and satisfaction.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Step 1:

[0108] The user accesses the platform using a terminal and logs in.

[0109] The user enters their user ID and password on the device's input screen and sends the authentication information to the server. The server receives the authentication information, performs user authentication, and returns the authentication result to the device. If user authentication is successful, the user can proceed to the next step.

[0110] Step 2:

[0111] The user enters information about their learning goals and learning style.

[0112] Through the device's interface, users input the content they want to learn (e.g., "How to solve quadratic equations") as their learning goal. They also select their preferred learning style, such as visual learning or hands-on learning. The input information is sent from the device to the server, which then sends it to the server as JSON-formatted data, where it is stored in a database.

[0113] Step 3:

[0114] The server analyzes the user's input and generates a prompt.

[0115] The server analyzes the received JSON-formatted user information and creates a prompt to generate educational content. For example, it generates a prompt such as, "Please generate educational content that includes a visual explanation video and interactive practice problems on how to solve quadratic equations in mathematics." This prompt is then input into the generative artificial intelligence.

[0116] Step 4:

[0117] The server generates educational content using generative artificial intelligence.

[0118] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to generate educational content. Based on the prompt, the generative AI generates educational content, including visual instructional videos and interactive exercises, and returns the results to the server.

[0119] Step 5:

[0120] The server transmits the generated educational content to the terminal.

[0121] The server transmits the educational content received from the generative AI to the user's device. This content includes learning materials and exercises according to the learning objectives. The device receives this content and displays it to the user.

[0122] Step 6:

[0123] The user studies the educational content and provides feedback.

[0124] Users view and study the educational content provided on their devices. After completing the study, they enter feedback such as satisfaction, level of understanding, and specific areas for improvement into the device's interface. This feedback information is then sent back to the server in JSON format.

[0125] Step 7:

[0126] The server receives and analyzes the feedback.

[0127] The server receives the feedback information sent from the device and stores it in a database. The saved feedback information is analyzed and insights are extracted to be reflected in the next generation of educational content. For example, an action item such as "We need to generate content that includes more specific and simple explanations" can be obtained.

[0128] Step 8:

[0129] The server regenerates the prompt text reflecting the feedback and generates the next educational content.

[0130] The server generates a new prompt based on the feedback analysis results. For example, it might generate a prompt such as, "Please generate educational content on how to solve quadratic equations with more specific and simpler explanations." This prompt is then fed back into the generative AI to generate improved educational content, further improving the user's next learning experience.

[0131] The above is the specific processing flow of this system.

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Conventional educational systems have had difficulty providing appropriate educational content tailored to individual users' learning needs and levels of understanding. Furthermore, fixed educational content may reduce learning effectiveness because it cannot fully address the specific problems and levels of understanding that users have. Furthermore, there are insufficient means to effectively reflect feedback in the generation of the next educational content, making it impossible to maximize the effectiveness of individualized instruction.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's information processing device, means for collecting and storing user feedback on the educational content displayed on the information processing device, and means for adjusting the next generation of the educational content based on the feedback, thereby providing the user with educational content optimized for the user, thereby improving learning outcomes and increasing user satisfaction.

[0137] "Generative AI" is an advanced AI that uses machine learning and natural language processing technology to generate optimal educational content based on input information provided by users.

[0138] "Personalized educational content" refers to educational materials and learning materials that are customized according to a user's learning goals and learning style.

[0139] "User input information" refers to data about learning goals and learning styles that users provide to the system, and optimized educational content is generated based on this data.

[0140] "Information processing device" refers to a device used by a user, such as a smartphone, smart glasses, or head-mounted display, which can display and operate the generated educational content.

[0141] "Feedback" refers to evaluation information such as satisfaction, level of understanding, and comments provided by users after using educational content, and is reflected in the next content generation.

[0142] A "prompt" refers to text input that provides specific instructions or requests to a generative artificial intelligence to generate the desired educational content.

[0143] "Adjusting the next generation of educational content" refers to the process of optimizing the next generation of educational content based on previous feedback information to provide a better learning experience.

[0144] The present invention is a system for providing users with personalized educational content using generative artificial intelligence, in which a server, a terminal, and a user each play specific roles.

[0145] First, a user logs in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display, and enters information about their learning goals and learning style. For example, a high school student can select "solving quadratic equations" and "visual learning."

[0146] The server receives the information entered by the user and uses a generative AI model to automatically generate personalized educational content. Specific prompts are used in this process. An example of a prompt is as follows:

[0147] User Information:

[0148] Learning Objective: Solving quadratic equations

[0149] Learning Style: Visual Learning

[0150] Use this information to create visual instructional content. Your educational content should include:

[0151] 1. Basic Concepts of Quadratic Equations

[0152] 2. Step-by-step explanation of the solution (visually presented)

[0153] 3. Interactive Exercises

[0154] The generated educational content is sent from the server to the user's terminal, where it is displayed. The user studies the educational content and solves the exercises according to the displayed content.

[0155] After completing the learning, the user inputs feedback regarding their satisfaction and level of understanding. This feedback data is sent back to the server. The server analyzes the collected feedback and reflects it in the creation of the next educational content. This feedback includes an evaluation of how much the user understood the learning content and how easy the explanation was to understand. Another example of feedback could be a comment such as "The explanation was a little difficult."

[0156] This allows the system to provide an optimized educational experience for each user and improve learning outcomes. The software explicitly used includes generative AI models (e.g., OpenAI's GPT-3).

[0157] To maximize the effectiveness of this system, it is important to effectively analyze the feedback data collected from users and optimize the process of adjusting learning content using generative AI. This process will enable the provision of continuously improved educational content to users.

[0158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0159] Step 1:

[0160] Users log in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display and input information about their learning goals and learning style. This input information includes the learning goal of "solving quadratic equations" and the learning style of "visual learning."

[0161] Input: learning goals, learning styles

[0162] Output: Learning goals and learning style data

[0163] Step 2:

[0164] The terminal transmits the learning goal and learning style data input by the user to the server.

[0165] Input: Learning objectives, learning style data

[0166] Output: Learning objectives and learning style data sent to the server

[0167] Step 3:

[0168] The server receives the user's input information and uses the generative AI model to generate personalized educational content. The server generates a specific prompt sentence and passes it to the generative AI model to obtain the educational content.

[0169] Specific examples of prompts are as follows:

[0170] User Information:

[0171] Learning Objective: Solving quadratic equations

[0172] Learning Style: Visual Learning

[0173] Use this information to create visual instructional content. Your educational content should include:

[0174] 1. Basic Concepts of Quadratic Equations

[0175] 2. Step-by-step explanation of the solution (visually presented)

[0176] 3. Interactive Exercises

[0177] Input: Learning objectives and learning style data

[0178] Output: Personalized educational content

[0179] Step 4:

[0180] The server transmits the generated educational content to the user's terminal.

[0181] Input: personalized educational content

[0182] Output: Delivery of educational content to user devices

[0183] Step 5:

[0184] The terminal displays the received educational content to the user, who then studies the displayed educational content and solves the set exercises.

[0185] Input: Educational content

[0186] Output: Educational content displayed to the user

[0187] Step 6:

[0188] After completing the learning process, users can enter feedback on their device regarding their satisfaction and understanding. Feedback includes user-provided ratings and comments (e.g., "The explanation was a little difficult").

[0189] Input: User feedback

[0190] Output: Feedback data

[0191] Step 7:

[0192] The terminal transmits the feedback data to the server.

[0193] Input: Feedback data

[0194] Output: Feedback data sent to the server

[0195] Step 8:

[0196] The server analyzes the collected feedback and reflects it in the next generation of educational content. This analysis allows for content refinement based on the user's level of understanding and satisfaction.

[0197] Input: Feedback data

[0198] Output: Analysis results for improved educational content generation

[0199] By repeating this process, it is possible to provide users with continuously improved educational content, which helps them learn more effectively and improve their learning outcomes.

[0200] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0201] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content, and further combines an emotion engine to recognize users' emotions and optimize the learning experience. This system is implemented as follows, with the server, terminal, and user each playing a specific role.

[0202] The system's program begins when a user inputs information about their learning goals and learning style through a terminal. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the terminal and provided to the user.

[0203] The role of the emotional engine

[0204] The system incorporates an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotional state by analyzing the user's facial expressions, voice, and operating behavior. The emotional state recognized by the emotion engine is fed back to the generative AI and reflected in the generation of the next educational content and the dynamic adjustment of the current content.

[0205] Program flow and examples

[0206] Example 1: High school English class

[0207] User Actions

[0208] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[0209] Server Operation

[0210] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[0211] Emotion Engine Operation

[0212] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[0213] Device behavior

[0214] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[0215] User behavior (feedback)

[0216] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[0217] Server operation (reflecting feedback)

[0218] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[0219] Example 2: Corporate training programs

[0220] User Actions

[0221] The user (a company's training officer) logs in to the platform using a terminal. After logging in, they input "communication skills" and "team building" as learning objectives to create a training program for new employees. The user then selects "hands-on learning" as the learning style for new employees.

[0222] Server Operation

[0223] The server takes user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[0224] Emotion Engine Operation

[0225] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[0226] Device behavior

[0227] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[0228] User behavior (feedback)

[0229] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[0230] Server operation (reflecting feedback)

[0231] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[0232] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction. Furthermore, by incorporating an emotion engine, dynamic content optimization based on the user's emotional state is possible, providing a richer and more effective learning experience.

[0233] The processing flow will be explained below.

[0234] Example 1: High school English class

[0235] Program processing flow

[0236] Step 1:

[0237] The user logs in to the platform through the terminal, enters the user ID and password for authentication, and if the authentication is successful, the user profile is loaded.

[0238] Step 2:

[0239] The user inputs initial information about their learning goals and learning style into the terminal, such as "English," "improving listening skills," "auditory learning," etc. Once this information is entered, the terminal transmits it to the server.

[0240] Step 3:

[0241] The server stores the received information in a database, which creates a personalized learning profile for each user.

[0242] Step 4:

[0243] The user selects the specific topic they want to study on their device and enters the details, for example, "listening practice," after which the device sends this information to the server.

[0244] Step 5:

[0245] Based on the received topic information, the server sends a request to the generative AI, which then generates customized educational content tailored to the user's learning goals and style.

[0246] Step 6:

[0247] The generative AI sends the generated educational content back to the server, which receives the content and sends it to the user's device.

[0248] Step 7:

[0249] The device receives educational content from the server and displays it to the user, such as audio clips for listening practice or interactive quizzes.

[0250] Step 8:

[0251] The emotion engine monitors the user's reactions, analyzing the user's facial expressions and voice in real time and sending emotional data to the server. For example, it detects distracted facial expressions and tone of voice.

[0252] Step 9:

[0253] The server receives data from the emotion engine and adjusts the content in real time, for example, lowering the difficulty of the content or adding interactive elements if it determines that the user is not concentrating.

[0254] Step 10:

[0255] After completing the learning process, the user enters their satisfaction and understanding in a feedback form. The device then sends this feedback to the server, along with the data collected by the emotion engine.

[0256] Step 11:

[0257] The server analyzes the feedback and emotion data and reflects it in the next generation of educational content. For example, if the user feels that the practice questions are difficult, the generative AI will adjust to provide easier questions for the next content.

[0258] Example 2: Corporate training programs

[0259] Program processing flow

[0260] Step 1:

[0261] The user (a company's training manager) logs into the platform through a terminal. After logging in, they input the initial information for creating a training program. For example, this information may include "communication skills," "team building," and "practical learning." This information is then sent to the server.

[0262] Step 2:

[0263] The server stores the received information in a database and the user profile is updated.

[0264] Step 3:

[0265] The user selects a specific training content and inputs its details, for example, "role-playing" or "group discussion." After inputting, the device sends this information to the server.

[0266] Step 4:

[0267] Based on the received training information, the server sends a request to the generative AI, which then generates customized training materials tailored to the user's training goals and style.

[0268] Step 5:

[0269] The generative AI returns the generated training materials to the server, which receives them and sends them to the user's device.

[0270] Step 6:

[0271] The terminal displays the training materials received from the server, and the training begins, such as a practical workshop or role-playing training.

[0272] Step 7:

[0273] The emotion engine monitors the new employee's reactions, analyzing their facial expressions, tone of voice, and operational behavior, and sends the emotional data to the server. For example, it detects a loss of interest in their facial expressions or tone of voice.

[0274] Step 8:

[0275] The server receives data from the emotion engine and adjusts the training materials in real time, for example by adding new activities if participants' reactions are poor.

[0276] Step 9:

[0277] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[0278] Step 10:

[0279] The server analyzes the feedback and emotion data and reflects it in the generation of the next training materials. For example, if a new employee feels that "role-playing was helpful," the generative AI and emotion engine will adjust the next training materials to include more role-playing.

[0280] This series of steps provides users with an optimized educational experience. The introduction of an emotion engine enables content adjustment in real time, further improving learner engagement and learning outcomes.

[0281] Example 2

[0282] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0283] Conventional online education systems struggle to provide personalized educational content tailored to each user's individual learning needs and learning styles. Furthermore, they are unable to grasp the user's emotional state during learning and dynamically adjust educational content accordingly, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to reflect user feedback in the generation of the next educational content. A new system is needed to address these issues.

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

[0285] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and storing user feedback on the educational content displayed on the terminal, means for analyzing the user's emotional state, and means for dynamically adjusting the content based on the analyzed emotional information, thereby making it possible to provide a personalized educational experience according to the user's individual learning needs and emotional state.

[0286] "Generative AI" refers to an AI system that generates natural language and provides support for problem-solving based on user input and prompts.

[0287] "Personalized educational content" means educational materials and learning programs that are customized to a user's specific learning goals, learning style, and individual needs.

[0288] "User's terminal" refers to a device, such as a computer, tablet, or smartphone, that a user uses to access the system and use educational content.

[0289] "Feedback" refers to opinions and impressions such as satisfaction and understanding provided by users after using educational content.

[0290] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and operating behavior to recognize their emotional state in real time.

[0291] "Dynamic adjustment" refers to changing the content and difficulty of educational content in real time based on the user's emotional state and feedback.

[0292] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content and, by combining it with an emotion engine, recognizes the user's emotions and optimizes the learning experience. This system is implemented by a server, a terminal, and a user, each playing a specific role.

[0293] Hardware and software used

[0294] The system includes the following hardware and software:

[0295] Server: The server is responsible for processing and storing data, running the generative artificial intelligence and emotion engine. A specific example would be a cloud computing platform (AWS, Google Cloud, etc.).

[0296] Terminal: A terminal is a device through which a user accesses the system, and can include a PC, tablet, smartphone, etc.

[0297] Generative AI: Natural language processing models (e.g., GPT-4, BERT) are used as generative AI.

[0298] Emotion engine: Uses facial expression recognition software and voice analysis software (e.g., Azure Emotion API, Facial Recognition API) to analyze the user's emotional state.

[0299] Specific examples of program processing

[0300] Example 1: High school English class

[0301] User Actions

[0302] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[0303] Server Operation

[0304] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[0305] Emotion Engine Operation

[0306] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[0307] Device behavior

[0308] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[0309] User behavior (feedback)

[0310] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[0311] Server operation (reflecting feedback)

[0312] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[0313] Example 2: Corporate training programs

[0314] User Actions

[0315] The user (a company training officer) logs into the platform using a terminal and inputs "communication skills" and "team building" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[0316] Server Operation

[0317] The server receives user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[0318] Emotion Engine Operation

[0319] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[0320] Device behavior

[0321] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[0322] User behavior (feedback)

[0323] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[0324] Server operation (reflecting feedback)

[0325] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[0326] Specific prompt examples

[0327] 1. High school English classes

[0328] "Generate audio clips and interactive quizzes to improve listening skills for high school students. My learning style is auditory."

[0329] 2. Corporate Training Programs

[0330] "Generate training materials for new employees that include hands-on workshops and role-playing that strengthen communication skills and team building."

[0331] This system allows users to enjoy an educational experience that is tailored to their individual learning needs and emotional state, which is expected to improve learning outcomes and satisfaction.

[0332] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0333] Step 1:

[0334] A user logs into the platform

[0335] Specific operation: The user launches the web browser on the device and accesses the platform's login page. On the login screen, the user enters the username and password and clicks the "Login" button.

[0336] Input: Username, Password

[0337] Output: Login successful, user data loaded

[0338] Step 2:

[0339] Users input their learning goals and learning styles

[0340] Specific operation: After logging in, the user enters their learning goal (e.g., "Improve listening skills") and learning style (e.g., "Auditory learning") into the form displayed on the homepage and clicks the submit button.

[0341] Input: learning goals, learning styles

[0342] Output: Sending user input information, receiving data on the server

[0343] Step 3:

[0344] The server receives the input information

[0345] Specific operations: The server receives the learning objectives and learning style information entered by the user and prepares appropriate processing. It receives the HTTP request and stores it in the database.

[0346] Input: User's learning goals, learning style

[0347] Output: Learning objectives and learning styles stored in a database

[0348] Step 4:

[0349] The server generates educational content using generative artificial intelligence

[0350] How it works: The server accesses the API of a generative artificial intelligence (e.g., GPT-4) to create prompts based on the user's learning goals and style, and then sends them to the AI ​​model to generate customized educational content.

[0351] Input: Prompt statement (e.g., "Generate an audio clip to improve your listening skills.")

[0352] Output: Customized educational content (audio clips, quizzes, etc.)

[0353] Step 5:

[0354] The device receives the educational content

[0355] Specific operation: The server sends the generated educational content to the terminal, which receives the content and displays it on the user interface.

[0356] Input: Customized educational content

[0357] Output: Educational content displayed on the device

[0358] Step 6:

[0359] The emotion engine collects user emotion data

[0360] Specific operation: While the user is using educational content, the device's camera and microphone are used to collect the user's facial expressions and voice data, which are then analyzed by the emotion engine.

[0361] Input: User's facial expressions and voice data

[0362] Output: Parsed emotion data

[0363] Step 7:

[0364] The device feeds back the collected data to the server.

[0365] Specific operation: The emotion engine sends collected data from the device to the server, which receives the data and stores it for the next content generation.

[0366] Input: Parsed emotion data

[0367] Output: Emotion data stored on the server

[0368] Step 8:

[0369] The server adjusts the content based on the feedback.

[0370] Specific behavior: The server analyzes the received emotional data and adjusts the current educational content in real time, for example, changing the task to an easier one if the user is tired.

[0371] Input: Feedback data, emotion data

[0372] Output: Tailored educational content

[0373] Step 9:

[0374] User enters feedback

[0375] Specific operation: After completing the learning, the user inputs and submits feedback on their satisfaction and understanding into the device. This data is sent to the server.

[0376] Input: Feedback (satisfaction, understanding)

[0377] output: Feedback data stored on the server

[0378] Step 10:

[0379] The server analyzes the feedback and reflects it in the next content generation.

[0380] Specific operation: The server combines and analyzes the user's feedback and emotional data, and reflects the results in the next educational content generation. Additionally, as an improvement, supplementary materials are added if the level of understanding in a particular area is low.

[0381] Input: Feedback, emotion data

[0382] Output: Improved educational content for next time learning

[0383] (Application example 2)

[0384] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0385] Conventional educational content delivery systems have the problem of being difficult to personalize content that takes into account each user's individual learning style and emotional state, making it difficult to maintain motivation to learn and maximize educational effectiveness.

[0386] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating personalized educational content based on user input information using a generative artificial intelligence; means for providing the generated educational content to the user's terminal; means for collecting and saving user feedback on the educational content displayed on the terminal; means for collecting user emotion data using an emotion engine that recognizes the user's emotional state; and means for feeding back the emotion data recognized by the emotion engine to the generative artificial intelligence and reflecting it in dynamic adjustment of the educational content. This makes it possible to provide optimal educational content according to the user's individual learning style and real-time emotional state.

[0387] "Generative AI" is an AI technology that generates content to perform specific tasks based on user input.

[0388] "Educational Content" refers to customized educational and learning materials provided to assist users in their learning.

[0389] A "terminal" is a device that a user uses to view educational content and enter feedback.

[0390] "Feedback" refers to the user providing information about their impressions of educational content and their level of understanding.

[0391] An "emotion engine" is a technology that analyzes data such as the user's facial expressions and voice to recognize the user's emotional state.

[0392] "Emotion data" is data relating to the user's emotional state as recognized by the emotion engine.

[0393] "Dynamic adjustment" refers to the process of changing the content and difficulty of educational content in real time based on collected feedback and sentiment data.

[0394] An "interface" is a function that allows users to input information about their learning goals and learning styles.

[0395] The present invention is a system for providing personalized educational content to users, which is implemented with a server, a terminal, and a user each playing a specific role.

[0396] Server Operation

[0397] The server uses generative artificial intelligence to generate personalized educational content based on the learning goals and learning style entered by the user. Examples of generative AI models used in this process include natural language processing models such as GPT-2. The generated educational content is sent to the device and provided to the user. The server also collects user feedback and emotional data sent from the emotion engine, and reflects this in the next educational content generation.

[0398] Device behavior

[0399] Users log in to the system using their devices and input information about their learning goals and learning styles. The devices then send the information to the server, which then displays personalized educational content. The devices also support an emotion engine that uses a built-in camera and microphone to analyze the user's facial expressions and voice to collect emotional data. This allows the obtained emotional data to be fed back to the server in real time.

[0400] User Actions

[0401] Users input information based on their learning goals and learning style through an interface displayed on their device. This information is sent to the server, and personalized educational content is generated by generative artificial intelligence. Users can provide feedback on the educational content provided, which is reflected in the next content generation. Emotional data obtained during learning is also sent to the server and used to generate the next content.

[0402] Hardware and software used

[0403] This system uses devices such as smartphones, tablets, and PCs. The emotion engine is implemented using image processing libraries such as OpenCV and machine learning frameworks such as TensorFlow and Keras. The generative artificial intelligence part uses GPT-2 and other natural language processing models.

[0404] Specific examples

[0405] Example 1: High school English class

[0406] A user (high school student) logs in to a device and enters "improving listening skills" as their learning goal. They also select "auditory learning" as their preferred learning style. The server receives this information and uses generative artificial intelligence to generate customized educational content to improve listening skills. This content includes audio clips for listening practice and interactive quizzes. While learning, an emotion engine analyzes the user's facial expressions and voice, collecting emotional data in real time, such as when they are not concentrating, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more appropriate learning materials.

[0407] Prompt Sentence Examples

[0408] "I'm a high school student who wants to improve my listening skills. Please provide content with interesting audio clips and quizzes."

[0409] Example 2: Corporate training programs

[0410] The user (corporate training manager) logs in to the device and enters "communication skills" and "team building" as learning objectives. The server receives this information and uses generative artificial intelligence to generate customized educational content. This content includes practical workshops and role-playing. During the learning process, an emotion engine analyzes the new employee's facial expressions and reactions, collecting emotional data in real time, such as when they lose interest, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more effective training materials.

[0411] Prompt Sentence Examples

[0412] "Create a training program for your new employees by providing customized content on communication skills and team building with hands-on learning methods."

[0413] The above is a specific embodiment of the present invention.

[0414] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0415] Step 1:

[0416] Users log in to their devices and enter information about their learning goals and learning style. At this time, they can select specific subjects, skill goals, and learning methods (e.g., "English," "improving listening skills," "auditory learning"). This input information is sent to the server.

[0417] Input: Information about the user's learning goals and learning style

[0418] Output: Learning objectives and learning style information sent to the server

[0419] Step 2:

[0420] The server uses a generative AI model to generate personalized educational content based on the user's input, using natural language processing models such as GPT-2 to generate optimal content based on the prompt.

[0421] Input: Learning objectives and learning style information

[0422] Output: Generated personalized educational content

[0423] Step 3:

[0424] The server transmits the generated educational content to the terminal, which receives it and displays it to the user.

[0425] Input: Generated educational content

[0426] Output: Educational content displayed on the device

[0427] Step 4:

[0428] The user studies the educational content displayed on the device, which uses a built-in camera and microphone to capture the user's facial expressions and voice in real time and collects the user's emotional data using an emotion engine.

[0429] Input: User's facial expression and voice data

[0430] Output: Emotion data recognized by the emotion engine

[0431] Step 5:

[0432] The emotion engine sends the recognized emotion data to the server, which collects it and uses it to dynamically adjust the current educational content and generate the next educational content.

[0433] Input: Emotion data recognized by the emotion engine

[0434] Output: Emotion data sent to the server

[0435] Step 6:

[0436] After learning the educational content, users provide feedback on their satisfaction and understanding of the content, which is sent from their devices to the server.

[0437] Input: User feedback

[0438] Output: Feedback sent to the server

[0439] Step 7:

[0440] The server analyzes the collected feedback and emotional data and inputs it as feedback into the generative AI model, which then optimizes the next educational content to be more suitable for the user.

[0441] Input: User feedback and sentiment data

[0442] Output: Information to be reflected in the next educational content generation

[0443] Through these steps, the present invention provides users with an individually optimized educational experience, improving learning outcomes and satisfaction.

[0444] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0445] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0446] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0447] [Second embodiment]

[0448] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0449] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0450] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0451] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0452] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0453] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0454] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0455] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0456] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0457] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0458] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0459] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0460] The present invention is a system for providing users with personalized educational content using generative artificial intelligence. This system is implemented as follows, with a server, a terminal, and a user each playing a specific role.

[0461] The system's program begins when a user inputs information about their learning goals and learning style through their device. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the device and provided to the user. The user studies the content and then provides feedback. This feedback is sent back to the server and reflected in the next generation of educational content. This series of steps makes it possible to provide the user with an optimized educational experience.

[0462] Example 1: High school math class

[0463] User Actions

[0464] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "Mathematics" and enters "Solution of Quadratic Equations" as the specific learning goal. The user also selects "Visual Learning" as the preferred learning style.

[0465] Server Operation

[0466] The server receives user input and uses generative artificial intelligence to generate customized educational content on solving quadratic equations, including visual instructional videos and interactive exercises.

[0467] Device behavior

[0468] The terminal receives the educational content sent from the server and displays it to the user, who then watches the content and solves the exercises.

[0469] User behavior (feedback)

[0470] After completing the study, the user inputs feedback on their satisfaction and understanding, which is then sent from the device to the server.

[0471] Server operation (reflecting feedback)

[0472] The server analyzes the user's feedback and reflects it in the next content generation. For example, if the user feels that the explanation is difficult, the generative AI will adjust the next content to provide a more concise and easy-to-understand explanation.

[0473] Example 2: Corporate training programs

[0474] User Actions

[0475] The user (a company's training officer) logs in to the platform using a terminal. After logging in, he / she enters "project management" and "agile methods" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[0476] Server Operation

[0477] The server takes user input and uses generative artificial intelligence to generate customized training materials on agile methods, including hands-on workshops and simulation training.

[0478] Device behavior

[0479] The terminal receives the training materials sent from the server and provides them to the user, who then uses the training materials to provide training to new employees.

[0480] User behavior (feedback)

[0481] After the training is completed, the trainer collects feedback from the new employees and sends it to the server from their devices, including the usefulness of the training and areas for improvement.

[0482] Server operation (reflecting feedback)

[0483] The server analyzes the collected feedback and reflects it in the generation of the next training materials. For example, if a new employee feels that "more practical examples are needed," the generative AI will adjust the next training materials to include more practical examples.

[0484] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction.

[0485] The processing flow will be explained below.

[0486] Step 1:

[0487] The user logs in to the platform through the terminal. The user enters the user ID and password for authentication. If the login is successful, the user profile is loaded.

[0488] Step 2:

[0489] The user inputs initial information about their learning goals and learning style into the terminal, including the subject, topic, learning goals, and preferred learning style (visual, auditory, movement, etc.). Once the information is input, the terminal sends it to the server.

[0490] Step 3:

[0491] The server stores the received user information in a database, which creates a personalized learning profile for each user.

[0492] Step 4:

[0493] Users select the specific topic they want to learn about on their device and enter details about it, after which the device sends this information to the server.

[0494] Step 5:

[0495] Based on the received topic information, the server sends a request to the generative AI, which then generates educational content customized to the user's learning goals and learning style.

[0496] Step 6:

[0497] The generative AI returns the generated customized educational content to the server, which receives the content and sends it to the user's device.

[0498] Step 7:

[0499] The device displays educational content received from the server. Users use this content to learn. Examples of content include visual instructional videos, interactive exercises, and simulations.

[0500] Step 8:

[0501] After the user has completed the learning, they can input feedback via the device, including their satisfaction with the learning content, their level of understanding, and areas for improvement.

[0502] Step 9:

[0503] The device sends the user's feedback to the server, which stores the received feedback in a database and reflects it in the generation of the next learning content.

[0504] Step 10:

[0505] The server analyzes the feedback and uses it as data to generate new learning content. The generative AI also uses this feedback to optimize the next content generation process.

[0506] This sequence of steps provides an optimized learning experience for the user.

[0507] Example 1

[0508] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0509] Conventional educational content delivery systems have struggled to effectively provide content tailored to individual users' learning goals and learning styles. Furthermore, mechanisms for incorporating feedback into subsequent content generation are inadequate, making it impossible to maximize users' learning effectiveness and satisfaction. Furthermore, systems that effectively utilize generative artificial intelligence to generate personalized educational content require the generation and effective use of prompt sentences. The present invention aims to solve these problems and provide users with educational content optimized for their needs.

[0510] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0511] In this invention, the server includes means for generating personalized educational content based on user input information using a generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and saving user feedback on the educational content displayed on the terminal, means for analyzing the feedback and reflecting it in the generation of the next educational content, and means for generating prompt sentences based on the user input information and inputting them into the generative artificial intelligence. This makes it possible to provide highly personalized educational content tailored to the needs of each individual user, thereby improving learning effectiveness and satisfaction.

[0512] "Generative AI" is an AI technology that can generate adaptive and personalized responses and content based on user input.

[0513] "Educational content" means teaching materials, resources, questions, and other learning aids designed to help learners acquire specific knowledge or skills.

[0514] A "terminal" is an electronic device that allows a user to access the system, input learning objectives, display educational content, and provide feedback.

[0515] "Feedback" is information that users provide to the system, such as their opinions on educational content, their level of satisfaction, their level of understanding, and areas for improvement.

[0516] A "prompt sentence" is a sentence that instructs a generative artificial intelligence to produce a specific output, and is generated based on information input by the user.

[0517] "Learning objectives" are specific educational goals or themes that a user wants to achieve.

[0518] "Learning style" refers to the type of teaching method or learning method that a user prefers, including visual learning, hands-on learning, etc.

[0519] "Personalization" means optimizing educational content and services to suit the specific needs and preferences of individual users.

[0520] "Analysis" is the act of digging deep into collected feedback and other data to extract insights.

[0521] This invention is a system that uses generative artificial intelligence to provide users with personalized educational content. In this system, the server, terminal, and user each play specific roles, and the specific process for implementing the invention is as follows:

[0522] First, a user accesses the platform using a terminal and inputs information about their learning goals and learning style. For example, if a user wants to learn how to solve quadratic equations in mathematics, they can input "how to solve quadratic equations" as their learning goal and select "visual learning" as their preferred learning style.

[0523] The device then sends the user's input information to a server, which uses generative artificial intelligence (such as OpenAI's GPT-3) to create a prompt to generate educational content optimized for the user's learning goals and style. An example prompt might be, "Generate educational content that includes visual explanation videos and interactive practice problems on how to solve quadratic equations in mathematics."

[0524] The server inputs the generated prompt sentences into a generative artificial intelligence (AI) to generate educational content customized for the user. This educational content includes visual instruction videos, interactive exercises, etc. The generated educational content is sent from the server to the device, which displays it to the user. The user then views the educational content on the device and works on the exercises.

[0525] After completing the learning process, the user inputs feedback on the educational content into the server from their device. The feedback includes satisfaction, level of understanding, and areas for improvement, and specific comments such as "I found the explanation in this part difficult to understand" can be entered.

[0526] The server receives the feedback sent from the device and analyzes it. Based on the analysis results, it reflects the results in the next educational content generation. Through this process, the generative AI generates prompts that reflect the feedback, and the next time, more personalized content is provided.

[0527] To give a specific example, when a high school student is learning "how to solve quadratic equations" in a mathematics class, the process proceeds as follows: The user (high school student) uses a device to select the "Mathematics" subject, enters "how to solve quadratic equations" as the learning goal, and selects "visual learning" as the preferred learning style. The user's input information is sent to the server, which then sends a prompt to the generative AI such as "Please generate visual educational content on how to solve quadratic equations." The educational content generated by the generative AI is sent to the device, and the user studies it. After completing the study, the feedback entered by the user is reflected in the next content generation.

[0528] This series of steps allows users to receive an optimized educational experience, increasing learning effectiveness and satisfaction.

[0529] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0530] Step 1:

[0531] The user accesses the platform using a terminal and logs in.

[0532] The user enters their user ID and password on the device's input screen and sends the authentication information to the server. The server receives the authentication information, performs user authentication, and returns the authentication result to the device. If user authentication is successful, the user can proceed to the next step.

[0533] Step 2:

[0534] The user enters information about their learning goals and learning style.

[0535] Through the device's interface, users input the content they want to learn (e.g., "How to solve quadratic equations") as their learning goal. They also select their preferred learning style, such as visual learning or hands-on learning. The input information is sent from the device to the server, which then sends it to the server as JSON-formatted data, where it is stored in a database.

[0536] Step 3:

[0537] The server analyzes the user's input and generates a prompt.

[0538] The server analyzes the received JSON-formatted user information and creates a prompt to generate educational content. For example, it generates a prompt such as, "Please generate educational content that includes a visual explanation video and interactive practice problems on how to solve quadratic equations in mathematics." This prompt is then input into the generative artificial intelligence.

[0539] Step 4:

[0540] The server generates educational content using generative artificial intelligence.

[0541] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to generate educational content. Based on the prompt, the generative AI generates educational content, including visual instructional videos and interactive exercises, and returns the results to the server.

[0542] Step 5:

[0543] The server transmits the generated educational content to the terminal.

[0544] The server transmits the educational content received from the generative AI to the user's device. This content includes learning materials and exercises according to the learning objectives. The device receives this content and displays it to the user.

[0545] Step 6:

[0546] The user studies the educational content and provides feedback.

[0547] Users view and study the educational content provided on their devices. After completing the study, they enter feedback such as satisfaction, level of understanding, and specific areas for improvement into the device's interface. This feedback information is then sent back to the server in JSON format.

[0548] Step 7:

[0549] The server receives and analyzes the feedback.

[0550] The server receives the feedback information sent from the device and stores it in a database. The saved feedback information is analyzed and insights are extracted to be reflected in the next generation of educational content. For example, an action item such as "We need to generate content that includes more specific and simple explanations" can be obtained.

[0551] Step 8:

[0552] The server regenerates the prompt text reflecting the feedback and generates the next educational content.

[0553] The server generates a new prompt based on the feedback analysis results. For example, it might generate a prompt such as, "Please generate educational content on how to solve quadratic equations with more specific and simpler explanations." This prompt is then fed back into the generative AI to generate improved educational content, further improving the user's next learning experience.

[0554] The above is the specific processing flow of this system.

[0555] (Application example 1)

[0556] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0557] Conventional educational systems have had difficulty providing appropriate educational content tailored to individual users' learning needs and levels of understanding. Furthermore, fixed educational content may reduce learning effectiveness because it cannot fully address the specific problems and levels of understanding that users have. Furthermore, there are insufficient means to effectively reflect feedback in the generation of the next educational content, making it impossible to maximize the effectiveness of individualized instruction.

[0558] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0559] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's information processing device, means for collecting and storing user feedback on the educational content displayed on the information processing device, and means for adjusting the next generation of the educational content based on the feedback, thereby providing the user with educational content optimized for the user, thereby improving learning outcomes and increasing user satisfaction.

[0560] "Generative AI" is an advanced AI that uses machine learning and natural language processing technology to generate optimal educational content based on input information provided by users.

[0561] "Personalized educational content" refers to educational materials and learning materials that are customized according to a user's learning goals and learning style.

[0562] "User input information" refers to data about learning goals and learning styles that users provide to the system, and optimized educational content is generated based on this data.

[0563] "Information processing device" refers to a device used by a user, such as a smartphone, smart glasses, or head-mounted display, which can display and operate the generated educational content.

[0564] "Feedback" refers to evaluation information such as satisfaction, level of understanding, and comments provided by users after using educational content, and is reflected in the next content generation.

[0565] A "prompt" refers to text input that provides specific instructions or requests to a generative artificial intelligence to generate the desired educational content.

[0566] "Adjusting the next generation of educational content" refers to the process of optimizing the next generation of educational content based on previous feedback information to provide a better learning experience.

[0567] The present invention is a system for providing users with personalized educational content using generative artificial intelligence, in which a server, a terminal, and a user each play specific roles.

[0568] First, a user logs in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display, and enters information about their learning goals and learning style. For example, a high school student can select "solving quadratic equations" and "visual learning."

[0569] The server receives the information entered by the user and uses a generative AI model to automatically generate personalized educational content. Specific prompts are used in this process. An example of a prompt is as follows:

[0570] User Information:

[0571] Learning Objective: Solving quadratic equations

[0572] Learning Style: Visual Learning

[0573] Use this information to create visual instructional content. Your educational content should include:

[0574] 1. Basic Concepts of Quadratic Equations

[0575] 2. Step-by-step explanation of the solution (visually presented)

[0576] 3. Interactive Exercises

[0577] The generated educational content is sent from the server to the user's terminal, where it is displayed. The user studies the educational content and solves the exercises according to the displayed content.

[0578] After completing the learning, the user inputs feedback regarding their satisfaction and level of understanding. This feedback data is sent back to the server. The server analyzes the collected feedback and reflects it in the creation of the next educational content. This feedback includes an evaluation of how much the user understood the learning content and how easy the explanation was to understand. Another example of feedback could be a comment such as "The explanation was a little difficult."

[0579] This allows the system to provide an optimized educational experience for each user and improve learning outcomes. The software explicitly used includes generative AI models (e.g., OpenAI's GPT-3).

[0580] To maximize the effectiveness of this system, it is important to effectively analyze the feedback data collected from users and optimize the process of adjusting learning content using generative AI. This process will enable the provision of continuously improved educational content to users.

[0581] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0582] Step 1:

[0583] Users log in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display and input information about their learning goals and learning style. This input information includes the learning goal of "solving quadratic equations" and the learning style of "visual learning."

[0584] Input: learning goals, learning styles

[0585] Output: Learning goals and learning style data

[0586] Step 2:

[0587] The terminal transmits the learning goal and learning style data input by the user to the server.

[0588] Input: Learning objectives, learning style data

[0589] Output: Learning objectives and learning style data sent to the server

[0590] Step 3:

[0591] The server receives the user's input information and uses the generative AI model to generate personalized educational content. The server generates a specific prompt sentence and passes it to the generative AI model to obtain the educational content.

[0592] Specific examples of prompts are as follows:

[0593] User Information:

[0594] Learning Objective: Solving quadratic equations

[0595] Learning Style: Visual Learning

[0596] Use this information to create visual instructional content. Your educational content should include:

[0597] 1. Basic Concepts of Quadratic Equations

[0598] 2. Step-by-step explanation of the solution (visually presented)

[0599] 3. Interactive Exercises

[0600] Input: Learning objectives and learning style data

[0601] Output: Personalized educational content

[0602] Step 4:

[0603] The server transmits the generated educational content to the user's terminal.

[0604] Input: personalized educational content

[0605] Output: Delivery of educational content to user devices

[0606] Step 5:

[0607] The terminal displays the received educational content to the user, who then studies the displayed educational content and solves the set exercises.

[0608] Input: Educational content

[0609] Output: Educational content displayed to the user

[0610] Step 6:

[0611] After completing the learning process, users can enter feedback on their device regarding their satisfaction and understanding. Feedback includes user-provided ratings and comments (e.g., "The explanation was a little difficult").

[0612] Input: User feedback

[0613] Output: Feedback data

[0614] Step 7:

[0615] The terminal transmits the feedback data to the server.

[0616] Input: Feedback data

[0617] Output: Feedback data sent to the server

[0618] Step 8:

[0619] The server analyzes the collected feedback and reflects it in the next generation of educational content. This analysis allows for content refinement based on the user's level of understanding and satisfaction.

[0620] Input: Feedback data

[0621] Output: Analysis results for improved educational content generation

[0622] By repeating this process, it is possible to provide users with continuously improved educational content, which helps them learn more effectively and improve their learning outcomes.

[0623] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0624] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content, and further combines an emotion engine to recognize users' emotions and optimize the learning experience. This system is implemented as follows, with the server, terminal, and user each playing a specific role.

[0625] The system's program begins when a user inputs information about their learning goals and learning style through a terminal. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the terminal and provided to the user.

[0626] The role of the emotional engine

[0627] The system incorporates an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotional state by analyzing the user's facial expressions, voice, and operating behavior. The emotional state recognized by the emotion engine is fed back to the generative AI and reflected in the generation of the next educational content and the dynamic adjustment of the current content.

[0628] Program flow and examples

[0629] Example 1: High school English class

[0630] User Actions

[0631] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[0632] Server Operation

[0633] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[0634] Emotion Engine Operation

[0635] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[0636] Device behavior

[0637] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[0638] User behavior (feedback)

[0639] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[0640] Server operation (reflecting feedback)

[0641] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[0642] Example 2: Corporate training programs

[0643] User Actions

[0644] The user (a company's training officer) logs in to the platform using a terminal. After logging in, they input "communication skills" and "team building" as learning objectives to create a training program for new employees. The user then selects "hands-on learning" as the learning style for new employees.

[0645] Server Operation

[0646] The server takes user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[0647] Emotion Engine Operation

[0648] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[0649] Device behavior

[0650] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[0651] User behavior (feedback)

[0652] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[0653] Server operation (reflecting feedback)

[0654] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[0655] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction. Furthermore, by incorporating an emotion engine, dynamic content optimization based on the user's emotional state is possible, providing a richer and more effective learning experience.

[0656] The processing flow will be explained below.

[0657] Example 1: High school English class

[0658] Program processing flow

[0659] Step 1:

[0660] The user logs in to the platform through the terminal, enters the user ID and password for authentication, and if the authentication is successful, the user profile is loaded.

[0661] Step 2:

[0662] The user inputs initial information about their learning goals and learning style into the terminal, such as "English," "improving listening skills," "auditory learning," etc. Once this information is entered, the terminal transmits it to the server.

[0663] Step 3:

[0664] The server stores the received information in a database, which creates a personalized learning profile for each user.

[0665] Step 4:

[0666] The user selects the specific topic they want to study on their device and enters the details, for example, "listening practice," after which the device sends this information to the server.

[0667] Step 5:

[0668] Based on the received topic information, the server sends a request to the generative AI, which then generates customized educational content tailored to the user's learning goals and style.

[0669] Step 6:

[0670] The generative AI sends the generated educational content back to the server, which receives the content and sends it to the user's device.

[0671] Step 7:

[0672] The device receives educational content from the server and displays it to the user, such as audio clips for listening practice or interactive quizzes.

[0673] Step 8:

[0674] The emotion engine monitors the user's reactions, analyzing the user's facial expressions and voice in real time and sending emotional data to the server. For example, it detects distracted facial expressions and tone of voice.

[0675] Step 9:

[0676] The server receives data from the emotion engine and adjusts the content in real time, for example, lowering the difficulty of the content or adding interactive elements if it determines that the user is not concentrating.

[0677] Step 10:

[0678] After completing the learning process, the user enters their satisfaction and understanding in a feedback form. The device then sends this feedback to the server, along with the data collected by the emotion engine.

[0679] Step 11:

[0680] The server analyzes the feedback and emotion data and reflects it in the next generation of educational content. For example, if the user feels that the practice questions are difficult, the generative AI will adjust to provide easier questions for the next content.

[0681] Example 2: Corporate training programs

[0682] Program processing flow

[0683] Step 1:

[0684] The user (a company's training manager) logs into the platform through a terminal. After logging in, they input the initial information for creating a training program. For example, this information may include "communication skills," "team building," and "practical learning." This information is then sent to the server.

[0685] Step 2:

[0686] The server stores the received information in a database and the user profile is updated.

[0687] Step 3:

[0688] The user selects a specific training content and inputs its details, for example, "role-playing" or "group discussion." After inputting, the device sends this information to the server.

[0689] Step 4:

[0690] Based on the received training information, the server sends a request to the generative AI, which then generates customized training materials tailored to the user's training goals and style.

[0691] Step 5:

[0692] The generative AI returns the generated training materials to the server, which receives them and sends them to the user's device.

[0693] Step 6:

[0694] The terminal displays the training materials received from the server, and the training begins, such as a practical workshop or role-playing training.

[0695] Step 7:

[0696] The emotion engine monitors the new employee's reactions, analyzing their facial expressions, tone of voice, and operational behavior, and sends the emotional data to the server. For example, it detects a loss of interest in their facial expressions or tone of voice.

[0697] Step 8:

[0698] The server receives data from the emotion engine and adjusts the training materials in real time, for example by adding new activities if participants' reactions are poor.

[0699] Step 9:

[0700] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[0701] Step 10:

[0702] The server analyzes the feedback and emotion data and reflects it in the generation of the next training materials. For example, if a new employee feels that "role-playing was helpful," the generative AI and emotion engine will adjust the next training materials to include more role-playing.

[0703] This series of steps provides users with an optimized educational experience. The introduction of an emotion engine enables content adjustment in real time, further improving learner engagement and learning outcomes.

[0704] Example 2

[0705] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0706] Conventional online education systems struggle to provide personalized educational content tailored to each user's individual learning needs and learning styles. Furthermore, they are unable to grasp the user's emotional state during learning and dynamically adjust educational content accordingly, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to reflect user feedback in the generation of the next educational content. A new system is needed to address these issues.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0708] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and storing user feedback on the educational content displayed on the terminal, means for analyzing the user's emotional state, and means for dynamically adjusting the content based on the analyzed emotional information, thereby making it possible to provide a personalized educational experience according to the user's individual learning needs and emotional state.

[0709] "Generative AI" refers to an AI system that generates natural language and provides support for problem-solving based on user input and prompts.

[0710] "Personalized educational content" means educational materials and learning programs that are customized to a user's specific learning goals, learning style, and individual needs.

[0711] "User's terminal" refers to a device, such as a computer, tablet, or smartphone, that a user uses to access the system and use educational content.

[0712] "Feedback" refers to opinions and impressions such as satisfaction and understanding provided by users after using educational content.

[0713] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and operating behavior to recognize their emotional state in real time.

[0714] "Dynamic adjustment" refers to changing the content and difficulty of educational content in real time based on the user's emotional state and feedback.

[0715] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content and, by combining it with an emotion engine, recognizes the user's emotions and optimizes the learning experience. This system is implemented by a server, a terminal, and a user, each playing a specific role.

[0716] Hardware and software used

[0717] The system includes the following hardware and software:

[0718] Server: The server is responsible for processing and storing data, running the generative artificial intelligence and emotion engine. A specific example would be a cloud computing platform (AWS, Google Cloud, etc.).

[0719] Terminal: A terminal is a device through which a user accesses the system, and can include a PC, tablet, smartphone, etc.

[0720] Generative AI: Natural language processing models (e.g., GPT-4, BERT) are used as generative AI.

[0721] Emotion engine: Uses facial expression recognition software and voice analysis software (e.g., Azure Emotion API, Facial Recognition API) to analyze the user's emotional state.

[0722] Specific examples of program processing

[0723] Example 1: High school English class

[0724] User Actions

[0725] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[0726] Server Operation

[0727] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[0728] Emotion Engine Operation

[0729] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[0730] Device behavior

[0731] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[0732] User behavior (feedback)

[0733] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[0734] Server operation (reflecting feedback)

[0735] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[0736] Example 2: Corporate training programs

[0737] User Actions

[0738] The user (a company training officer) logs into the platform using a terminal and inputs "communication skills" and "team building" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[0739] Server Operation

[0740] The server receives user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[0741] Emotion Engine Operation

[0742] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[0743] Device behavior

[0744] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[0745] User behavior (feedback)

[0746] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[0747] Server operation (reflecting feedback)

[0748] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[0749] Specific prompt examples

[0750] 1. High school English classes

[0751] "Generate audio clips and interactive quizzes to improve listening skills for high school students. My learning style is auditory."

[0752] 2. Corporate Training Programs

[0753] "Generate training materials for new employees that include hands-on workshops and role-playing that strengthen communication skills and team building."

[0754] This system allows users to enjoy an educational experience that is tailored to their individual learning needs and emotional state, which is expected to improve learning outcomes and satisfaction.

[0755] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0756] Step 1:

[0757] A user logs into the platform

[0758] Specific operation: The user launches the web browser on the device and accesses the platform's login page. On the login screen, the user enters the username and password and clicks the "Login" button.

[0759] Input: Username, Password

[0760] Output: Login successful, user data loaded

[0761] Step 2:

[0762] Users input their learning goals and learning styles

[0763] Specific operation: After logging in, the user enters their learning goal (e.g., "Improve listening skills") and learning style (e.g., "Auditory learning") into the form displayed on the homepage and clicks the submit button.

[0764] Input: learning goals, learning styles

[0765] Output: Sending user input information, receiving data on the server

[0766] Step 3:

[0767] The server receives the input information

[0768] Specific operations: The server receives the learning objectives and learning style information entered by the user and prepares appropriate processing. It receives the HTTP request and stores it in the database.

[0769] Input: User's learning goals, learning style

[0770] Output: Learning objectives and learning styles stored in a database

[0771] Step 4:

[0772] The server generates educational content using generative artificial intelligence

[0773] How it works: The server accesses the API of a generative artificial intelligence (e.g., GPT-4) to create prompts based on the user's learning goals and style, and then sends them to the AI ​​model to generate customized educational content.

[0774] Input: Prompt statement (e.g., "Generate an audio clip to improve your listening skills.")

[0775] Output: Customized educational content (audio clips, quizzes, etc.)

[0776] Step 5:

[0777] The device receives the educational content

[0778] Specific operation: The server sends the generated educational content to the terminal, which receives the content and displays it on the user interface.

[0779] Input: Customized educational content

[0780] Output: Educational content displayed on the device

[0781] Step 6:

[0782] The emotion engine collects user emotion data

[0783] Specific operation: While the user is using educational content, the device's camera and microphone are used to collect the user's facial expressions and voice data, which are then analyzed by the emotion engine.

[0784] Input: User's facial expressions and voice data

[0785] Output: Parsed emotion data

[0786] Step 7:

[0787] The device feeds back the collected data to the server.

[0788] Specific operation: The emotion engine sends collected data from the device to the server, which receives the data and stores it for the next content generation.

[0789] Input: Parsed emotion data

[0790] Output: Emotion data stored on the server

[0791] Step 8:

[0792] The server adjusts the content based on the feedback.

[0793] Specific behavior: The server analyzes the received emotional data and adjusts the current educational content in real time, for example, changing the task to an easier one if the user is tired.

[0794] Input: Feedback data, emotion data

[0795] Output: Tailored educational content

[0796] Step 9:

[0797] User enters feedback

[0798] Specific operation: After completing the learning, the user inputs and submits feedback on their satisfaction and understanding into the device. This data is sent to the server.

[0799] Input: Feedback (satisfaction, understanding)

[0800] output: Feedback data stored on the server

[0801] Step 10:

[0802] The server analyzes the feedback and reflects it in the next content generation.

[0803] Specific operation: The server combines and analyzes the user's feedback and emotional data, and reflects the results in the next educational content generation. Additionally, as an improvement, supplementary materials are added if the level of understanding in a particular area is low.

[0804] Input: Feedback, emotion data

[0805] Output: Improved educational content for next time learning

[0806] (Application example 2)

[0807] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0808] Conventional educational content delivery systems have the problem of being difficult to personalize content that takes into account each user's individual learning style and emotional state, making it difficult to maintain motivation to learn and maximize educational effectiveness.

[0809] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating personalized educational content based on user input information using a generative artificial intelligence; means for providing the generated educational content to the user's terminal; means for collecting and saving user feedback on the educational content displayed on the terminal; means for collecting user emotion data using an emotion engine that recognizes the user's emotional state; and means for feeding back the emotion data recognized by the emotion engine to the generative artificial intelligence and reflecting it in dynamic adjustment of the educational content. This makes it possible to provide optimal educational content according to the user's individual learning style and real-time emotional state.

[0810] "Generative AI" is an AI technology that generates content to perform specific tasks based on user input.

[0811] "Educational Content" refers to customized educational and learning materials provided to assist users in their learning.

[0812] A "terminal" is a device that a user uses to view educational content and enter feedback.

[0813] "Feedback" refers to the user providing information about their impressions of educational content and their level of understanding.

[0814] An "emotion engine" is a technology that analyzes data such as the user's facial expressions and voice to recognize the user's emotional state.

[0815] "Emotion data" is data relating to the user's emotional state as recognized by the emotion engine.

[0816] "Dynamic adjustment" refers to the process of changing the content and difficulty of educational content in real time based on collected feedback and sentiment data.

[0817] An "interface" is a function that allows users to input information about their learning goals and learning styles.

[0818] The present invention is a system for providing personalized educational content to users, which is implemented with a server, a terminal, and a user each playing a specific role.

[0819] Server Operation

[0820] The server uses generative artificial intelligence to generate personalized educational content based on the learning goals and learning style entered by the user. Examples of generative AI models used in this process include natural language processing models such as GPT-2. The generated educational content is sent to the device and provided to the user. The server also collects user feedback and emotional data sent from the emotion engine, and reflects this in the next educational content generation.

[0821] Device behavior

[0822] Users log in to the system using their devices and input information about their learning goals and learning styles. The devices then send the information to the server, which then displays personalized educational content. The devices also support an emotion engine that uses a built-in camera and microphone to analyze the user's facial expressions and voice to collect emotional data. This allows the obtained emotional data to be fed back to the server in real time.

[0823] User Actions

[0824] Users input information based on their learning goals and learning style through an interface displayed on their device. This information is sent to the server, and personalized educational content is generated by generative artificial intelligence. Users can provide feedback on the educational content provided, which is reflected in the next content generation. Emotional data obtained during learning is also sent to the server and used to generate the next content.

[0825] Hardware and software used

[0826] This system uses devices such as smartphones, tablets, and PCs. The emotion engine is implemented using image processing libraries such as OpenCV and machine learning frameworks such as TensorFlow and Keras. The generative artificial intelligence part uses GPT-2 and other natural language processing models.

[0827] Specific examples

[0828] Example 1: High school English class

[0829] A user (high school student) logs in to a device and enters "improving listening skills" as their learning goal. They also select "auditory learning" as their preferred learning style. The server receives this information and uses generative artificial intelligence to generate customized educational content to improve listening skills. This content includes audio clips for listening practice and interactive quizzes. While learning, an emotion engine analyzes the user's facial expressions and voice, collecting emotional data in real time, such as when they are not concentrating, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more appropriate learning materials.

[0830] Prompt Sentence Examples

[0831] "I'm a high school student who wants to improve my listening skills. Please provide content with interesting audio clips and quizzes."

[0832] Example 2: Corporate training programs

[0833] The user (corporate training manager) logs in to the device and enters "communication skills" and "team building" as learning objectives. The server receives this information and uses generative artificial intelligence to generate customized educational content. This content includes practical workshops and role-playing. During the learning process, an emotion engine analyzes the new employee's facial expressions and reactions, collecting emotional data in real time, such as when they lose interest, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more effective training materials.

[0834] Prompt Sentence Examples

[0835] "Create a training program for your new employees by providing customized content on communication skills and team building with hands-on learning methods."

[0836] The above is a specific embodiment of the present invention.

[0837] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0838] Step 1:

[0839] Users log in to their devices and enter information about their learning goals and learning style. At this time, they can select specific subjects, skill goals, and learning methods (e.g., "English," "improving listening skills," "auditory learning"). This input information is sent to the server.

[0840] Input: Information about the user's learning goals and learning style

[0841] Output: Learning objectives and learning style information sent to the server

[0842] Step 2:

[0843] The server uses a generative AI model to generate personalized educational content based on the user's input, using natural language processing models such as GPT-2 to generate optimal content based on the prompt.

[0844] Input: Learning objectives and learning style information

[0845] Output: Generated personalized educational content

[0846] Step 3:

[0847] The server transmits the generated educational content to the terminal, which receives it and displays it to the user.

[0848] Input: Generated educational content

[0849] Output: Educational content displayed on the device

[0850] Step 4:

[0851] The user studies the educational content displayed on the device, which uses a built-in camera and microphone to capture the user's facial expressions and voice in real time and collects the user's emotional data using an emotion engine.

[0852] Input: User's facial expression and voice data

[0853] Output: Emotion data recognized by the emotion engine

[0854] Step 5:

[0855] The emotion engine sends the recognized emotion data to the server, which collects it and uses it to dynamically adjust the current educational content and generate the next educational content.

[0856] Input: Emotion data recognized by the emotion engine

[0857] Output: Emotion data sent to the server

[0858] Step 6:

[0859] After learning the educational content, users provide feedback on their satisfaction and understanding of the content, which is sent from their devices to the server.

[0860] Input: User feedback

[0861] Output: Feedback sent to the server

[0862] Step 7:

[0863] The server analyzes the collected feedback and emotional data and inputs it as feedback into the generative AI model, which then optimizes the next educational content to be more suitable for the user.

[0864] Input: User feedback and sentiment data

[0865] Output: Information to be reflected in the next educational content generation

[0866] Through these steps, the present invention provides users with an individually optimized educational experience, improving learning outcomes and satisfaction.

[0867] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0868] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0869] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0870] [Third embodiment]

[0871] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0872] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0873] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0874] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0875] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0876] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0877] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0878] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0879] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0880] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0881] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0882] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0883] The present invention is a system for providing users with personalized educational content using generative artificial intelligence. This system is implemented as follows, with a server, a terminal, and a user each playing a specific role.

[0884] The system's program begins when a user inputs information about their learning goals and learning style through their device. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the device and provided to the user. The user studies the content and then provides feedback. This feedback is sent back to the server and reflected in the next generation of educational content. This series of steps makes it possible to provide the user with an optimized educational experience.

[0885] Example 1: High school math class

[0886] User Actions

[0887] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "Mathematics" and enters "Solution of Quadratic Equations" as the specific learning goal. The user also selects "Visual Learning" as the preferred learning style.

[0888] Server Operation

[0889] The server receives user input and uses generative artificial intelligence to generate customized educational content on solving quadratic equations, including visual instructional videos and interactive exercises.

[0890] Device behavior

[0891] The terminal receives the educational content sent from the server and displays it to the user, who then watches the content and solves the exercises.

[0892] User behavior (feedback)

[0893] After completing the study, the user inputs feedback on their satisfaction and understanding, which is then sent from the device to the server.

[0894] Server operation (reflecting feedback)

[0895] The server analyzes the user's feedback and reflects it in the next content generation. For example, if the user feels that the explanation is difficult, the generative AI will adjust the next content to provide a more concise and easy-to-understand explanation.

[0896] Example 2: Corporate training programs

[0897] User Actions

[0898] The user (a company's training officer) logs in to the platform using a terminal. After logging in, he / she enters "project management" and "agile methods" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[0899] Server Operation

[0900] The server takes user input and uses generative artificial intelligence to generate customized training materials on agile methods, including hands-on workshops and simulation training.

[0901] Device behavior

[0902] The terminal receives the training materials sent from the server and provides them to the user, who then uses the training materials to provide training to new employees.

[0903] User behavior (feedback)

[0904] After the training is completed, the trainer collects feedback from the new employees and sends it to the server from their devices, including the usefulness of the training and areas for improvement.

[0905] Server operation (reflecting feedback)

[0906] The server analyzes the collected feedback and reflects it in the generation of the next training materials. For example, if a new employee feels that "more practical examples are needed," the generative AI will adjust the next training materials to include more practical examples.

[0907] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction.

[0908] The processing flow will be explained below.

[0909] Step 1:

[0910] The user logs in to the platform through the terminal. The user enters the user ID and password for authentication. If the login is successful, the user profile is loaded.

[0911] Step 2:

[0912] The user inputs initial information about their learning goals and learning style into the terminal, including the subject, topic, learning goals, and preferred learning style (visual, auditory, movement, etc.). Once the information is input, the terminal sends it to the server.

[0913] Step 3:

[0914] The server stores the received user information in a database, which creates a personalized learning profile for each user.

[0915] Step 4:

[0916] Users select the specific topic they want to learn about on their device and enter details about it, after which the device sends this information to the server.

[0917] Step 5:

[0918] Based on the received topic information, the server sends a request to the generative AI, which then generates educational content customized to the user's learning goals and learning style.

[0919] Step 6:

[0920] The generative AI returns the generated customized educational content to the server, which receives the content and sends it to the user's device.

[0921] Step 7:

[0922] The device displays educational content received from the server. Users use this content to learn. Examples of content include visual instructional videos, interactive exercises, and simulations.

[0923] Step 8:

[0924] After the user has completed the learning, they can input feedback via the device, including their satisfaction with the learning content, their level of understanding, and areas for improvement.

[0925] Step 9:

[0926] The device sends the user's feedback to the server, which stores the received feedback in a database and reflects it in the generation of the next learning content.

[0927] Step 10:

[0928] The server analyzes the feedback and uses it as data to generate new learning content. The generative AI also uses this feedback to optimize the next content generation process.

[0929] This sequence of steps provides an optimized learning experience for the user.

[0930] Example 1

[0931] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0932] Conventional educational content delivery systems have struggled to effectively provide content tailored to individual users' learning goals and learning styles. Furthermore, mechanisms for incorporating feedback into subsequent content generation are inadequate, making it impossible to maximize users' learning effectiveness and satisfaction. Furthermore, systems that effectively utilize generative artificial intelligence to generate personalized educational content require the generation and effective use of prompt sentences. The present invention aims to solve these problems and provide users with educational content optimized for their needs.

[0933] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0934] In this invention, the server includes means for generating personalized educational content based on user input information using a generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and saving user feedback on the educational content displayed on the terminal, means for analyzing the feedback and reflecting it in the generation of the next educational content, and means for generating prompt sentences based on the user input information and inputting them into the generative artificial intelligence. This makes it possible to provide highly personalized educational content tailored to the needs of each individual user, thereby improving learning effectiveness and satisfaction.

[0935] "Generative AI" is an AI technology that can generate adaptive and personalized responses and content based on user input.

[0936] "Educational content" means teaching materials, resources, questions, and other learning aids designed to help learners acquire specific knowledge or skills.

[0937] A "terminal" is an electronic device that allows a user to access the system, input learning objectives, display educational content, and provide feedback.

[0938] "Feedback" is information that users provide to the system, such as their opinions on educational content, their level of satisfaction, their level of understanding, and areas for improvement.

[0939] A "prompt sentence" is a sentence that instructs a generative artificial intelligence to produce a specific output, and is generated based on information input by the user.

[0940] "Learning objectives" are specific educational goals or themes that a user wants to achieve.

[0941] "Learning style" refers to the type of teaching method or learning method that a user prefers, including visual learning, hands-on learning, etc.

[0942] "Personalization" means optimizing educational content and services to suit the specific needs and preferences of individual users.

[0943] "Analysis" is the act of digging deep into collected feedback and other data to extract insights.

[0944] This invention is a system that uses generative artificial intelligence to provide users with personalized educational content. In this system, the server, terminal, and user each play specific roles, and the specific process for implementing the invention is as follows:

[0945] First, a user accesses the platform using a terminal and inputs information about their learning goals and learning style. For example, if a user wants to learn how to solve quadratic equations in mathematics, they can input "how to solve quadratic equations" as their learning goal and select "visual learning" as their preferred learning style.

[0946] The device then sends the user's input information to a server, which uses generative artificial intelligence (such as OpenAI's GPT-3) to create a prompt to generate educational content optimized for the user's learning goals and style. An example prompt might be, "Generate educational content that includes visual explanation videos and interactive practice problems on how to solve quadratic equations in mathematics."

[0947] The server inputs the generated prompt sentences into a generative artificial intelligence (AI) to generate educational content customized for the user. This educational content includes visual instruction videos, interactive exercises, etc. The generated educational content is sent from the server to the device, which displays it to the user. The user then views the educational content on the device and works on the exercises.

[0948] After completing the learning process, the user inputs feedback on the educational content into the server from their device. The feedback includes satisfaction, level of understanding, and areas for improvement, and specific comments such as "I found the explanation in this part difficult to understand" can be entered.

[0949] The server receives the feedback sent from the device and analyzes it. Based on the analysis results, it reflects the results in the next educational content generation. Through this process, the generative AI generates prompts that reflect the feedback, and the next time, more personalized content is provided.

[0950] To give a specific example, when a high school student is learning "how to solve quadratic equations" in a mathematics class, the process proceeds as follows: The user (high school student) uses a device to select the "Mathematics" subject, enters "how to solve quadratic equations" as the learning goal, and selects "visual learning" as the preferred learning style. The user's input information is sent to the server, which then sends a prompt to the generative AI such as "Please generate visual educational content on how to solve quadratic equations." The educational content generated by the generative AI is sent to the device, and the user studies it. After completing the study, the feedback entered by the user is reflected in the next content generation.

[0951] This series of steps allows users to receive an optimized educational experience, increasing learning effectiveness and satisfaction.

[0952] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0953] Step 1:

[0954] The user accesses the platform using a terminal and logs in.

[0955] The user enters their user ID and password on the device's input screen and sends the authentication information to the server. The server receives the authentication information, performs user authentication, and returns the authentication result to the device. If user authentication is successful, the user can proceed to the next step.

[0956] Step 2:

[0957] The user enters information about their learning goals and learning style.

[0958] Through the device's interface, users input the content they want to learn (e.g., "How to solve quadratic equations") as their learning goal. They also select their preferred learning style, such as visual learning or hands-on learning. The input information is sent from the device to the server, which then sends it to the server as JSON-formatted data, where it is stored in a database.

[0959] Step 3:

[0960] The server analyzes the user's input and generates a prompt.

[0961] The server analyzes the received JSON-formatted user information and creates a prompt to generate educational content. For example, it generates a prompt such as, "Please generate educational content that includes a visual explanation video and interactive practice problems on how to solve quadratic equations in mathematics." This prompt is then input into the generative artificial intelligence.

[0962] Step 4:

[0963] The server generates educational content using generative artificial intelligence.

[0964] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to generate educational content. Based on the prompt, the generative AI generates educational content, including visual instructional videos and interactive exercises, and returns the results to the server.

[0965] Step 5:

[0966] The server transmits the generated educational content to the terminal.

[0967] The server transmits the educational content received from the generative AI to the user's device. This content includes learning materials and exercises according to the learning objectives. The device receives this content and displays it to the user.

[0968] Step 6:

[0969] The user studies the educational content and provides feedback.

[0970] Users view and study the educational content provided on their devices. After completing the study, they enter feedback such as satisfaction, level of understanding, and specific areas for improvement into the device's interface. This feedback information is then sent back to the server in JSON format.

[0971] Step 7:

[0972] The server receives and analyzes the feedback.

[0973] The server receives the feedback information sent from the device and stores it in a database. The saved feedback information is analyzed and insights are extracted to be reflected in the next generation of educational content. For example, an action item such as "We need to generate content that includes more specific and simple explanations" can be obtained.

[0974] Step 8:

[0975] The server regenerates the prompt text reflecting the feedback and generates the next educational content.

[0976] The server generates a new prompt based on the feedback analysis results. For example, it might generate a prompt such as, "Please generate educational content on how to solve quadratic equations with more specific and simpler explanations." This prompt is then fed back into the generative AI to generate improved educational content, further improving the user's next learning experience.

[0977] The above is the specific processing flow of this system.

[0978] (Application example 1)

[0979] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0980] Conventional educational systems have had difficulty providing appropriate educational content tailored to individual users' learning needs and levels of understanding. Furthermore, fixed educational content may reduce learning effectiveness because it cannot fully address the specific problems and levels of understanding that users have. Furthermore, there are insufficient means to effectively reflect feedback in the generation of the next educational content, making it impossible to maximize the effectiveness of individualized instruction.

[0981] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0982] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's information processing device, means for collecting and storing user feedback on the educational content displayed on the information processing device, and means for adjusting the next generation of the educational content based on the feedback, thereby providing the user with educational content optimized for the user, thereby improving learning outcomes and increasing user satisfaction.

[0983] "Generative AI" is an advanced AI that uses machine learning and natural language processing technology to generate optimal educational content based on input information provided by users.

[0984] "Personalized educational content" refers to educational materials and learning materials that are customized according to a user's learning goals and learning style.

[0985] "User input information" refers to data about learning goals and learning styles that users provide to the system, and optimized educational content is generated based on this data.

[0986] "Information processing device" refers to a device used by a user, such as a smartphone, smart glasses, or head-mounted display, which can display and operate the generated educational content.

[0987] "Feedback" refers to evaluation information such as satisfaction, level of understanding, and comments provided by users after using educational content, and is reflected in the next content generation.

[0988] A "prompt" refers to text input that provides specific instructions or requests to a generative artificial intelligence to generate the desired educational content.

[0989] "Adjusting the next generation of educational content" refers to the process of optimizing the next generation of educational content based on previous feedback information to provide a better learning experience.

[0990] The present invention is a system for providing users with personalized educational content using generative artificial intelligence, in which a server, a terminal, and a user each play specific roles.

[0991] First, a user logs in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display, and enters information about their learning goals and learning style. For example, a high school student can select "solving quadratic equations" and "visual learning."

[0992] The server receives the information entered by the user and uses a generative AI model to automatically generate personalized educational content. Specific prompts are used in this process. An example of a prompt is as follows:

[0993] User Information:

[0994] Learning Objective: Solving quadratic equations

[0995] Learning Style: Visual Learning

[0996] Use this information to create visual instructional content. Your educational content should include:

[0997] 1. Basic Concepts of Quadratic Equations

[0998] 2. Step-by-step explanation of the solution (visually presented)

[0999] 3. Interactive Exercises

[1000] The generated educational content is sent from the server to the user's terminal, where it is displayed. The user studies the educational content and solves the exercises according to the displayed content.

[1001] After completing the learning, the user inputs feedback regarding their satisfaction and level of understanding. This feedback data is sent back to the server. The server analyzes the collected feedback and reflects it in the creation of the next educational content. This feedback includes an evaluation of how much the user understood the learning content and how easy the explanation was to understand. Another example of feedback could be a comment such as "The explanation was a little difficult."

[1002] This allows the system to provide an optimized educational experience for each user and improve learning outcomes. The software explicitly used includes generative AI models (e.g., OpenAI's GPT-3).

[1003] To maximize the effectiveness of this system, it is important to effectively analyze the feedback data collected from users and optimize the process of adjusting learning content using generative AI. This process will enable the provision of continuously improved educational content to users.

[1004] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1005] Step 1:

[1006] Users log in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display and input information about their learning goals and learning style. This input information includes the learning goal of "solving quadratic equations" and the learning style of "visual learning."

[1007] Input: learning goals, learning styles

[1008] Output: Learning goals and learning style data

[1009] Step 2:

[1010] The terminal transmits the learning goal and learning style data input by the user to the server.

[1011] Input: Learning objectives, learning style data

[1012] Output: Learning objectives and learning style data sent to the server

[1013] Step 3:

[1014] The server receives the user's input information and uses the generative AI model to generate personalized educational content. The server generates a specific prompt sentence and passes it to the generative AI model to obtain the educational content.

[1015] Specific examples of prompts are as follows:

[1016] User Information:

[1017] Learning Objective: Solving quadratic equations

[1018] Learning Style: Visual Learning

[1019] Use this information to create visual instructional content. Your educational content should include:

[1020] 1. Basic Concepts of Quadratic Equations

[1021] 2. Step-by-step explanation of the solution (visually presented)

[1022] 3. Interactive Exercises

[1023] Input: Learning objectives and learning style data

[1024] Output: Personalized educational content

[1025] Step 4:

[1026] The server transmits the generated educational content to the user's terminal.

[1027] Input: personalized educational content

[1028] Output: Delivery of educational content to user devices

[1029] Step 5:

[1030] The terminal displays the received educational content to the user, who then studies the displayed educational content and solves the set exercises.

[1031] Input: Educational content

[1032] Output: Educational content displayed to the user

[1033] Step 6:

[1034] After completing the learning process, users can enter feedback on their device regarding their satisfaction and understanding. Feedback includes user-provided ratings and comments (e.g., "The explanation was a little difficult").

[1035] Input: User feedback

[1036] Output: Feedback data

[1037] Step 7:

[1038] The terminal transmits the feedback data to the server.

[1039] Input: Feedback data

[1040] Output: Feedback data sent to the server

[1041] Step 8:

[1042] The server analyzes the collected feedback and reflects it in the next generation of educational content. This analysis allows for content refinement based on the user's level of understanding and satisfaction.

[1043] Input: Feedback data

[1044] Output: Analysis results for improved educational content generation

[1045] By repeating this process, it is possible to provide users with continuously improved educational content, which helps them learn more effectively and improve their learning outcomes.

[1046] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1047] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content, and further combines an emotion engine to recognize users' emotions and optimize the learning experience. This system is implemented as follows, with the server, terminal, and user each playing a specific role.

[1048] The system's program begins when a user inputs information about their learning goals and learning style through a terminal. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the terminal and provided to the user.

[1049] The role of the emotional engine

[1050] The system incorporates an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotional state by analyzing the user's facial expressions, voice, and operating behavior. The emotional state recognized by the emotion engine is fed back to the generative AI and reflected in the generation of the next educational content and the dynamic adjustment of the current content.

[1051] Program flow and examples

[1052] Example 1: High school English class

[1053] User Actions

[1054] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[1055] Server Operation

[1056] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[1057] Emotion Engine Operation

[1058] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[1059] Device behavior

[1060] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[1061] User behavior (feedback)

[1062] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[1063] Server operation (reflecting feedback)

[1064] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[1065] Example 2: Corporate training programs

[1066] User Actions

[1067] The user (a company's training officer) logs in to the platform using a terminal. After logging in, they input "communication skills" and "team building" as learning objectives to create a training program for new employees. The user then selects "hands-on learning" as the learning style for new employees.

[1068] Server Operation

[1069] The server takes user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[1070] Emotion Engine Operation

[1071] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[1072] Device behavior

[1073] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[1074] User behavior (feedback)

[1075] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[1076] Server operation (reflecting feedback)

[1077] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[1078] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction. Furthermore, by incorporating an emotion engine, dynamic content optimization based on the user's emotional state is possible, providing a richer and more effective learning experience.

[1079] The processing flow will be explained below.

[1080] Example 1: High school English class

[1081] Program processing flow

[1082] Step 1:

[1083] The user logs in to the platform through the terminal, enters the user ID and password for authentication, and if the authentication is successful, the user profile is loaded.

[1084] Step 2:

[1085] The user inputs initial information about their learning goals and learning style into the terminal, such as "English," "improving listening skills," "auditory learning," etc. Once this information is entered, the terminal transmits it to the server.

[1086] Step 3:

[1087] The server stores the received information in a database, which creates a personalized learning profile for each user.

[1088] Step 4:

[1089] The user selects the specific topic they want to study on their device and enters the details, for example, "listening practice," after which the device sends this information to the server.

[1090] Step 5:

[1091] Based on the received topic information, the server sends a request to the generative AI, which then generates customized educational content tailored to the user's learning goals and style.

[1092] Step 6:

[1093] The generative AI sends the generated educational content back to the server, which receives the content and sends it to the user's device.

[1094] Step 7:

[1095] The device receives educational content from the server and displays it to the user, such as audio clips for listening practice or interactive quizzes.

[1096] Step 8:

[1097] The emotion engine monitors the user's reactions, analyzing the user's facial expressions and voice in real time and sending emotional data to the server. For example, it detects distracted facial expressions and tone of voice.

[1098] Step 9:

[1099] The server receives data from the emotion engine and adjusts the content in real time, for example, lowering the difficulty of the content or adding interactive elements if it determines that the user is not concentrating.

[1100] Step 10:

[1101] After completing the learning process, the user enters their satisfaction and understanding in a feedback form. The device then sends this feedback to the server, along with the data collected by the emotion engine.

[1102] Step 11:

[1103] The server analyzes the feedback and emotion data and reflects it in the next generation of educational content. For example, if the user feels that the practice questions are difficult, the generative AI will adjust to provide easier questions for the next content.

[1104] Example 2: Corporate training programs

[1105] Program processing flow

[1106] Step 1:

[1107] The user (a company's training manager) logs into the platform through a terminal. After logging in, they input the initial information for creating a training program. For example, this information may include "communication skills," "team building," and "practical learning." This information is then sent to the server.

[1108] Step 2:

[1109] The server stores the received information in a database and the user profile is updated.

[1110] Step 3:

[1111] The user selects a specific training content and inputs its details, for example, "role-playing" or "group discussion." After inputting, the device sends this information to the server.

[1112] Step 4:

[1113] Based on the received training information, the server sends a request to the generative AI, which then generates customized training materials tailored to the user's training goals and style.

[1114] Step 5:

[1115] The generative AI returns the generated training materials to the server, which receives them and sends them to the user's device.

[1116] Step 6:

[1117] The terminal displays the training materials received from the server, and the training begins, such as a practical workshop or role-playing training.

[1118] Step 7:

[1119] The emotion engine monitors the new employee's reactions, analyzing their facial expressions, tone of voice, and operational behavior, and sends the emotional data to the server. For example, it detects a loss of interest in their facial expressions or tone of voice.

[1120] Step 8:

[1121] The server receives data from the emotion engine and adjusts the training materials in real time, for example by adding new activities if participants' reactions are poor.

[1122] Step 9:

[1123] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[1124] Step 10:

[1125] The server analyzes the feedback and emotion data and reflects it in the generation of the next training materials. For example, if a new employee feels that "role-playing was helpful," the generative AI and emotion engine will adjust the next training materials to include more role-playing.

[1126] This series of steps provides users with an optimized educational experience. The introduction of an emotion engine enables content adjustment in real time, further improving learner engagement and learning outcomes.

[1127] Example 2

[1128] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1129] Conventional online education systems struggle to provide personalized educational content tailored to each user's individual learning needs and learning styles. Furthermore, they are unable to grasp the user's emotional state during learning and dynamically adjust educational content accordingly, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to reflect user feedback in the generation of the next educational content. A new system is needed to address these issues.

[1130] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1131] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and storing user feedback on the educational content displayed on the terminal, means for analyzing the user's emotional state, and means for dynamically adjusting the content based on the analyzed emotional information, thereby making it possible to provide a personalized educational experience according to the user's individual learning needs and emotional state.

[1132] "Generative AI" refers to an AI system that generates natural language and provides support for problem-solving based on user input and prompts.

[1133] "Personalized educational content" means educational materials and learning programs that are customized to a user's specific learning goals, learning style, and individual needs.

[1134] "User's terminal" refers to a device, such as a computer, tablet, or smartphone, that a user uses to access the system and use educational content.

[1135] "Feedback" refers to opinions and impressions such as satisfaction and understanding provided by users after using educational content.

[1136] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and operating behavior to recognize their emotional state in real time.

[1137] "Dynamic adjustment" refers to changing the content and difficulty of educational content in real time based on the user's emotional state and feedback.

[1138] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content and, by combining it with an emotion engine, recognizes the user's emotions and optimizes the learning experience. This system is implemented by a server, a terminal, and a user, each playing a specific role.

[1139] Hardware and software used

[1140] The system includes the following hardware and software:

[1141] Server: The server is responsible for processing and storing data, running the generative artificial intelligence and emotion engine. A specific example would be a cloud computing platform (AWS, Google Cloud, etc.).

[1142] Terminal: A terminal is a device through which a user accesses the system, and can include a PC, tablet, smartphone, etc.

[1143] Generative AI: Natural language processing models (e.g., GPT-4, BERT) are used as generative AI.

[1144] Emotion engine: Uses facial expression recognition software and voice analysis software (e.g., Azure Emotion API, Facial Recognition API) to analyze the user's emotional state.

[1145] Specific examples of program processing

[1146] Example 1: High school English class

[1147] User Actions

[1148] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[1149] Server Operation

[1150] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[1151] Emotion Engine Operation

[1152] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[1153] Device behavior

[1154] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[1155] User behavior (feedback)

[1156] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[1157] Server operation (reflecting feedback)

[1158] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[1159] Example 2: Corporate training programs

[1160] User Actions

[1161] The user (a company training officer) logs into the platform using a terminal and inputs "communication skills" and "team building" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[1162] Server Operation

[1163] The server receives user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[1164] Emotion Engine Operation

[1165] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[1166] Device behavior

[1167] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[1168] User behavior (feedback)

[1169] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[1170] Server operation (reflecting feedback)

[1171] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[1172] Specific prompt examples

[1173] 1. High school English classes

[1174] "Generate audio clips and interactive quizzes to improve listening skills for high school students. My learning style is auditory."

[1175] 2. Corporate Training Programs

[1176] "Generate training materials for new employees that include hands-on workshops and role-playing that strengthen communication skills and team building."

[1177] This system allows users to enjoy an educational experience that is tailored to their individual learning needs and emotional state, which is expected to improve learning outcomes and satisfaction.

[1178] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1179] Step 1:

[1180] A user logs into the platform

[1181] Specific operation: The user launches the web browser on the device and accesses the platform's login page. On the login screen, the user enters the username and password and clicks the "Login" button.

[1182] Input: Username, Password

[1183] Output: Login successful, user data loaded

[1184] Step 2:

[1185] Users input their learning goals and learning styles

[1186] Specific operation: After logging in, the user enters their learning goal (e.g., "Improve listening skills") and learning style (e.g., "Auditory learning") into the form displayed on the homepage and clicks the submit button.

[1187] Input: learning goals, learning styles

[1188] Output: Sending user input information, receiving data on the server

[1189] Step 3:

[1190] The server receives the input information

[1191] Specific operations: The server receives the learning objectives and learning style information entered by the user and prepares appropriate processing. It receives the HTTP request and stores it in the database.

[1192] Input: User's learning goals, learning style

[1193] Output: Learning objectives and learning styles stored in a database

[1194] Step 4:

[1195] The server generates educational content using generative artificial intelligence

[1196] How it works: The server accesses the API of a generative artificial intelligence (e.g., GPT-4) to create prompts based on the user's learning goals and style, and then sends them to the AI ​​model to generate customized educational content.

[1197] Input: Prompt statement (e.g., "Generate an audio clip to improve your listening skills.")

[1198] Output: Customized educational content (audio clips, quizzes, etc.)

[1199] Step 5:

[1200] The device receives the educational content

[1201] Specific operation: The server sends the generated educational content to the terminal, which receives the content and displays it on the user interface.

[1202] Input: Customized educational content

[1203] Output: Educational content displayed on the device

[1204] Step 6:

[1205] The emotion engine collects user emotion data

[1206] Specific operation: While the user is using educational content, the device's camera and microphone are used to collect the user's facial expressions and voice data, which are then analyzed by the emotion engine.

[1207] Input: User's facial expressions and voice data

[1208] Output: Parsed emotion data

[1209] Step 7:

[1210] The device feeds back the collected data to the server.

[1211] Specific operation: The emotion engine sends collected data from the device to the server, which receives the data and stores it for the next content generation.

[1212] Input: Parsed emotion data

[1213] Output: Emotion data stored on the server

[1214] Step 8:

[1215] The server adjusts the content based on the feedback.

[1216] Specific behavior: The server analyzes the received emotional data and adjusts the current educational content in real time, for example, changing the task to an easier one if the user is tired.

[1217] Input: Feedback data, emotion data

[1218] Output: Tailored educational content

[1219] Step 9:

[1220] User enters feedback

[1221] Specific operation: After completing the learning, the user inputs and submits feedback on their satisfaction and understanding into the device. This data is sent to the server.

[1222] Input: Feedback (satisfaction, understanding)

[1223] output: Feedback data stored on the server

[1224] Step 10:

[1225] The server analyzes the feedback and reflects it in the next content generation.

[1226] Specific operation: The server combines and analyzes the user's feedback and emotional data, and reflects the results in the next educational content generation. Additionally, as an improvement, supplementary materials are added if the level of understanding in a particular area is low.

[1227] Input: Feedback, emotion data

[1228] Output: Improved educational content for next time learning

[1229] (Application example 2)

[1230] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1231] Conventional educational content delivery systems have the problem of being difficult to personalize content that takes into account each user's individual learning style and emotional state, making it difficult to maintain motivation to learn and maximize educational effectiveness.

[1232] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating personalized educational content based on user input information using a generative artificial intelligence; means for providing the generated educational content to the user's terminal; means for collecting and saving user feedback on the educational content displayed on the terminal; means for collecting user emotion data using an emotion engine that recognizes the user's emotional state; and means for feeding back the emotion data recognized by the emotion engine to the generative artificial intelligence and reflecting it in dynamic adjustment of the educational content. This makes it possible to provide optimal educational content according to the user's individual learning style and real-time emotional state.

[1233] "Generative AI" is an AI technology that generates content to perform specific tasks based on user input.

[1234] "Educational Content" refers to customized educational and learning materials provided to assist users in their learning.

[1235] A "terminal" is a device that a user uses to view educational content and enter feedback.

[1236] "Feedback" refers to the user providing information about their impressions of educational content and their level of understanding.

[1237] An "emotion engine" is a technology that analyzes data such as the user's facial expressions and voice to recognize the user's emotional state.

[1238] "Emotion data" is data relating to the user's emotional state as recognized by the emotion engine.

[1239] "Dynamic adjustment" refers to the process of changing the content and difficulty of educational content in real time based on collected feedback and sentiment data.

[1240] An "interface" is a function that allows users to input information about their learning goals and learning styles.

[1241] The present invention is a system for providing personalized educational content to users, which is implemented with a server, a terminal, and a user each playing a specific role.

[1242] Server Operation

[1243] The server uses generative artificial intelligence to generate personalized educational content based on the learning goals and learning style entered by the user. Examples of generative AI models used in this process include natural language processing models such as GPT-2. The generated educational content is sent to the device and provided to the user. The server also collects user feedback and emotional data sent from the emotion engine, and reflects this in the next educational content generation.

[1244] Device behavior

[1245] Users log in to the system using their devices and input information about their learning goals and learning styles. The devices then send the information to the server, which then displays personalized educational content. The devices also support an emotion engine that uses a built-in camera and microphone to analyze the user's facial expressions and voice to collect emotional data. This allows the obtained emotional data to be fed back to the server in real time.

[1246] User Actions

[1247] Users input information based on their learning goals and learning style through an interface displayed on their device. This information is sent to the server, and personalized educational content is generated by generative artificial intelligence. Users can provide feedback on the educational content provided, which is reflected in the next content generation. Emotional data obtained during learning is also sent to the server and used to generate the next content.

[1248] Hardware and software used

[1249] This system uses devices such as smartphones, tablets, and PCs. The emotion engine is implemented using image processing libraries such as OpenCV and machine learning frameworks such as TensorFlow and Keras. The generative artificial intelligence part uses GPT-2 and other natural language processing models.

[1250] Specific examples

[1251] Example 1: High school English class

[1252] A user (high school student) logs in to a device and enters "improving listening skills" as their learning goal. They also select "auditory learning" as their preferred learning style. The server receives this information and uses generative artificial intelligence to generate customized educational content to improve listening skills. This content includes audio clips for listening practice and interactive quizzes. While learning, an emotion engine analyzes the user's facial expressions and voice, collecting emotional data in real time, such as when they are not concentrating, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more appropriate learning materials.

[1253] Prompt Sentence Examples

[1254] "I'm a high school student who wants to improve my listening skills. Please provide content with interesting audio clips and quizzes."

[1255] Example 2: Corporate training programs

[1256] The user (corporate training manager) logs in to the device and enters "communication skills" and "team building" as learning objectives. The server receives this information and uses generative artificial intelligence to generate customized educational content. This content includes practical workshops and role-playing. During the learning process, an emotion engine analyzes the new employee's facial expressions and reactions, collecting emotional data in real time, such as when they lose interest, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more effective training materials.

[1257] Prompt Sentence Examples

[1258] "Create a training program for your new employees by providing customized content on communication skills and team building with hands-on learning methods."

[1259] The above is a specific embodiment of the present invention.

[1260] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1261] Step 1:

[1262] Users log in to their devices and enter information about their learning goals and learning style. At this time, they can select specific subjects, skill goals, and learning methods (e.g., "English," "improving listening skills," "auditory learning"). This input information is sent to the server.

[1263] Input: Information about the user's learning goals and learning style

[1264] Output: Learning objectives and learning style information sent to the server

[1265] Step 2:

[1266] The server uses a generative AI model to generate personalized educational content based on the user's input, using natural language processing models such as GPT-2 to generate optimal content based on the prompt.

[1267] Input: Learning objectives and learning style information

[1268] Output: Generated personalized educational content

[1269] Step 3:

[1270] The server transmits the generated educational content to the terminal, which receives it and displays it to the user.

[1271] Input: Generated educational content

[1272] Output: Educational content displayed on the device

[1273] Step 4:

[1274] The user studies the educational content displayed on the device, which uses a built-in camera and microphone to capture the user's facial expressions and voice in real time and collects the user's emotional data using an emotion engine.

[1275] Input: User's facial expression and voice data

[1276] Output: Emotion data recognized by the emotion engine

[1277] Step 5:

[1278] The emotion engine sends the recognized emotion data to the server, which collects it and uses it to dynamically adjust the current educational content and generate the next educational content.

[1279] Input: Emotion data recognized by the emotion engine

[1280] Output: Emotion data sent to the server

[1281] Step 6:

[1282] After learning the educational content, users provide feedback on their satisfaction and understanding of the content, which is sent from their devices to the server.

[1283] Input: User feedback

[1284] Output: Feedback sent to the server

[1285] Step 7:

[1286] The server analyzes the collected feedback and emotional data and inputs it as feedback into the generative AI model, which then optimizes the next educational content to be more suitable for the user.

[1287] Input: User feedback and sentiment data

[1288] Output: Information to be reflected in the next educational content generation

[1289] Through these steps, the present invention provides users with an individually optimized educational experience, improving learning outcomes and satisfaction.

[1290] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1291] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1292] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1293] [Fourth embodiment]

[1294] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1295] 7, a 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.

[1296] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1297] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1298] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1299] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1300] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1301] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1302] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1303] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1304] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1305] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1306] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1307] The present invention is a system for providing users with personalized educational content using generative artificial intelligence. This system is implemented as follows, with a server, a terminal, and a user each playing a specific role.

[1308] The system's program begins when a user inputs information about their learning goals and learning style through their device. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the device and provided to the user. The user studies the content and then provides feedback. This feedback is sent back to the server and reflected in the next generation of educational content. This series of steps makes it possible to provide the user with an optimized educational experience.

[1309] Example 1: High school math class

[1310] User Actions

[1311] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "Mathematics" and enters "Solution of Quadratic Equations" as the specific learning goal. The user also selects "Visual Learning" as the preferred learning style.

[1312] Server Operation

[1313] The server receives user input and uses generative artificial intelligence to generate customized educational content on solving quadratic equations, including visual instructional videos and interactive exercises.

[1314] Device behavior

[1315] The terminal receives the educational content sent from the server and displays it to the user, who then watches the content and solves the exercises.

[1316] User behavior (feedback)

[1317] After completing the study, the user inputs feedback on their satisfaction and understanding, which is then sent from the device to the server.

[1318] Server operation (reflecting feedback)

[1319] The server analyzes the user's feedback and reflects it in the next content generation. For example, if the user feels that the explanation is difficult, the generative AI will adjust the next content to provide a more concise and easy-to-understand explanation.

[1320] Example 2: Corporate training programs

[1321] User Actions

[1322] The user (a company's training officer) logs in to the platform using a terminal. After logging in, he / she enters "project management" and "agile methods" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[1323] Server Operation

[1324] The server takes user input and uses generative artificial intelligence to generate customized training materials on agile methods, including hands-on workshops and simulation training.

[1325] Device behavior

[1326] The terminal receives the training materials sent from the server and provides them to the user, who then uses the training materials to provide training to new employees.

[1327] User behavior (feedback)

[1328] After the training is completed, the trainer collects feedback from the new employees and sends it to the server from their devices, including the usefulness of the training and areas for improvement.

[1329] Server operation (reflecting feedback)

[1330] The server analyzes the collected feedback and reflects it in the generation of the next training materials. For example, if a new employee feels that "more practical examples are needed," the generative AI will adjust the next training materials to include more practical examples.

[1331] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction.

[1332] The processing flow will be explained below.

[1333] Step 1:

[1334] The user logs in to the platform through the terminal. The user enters the user ID and password for authentication. If the login is successful, the user profile is loaded.

[1335] Step 2:

[1336] The user inputs initial information about their learning goals and learning style into the terminal, including the subject, topic, learning goals, and preferred learning style (visual, auditory, movement, etc.). Once the information is input, the terminal sends it to the server.

[1337] Step 3:

[1338] The server stores the received user information in a database, which creates a personalized learning profile for each user.

[1339] Step 4:

[1340] Users select the specific topic they want to learn about on their device and enter details about it, after which the device sends this information to the server.

[1341] Step 5:

[1342] Based on the received topic information, the server sends a request to the generative AI, which then generates educational content customized to the user's learning goals and learning style.

[1343] Step 6:

[1344] The generative AI returns the generated customized educational content to the server, which receives the content and sends it to the user's device.

[1345] Step 7:

[1346] The device displays educational content received from the server. Users use this content to learn. Examples of content include visual instructional videos, interactive exercises, and simulations.

[1347] Step 8:

[1348] After the user has completed the learning, they can input feedback via the device, including their satisfaction with the learning content, their level of understanding, and areas for improvement.

[1349] Step 9:

[1350] The device sends the user's feedback to the server, which stores the received feedback in a database and reflects it in the generation of the next learning content.

[1351] Step 10:

[1352] The server analyzes the feedback and uses it as data to generate new learning content. The generative AI also uses this feedback to optimize the next content generation process.

[1353] This sequence of steps provides an optimized learning experience for the user.

[1354] Example 1

[1355] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1356] Conventional educational content delivery systems have struggled to effectively provide content tailored to individual users' learning goals and learning styles. Furthermore, mechanisms for incorporating feedback into subsequent content generation are inadequate, making it impossible to maximize users' learning effectiveness and satisfaction. Furthermore, systems that effectively utilize generative artificial intelligence to generate personalized educational content require the generation and effective use of prompt sentences. The present invention aims to solve these problems and provide users with educational content optimized for their needs.

[1357] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1358] In this invention, the server includes means for generating personalized educational content based on user input information using a generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and saving user feedback on the educational content displayed on the terminal, means for analyzing the feedback and reflecting it in the generation of the next educational content, and means for generating prompt sentences based on the user input information and inputting them into the generative artificial intelligence. This makes it possible to provide highly personalized educational content tailored to the needs of each individual user, thereby improving learning effectiveness and satisfaction.

[1359] "Generative AI" is an AI technology that can generate adaptive and personalized responses and content based on user input.

[1360] "Educational content" means teaching materials, resources, questions, and other learning aids designed to help learners acquire specific knowledge or skills.

[1361] A "terminal" is an electronic device that allows a user to access the system, input learning objectives, display educational content, and provide feedback.

[1362] "Feedback" is information that users provide to the system, such as their opinions on educational content, their level of satisfaction, their level of understanding, and areas for improvement.

[1363] A "prompt sentence" is a sentence that instructs a generative artificial intelligence to produce a specific output, and is generated based on information input by the user.

[1364] "Learning objectives" are specific educational goals or themes that a user wants to achieve.

[1365] "Learning style" refers to the type of teaching method or learning method that a user prefers, including visual learning, hands-on learning, etc.

[1366] "Personalization" means optimizing educational content and services to suit the specific needs and preferences of individual users.

[1367] "Analysis" is the act of digging deep into collected feedback and other data to extract insights.

[1368] This invention is a system that uses generative artificial intelligence to provide users with personalized educational content. In this system, the server, terminal, and user each play specific roles, and the specific process for implementing the invention is as follows:

[1369] First, a user accesses the platform using a terminal and inputs information about their learning goals and learning style. For example, if a user wants to learn how to solve quadratic equations in mathematics, they can input "how to solve quadratic equations" as their learning goal and select "visual learning" as their preferred learning style.

[1370] The device then sends the user's input information to a server, which uses generative artificial intelligence (such as OpenAI's GPT-3) to create a prompt to generate educational content optimized for the user's learning goals and style. An example prompt might be, "Generate educational content that includes visual explanation videos and interactive practice problems on how to solve quadratic equations in mathematics."

[1371] The server inputs the generated prompt sentences into a generative artificial intelligence (AI) to generate educational content customized for the user. This educational content includes visual instruction videos, interactive exercises, etc. The generated educational content is sent from the server to the device, which displays it to the user. The user then views the educational content on the device and works on the exercises.

[1372] After completing the learning process, the user inputs feedback on the educational content into the server from their device. The feedback includes satisfaction, level of understanding, and areas for improvement, and specific comments such as "I found the explanation in this part difficult to understand" can be entered.

[1373] The server receives the feedback sent from the device and analyzes it. Based on the analysis results, it reflects the results in the next educational content generation. Through this process, the generative AI generates prompts that reflect the feedback, and the next time, more personalized content is provided.

[1374] To give a specific example, when a high school student is learning "how to solve quadratic equations" in a mathematics class, the process proceeds as follows: The user (high school student) uses a device to select the "Mathematics" subject, enters "how to solve quadratic equations" as the learning goal, and selects "visual learning" as the preferred learning style. The user's input information is sent to the server, which then sends a prompt to the generative AI such as "Please generate visual educational content on how to solve quadratic equations." The educational content generated by the generative AI is sent to the device, and the user studies it. After completing the study, the feedback entered by the user is reflected in the next content generation.

[1375] This series of steps allows users to receive an optimized educational experience, increasing learning effectiveness and satisfaction.

[1376] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1377] Step 1:

[1378] The user accesses the platform using a terminal and logs in.

[1379] The user enters their user ID and password on the device's input screen and sends the authentication information to the server. The server receives the authentication information, performs user authentication, and returns the authentication result to the device. If user authentication is successful, the user can proceed to the next step.

[1380] Step 2:

[1381] The user enters information about their learning goals and learning style.

[1382] Through the device's interface, users input the content they want to learn (e.g., "How to solve quadratic equations") as their learning goal. They also select their preferred learning style, such as visual learning or hands-on learning. The input information is sent from the device to the server, which then sends it to the server as JSON-formatted data, where it is stored in a database.

[1383] Step 3:

[1384] The server analyzes the user's input and generates a prompt.

[1385] The server analyzes the received JSON-formatted user information and creates a prompt to generate educational content. For example, it generates a prompt such as, "Please generate educational content that includes a visual explanation video and interactive practice problems on how to solve quadratic equations in mathematics." This prompt is then input into the generative artificial intelligence.

[1386] Step 4:

[1387] The server generates educational content using generative artificial intelligence.

[1388] The server uses the generated prompt to request a generative AI (e.g., GPT-3) to generate educational content. Based on the prompt, the generative AI generates educational content, including visual instructional videos and interactive exercises, and returns the results to the server.

[1389] Step 5:

[1390] The server transmits the generated educational content to the terminal.

[1391] The server transmits the educational content received from the generative AI to the user's device. This content includes learning materials and exercises according to the learning objectives. The device receives this content and displays it to the user.

[1392] Step 6:

[1393] The user studies the educational content and provides feedback.

[1394] Users view and study the educational content provided on their devices. After completing the study, they enter feedback such as satisfaction, level of understanding, and specific areas for improvement into the device's interface. This feedback information is then sent back to the server in JSON format.

[1395] Step 7:

[1396] The server receives and analyzes the feedback.

[1397] The server receives the feedback information sent from the device and stores it in a database. The saved feedback information is analyzed and insights are extracted to be reflected in the next generation of educational content. For example, an action item such as "We need to generate content that includes more specific and simple explanations" can be obtained.

[1398] Step 8:

[1399] The server regenerates the prompt text reflecting the feedback and generates the next educational content.

[1400] The server generates a new prompt based on the feedback analysis results. For example, it might generate a prompt such as, "Please generate educational content on how to solve quadratic equations with more specific and simpler explanations." This prompt is then fed back into the generative AI to generate improved educational content, further improving the user's next learning experience.

[1401] The above is the specific processing flow of this system.

[1402] (Application example 1)

[1403] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1404] Conventional educational systems have had difficulty providing appropriate educational content tailored to individual users' learning needs and levels of understanding. Furthermore, fixed educational content may reduce learning effectiveness because it cannot fully address the specific problems and levels of understanding that users have. Furthermore, there are insufficient means to effectively reflect feedback in the generation of the next educational content, making it impossible to maximize the effectiveness of individualized instruction.

[1405] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1406] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's information processing device, means for collecting and storing user feedback on the educational content displayed on the information processing device, and means for adjusting the next generation of the educational content based on the feedback, thereby providing the user with educational content optimized for the user, thereby improving learning outcomes and increasing user satisfaction.

[1407] "Generative AI" is an advanced AI that uses machine learning and natural language processing technology to generate optimal educational content based on input information provided by users.

[1408] "Personalized educational content" refers to educational materials and learning materials that are customized according to a user's learning goals and learning style.

[1409] "User input information" refers to data about learning goals and learning styles that users provide to the system, and optimized educational content is generated based on this data.

[1410] "Information processing device" refers to a device used by a user, such as a smartphone, smart glasses, or head-mounted display, which can display and operate the generated educational content.

[1411] "Feedback" refers to evaluation information such as satisfaction, level of understanding, and comments provided by users after using educational content, and is reflected in the next content generation.

[1412] A "prompt" refers to text input that provides specific instructions or requests to a generative artificial intelligence to generate the desired educational content.

[1413] "Adjusting the next generation of educational content" refers to the process of optimizing the next generation of educational content based on previous feedback information to provide a better learning experience.

[1414] The present invention is a system for providing users with personalized educational content using generative artificial intelligence, in which a server, a terminal, and a user each play specific roles.

[1415] First, a user logs in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display, and enters information about their learning goals and learning style. For example, a high school student can select "solving quadratic equations" and "visual learning."

[1416] The server receives the information entered by the user and uses a generative AI model to automatically generate personalized educational content. Specific prompts are used in this process. An example of a prompt is as follows:

[1417] User Information:

[1418] Learning Objective: Solving quadratic equations

[1419] Learning Style: Visual Learning

[1420] Use this information to create visual instructional content. Your educational content should include:

[1421] 1. Basic Concepts of Quadratic Equations

[1422] 2. Step-by-step explanation of the solution (visually presented)

[1423] 3. Interactive Exercises

[1424] The generated educational content is sent from the server to the user's terminal, where it is displayed. The user studies the educational content and solves the exercises according to the displayed content.

[1425] After completing the learning, the user inputs feedback regarding their satisfaction and level of understanding. This feedback data is sent back to the server. The server analyzes the collected feedback and reflects it in the creation of the next educational content. This feedback includes an evaluation of how much the user understood the learning content and how easy the explanation was to understand. Another example of feedback could be a comment such as "The explanation was a little difficult."

[1426] This allows the system to provide an optimized educational experience for each user and improve learning outcomes. The software explicitly used includes generative AI models (e.g., OpenAI's GPT-3).

[1427] To maximize the effectiveness of this system, it is important to effectively analyze the feedback data collected from users and optimize the process of adjusting learning content using generative AI. This process will enable the provision of continuously improved educational content to users.

[1428] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1429] Step 1:

[1430] Users log in to the system using an information processing device such as a smartphone, smart glasses, or head-mounted display and input information about their learning goals and learning style. This input information includes the learning goal of "solving quadratic equations" and the learning style of "visual learning."

[1431] Input: learning goals, learning styles

[1432] Output: Learning goals and learning style data

[1433] Step 2:

[1434] The terminal transmits the learning goal and learning style data input by the user to the server.

[1435] Input: Learning objectives, learning style data

[1436] Output: Learning objectives and learning style data sent to the server

[1437] Step 3:

[1438] The server receives the user's input information and uses the generative AI model to generate personalized educational content. The server generates a specific prompt sentence and passes it to the generative AI model to obtain the educational content.

[1439] Specific examples of prompts are as follows:

[1440] User Information:

[1441] Learning Objective: Solving quadratic equations

[1442] Learning Style: Visual Learning

[1443] Use this information to create visual instructional content. Your educational content should include:

[1444] 1. Basic Concepts of Quadratic Equations

[1445] 2. Step-by-step explanation of the solution (visually presented)

[1446] 3. Interactive Exercises

[1447] Input: Learning objectives and learning style data

[1448] Output: Personalized educational content

[1449] Step 4:

[1450] The server transmits the generated educational content to the user's terminal.

[1451] Input: personalized educational content

[1452] Output: Delivery of educational content to user devices

[1453] Step 5:

[1454] The terminal displays the received educational content to the user, who then studies the displayed educational content and solves the set exercises.

[1455] Input: Educational content

[1456] Output: Educational content displayed to the user

[1457] Step 6:

[1458] After completing the learning process, users can enter feedback on their device regarding their satisfaction and understanding. Feedback includes user-provided ratings and comments (e.g., "The explanation was a little difficult").

[1459] Input: User feedback

[1460] Output: Feedback data

[1461] Step 7:

[1462] The terminal transmits the feedback data to the server.

[1463] Input: Feedback data

[1464] Output: Feedback data sent to the server

[1465] Step 8:

[1466] The server analyzes the collected feedback and reflects it in the next generation of educational content. This analysis allows for content refinement based on the user's level of understanding and satisfaction.

[1467] Input: Feedback data

[1468] Output: Analysis results for improved educational content generation

[1469] By repeating this process, it is possible to provide users with continuously improved educational content, which helps them learn more effectively and improve their learning outcomes.

[1470] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1471] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content, and further combines an emotion engine to recognize users' emotions and optimize the learning experience. This system is implemented as follows, with the server, terminal, and user each playing a specific role.

[1472] The system's program begins when a user inputs information about their learning goals and learning style through a terminal. The server receives this information and uses generative artificial intelligence to generate customized educational content based on the user's information. The generated educational content is then sent to the terminal and provided to the user.

[1473] The role of the emotional engine

[1474] The system incorporates an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotional state by analyzing the user's facial expressions, voice, and operating behavior. The emotional state recognized by the emotion engine is fed back to the generative AI and reflected in the generation of the next educational content and the dynamic adjustment of the current content.

[1475] Program flow and examples

[1476] Example 1: High school English class

[1477] User Actions

[1478] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[1479] Server Operation

[1480] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[1481] Emotion Engine Operation

[1482] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[1483] Device behavior

[1484] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[1485] User behavior (feedback)

[1486] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[1487] Server operation (reflecting feedback)

[1488] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[1489] Example 2: Corporate training programs

[1490] User Actions

[1491] The user (a company's training officer) logs in to the platform using a terminal. After logging in, they input "communication skills" and "team building" as learning objectives to create a training program for new employees. The user then selects "hands-on learning" as the learning style for new employees.

[1492] Server Operation

[1493] The server takes user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[1494] Emotion Engine Operation

[1495] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[1496] Device behavior

[1497] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[1498] User behavior (feedback)

[1499] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[1500] Server operation (reflecting feedback)

[1501] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[1502] In this way, the present invention provides an educational experience that is optimized for each individual learner, improving learning outcomes and satisfaction. Furthermore, by incorporating an emotion engine, dynamic content optimization based on the user's emotional state is possible, providing a richer and more effective learning experience.

[1503] The processing flow will be explained below.

[1504] Example 1: High school English class

[1505] Program processing flow

[1506] Step 1:

[1507] The user logs in to the platform through the terminal, enters the user ID and password for authentication, and if the authentication is successful, the user profile is loaded.

[1508] Step 2:

[1509] The user inputs initial information about their learning goals and learning style into the terminal, such as "English," "improving listening skills," "auditory learning," etc. Once this information is entered, the terminal transmits it to the server.

[1510] Step 3:

[1511] The server stores the received information in a database, which creates a personalized learning profile for each user.

[1512] Step 4:

[1513] The user selects the specific topic they want to study on their device and enters the details, for example, "listening practice," after which the device sends this information to the server.

[1514] Step 5:

[1515] Based on the received topic information, the server sends a request to the generative AI, which then generates customized educational content tailored to the user's learning goals and style.

[1516] Step 6:

[1517] The generative AI sends the generated educational content back to the server, which receives the content and sends it to the user's device.

[1518] Step 7:

[1519] The device receives educational content from the server and displays it to the user, such as audio clips for listening practice or interactive quizzes.

[1520] Step 8:

[1521] The emotion engine monitors the user's reactions, analyzing the user's facial expressions and voice in real time and sending emotional data to the server. For example, it detects distracted facial expressions and tone of voice.

[1522] Step 9:

[1523] The server receives data from the emotion engine and adjusts the content in real time, for example, lowering the difficulty of the content or adding interactive elements if it determines that the user is not concentrating.

[1524] Step 10:

[1525] After completing the learning process, the user enters their satisfaction and understanding in a feedback form. The device then sends this feedback to the server, along with the data collected by the emotion engine.

[1526] Step 11:

[1527] The server analyzes the feedback and emotion data and reflects it in the next generation of educational content. For example, if the user feels that the practice questions are difficult, the generative AI will adjust to provide easier questions for the next content.

[1528] Example 2: Corporate training programs

[1529] Program processing flow

[1530] Step 1:

[1531] The user (a company's training manager) logs into the platform through a terminal. After logging in, they input the initial information for creating a training program. For example, this information may include "communication skills," "team building," and "practical learning." This information is then sent to the server.

[1532] Step 2:

[1533] The server stores the received information in a database and the user profile is updated.

[1534] Step 3:

[1535] The user selects a specific training content and inputs its details, for example, "role-playing" or "group discussion." After inputting, the device sends this information to the server.

[1536] Step 4:

[1537] Based on the received training information, the server sends a request to the generative AI, which then generates customized training materials tailored to the user's training goals and style.

[1538] Step 5:

[1539] The generative AI returns the generated training materials to the server, which receives them and sends them to the user's device.

[1540] Step 6:

[1541] The terminal displays the training materials received from the server, and the training begins, such as a practical workshop or role-playing training.

[1542] Step 7:

[1543] The emotion engine monitors the new employee's reactions, analyzing their facial expressions, tone of voice, and operational behavior, and sends the emotional data to the server. For example, it detects a loss of interest in their facial expressions or tone of voice.

[1544] Step 8:

[1545] The server receives data from the emotion engine and adjusts the training materials in real time, for example by adding new activities if participants' reactions are poor.

[1546] Step 9:

[1547] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[1548] Step 10:

[1549] The server analyzes the feedback and emotion data and reflects it in the generation of the next training materials. For example, if a new employee feels that "role-playing was helpful," the generative AI and emotion engine will adjust the next training materials to include more role-playing.

[1550] This series of steps provides users with an optimized educational experience. The introduction of an emotion engine enables content adjustment in real time, further improving learner engagement and learning outcomes.

[1551] Example 2

[1552] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1553] Conventional online education systems struggle to provide personalized educational content tailored to each user's individual learning needs and learning styles. Furthermore, they are unable to grasp the user's emotional state during learning and dynamically adjust educational content accordingly, resulting in insufficient learning effectiveness. Furthermore, they lack the functionality to reflect user feedback in the generation of the next educational content. A new system is needed to address these issues.

[1554] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1555] In this invention, the server includes means for generating personalized educational content based on user input information using generative artificial intelligence, means for providing the generated educational content to the user's terminal, means for collecting and storing user feedback on the educational content displayed on the terminal, means for analyzing the user's emotional state, and means for dynamically adjusting the content based on the analyzed emotional information, thereby making it possible to provide a personalized educational experience according to the user's individual learning needs and emotional state.

[1556] "Generative AI" refers to an AI system that generates natural language and provides support for problem-solving based on user input and prompts.

[1557] "Personalized educational content" means educational materials and learning programs that are customized to a user's specific learning goals, learning style, and individual needs.

[1558] "User's terminal" refers to a device, such as a computer, tablet, or smartphone, that a user uses to access the system and use educational content.

[1559] "Feedback" refers to opinions and impressions such as satisfaction and understanding provided by users after using educational content.

[1560] An "emotion engine" is software or hardware that analyzes a user's facial expressions, voice, and operating behavior to recognize their emotional state in real time.

[1561] "Dynamic adjustment" refers to changing the content and difficulty of educational content in real time based on the user's emotional state and feedback.

[1562] The present invention is a system that uses generative artificial intelligence to provide users with personalized educational content and, by combining it with an emotion engine, recognizes the user's emotions and optimizes the learning experience. This system is implemented by a server, a terminal, and a user, each playing a specific role.

[1563] Hardware and software used

[1564] The system includes the following hardware and software:

[1565] Server: The server is responsible for processing and storing data, running the generative artificial intelligence and emotion engine. A specific example would be a cloud computing platform (AWS, Google Cloud, etc.).

[1566] Terminal: A terminal is a device through which a user accesses the system, and can include a PC, tablet, smartphone, etc.

[1567] Generative AI: Natural language processing models (e.g., GPT-4, BERT) are used as generative AI.

[1568] Emotion engine: Uses facial expression recognition software and voice analysis software (e.g., Azure Emotion API, Facial Recognition API) to analyze the user's emotional state.

[1569] Specific examples of program processing

[1570] Example 1: High school English class

[1571] User Actions

[1572] A user (high school student) logs in to the platform using a terminal. After logging in, the user selects the subject "English" and enters "improving listening skills" as the learning goal. The user also selects "auditory learning" as the preferred learning style.

[1573] Server Operation

[1574] The server receives user input and uses generative artificial intelligence to generate customized educational content for improving listening skills, including audio clips for listening practice and interactive quizzes.

[1575] Emotion Engine Operation

[1576] As the user progresses with their learning, the emotion engine analyzes their facial expressions and voice in real time. For example, if the user looks distracted, the emotion engine will detect this and send feedback to the server.

[1577] Device behavior

[1578] The device displays educational content sent from the server. The user watches the content and solves practice problems. The emotion engine records the user's facial expressions and reactions and adjusts the difficulty and content of the content at the appropriate time.

[1579] User behavior (feedback)

[1580] After completing the learning process, the user enters feedback on their satisfaction and understanding, which is then sent from the device to the server, along with data collected by the emotion engine.

[1581] Server operation (reflecting feedback)

[1582] The server analyzes the user's feedback and the emotion engine's data and reflects it in the next content generation. For example, if the user feels that the exercises are too difficult, the generative AI and emotion engine will adjust the next content to provide easier exercises.

[1583] Example 2: Corporate training programs

[1584] User Actions

[1585] The user (a company training officer) logs into the platform using a terminal and inputs "communication skills" and "team building" as learning objectives to create a training program for new employees. The user selects "hands-on learning" as the learning style for new employees.

[1586] Server Operation

[1587] The server receives user input and uses generative artificial intelligence to generate customized training materials on communication skills and team building, including hands-on workshops and role-playing.

[1588] Emotion Engine Operation

[1589] During the training, the emotion engine analyzes the new employee's facial expressions and reactions. For example, if the new employee shows signs of losing interest during the training, the emotion engine detects this and sends feedback to the server.

[1590] Device behavior

[1591] The terminal receives the training materials sent from the server and provides them to the user. The user uses the training materials to train new employees. The emotion engine dynamically adjusts the training materials according to the new employees' reactions.

[1592] User behavior (feedback)

[1593] After the training is completed, the trainer collects feedback from the new employee and sends it to the server from the terminal, along with the data collected by the emotion engine.

[1594] Server operation (reflecting feedback)

[1595] The server analyzes the collected feedback and emotion engine data and reflects it in the generation of the next training materials. For example, if a new employee feels that the workshop was helpful, the generative AI and emotion engine will adjust the next training materials to include more workshops.

[1596] Specific prompt examples

[1597] 1. High school English classes

[1598] "Generate audio clips and interactive quizzes to improve listening skills for high school students. My learning style is auditory."

[1599] 2. Corporate Training Programs

[1600] "Generate training materials for new employees that include hands-on workshops and role-playing that strengthen communication skills and team building."

[1601] This system allows users to enjoy an educational experience that is tailored to their individual learning needs and emotional state, which is expected to improve learning outcomes and satisfaction.

[1602] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1603] Step 1:

[1604] A user logs into the platform

[1605] Specific operation: The user launches the web browser on the device and accesses the platform's login page. On the login screen, the user enters the username and password and clicks the "Login" button.

[1606] Input: Username, Password

[1607] Output: Login successful, user data loaded

[1608] Step 2:

[1609] Users input their learning goals and learning styles

[1610] Specific operation: After logging in, the user enters their learning goal (e.g., "Improve listening skills") and learning style (e.g., "Auditory learning") into the form displayed on the homepage and clicks the submit button.

[1611] Input: learning goals, learning styles

[1612] Output: Sending user input information, receiving data on the server

[1613] Step 3:

[1614] The server receives the input information

[1615] Specific operations: The server receives the learning objectives and learning style information entered by the user and prepares appropriate processing. It receives the HTTP request and stores it in the database.

[1616] Input: User's learning goals, learning style

[1617] Output: Learning objectives and learning styles stored in a database

[1618] Step 4:

[1619] The server generates educational content using generative artificial intelligence

[1620] How it works: The server accesses the API of a generative artificial intelligence (e.g., GPT-4) to create prompts based on the user's learning goals and style, and then sends them to the AI ​​model to generate customized educational content.

[1621] Input: Prompt statement (e.g., "Generate an audio clip to improve your listening skills.")

[1622] Output: Customized educational content (audio clips, quizzes, etc.)

[1623] Step 5:

[1624] The device receives the educational content

[1625] Specific operation: The server sends the generated educational content to the terminal, which receives the content and displays it on the user interface.

[1626] Input: Customized educational content

[1627] Output: Educational content displayed on the device

[1628] Step 6:

[1629] The emotion engine collects user emotion data

[1630] Specific operation: While the user is using educational content, the device's camera and microphone are used to collect the user's facial expressions and voice data, which are then analyzed by the emotion engine.

[1631] Input: User's facial expressions and voice data

[1632] Output: Parsed emotion data

[1633] Step 7:

[1634] The device feeds back the collected data to the server.

[1635] Specific operation: The emotion engine sends collected data from the device to the server, which receives the data and stores it for the next content generation.

[1636] Input: Parsed emotion data

[1637] Output: Emotion data stored on the server

[1638] Step 8:

[1639] The server adjusts the content based on the feedback.

[1640] Specific behavior: The server analyzes the received emotional data and adjusts the current educational content in real time, for example, changing the task to an easier one if the user is tired.

[1641] Input: Feedback data, emotion data

[1642] Output: Tailored educational content

[1643] Step 9:

[1644] User enters feedback

[1645] Specific operation: After completing the learning, the user inputs and submits feedback on their satisfaction and understanding into the device. This data is sent to the server.

[1646] Input: Feedback (satisfaction, understanding)

[1647] output: Feedback data stored on the server

[1648] Step 10:

[1649] The server analyzes the feedback and reflects it in the next content generation.

[1650] Specific operation: The server combines and analyzes the user's feedback and emotional data, and reflects the results in the next educational content generation. Additionally, as an improvement, supplementary materials are added if the level of understanding in a particular area is low.

[1651] Input: Feedback, emotion data

[1652] Output: Improved educational content for next time learning

[1653] (Application example 2)

[1654] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1655] Conventional educational content delivery systems have the problem of being difficult to personalize content that takes into account each user's individual learning style and emotional state, making it difficult to maintain motivation to learn and maximize educational effectiveness.

[1656] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating personalized educational content based on user input information using a generative artificial intelligence; means for providing the generated educational content to the user's terminal; means for collecting and saving user feedback on the educational content displayed on the terminal; means for collecting user emotion data using an emotion engine that recognizes the user's emotional state; and means for feeding back the emotion data recognized by the emotion engine to the generative artificial intelligence and reflecting it in dynamic adjustment of the educational content. This makes it possible to provide optimal educational content according to the user's individual learning style and real-time emotional state.

[1657] "Generative AI" is an AI technology that generates content to perform specific tasks based on user input.

[1658] "Educational Content" refers to customized educational and learning materials provided to assist users in their learning.

[1659] A "terminal" is a device that a user uses to view educational content and enter feedback.

[1660] "Feedback" refers to the user providing information about their impressions of educational content and their level of understanding.

[1661] An "emotion engine" is a technology that analyzes data such as the user's facial expressions and voice to recognize the user's emotional state.

[1662] "Emotion data" is data relating to the user's emotional state as recognized by the emotion engine.

[1663] "Dynamic adjustment" refers to the process of changing the content and difficulty of educational content in real time based on collected feedback and sentiment data.

[1664] An "interface" is a function that allows users to input information about their learning goals and learning styles.

[1665] The present invention is a system for providing personalized educational content to users, which is implemented with a server, a terminal, and a user each playing a specific role.

[1666] Server Operation

[1667] The server uses generative artificial intelligence to generate personalized educational content based on the learning goals and learning style entered by the user. Examples of generative AI models used in this process include natural language processing models such as GPT-2. The generated educational content is sent to the device and provided to the user. The server also collects user feedback and emotional data sent from the emotion engine, and reflects this in the next educational content generation.

[1668] Device behavior

[1669] Users log in to the system using their devices and input information about their learning goals and learning styles. The devices then send the information to the server, which then displays personalized educational content. The devices also support an emotion engine that uses a built-in camera and microphone to analyze the user's facial expressions and voice to collect emotional data. This allows the obtained emotional data to be fed back to the server in real time.

[1670] User Actions

[1671] Users input information based on their learning goals and learning style through an interface displayed on their device. This information is sent to the server, and personalized educational content is generated by generative artificial intelligence. Users can provide feedback on the educational content provided, which is reflected in the next content generation. Emotional data obtained during learning is also sent to the server and used to generate the next content.

[1672] Hardware and software used

[1673] This system uses devices such as smartphones, tablets, and PCs. The emotion engine is implemented using image processing libraries such as OpenCV and machine learning frameworks such as TensorFlow and Keras. The generative artificial intelligence part uses GPT-2 and other natural language processing models.

[1674] Specific examples

[1675] Example 1: High school English class

[1676] A user (high school student) logs in to a device and enters "improving listening skills" as their learning goal. They also select "auditory learning" as their preferred learning style. The server receives this information and uses generative artificial intelligence to generate customized educational content to improve listening skills. This content includes audio clips for listening practice and interactive quizzes. While learning, an emotion engine analyzes the user's facial expressions and voice, collecting emotional data in real time, such as when they are not concentrating, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more appropriate learning materials.

[1677] Prompt Sentence Examples

[1678] "I'm a high school student who wants to improve my listening skills. Please provide content with interesting audio clips and quizzes."

[1679] Example 2: Corporate training programs

[1680] The user (corporate training manager) logs in to the device and enters "communication skills" and "team building" as learning objectives. The server receives this information and uses generative artificial intelligence to generate customized educational content. This content includes practical workshops and role-playing. During the learning process, an emotion engine analyzes the new employee's facial expressions and reactions, collecting emotional data in real time, such as when they lose interest, and sending feedback to the server. This information is reflected in the next generation of educational content, providing more effective training materials.

[1681] Prompt Sentence Examples

[1682] "Create a training program for your new employees by providing customized content on communication skills and team building with hands-on learning methods."

[1683] The above is a specific embodiment of the present invention.

[1684] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1685] Step 1:

[1686] Users log in to their devices and enter information about their learning goals and learning style. At this time, they can select specific subjects, skill goals, and learning methods (e.g., "English," "improving listening skills," "auditory learning"). This input information is sent to the server.

[1687] Input: Information about the user's learning goals and learning style

[1688] Output: Learning objectives and learning style information sent to the server

[1689] Step 2:

[1690] The server uses a generative AI model to generate personalized educational content based on the user's input, using natural language processing models such as GPT-2 to generate optimal content based on the prompt.

[1691] Input: Learning objectives and learning style information

[1692] Output: Generated personalized educational content

[1693] Step 3:

[1694] The server transmits the generated educational content to the terminal, which receives it and displays it to the user.

[1695] Input: Generated educational content

[1696] Output: Educational content displayed on the device

[1697] Step 4:

[1698] The user studies the educational content displayed on the device, which uses a built-in camera and microphone to capture the user's facial expressions and voice in real time and collects the user's emotional data using an emotion engine.

[1699] Input: User's facial expression and voice data

[1700] Output: Emotion data recognized by the emotion engine

[1701] Step 5:

[1702] The emotion engine sends the recognized emotion data to the server, which collects it and uses it to dynamically adjust the current educational content and generate the next educational content.

[1703] Input: Emotion data recognized by the emotion engine

[1704] Output: Emotion data sent to the server

[1705] Step 6:

[1706] After learning the educational content, users provide feedback on their satisfaction and understanding of the content, which is sent from their devices to the server.

[1707] Input: User feedback

[1708] Output: Feedback sent to the server

[1709] Step 7:

[1710] The server analyzes the collected feedback and emotional data and inputs it as feedback into the generative AI model, which then optimizes the next educational content to be more suitable for the user.

[1711] Input: User feedback and sentiment data

[1712] Output: Information to be reflected in the next educational content generation

[1713] Through these steps, the present invention provides users with an individually optimized educational experience, improving learning outcomes and satisfaction.

[1714] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1715] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1716] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1717] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1718] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1719] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1720] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1721] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1722] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1723] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1724] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1725] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1726] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1727] 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.

[1728] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1729] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1730] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1731] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1732] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1733] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1734] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1735] The following is further disclosed regarding the above embodiment.

[1736] (Claim 1)

[1737] means for generating personalized educational content based on user input using generative artificial intelligence;

[1738] means for providing the generated educational content to a user's terminal;

[1739] means for collecting and storing user feedback regarding the educational content displayed on the device;

[1740] A system including:

[1741] (Claim 2)

[1742] 10. The system of claim 1, further comprising means for providing an interface into which a user can input information regarding learning goals and learning styles.

[1743] (Claim 3)

[1744] The system of claim 1 , further comprising means for reflecting the feedback information in the next generation of educational content.

[1745] "Example 1"

[1746] (Claim 1)

[1747] means for generating personalized educational content based on user input using generative artificial intelligence;

[1748] means for providing the generated educational content to a user's terminal;

[1749] means for collecting and storing user feedback regarding the educational content displayed on the device;

[1750] A means for analyzing the feedback and reflecting it in the generation of the next educational content;

[1751] A system including:

[1752] (Claim 2)

[1753] 10. The system of claim 1, further comprising means for providing an interface into which a user can input information regarding learning goals and learning styles.

[1754] (Claim 3)

[1755] 2. The system according to claim 1, further comprising means for generating a prompt sentence based on the user's input information and inputting the prompt sentence to the generative artificial intelligence.

[1756] "Application Example 1"

[1757] (Claim 1)

[1758] means for generating personalized educational content based on user input using generative artificial intelligence;

[1759] means for providing the generated educational content to a user's information processing device;

[1760] means for collecting and storing user feedback regarding the educational content displayed on the information processing device;

[1761] means for adjusting subsequent generation of educational content based on said feedback;

[1762] A system including:

[1763] (Claim 2)

[1764] 10. The system of claim 1, further comprising means for providing an interface into which a user can input information regarding learning goals and learning styles.

[1765] (Claim 3)

[1766] 10. The system of claim 1, further comprising means for generating generative artificial intelligence prompts and creating educational content based thereon.

[1767] "Example 2: Combining Emotion Engines"

[1768] (Claim 1)

[1769] means for generating personalized educational content based on user input using generative artificial intelligence;

[1770] means for providing the generated educational content to a user's terminal;

[1771] means for collecting and storing user feedback regarding the educational content displayed on the device;

[1772] means for analyzing the emotional state of a user;

[1773] means for dynamically adjusting content based on the analyzed emotion information;

[1774] A system including:

[1775] (Claim 2)

[1776] 10. The system of claim 1, further comprising means for providing an interface into which a user can input information regarding learning goals and learning styles.

[1777] (Claim 3)

[1778] The system of claim 1 , further comprising: means for reflecting the feedback and emotion information in subsequent generation of educational content.

[1779] "Application example 2 when combining emotion engines"

[1780] (Claim 1)

[1781] means for generating personalized educational content based on user input using generative artificial intelligence;

[1782] means for providing the generated educational content to a user's terminal;

[1783] means for collecting and storing user feedback regarding the educational content displayed on the device;

[1784] means for collecting user emotion data using an emotion engine that recognizes the user's emotional state;

[1785] a means for feeding back the emotion data recognized by the emotion engine to the generative artificial intelligence and reflecting the data in dynamic adjustment of the educational content;

[1786] A system including:

[1787] (Claim 2)

[1788] 10. The system of claim 1, further comprising means for providing an interface into which a user can input information regarding learning goals and learning styles.

[1789] (Claim 3)

[1790] The system of claim 1 , further comprising means for reflecting the feedback information and emotion data in the generation of next educational content. [Explanation of symbols]

[1791] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for generating personalized educational content based on user input using generative artificial intelligence; means for providing the generated educational content to a user's terminal; means for collecting and storing user feedback regarding the educational content displayed on the device; A system including:

2. 10. The system of claim 1, further comprising means for providing an interface into which a user can input information regarding learning goals and learning styles.

3. The system according to claim 1 , further comprising means for reflecting the feedback information in the next generation of educational content.

Images