system

Abstract

We provide the system. [Solution] Means of collecting educational information from multiple educational providers, A means of obtaining attribute information for individual users, A means for generating an educational program using a generative model based on the aforementioned educational information and user attribute information, Means for providing the generated educational program to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional educational systems, it is difficult to provide a learning program optimized for an individual's needs and skill level, and there is a problem that learning efficiency decreases due to uniform educational content. Also, the high cost of educational services and the lack of a mechanism for efficiently reflecting user feedback have been barriers to improving the quality of educational services.

Means for Solving the Problems

[0005] This invention provides a means for automatically generating educational programs tailored to user needs using a generative model, by collecting information from multiple educational providers and obtaining user attribute information. The generated educational programs are delivered to users, and user feedback is collected and used to improve the programs. Furthermore, as a monetization strategy, a mechanism is provided to return advertising revenue as points, reducing the user's cost burden while improving satisfaction.

[0006] "Educational information" refers to all data related to education, such as the content, objectives, target audience, schedule, price, and format of courses offered by educational providers.

[0007] "User attribute information" refers to information related to a user's profile, such as educational background, work history, current skill level, areas of interest, learning objectives, and desired career path, provided by the individual user.

[0008] A "generative model" refers to machine learning algorithms and AI technologies that automatically generate optimal educational programs based on collected educational information and user attribute information.

[0009] An "educational program" refers to a set of learning courses customized to the user's learning objectives and needs, including specific learning content and schedules.

[0010] "Advertising revenue" refers to the economic benefits obtained through advertisements displayed on the education platform.

[0011] "Point rewards" refers to a system where a portion of advertising revenue is given to users as points, which can then be used when using educational services in the future. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

[0020] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0033] The system of the present invention consists of the processes of collecting information from educational providers, acquiring user information, generating and providing educational programs using a generative model, processing feedback, and monetizing through advertising. The following describes specific embodiments of this system.

[0034] The server connects to databases of multiple education providers via the internet to retrieve the latest educational course information. This information is integrated and stored in a database on the server.

[0035] Users access the educational platform using their devices and enter attribute information such as their educational background, skills, and learning objectives. This information is securely transmitted from the device to the server.

[0036] The server executes a generative model based on the received user attribute information and the information from educational providers that it has stored on its own. This model generates an educational program optimized for the user's needs and attributes, and makes it available to the user.

[0037] The generated educational program is delivered to the user via their device. The user can view this program, select the courses offered as needed, and take them.

[0038] Furthermore, users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback information and uses it to create future programs and improve the system.

[0039] From a monetization perspective, the server displays advertisements on the platform and generates revenue from them. A portion of this revenue is returned to users as points, which can then be used for discounts and benefits when selecting courses.

[0040] As a concrete example, consider a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and wishes to specialize in data science. After the user enters the necessary information, the server uses a generative model to analyze the latest data science-related courses and proposes an educational program that includes short-term intensive courses and lectures focusing on specific AI technologies. In this way, a personalized program tailored to individual needs and career goals is provided.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server periodically collects the latest educational course information from multiple educational provider platforms via APIs and web scraping. This includes details such as course name, curriculum, target audience, fees, and start date. The collected information is organized and stored in a database.

[0044] Step 2:

[0045] Users access the learning platform using their device and enter their educational background, work experience, skill level, areas of interest, and learning objectives. The detailed information provided is encrypted and transmitted to the server securely.

[0046] Step 3:

[0047] The server uses a generative model to design the optimal educational program based on collected educational information and user attribute information. This model selects the appropriate combination of courses and learning paths while taking into account the user's goals and interests.

[0048] Step 4:

[0049] The server individually customizes the content of the generated educational program and sends it to the terminal. Users can review this program through their terminal and view detailed information about recommended courses and suggested plans.

[0050] Step 5:

[0051] Users register for courses of interest based on the provided program and begin taking the courses. A feature is also provided to provide feedback on learning progress and results for the courses taken.

[0052] Step 6:

[0053] User feedback is sent from the device to the server. The server analyzes this feedback and uses it to improve the generation model and suggestions so that the feedback can be reflected in the next program generation.

[0054] Step 7:

[0055] The server manages the advertisements displayed on the platform and tracks their revenue. A portion of the revenue earned is returned to users as points that can be used for future educational program registrations or service usage.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Modern education systems are required to respond quickly to rapidly changing learner needs and technological advancements. Furthermore, there is a need to establish methods for dynamically and efficiently delivering educational content best suited to individual users. However, traditional systems have limitations in providing optimal learning experiences because the processes of collecting educational data, generating content tailored to user characteristics, and delivering content to users are partial and lack integration. Moreover, the introduction of new monetization methods is a crucial challenge for the sustainable operation of platforms.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for collecting educational data obtained from educational institutions, means for acquiring user characteristic information, and means for creating educational content using a generation algorithm based on the educational data and user characteristic information. This makes it possible to provide educational content tailored to the needs of individual users and to enhance the sustainability of the platform operation through the monetization of commercial information.

[0061] An "educational institution" refers to an organization or group that provides various educational data and information.

[0062] "Educational data" refers to information collected from educational institutions, including course information and detailed curriculum information.

[0063] "Users" refers to individuals or organizations that use an educational platform to receive learning content.

[0064] "Characteristic information" refers to information about an individual's characteristics, such as educational background, skills, and learning objectives, provided by the user.

[0065] A "generative algorithm" refers to a computational method used to create optimal educational content based on user characteristics and educational data.

[0066] "Educational content" refers to learning materials and courses provided to users, which are created using generative algorithms.

[0067] "Commercial information" refers to advertisements and marketing information displayed on the platform that are relevant to the user.

[0068] "Monetization" refers to the process of generating revenue through the display of commercial information on a platform.

[0069] The system implementing this invention consists of a server operating via the internet, a terminal that accepts user input, and a generative AI model that generates educational content based on educational data and user information. This system acquires educational data from educational institutions in real time, collects characteristic information for each user, and analyzes it comprehensively to provide personalized educational content that meets user needs.

[0070] The server accesses databases from multiple educational institutions, retrieves the latest educational data using APIs, and stores it in its own database. This data includes course names, instructors, dates, and content summaries. Users access the system using their devices and input their educational background, skills, and learning objectives. The device encrypts this information and sends it to the server, where it is securely stored.

[0071] The server uses an AI-powered generative model to generate appropriate educational content based on collected educational data and user characteristic information. This generative AI model is built using machine learning algorithms and automatically selects and combines courses that meet user needs. The generated educational content is immediately delivered to the user's device, allowing the user to view, select, and take courses.

[0072] To give a concrete example, imagine a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and desires a course specializing in data science. The server can use a generative AI model to provide a personalized educational program, including short, intensive data science courses and lectures related to AI technology.

[0073] An example of a prompt message would be, "Please suggest a short, intensive data science course to advance my career in the AI ​​field." By sending a message tailored to the user's specific learning needs to the server, the system can automatically generate optimal educational content.

[0074] This system allows users to access optimal educational resources that quickly address their individual needs, enabling them to have an efficient learning experience.

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

[0076] Step 1:

[0077] The server accesses databases of multiple educational institutions and retrieves the latest educational data using APIs. It uses API keys and connection information as input, and based on this, collects educational information such as course names, instructors, and content from the institutions' databases. The collected information is stored in a database on the server, and data processing, such as duplicate checks, is performed to ensure data consistency.

[0078] Step 2:

[0079] Users access the educational platform via their devices and enter personal attribute information such as their educational background, skills, and learning objectives into a login form. The device receives this information as input and then securely transmits it to the server after an encryption process. As output, the server stores the user's characteristic information.

[0080] Step 3:

[0081] The server takes collected educational data and user characteristic information as input and runs a generative AI model. This model uses machine learning algorithms to select the optimal educational content according to the user's needs. The model's calculations generate courses that match the user's interests and career goals. This generation process involves data calculations, and the output is a personalized educational program.

[0082] Step 4:

[0083] The server organizes the generated educational programs and sends them to the terminal. The terminal receives them and displays the program and course information in a user-friendly format. Users can evaluate and select the displayed content as input and decide which courses to take. As output, the user's selection history and course progress are recorded as logs.

[0084] Step 5:

[0085] Users send feedback about the courses they have taken to the server as input from their device. The device receives this feedback data, quantifies the information entered in the feedback form, encrypts it, and sends it to the server. The server analyzes this information and performs data calculations so that it can be used to improve future educational content.

[0086] Step 6:

[0087] The server dynamically displays commercial information, i.e., advertisements, related to the user's profile on the system. Based on the display of commercial information, revenue is generated, and a portion of the resources obtained is returned to the user as points. This allows the user to use the points as a discount when selecting a course next time.

[0088] (Application Example 1)

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

[0090] It is not easy for users to find the educational program that best suits them, and it is particularly difficult to provide educational programs that cater to the diverse learning needs and goals of each user. Furthermore, there is a need for a system that individually optimizes educational programs based on users' interests and goals, thereby effectively and efficiently improving the learning experience. Additionally, there are challenges such as the difficulty of accessing user-friendly interfaces using smart devices, and a lack of features to maintain learning motivation and continuity.

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

[0092] In this invention, the server includes means for collecting educational information from multiple educational providers, means for acquiring attribute information of individual users, means for constructing educational programs using generative models, means for optimizing educational programs based on interests and goals input by users, and means for providing a user-friendly interface using smart devices. This makes it possible to provide personalized educational programs that meet the learning needs of each user, thereby realizing an effective learning experience.

[0093] An "education provider" is an organization or individual that generates and provides educational information to learners.

[0094] "Educational information" refers to content and materials necessary for learners to acquire specific subjects or skills.

[0095] A "user" is an individual learner who receives an educational program and utilizes its services.

[0096] "Attribute information" refers to information about an individual, including their educational background, skills, interests, and learning goals.

[0097] A "generative model" is an algorithm that generates the optimal educational program based on input educational information and user attribute information.

[0098] "Optimization" is the process of customizing educational programs according to the user's interests and goals to maximize learning effectiveness.

[0099] A "smart device" is a portable electronic device that has computing capabilities and can connect to a network.

[0100] A "user-friendly interface" is a user interface for a computer program that is designed to allow users to operate it intuitively.

[0101] A "personalized education program" is educational content optimized for the specific needs and objectives of a particular user.

[0102] This section describes an embodiment for carrying out the invention. The system that realizes this application collects educational information from various educational providers and generates an optimal educational program using a generative AI model based on the user's attribute information. The server retrieves the latest educational information from the database of educational providers via the internet and stores it in the database. The user accesses the educational platform using a terminal and inputs attribute information such as academic background, skills, and learning goals. This information is securely transmitted from the terminal to the server.

[0103] The server generates educational programs by executing a generative AI model based on collected educational information and user attribute information. This generation process utilizes machine learning frameworks such as TENSORFLOW® and PyTorch. The generated educational programs are delivered to the user's device. Here, the smart device interface allows the user to intuitively view and take the programs.

[0104] Users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback and uses it to create future programs and improve the system. Advertisements are displayed on the platform, and a portion of the revenue is returned to users as points that can be used for further learning.

[0105] As a concrete example, consider a scenario where a user inputs "I want to deepen my knowledge of machine learning" into the app. The system proposes a curriculum that starts with the basics of Python programming and then progresses to detailed lectures on machine learning algorithms. An example of a prompt message would be, "I am interested in machine learning, but I am a beginner in programming. Please propose a curriculum that will allow me to learn efficiently."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server connects to a database of educational providers via the internet. It collects the latest educational information from these providers and integrates and stores it in the server's database. The input consists of various educational content provided by the providers, and the output is a database of integrated educational information. This process involves data collection, format conversion, and storage in a standardized format.

[0109] Step 2:

[0110] Users access the educational platform from their devices and enter attribute information such as educational background, skills, and learning objectives. This information is sent to the server using secure protocols such as NI. Based on the input from the device, the server updates the user database. The input is user attribute information, and the output is the updated user database. Data validation and encoding are also performed.

[0111] Step 3:

[0112] The server provides integrated educational information and user attribute information as input to a generative AI model. The generative AI model operates using TensorFlow or PyTorch and generates an optimized educational program. The input is integrated educational content and user attribute information, and the output is a customized educational program. This step involves data analysis and algorithmic inference.

[0113] Step 4:

[0114] The server delivers the generated educational program to the user's device. Users can view the educational program through an intuitive interface via their smart device. The input is the data of the generated educational program, and the output is the educational content provided to the user. Data transmission and UI rendering take place here.

[0115] Step 5:

[0116] Users send feedback about the educational programs they have taken from their terminals to the server. The server receives this feedback and analyzes the data to generate future programs and improve the system. The input is the user's feedback, and the output is the analyzed data. In this step, the feedback is analyzed and the feedback data is integrated into the learning model.

[0117] Step 6:

[0118] The server manages advertisements on the platform and generates revenue. A portion of the advertising revenue is returned to users as points, which are recorded in the user database as available rewards. The input is ad viewing data, and the output is point information. Revenue data management and point system updates are performed here.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] The system of the present invention collects educational information, acquires user information, and generates and provides educational programs by combining a generative model and an emotion engine. Specific embodiments thereof are described below.

[0121] The server connects with databases of multiple education providers via the internet to collect information about educational courses. This collected information is stored in a database on the server and used for later analysis.

[0122] Users access the learning platform using their devices and enter attribute information such as their educational background, work experience, learning objectives, and areas of interest. The device then sends this information to the server.

[0123] The server executes a generative model based on the user's attribute and educational information to design an optimal educational program for the user. In this process, it utilizes an emotion engine to analyze the user's input data and behavioral patterns to understand the user's emotional state.

[0124] The emotional state of the user, as recognized by the emotion engine, is used to optimize the educational program. For example, if a user expresses a loss of interest in learning, the server can suggest more stimulating and engaging content. Similarly, for users experiencing stress, a relaxing learning plan can be created.

[0125] The generated educational programs are delivered to the user via a terminal. The user can select and actually take part in these programs. During learning, the emotion engine continuously monitors the user's emotional state based on their actions and inputs, and dynamically adjusts the program as needed.

[0126] Users send feedback about the programs they have taken from their devices to the server. The server combines this feedback with the results of the emotion engine's analysis to improve the educational programs and fine-tune the generative model. This improves the accuracy of the next educational program recommendations.

[0127] As a concrete example, consider a case where a user interested in AI technology and wanting to learn programming accesses the system. Based on the user's input information and the emotion engine's analysis, the server generates an interactive program that will capture the user's interest. If the emotion engine determines that the user is feeling anxious, it adjusts the learning pace and provides reassuring support. In this way, the user experience is improved and the learning effect is maximized.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server collects educational information from educational providers using APIs and other data acquisition methods. This information includes the content, target audience, fees, and teaching methods of each educational course. The server stores this information in a database and updates it periodically as needed.

[0131] Step 2:

[0132] Users access the learning platform via their device and enter their educational background, work experience, current skills, and areas of interest. They also enter their learning objectives and long-term career goals, and transmit this information from their device to the server.

[0133] Step 3:

[0134] After receiving user attribute information, the server activates the emotion engine to analyze the user's emotional state from the input data. The server uses indicators such as keyboard input speed and selected content patterns to infer the user's psychological state.

[0135] Step 4:

[0136] The server runs a generative model, combining collected educational information, user attribute information, and evaluations from the emotion engine to create an optimal educational program for the user. For example, a user identified as experiencing stress will be offered a more flexible learning plan.

[0137] Step 5:

[0138] The server sends the generated educational program to the terminal and displays it visually to the user. The user can review the provided program, select the course that best suits their needs, and begin learning.

[0139] Step 6:

[0140] The user provides continuous feedback by having their device capture changes in their emotions during learning and their reactions to the tasks they complete. This allows the emotion engine to perform real-time emotion analysis and send it to the server.

[0141] Step 7:

[0142] The server dynamically adjusts the educational program as needed based on the new sentiment analysis results. This makes it possible to rearrange the order of content or add new supplementary materials to engage learners.

[0143] Step 8:

[0144] After completing the learning process, the user sends comprehensive feedback on the entire learning program to the server via their device. The server then continuously optimizes the educational program and generative model based on this feedback and data from the emotion engine.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] Traditional educational programs often fail to adequately consider the individual needs and emotional states of learners, resulting in low learning effectiveness and satisfaction. Furthermore, the fixed content and delivery methods of these programs make it difficult to incorporate learner feedback for improvement.

[0148] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0149] In this invention, the server includes means for collecting education-related information from multiple educational institutions, means for acquiring attribute data of individual learners, means for designing an educational program using a generative artificial intelligence model based on the education-related information and the learner's attribute data, means for evaluating the learner's emotional state using an emotion analysis engine and optimizing the educational program, and means for receiving feedback from learners and reflecting it in improving the educational program and adjusting the generative model. This makes it possible to provide effective and flexible educational programs tailored to the needs of individual learners.

[0150] An "educational provider" refers to an organization or group that provides information and programs related to learning and training.

[0151] "Education-related information" includes all data related to learning, such as course content, teaching materials, and instructor information for educational programs.

[0152] A "learner" refers to an individual who participates in an educational program with the aim of acquiring specific knowledge or skills.

[0153] "Attribute data" refers to personal information about learners, including educational background, work experience, learning objectives, and areas of interest.

[0154] A "generative artificial intelligence model" refers to an algorithm or system that generates an output that conforms to a specific purpose based on the input information.

[0155] An "emotion analysis engine" refers to a technology or system used to analyze and evaluate an individual's emotional state from input data.

[0156] "Feedback" refers to information provided by participants regarding their opinions, evaluations, and suggestions for improvement regarding the program and learning experience.

[0157] "Learner needs" refer to the knowledge and skills that learners are trying to achieve, as well as their learning objectives and goals.

[0158] Embodiments of the present invention are systems for collecting education-related information, acquiring learner attribute data, and generating and providing educational programs by combining a generative artificial intelligence model and an emotion analysis engine.

[0159] The server collects educational information from multiple educational institutions via the internet. Specifically, the server uses a REST API to connect, retrieves data on educational courses in JSON format, and stores it in a database. This allows for the accumulation of a wealth of educational information, which can then be used for analysis and program design.

[0160] The terminal is operated by the learner and provides a means of accessing the learning platform. The learner inputs attribute data such as their educational background, work experience, learning objectives, and areas of interest, and transmits this information to the server via the terminal. The HTTPS protocol is used for this communication, ensuring secure data transfer.

[0161] The server uses a generative artificial intelligence model to design the optimal educational program based on collected educational information and learner attribute data. During this process, prompt statements are input to the generative AI model to determine the necessary program content. An example of a specific prompt statement would be, "Please suggest a program for beginners who want to learn AI technology."

[0162] Furthermore, the server utilizes an emotion analysis engine to evaluate the learner's emotional state. By analyzing the text and behavioral patterns entered by the learner, it can detect changes in emotions such as loss of interest or stress, and dynamically optimize the educational program. This ensures that learners are provided with the optimal learning pace and content, resulting in an effective learning experience.

[0163] The generated educational programs are delivered to learners via their devices. Learners use these devices to select programs and proceed with their studies. This enhances the individual learner's learning experience and maximizes learning effectiveness.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server collects education-related information from educational institutions via the internet. Specifically, the server uses a REST API to retrieve data. The input is the API endpoint of the educational institution, and the output is education-related information in JSON format. This information is later stored in a database.

[0167] Step 2:

[0168] Users access the learning platform using their device and enter attribute data such as their educational background, work experience, learning objectives, and areas of interest into a form. The device encrypts the entered data using the HTTPS protocol and sends it to the server. The input is text data entered by the user, and the output is secure data communication passed to the server.

[0169] Step 3:

[0170] The server integrates collected educational information and attribute data received from users, and inputs it into a generative artificial intelligence model. Here, a prompt (e.g., "Please suggest a program for beginners who want to learn AI technology") is provided to the generative AI model. The input consists of educational information and user attribute information, and the output is the content of an optimized educational program.

[0171] Step 4:

[0172] The server analyzes user behavior data using an emotion analysis engine to evaluate the user's emotional state. Input consists of learning behavioral patterns and text data acquired from the device, while output is an analysis result representing the user's emotional state. This analysis dynamically optimizes the program's content and delivery pace.

[0173] Step 5:

[0174] The server delivers the generated educational program to the terminal. The user selects this program using the terminal and begins learning. The input is the program data generated by the server, and the output is the program content displayed on the terminal.

[0175] Step 6:

[0176] After completing the program, users fill out feedback on their terminal and send it to the server. This feedback consists of evaluations of the program and suggestions for improvement. The server then uses this feedback data to adjust its generative model and further improve the educational program. The input is user feedback data, and the output is specific actions taken for improvement.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0179] In modern society, there is a need for individual learners to receive educational programs tailored to their own attributes and interests. Furthermore, there is a need to develop systems that enable dynamic educational delivery that takes into account the emotional state of learners. However, conventional systems have made it difficult to adjust educational plans to reflect emotional states, making it challenging for learners to obtain the optimal educational experience.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes means for collecting educational resources from multiple educational providers, means for acquiring attribute data of individual users, and means for generating educational plans using an artificial intelligence model, adjusting them according to the user's emotional state using an emotion recognition engine, and providing them. This makes it possible to provide personalized educational experiences based on the user's attributes and emotional state.

[0182] "Educational resources" refer to information and data such as curricula, teaching materials, and educational content collected from education providers.

[0183] "User attribute data" refers to information such as the educational background, work history, learning objectives, and areas of interest of individual learners.

[0184] An "artificial intelligence model" is a machine learning algorithm used to generate an optimal educational plan based on user attribute data and educational resources.

[0185] An "emotion recognition engine" is software that analyzes a user's behavior patterns and input data to understand their emotional state.

[0186] An "educational plan" is a learning program tailored to the user, generated by an artificial intelligence model and adjusted by an emotion recognition engine.

[0187] A "virtual system" refers to a platform that users can access online and purchase or use educational media and resources.

[0188] The invention describes embodiments for carrying out the invention. This invention collects educational resources from multiple educational providers onto a server, and users access it to provide an optimal educational plan for each individual learner.

[0189] The server connects with a database of educational providers via the internet to collect educational resources. The collected resources are stored in the server's database and used for later analysis. Users access the virtual system using a terminal and input their attribute data, including educational background, work experience, learning objectives, and areas of interest. The terminal then transmits the collected attribute data to the server.

[0190] The server generates an educational plan tailored to the user by running an artificial intelligence model using accumulated educational resources and user attribute data. In this process, it utilizes an emotion recognition engine to analyze the user's input data and behavioral patterns to understand their emotional state. Based on the emotional state obtained by the emotion recognition engine, the educational plan is dynamically adjusted to provide the user with an optimal learning experience.

[0191] A concrete example would be a user who wants to learn programming accessing a virtual system. In this case, the server would suggest a programming course for beginners and provide reassuring support by adjusting the learning pace if the user expresses concerns. This would allow the user to learn at their own pace.

[0192] An example of a prompt message used is: "User information: {'Education': 'High school graduate', 'Work experience': 'None', 'Learning objective': 'Career advancement', 'Areas of interest': 'Programming'} Emotional state: 'Anxious' Please provide the optimal educational program." This enables the use of a generative AI model to provide an educational plan tailored to the user.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The server collects educational resources from databases of multiple educational providers via the internet. It stores the retrieved educational content data locally and prepares it for analysis. The input is the query results from the educational provider databases, and the output is the educational resources recorded in the server's database.

[0196] Step 2:

[0197] Users access a virtual system through a terminal and input attribute data such as educational background, work experience, learning objectives, and areas of interest. This data is sent to the server in real time and stored for the next process. The input is attribute data from the user, and the output is user information transferred to the server.

[0198] Step 3:

[0199] The server uses the received user attribute data and stored educational resources to run a generative AI model and generate a new educational plan. The input is the user's attribute data and educational resources, and the output is the optimal educational plan. During the generation process, machine learning algorithms are applied to combine diverse data to construct an appropriate learning plan.

[0200] Step 4:

[0201] The server further utilizes an emotion recognition engine to analyze user input data and behavioral patterns to understand their emotional state. Input consists of user behavior logs and reaction data, providing information about their emotional state. Output is analytical data regarding the user's emotional state.

[0202] Step 5:

[0203] Based on the output of the emotion recognition engine, the server dynamically adjusts the educational plan to prevent stress and loss of interest. The input is the educational plan and emotional state data, and the output is the adjusted educational plan. Specifically, this involves readjusting the learning pace and changing the content balance.

[0204] Step 6:

[0205] The server provides the adjusted educational plan to the terminal and prepares the environment for the user to begin learning. The user can then take the educational program and learn based on this plan. The input is the adjusted educational plan, and the output is the learning content provided to the user.

[0206] Step 7:

[0207] Users send learning progress and feedback from their devices to the server. The server then uses this feedback to further improve the educational plan. The input is user feedback data, and the output is improvement data that can be used to inform the next educational plan.

[0208] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0224] The system of the present invention consists of the processes of collecting information from educational providers, acquiring user information, generating and providing educational programs using a generative model, processing feedback, and monetizing through advertising. The following describes specific embodiments of this system.

[0225] The server connects to databases of multiple education providers via the internet to retrieve the latest educational course information. This information is integrated and stored in a database on the server.

[0226] Users access the educational platform using their devices and enter attribute information such as their educational background, skills, and learning objectives. This information is securely transmitted from the device to the server.

[0227] The server executes a generative model based on the received user attribute information and the information from educational providers that it has stored on its own. This model generates an educational program optimized for the user's needs and attributes, and makes it available to the user.

[0228] The generated educational program is delivered to the user via their device. The user can view this program, select the courses offered as needed, and take them.

[0229] Furthermore, users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback information and uses it to create future programs and improve the system.

[0230] From a monetization perspective, the server displays advertisements on the platform and generates revenue from them. A portion of this revenue is returned to users as points, which can then be used for discounts and benefits when selecting courses.

[0231] As a concrete example, consider a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and wishes to specialize in data science. After the user enters the necessary information, the server uses a generative model to analyze the latest data science-related courses and proposes an educational program that includes short-term intensive courses and lectures focusing on specific AI technologies. In this way, a personalized program tailored to individual needs and career goals is provided.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The server periodically collects the latest educational course information from multiple educational provider platforms via APIs and web scraping. This includes details such as course name, curriculum, target audience, fees, and start date. The collected information is organized and stored in a database.

[0235] Step 2:

[0236] Users access the learning platform using their device and enter their educational background, work experience, skill level, areas of interest, and learning objectives. The detailed information provided is encrypted and transmitted to the server securely.

[0237] Step 3:

[0238] The server uses a generative model to design the optimal educational program based on collected educational information and user attribute information. This model selects the appropriate combination of courses and learning paths while taking into account the user's goals and interests.

[0239] Step 4:

[0240] The server individually customizes the content of the generated educational program and sends it to the terminal. Users can review this program through their terminal and view detailed information about recommended courses and suggested plans.

[0241] Step 5:

[0242] Users register for courses of interest based on the provided program and begin taking the courses. A feature is also provided to provide feedback on learning progress and results for the courses taken.

[0243] Step 6:

[0244] User feedback is sent from the device to the server. The server analyzes this feedback and uses it to improve the generation model and suggestions so that the feedback can be reflected in the next program generation.

[0245] Step 7:

[0246] The server manages the advertisements displayed on the platform and tracks their revenue. A portion of the revenue earned is returned to users as points that can be used for future educational program registrations or service usage.

[0247] (Example 1)

[0248] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0249] Modern education systems are required to respond quickly to rapidly changing learner needs and technological advancements. Furthermore, there is a need to establish methods for dynamically and efficiently delivering educational content best suited to individual users. However, traditional systems have limitations in providing optimal learning experiences because the processes of collecting educational data, generating content tailored to user characteristics, and delivering content to users are partial and lack integration. Moreover, the introduction of new monetization methods is a crucial challenge for the sustainable operation of platforms.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes means for collecting educational data obtained from educational institutions, means for acquiring user characteristic information, and means for creating educational content using a generation algorithm based on the educational data and user characteristic information. This makes it possible to provide educational content tailored to the needs of individual users and to enhance the sustainability of the platform operation through the monetization of commercial information.

[0252] An "educational institution" refers to an organization or group that provides various educational data and information.

[0253] "Educational data" refers to information collected from educational institutions, including course information and detailed curriculum information.

[0254] "Users" refers to individuals or organizations that use an educational platform to receive learning content.

[0255] "Characteristic information" refers to information about an individual's characteristics, such as educational background, skills, and learning objectives, provided by the user.

[0256] A "generative algorithm" refers to a computational method used to create optimal educational content based on user characteristics and educational data.

[0257] "Educational content" refers to learning materials and courses provided to users, which are created using generative algorithms.

[0258] "Commercial information" refers to advertisements and marketing information displayed on the platform that are relevant to the user.

[0259] "Monetization" refers to the process of generating revenue through the display of commercial information on a platform.

[0260] The system implementing this invention consists of a server operating via the internet, a terminal that accepts user input, and a generative AI model that generates educational content based on educational data and user information. This system acquires educational data from educational institutions in real time, collects characteristic information for each user, and analyzes it comprehensively to provide personalized educational content that meets user needs.

[0261] The server accesses databases from multiple educational institutions, retrieves the latest educational data using APIs, and stores it in its own database. This data includes course names, instructors, dates, and content summaries. Users access the system using their devices and input their educational background, skills, and learning objectives. The device encrypts this information and sends it to the server, where it is securely stored.

[0262] The server uses an AI-powered generative model to generate appropriate educational content based on collected educational data and user characteristic information. This generative AI model is built using machine learning algorithms and automatically selects and combines courses that meet user needs. The generated educational content is immediately delivered to the user's device, allowing the user to view, select, and take courses.

[0263] To give a concrete example, imagine a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and desires a course specializing in data science. The server can use a generative AI model to provide a personalized educational program, including short, intensive data science courses and lectures related to AI technology.

[0264] An example of a prompt message would be, "Please suggest a short, intensive data science course to advance my career in the AI ​​field." By sending a message tailored to the user's specific learning needs to the server, the system can automatically generate optimal educational content.

[0265] This system allows users to access optimal educational resources that quickly address their individual needs, enabling them to have an efficient learning experience.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The server accesses databases of multiple educational institutions and retrieves the latest educational data using APIs. It uses API keys and connection information as input, and based on this, collects educational information such as course names, instructors, and content from the institutions' databases. The collected information is stored in a database on the server, and data processing, such as duplicate checks, is performed to ensure data consistency.

[0269] Step 2:

[0270] Users access the educational platform via their devices and enter personal attribute information such as their educational background, skills, and learning objectives into a login form. The device receives this information as input and then securely transmits it to the server after an encryption process. As output, the server stores the user's characteristic information.

[0271] Step 3:

[0272] The server takes collected educational data and user characteristic information as input and runs a generative AI model. This model uses machine learning algorithms to select the optimal educational content according to the user's needs. The model's calculations generate courses that match the user's interests and career goals. This generation process involves data calculations, and the output is a personalized educational program.

[0273] Step 4:

[0274] The server organizes the generated educational programs and sends them to the terminal. The terminal receives them and displays the program and course information in a user-friendly format. Users can evaluate and select the displayed content as input and decide which courses to take. As output, the user's selection history and course progress are recorded as logs.

[0275] Step 5:

[0276] Users send feedback about the courses they have taken to the server as input from their device. The device receives this feedback data, quantifies the information entered in the feedback form, encrypts it, and sends it to the server. The server analyzes this information and performs data calculations so that it can be used to improve future educational content.

[0277] Step 6:

[0278] The server dynamically displays commercial information, i.e., advertisements, related to the user's profile on the system. Based on the display of commercial information, revenue is generated, and a portion of the resources obtained is returned to the user as points. This allows the user to use the points as a discount when selecting a course next time.

[0279] (Application Example 1)

[0280] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0281] It is not easy for users to find the most suitable educational program for themselves. In particular, it is difficult to provide educational programs that meet the different learning needs and goals of each user. In addition, there is a need for a mechanism to optimize educational programs individually based on users' interests and goals and to improve the learning experience effectively and efficiently. Furthermore, there is a problem that it is difficult to access with a user-friendly interface using smart devices, and there is a lack of functions for maintaining learning motivation and continuity.

[0282] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0283] In this invention, the server includes means for collecting educational information from a plurality of educational providers, means for obtaining attribute information of individual users, means for constructing an educational program using a generation model, means for optimizing an educational program based on the interests and goals input by the user, and means for providing a user-friendly interface using a smart device. As a result, it becomes possible to provide a personalized educational program according to the learning needs of each user, and an effective learning experience can be realized.

[0284] An "educational provider" is an organization or individual that generates educational information and provides it to learners.

[0285] "Educational information" is content and materials necessary for learners to acquire specific fields and skills.

[0286] A "user" is an individual learner who receives an educational program and uses its service.

[0287] "Attribute information" is information about an individual including the user's educational background, skills, interests, learning goals, etc.

[0288] A "generation model" is an algorithm that generates an optimal educational program based on the input educational information and the user's attribute information.

[0289] "Optimization" is the process of customizing educational programs according to the user's interests and goals to maximize learning effectiveness.

[0290] A "smart device" is a portable electronic device that has computing capabilities and can connect to a network.

[0291] A "user-friendly interface" is a user interface for a computer program that is designed to allow users to operate it intuitively.

[0292] A "personalized education program" is educational content optimized for the specific needs and objectives of a particular user.

[0293] This section describes an embodiment for carrying out the invention. The system that realizes this application collects educational information from various educational providers and generates an optimal educational program using a generative AI model based on the user's attribute information. The server retrieves the latest educational information from the database of educational providers via the internet and stores it in the database. The user accesses the educational platform using a terminal and inputs attribute information such as academic background, skills, and learning goals. This information is securely transmitted from the terminal to the server.

[0294] The server generates educational programs by executing a generative AI model based on collected educational information and user attribute information. This generation process utilizes machine learning frameworks such as TensorFlow and PyTorch. The generated educational programs are then delivered to the user's device. Through the smart device's interface, users can intuitively view and participate in the programs.

[0295] Users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback and uses it to create future programs and improve the system. Advertisements are displayed on the platform, and a portion of the revenue is returned to users as points that can be used for further learning.

[0296] As a concrete example, consider a scenario where a user inputs "I want to deepen my knowledge of machine learning" into the app. The system proposes a curriculum that starts with the basics of Python programming and then progresses to detailed lectures on machine learning algorithms. An example of a prompt message would be, "I am interested in machine learning, but I am a beginner in programming. Please propose a curriculum that will allow me to learn efficiently."

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] The server connects to a database of educational providers via the internet. It collects the latest educational information from these providers and integrates and stores it in the server's database. The input consists of various educational content provided by the providers, and the output is a database of integrated educational information. This process involves data collection, format conversion, and storage in a standardized format.

[0300] Step 2:

[0301] Users access the educational platform from their devices and enter attribute information such as educational background, skills, and learning objectives. This information is sent to the server using secure protocols such as NI. Based on the input from the device, the server updates the user database. The input is user attribute information, and the output is the updated user database. Data validation and encoding are also performed.

[0302] Step 3:

[0303] The server provides the integrated education information and the user's attribute information as inputs to the generation AI model. The generation AI model operates using TensorFlow or PyTorch and generates an optimized education program. The input is the integrated education content and the user's attribute information, and the output is a customized education program. In this step, data analysis and inference based on algorithms are performed.

[0304] Step 4:

[0305] The server distributes the generated education program to the user's terminal. The user can view the education program through an intuitive interface via a smart device. The input is the data of the generated education program, and the output is the education content provided to the user. Here, data transmission and UI rendering are performed.

[0306] Step 5:

[0307] The user sends feedback on the attended education program from the terminal to the server. The server receives this feedback and analyzes the data for the next program generation and system improvement. The input is the user's feedback, and the output is the analysis data. In this step, feedback analysis and integration of feedback data into the learning model are performed.

[0308] Step 6:

[0309] The server manages advertisements on the platform and obtains revenue. Part of the advertising revenue is returned to the user as points and recorded in the user database as available privileges. The input is the advertisement viewing data, and the output is the point information. Here, revenue data management and point system update are performed.

[0310] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0311] The system of the present invention collects educational information, acquires user information, and generates and provides educational programs by combining a generative model and an emotion engine. Specific embodiments thereof are described below.

[0312] The server connects with databases of multiple education providers via the internet to collect information about educational courses. This collected information is stored in a database on the server and used for later analysis.

[0313] Users access the learning platform using their devices and enter attribute information such as their educational background, work experience, learning objectives, and areas of interest. The device then sends this information to the server.

[0314] The server executes a generative model based on the user's attribute and educational information to design an optimal educational program for the user. In this process, it utilizes an emotion engine to analyze the user's input data and behavioral patterns to understand the user's emotional state.

[0315] The emotional state of the user, as recognized by the emotion engine, is used to optimize the educational program. For example, if a user expresses a loss of interest in learning, the server can suggest more stimulating and engaging content. Similarly, for users experiencing stress, a relaxing learning plan can be created.

[0316] The generated educational programs are delivered to the user via a terminal. The user can select and actually take part in these programs. During learning, the emotion engine continuously monitors the user's emotional state based on their actions and inputs, and dynamically adjusts the program as needed.

[0317] Users send feedback about the programs they have taken from their devices to the server. The server combines this feedback with the results of the emotion engine's analysis to improve the educational programs and fine-tune the generative model. This improves the accuracy of the next educational program recommendations.

[0318] As a concrete example, consider a case where a user interested in AI technology and wanting to learn programming accesses the system. Based on the user's input information and the emotion engine's analysis, the server generates an interactive program that will capture the user's interest. If the emotion engine determines that the user is feeling anxious, it adjusts the learning pace and provides reassuring support. In this way, the user experience is improved and the learning effect is maximized.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The server collects educational information from educational providers using APIs and other data acquisition methods. This information includes the content, target audience, fees, and teaching methods of each educational course. The server stores this information in a database and updates it periodically as needed.

[0322] Step 2:

[0323] Users access the learning platform via their device and enter their educational background, work experience, current skills, and areas of interest. They also enter their learning objectives and long-term career goals, and transmit this information from their device to the server.

[0324] Step 3:

[0325] After receiving user attribute information, the server activates the emotion engine to analyze the user's emotional state from the input data. The server uses indicators such as keyboard input speed and selected content patterns to infer the user's psychological state.

[0326] Step 4:

[0327] The server runs a generative model, combining collected educational information, user attribute information, and evaluations from the emotion engine to create an optimal educational program for the user. For example, a user identified as experiencing stress will be offered a more flexible learning plan.

[0328] Step 5:

[0329] The server sends the generated educational program to the terminal and displays it visually to the user. The user can review the provided program, select the course that best suits their needs, and begin learning.

[0330] Step 6:

[0331] The user provides continuous feedback by having their device capture changes in their emotions during learning and their reactions to the tasks they complete. This allows the emotion engine to perform real-time emotion analysis and send it to the server.

[0332] Step 7:

[0333] The server dynamically adjusts the educational program as needed based on the new sentiment analysis results. This makes it possible to rearrange the order of content or add new supplementary materials to engage learners.

[0334] Step 8:

[0335] After completing the learning process, the user sends comprehensive feedback on the entire learning program to the server via their device. The server then continuously optimizes the educational program and generative model based on this feedback and data from the emotion engine.

[0336] (Example 2)

[0337] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0338] Traditional educational programs often fail to adequately consider the individual needs and emotional states of learners, resulting in low learning effectiveness and satisfaction. Furthermore, the fixed content and delivery methods of these programs make it difficult to incorporate learner feedback for improvement.

[0339] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0340] In this invention, the server includes means for collecting education-related information from multiple educational institutions, means for acquiring attribute data of individual learners, means for designing an educational program using a generative artificial intelligence model based on the education-related information and the learner's attribute data, means for evaluating the learner's emotional state using an emotion analysis engine and optimizing the educational program, and means for receiving feedback from learners and reflecting it in improving the educational program and adjusting the generative model. This makes it possible to provide effective and flexible educational programs tailored to the needs of individual learners.

[0341] An "educational provider" refers to an organization or group that provides information and programs related to learning and training.

[0342] "Education-related information" includes all data related to learning, such as course content, teaching materials, and instructor information for educational programs.

[0343] A "learner" refers to an individual who participates in an educational program with the aim of acquiring specific knowledge or skills.

[0344] "Attribute data" refers to personal information about learners, including educational background, work experience, learning objectives, and areas of interest.

[0345] A "generative artificial intelligence model" refers to an algorithm or system that generates an output that conforms to a specific purpose based on the input information.

[0346] An "emotion analysis engine" refers to a technology or system used to analyze and evaluate an individual's emotional state from input data.

[0347] "Feedback" refers to information provided by participants regarding their opinions, evaluations, and suggestions for improvement regarding the program and learning experience.

[0348] "Learner needs" refer to the knowledge and skills that learners are trying to achieve, as well as their learning objectives and goals.

[0349] Embodiments of the present invention are systems for collecting education-related information, acquiring learner attribute data, and generating and providing educational programs by combining a generative artificial intelligence model and an emotion analysis engine.

[0350] The server collects educational information from multiple educational institutions via the internet. Specifically, the server uses a REST API to connect, retrieves data on educational courses in JSON format, and stores it in a database. This allows for the accumulation of a wealth of educational information, which can then be used for analysis and program design.

[0351] The terminal is operated by the learner and provides a means of accessing the learning platform. The learner inputs attribute data such as their educational background, work experience, learning objectives, and areas of interest, and transmits this information to the server via the terminal. The HTTPS protocol is used for this communication, ensuring secure data transfer.

[0352] The server uses a generative artificial intelligence model to design the optimal educational program based on collected educational information and learner attribute data. During this process, prompt statements are input to the generative AI model to determine the necessary program content. An example of a specific prompt statement would be, "Please suggest a program for beginners who want to learn AI technology."

[0353] Furthermore, the server utilizes an emotion analysis engine to evaluate the learner's emotional state. By analyzing the text and behavioral patterns entered by the learner, it can detect changes in emotions such as loss of interest or stress, and dynamically optimize the educational program. This ensures that learners are provided with the optimal learning pace and content, resulting in an effective learning experience.

[0354] The generated educational programs are delivered to learners via their devices. Learners use these devices to select programs and proceed with their studies. This enhances the individual learner's learning experience and maximizes learning effectiveness.

[0355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0356] Step 1:

[0357] The server collects education-related information from educational institutions via the internet. Specifically, the server uses a REST API to retrieve data. The input is the API endpoint of the educational institution, and the output is education-related information in JSON format. This information is later stored in a database.

[0358] Step 2:

[0359] Users access the learning platform using their device and enter attribute data such as their educational background, work experience, learning objectives, and areas of interest into a form. The device encrypts the entered data using the HTTPS protocol and sends it to the server. The input is text data entered by the user, and the output is secure data communication passed to the server.

[0360] Step 3:

[0361] The server integrates collected educational information and attribute data received from users, and inputs it into a generative artificial intelligence model. Here, a prompt (e.g., "Please suggest a program for beginners who want to learn AI technology") is provided to the generative AI model. The input consists of educational information and user attribute information, and the output is the content of an optimized educational program.

[0362] Step 4:

[0363] The server analyzes user behavior data using an emotion analysis engine to evaluate the user's emotional state. Input consists of learning behavioral patterns and text data acquired from the device, while output is an analysis result representing the user's emotional state. This analysis dynamically optimizes the program's content and delivery pace.

[0364] Step 5:

[0365] The server delivers the generated educational program to the terminal. The user selects this program using the terminal and begins learning. The input is the program data generated by the server, and the output is the program content displayed on the terminal.

[0366] Step 6:

[0367] After completing the program, users fill out feedback on their terminal and send it to the server. This feedback consists of evaluations of the program and suggestions for improvement. The server then uses this feedback data to adjust its generative model and further improve the educational program. The input is user feedback data, and the output is specific actions taken for improvement.

[0368] (Application Example 2)

[0369] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0370] In modern society, there is a need for individual learners to receive educational programs tailored to their own attributes and interests. Furthermore, there is a need to develop systems that enable dynamic educational delivery that takes into account the emotional state of learners. However, conventional systems have made it difficult to adjust educational plans to reflect emotional states, making it challenging for learners to obtain the optimal educational experience.

[0371] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0372] In this invention, the server includes means for collecting educational resources from multiple educational providers, means for acquiring attribute data of individual users, and means for generating educational plans using an artificial intelligence model, adjusting them according to the user's emotional state using an emotion recognition engine, and providing them. This makes it possible to provide personalized educational experiences based on the user's attributes and emotional state.

[0373] "Educational resources" refer to information and data such as curricula, teaching materials, and educational content collected from education providers.

[0374] "User attribute data" refers to information such as the educational background, work history, learning objectives, and areas of interest of individual learners.

[0375] An "artificial intelligence model" is a machine learning algorithm used to generate an optimal educational plan based on user attribute data and educational resources.

[0376] An "emotion recognition engine" is software that analyzes a user's behavior patterns and input data to understand their emotional state.

[0377] An "educational plan" is a learning program tailored to the user, generated by an artificial intelligence model and adjusted by an emotion recognition engine.

[0378] A "virtual system" refers to a platform that users can access online and purchase or use educational media and resources.

[0379] The invention describes embodiments for carrying out the invention. This invention collects educational resources from multiple educational providers onto a server, and users access it to provide an optimal educational plan for each individual learner.

[0380] The server connects with a database of educational providers via the internet to collect educational resources. The collected resources are stored in the server's database and used for later analysis. Users access the virtual system using a terminal and input their attribute data, including educational background, work experience, learning objectives, and areas of interest. The terminal then transmits the collected attribute data to the server.

[0381] The server generates an educational plan tailored to the user by running an artificial intelligence model using accumulated educational resources and user attribute data. In this process, it utilizes an emotion recognition engine to analyze the user's input data and behavioral patterns to understand their emotional state. Based on the emotional state obtained by the emotion recognition engine, the educational plan is dynamically adjusted to provide the user with an optimal learning experience.

[0382] A concrete example would be a user who wants to learn programming accessing a virtual system. In this case, the server would suggest a programming course for beginners and provide reassuring support by adjusting the learning pace if the user expresses concerns. This would allow the user to learn at their own pace.

[0383] An example of a prompt message used is: "User information: {'Education': 'High school graduate', 'Work experience': 'None', 'Learning objective': 'Career advancement', 'Areas of interest': 'Programming'} Emotional state: 'Anxious' Please provide the optimal educational program." This enables the use of a generative AI model to provide an educational plan tailored to the user.

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server collects educational resources from databases of multiple educational providers via the internet. It stores the retrieved educational content data locally and prepares it for analysis. The input is the query results from the educational provider databases, and the output is the educational resources recorded in the server's database.

[0387] Step 2:

[0388] Users access a virtual system through a terminal and input attribute data such as educational background, work experience, learning objectives, and areas of interest. This data is sent to the server in real time and stored for the next process. The input is attribute data from the user, and the output is user information transferred to the server.

[0389] Step 3:

[0390] The server uses the received user attribute data and stored educational resources to run a generative AI model and generate a new educational plan. The input is the user's attribute data and educational resources, and the output is the optimal educational plan. During the generation process, machine learning algorithms are applied to combine diverse data to construct an appropriate learning plan.

[0391] Step 4:

[0392] The server further utilizes an emotion recognition engine to analyze user input data and behavioral patterns to understand their emotional state. Input consists of user behavior logs and reaction data, providing information about their emotional state. Output is analytical data regarding the user's emotional state.

[0393] Step 5:

[0394] Based on the output of the emotion recognition engine, the server dynamically adjusts the educational plan to prevent stress and loss of interest. The input is the educational plan and emotional state data, and the output is the adjusted educational plan. Specifically, this involves readjusting the learning pace and changing the content balance.

[0395] Step 6:

[0396] The server provides the adjusted educational plan to the terminal and prepares the environment for the user to begin learning. The user can then take the educational program and learn based on this plan. The input is the adjusted educational plan, and the output is the learning content provided to the user.

[0397] Step 7:

[0398] Users send learning progress and feedback from their devices to the server. The server then uses this feedback to further improve the educational plan. The input is user feedback data, and the output is improvement data that can be used to inform the next educational plan.

[0399] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0400] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0401] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0402] [Third Embodiment]

[0403] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0404] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0405] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0406] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0407] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0408] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0409] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0410] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0411] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0412] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0413] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0414] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0415] The system of the present invention consists of the processes of collecting information from educational providers, acquiring user information, generating and providing educational programs using a generative model, processing feedback, and monetizing through advertising. The following describes specific embodiments of this system.

[0416] The server connects to databases of multiple education providers via the internet to retrieve the latest educational course information. This information is integrated and stored in a database on the server.

[0417] Users access the educational platform using their devices and enter attribute information such as their educational background, skills, and learning objectives. This information is securely transmitted from the device to the server.

[0418] The server executes a generative model based on the received user attribute information and the information from educational providers that it has stored on its own. This model generates an educational program optimized for the user's needs and attributes, and makes it available to the user.

[0419] The generated educational program is delivered to the user via their device. The user can view this program, select the courses offered as needed, and take them.

[0420] Furthermore, users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback information and uses it to create future programs and improve the system.

[0421] From a monetization perspective, the server displays advertisements on the platform and generates revenue from them. A portion of this revenue is returned to users as points, which can then be used for discounts and benefits when selecting courses.

[0422] As a concrete example, consider a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and wishes to specialize in data science. After the user enters the necessary information, the server uses a generative model to analyze the latest data science-related courses and proposes an educational program that includes short-term intensive courses and lectures focusing on specific AI technologies. In this way, a personalized program tailored to individual needs and career goals is provided.

[0423] The following describes the processing flow.

[0424] Step 1:

[0425] The server periodically collects the latest educational course information from multiple educational provider platforms via APIs and web scraping. This includes details such as course name, curriculum, target audience, fees, and start date. The collected information is organized and stored in a database.

[0426] Step 2:

[0427] Users access the learning platform using their device and enter their educational background, work experience, skill level, areas of interest, and learning objectives. The detailed information provided is encrypted and transmitted to the server securely.

[0428] Step 3:

[0429] The server uses a generative model to design the optimal educational program based on collected educational information and user attribute information. This model selects the appropriate combination of courses and learning paths while taking into account the user's goals and interests.

[0430] Step 4:

[0431] The server individually customizes the content of the generated educational program and sends it to the terminal. Users can review this program through their terminal and view detailed information about recommended courses and suggested plans.

[0432] Step 5:

[0433] Users register for courses of interest based on the provided program and begin taking the courses. A feature is also provided to provide feedback on learning progress and results for the courses taken.

[0434] Step 6:

[0435] User feedback is sent from the device to the server. The server analyzes this feedback and uses it to improve the generation model and suggestions so that the feedback can be reflected in the next program generation.

[0436] Step 7:

[0437] The server manages the advertisements displayed on the platform and tracks their revenue. A portion of the revenue earned is returned to users as points that can be used for future educational program registrations or service usage.

[0438] (Example 1)

[0439] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0440] Modern education systems are required to respond quickly to rapidly changing learner needs and technological advancements. Furthermore, there is a need to establish methods for dynamically and efficiently delivering educational content best suited to individual users. However, traditional systems have limitations in providing optimal learning experiences because the processes of collecting educational data, generating content tailored to user characteristics, and delivering content to users are partial and lack integration. Moreover, the introduction of new monetization methods is a crucial challenge for the sustainable operation of platforms.

[0441] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0442] In this invention, the server includes means for collecting educational data obtained from educational institutions, means for acquiring user characteristic information, and means for creating educational content using a generation algorithm based on the educational data and user characteristic information. This makes it possible to provide educational content tailored to the needs of individual users and to enhance the sustainability of the platform operation through the monetization of commercial information.

[0443] An "educational institution" refers to an organization or group that provides various educational data and information.

[0444] "Educational data" refers to information collected from educational institutions, including course information and detailed curriculum information.

[0445] "Users" refers to individuals or organizations that use an educational platform to receive learning content.

[0446] "Characteristic information" refers to information about an individual's characteristics, such as educational background, skills, and learning objectives, provided by the user.

[0447] A "generative algorithm" refers to a computational method used to create optimal educational content based on user characteristics and educational data.

[0448] "Educational content" refers to learning materials and courses provided to users, which are created using generative algorithms.

[0449] "Commercial information" refers to advertisements and marketing information displayed on the platform that are relevant to the user.

[0450] "Monetization" refers to the process of generating revenue through the display of commercial information on a platform.

[0451] The system implementing this invention consists of a server operating via the internet, a terminal that accepts user input, and a generative AI model that generates educational content based on educational data and user information. This system acquires educational data from educational institutions in real time, collects characteristic information for each user, and analyzes it comprehensively to provide personalized educational content that meets user needs.

[0452] The server accesses databases from multiple educational institutions, retrieves the latest educational data using APIs, and stores it in its own database. This data includes course names, instructors, dates, and content summaries. Users access the system using their devices and input their educational background, skills, and learning objectives. The device encrypts this information and sends it to the server, where it is securely stored.

[0453] The server uses an AI-powered generative model to generate appropriate educational content based on collected educational data and user characteristic information. This generative AI model is built using machine learning algorithms and automatically selects and combines courses that meet user needs. The generated educational content is immediately delivered to the user's device, allowing the user to view, select, and take courses.

[0454] To give a concrete example, imagine a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and desires a course specializing in data science. The server can use a generative AI model to provide a personalized educational program, including short, intensive data science courses and lectures related to AI technology.

[0455] An example of a prompt message would be, "Please suggest a short, intensive data science course to advance my career in the AI ​​field." By sending a message tailored to the user's specific learning needs to the server, the system can automatically generate optimal educational content.

[0456] This system allows users to access optimal educational resources that quickly address their individual needs, enabling them to have an efficient learning experience.

[0457] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0458] Step 1:

[0459] The server accesses databases of multiple educational institutions and retrieves the latest educational data using APIs. It uses API keys and connection information as input, and based on this, collects educational information such as course names, instructors, and content from the institutions' databases. The collected information is stored in a database on the server, and data processing, such as duplicate checks, is performed to ensure data consistency.

[0460] Step 2:

[0461] Users access the educational platform via their devices and enter personal attribute information such as their educational background, skills, and learning objectives into a login form. The device receives this information as input and then securely transmits it to the server after an encryption process. As output, the server stores the user's characteristic information.

[0462] Step 3:

[0463] The server takes collected educational data and user characteristic information as input and runs a generative AI model. This model uses machine learning algorithms to select the optimal educational content according to the user's needs. The model's calculations generate courses that match the user's interests and career goals. This generation process involves data calculations, and the output is a personalized educational program.

[0464] Step 4:

[0465] The server organizes the generated educational programs and sends them to the terminal. The terminal receives them and displays the program and course information in a user-friendly format. Users can evaluate and select the displayed content as input and decide which courses to take. As output, the user's selection history and course progress are recorded as logs.

[0466] Step 5:

[0467] Users send feedback about the courses they have taken to the server as input from their device. The device receives this feedback data, quantifies the information entered in the feedback form, encrypts it, and sends it to the server. The server analyzes this information and performs data calculations so that it can be used to improve future educational content.

[0468] Step 6:

[0469] The server dynamically displays commercial information, i.e., advertisements, related to the user's profile on the system. Based on the display of commercial information, revenue is generated, and a portion of the resources obtained is returned to the user as points. This allows the user to use the points as a discount when selecting a course next time.

[0470] (Application Example 1)

[0471] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0472] It is not easy for users to find the educational program that best suits them, and it is particularly difficult to provide educational programs that cater to the diverse learning needs and goals of each user. Furthermore, there is a need for a system that individually optimizes educational programs based on users' interests and goals, thereby effectively and efficiently improving the learning experience. Additionally, there are challenges such as the difficulty of accessing user-friendly interfaces using smart devices, and a lack of features to maintain learning motivation and continuity.

[0473] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0474] In this invention, the server includes means for collecting educational information from multiple educational providers, means for acquiring attribute information of individual users, means for constructing educational programs using generative models, means for optimizing educational programs based on interests and goals input by users, and means for providing a user-friendly interface using smart devices. This makes it possible to provide personalized educational programs that meet the learning needs of each user, thereby realizing an effective learning experience.

[0475] An "education provider" is an organization or individual that generates and provides educational information to learners.

[0476] "Educational information" refers to content and materials necessary for learners to acquire specific subjects or skills.

[0477] A "user" is an individual learner who receives an educational program and utilizes its services.

[0478] "Attribute information" refers to information about an individual, including their educational background, skills, interests, and learning goals.

[0479] A "generative model" is an algorithm that generates the optimal educational program based on input educational information and user attribute information.

[0480] "Optimization" is the process of customizing educational programs according to the user's interests and goals to maximize learning effectiveness.

[0481] A "smart device" is a portable electronic device that has computing capabilities and can connect to a network.

[0482] A "user-friendly interface" is a user interface for a computer program that is designed to allow users to operate it intuitively.

[0483] A "personalized education program" is educational content optimized for the specific needs and objectives of a particular user.

[0484] This section describes an embodiment for carrying out the invention. The system that realizes this application collects educational information from various educational providers and generates an optimal educational program using a generative AI model based on the user's attribute information. The server retrieves the latest educational information from the database of educational providers via the internet and stores it in the database. The user accesses the educational platform using a terminal and inputs attribute information such as academic background, skills, and learning goals. This information is securely transmitted from the terminal to the server.

[0485] The server generates educational programs by executing a generative AI model based on collected educational information and user attribute information. This generation process utilizes machine learning frameworks such as TensorFlow and PyTorch. The generated educational programs are then delivered to the user's device. Through the smart device's interface, users can intuitively view and participate in the programs.

[0486] Users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback and uses it to create future programs and improve the system. Advertisements are displayed on the platform, and a portion of the revenue is returned to users as points that can be used for further learning.

[0487] As a concrete example, consider a scenario where a user inputs "I want to deepen my knowledge of machine learning" into the app. The system proposes a curriculum that starts with the basics of Python programming and then progresses to detailed lectures on machine learning algorithms. An example of a prompt message would be, "I am interested in machine learning, but I am a beginner in programming. Please propose a curriculum that will allow me to learn efficiently."

[0488] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0489] Step 1:

[0490] The server connects to a database of educational providers via the internet. It collects the latest educational information from these providers and integrates and stores it in the server's database. The input consists of various educational content provided by the providers, and the output is a database of integrated educational information. This process involves data collection, format conversion, and storage in a standardized format.

[0491] Step 2:

[0492] Users access the educational platform from their devices and enter attribute information such as educational background, skills, and learning objectives. This information is sent to the server using secure protocols such as NI. Based on the input from the device, the server updates the user database. The input is user attribute information, and the output is the updated user database. Data validation and encoding are also performed.

[0493] Step 3:

[0494] The server provides integrated educational information and user attribute information as input to a generative AI model. The generative AI model operates using TensorFlow or PyTorch and generates an optimized educational program. The input is integrated educational content and user attribute information, and the output is a customized educational program. This step involves data analysis and algorithmic inference.

[0495] Step 4:

[0496] The server delivers the generated educational program to the user's device. Users can view the educational program through an intuitive interface via their smart device. The input is the data of the generated educational program, and the output is the educational content provided to the user. Data transmission and UI rendering take place here.

[0497] Step 5:

[0498] Users send feedback about the educational programs they have taken from their terminals to the server. The server receives this feedback and analyzes the data to generate future programs and improve the system. The input is the user's feedback, and the output is the analyzed data. In this step, the feedback is analyzed and the feedback data is integrated into the learning model.

[0499] Step 6:

[0500] The server manages advertisements on the platform and generates revenue. A portion of the advertising revenue is returned to users as points, which are recorded in the user database as available rewards. The input is ad viewing data, and the output is point information. Revenue data management and point system updates are performed here.

[0501] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0502] The system of the present invention collects educational information, acquires user information, and generates and provides educational programs by combining a generative model and an emotion engine. Specific embodiments thereof are described below.

[0503] The server connects with databases of multiple education providers via the internet to collect information about educational courses. This collected information is stored in a database on the server and used for later analysis.

[0504] Users access the learning platform using their devices and enter attribute information such as their educational background, work experience, learning objectives, and areas of interest. The device then sends this information to the server.

[0505] The server executes a generative model based on the user's attribute and educational information to design an optimal educational program for the user. In this process, it utilizes an emotion engine to analyze the user's input data and behavioral patterns to understand the user's emotional state.

[0506] The emotional state of the user, as recognized by the emotion engine, is used to optimize the educational program. For example, if a user expresses a loss of interest in learning, the server can suggest more stimulating and engaging content. Similarly, for users experiencing stress, a relaxing learning plan can be created.

[0507] The generated educational programs are delivered to the user via a terminal. The user can select and actually take part in these programs. During learning, the emotion engine continuously monitors the user's emotional state based on their actions and inputs, and dynamically adjusts the program as needed.

[0508] Users send feedback about the programs they have taken from their devices to the server. The server combines this feedback with the results of the emotion engine's analysis to improve the educational programs and fine-tune the generative model. This improves the accuracy of the next educational program recommendations.

[0509] As a concrete example, consider a case where a user interested in AI technology and wanting to learn programming accesses the system. Based on the user's input information and the emotion engine's analysis, the server generates an interactive program that will capture the user's interest. If the emotion engine determines that the user is feeling anxious, it adjusts the learning pace and provides reassuring support. In this way, the user experience is improved and the learning effect is maximized.

[0510] The following describes the processing flow.

[0511] Step 1:

[0512] The server collects educational information from educational providers using APIs and other data acquisition methods. This information includes the content, target audience, fees, and teaching methods of each educational course. The server stores this information in a database and updates it periodically as needed.

[0513] Step 2:

[0514] Users access the learning platform via their device and enter their educational background, work experience, current skills, and areas of interest. They also enter their learning objectives and long-term career goals, and transmit this information from their device to the server.

[0515] Step 3:

[0516] After receiving user attribute information, the server activates the emotion engine to analyze the user's emotional state from the input data. The server uses indicators such as keyboard input speed and selected content patterns to infer the user's psychological state.

[0517] Step 4:

[0518] The server runs a generative model, combining collected educational information, user attribute information, and evaluations from the emotion engine to create an optimal educational program for the user. For example, a user identified as experiencing stress will be offered a more flexible learning plan.

[0519] Step 5:

[0520] The server sends the generated educational program to the terminal and displays it visually to the user. The user can review the provided program, select the course that best suits their needs, and begin learning.

[0521] Step 6:

[0522] The user provides continuous feedback by having their device capture changes in their emotions during learning and their reactions to the tasks they complete. This allows the emotion engine to perform real-time emotion analysis and send it to the server.

[0523] Step 7:

[0524] The server dynamically adjusts the educational program as needed based on the new sentiment analysis results. This makes it possible to rearrange the order of content or add new supplementary materials to engage learners.

[0525] Step 8:

[0526] After completing the learning process, the user sends comprehensive feedback on the entire learning program to the server via their device. The server then continuously optimizes the educational program and generative model based on this feedback and data from the emotion engine.

[0527] (Example 2)

[0528] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0529] Traditional educational programs often fail to adequately consider the individual needs and emotional states of learners, resulting in low learning effectiveness and satisfaction. Furthermore, the fixed content and delivery methods of these programs make it difficult to incorporate learner feedback for improvement.

[0530] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0531] In this invention, the server includes means for collecting education-related information from multiple educational institutions, means for acquiring attribute data of individual learners, means for designing an educational program using a generative artificial intelligence model based on the education-related information and the learner's attribute data, means for evaluating the learner's emotional state using an emotion analysis engine and optimizing the educational program, and means for receiving feedback from learners and reflecting it in improving the educational program and adjusting the generative model. This makes it possible to provide effective and flexible educational programs tailored to the needs of individual learners.

[0532] An "educational provider" refers to an organization or group that provides information and programs related to learning and training.

[0533] "Education-related information" includes all data related to learning, such as course content, teaching materials, and instructor information for educational programs.

[0534] A "learner" refers to an individual who participates in an educational program with the aim of acquiring specific knowledge or skills.

[0535] "Attribute data" refers to personal information about learners, including educational background, work experience, learning objectives, and areas of interest.

[0536] A "generative artificial intelligence model" refers to an algorithm or system that generates an output that conforms to a specific purpose based on the input information.

[0537] An "emotion analysis engine" refers to a technology or system used to analyze and evaluate an individual's emotional state from input data.

[0538] "Feedback" refers to information provided by participants regarding their opinions, evaluations, and suggestions for improvement regarding the program and learning experience.

[0539] "Learner needs" refer to the knowledge and skills that learners are trying to achieve, as well as their learning objectives and goals.

[0540] Embodiments of the present invention are systems for collecting education-related information, acquiring learner attribute data, and generating and providing educational programs by combining a generative artificial intelligence model and an emotion analysis engine.

[0541] The server collects educational information from multiple educational institutions via the internet. Specifically, the server uses a REST API to connect, retrieves data on educational courses in JSON format, and stores it in a database. This allows for the accumulation of a wealth of educational information, which can then be used for analysis and program design.

[0542] The terminal is operated by the learner and provides a means of accessing the learning platform. The learner inputs attribute data such as their educational background, work experience, learning objectives, and areas of interest, and transmits this information to the server via the terminal. The HTTPS protocol is used for this communication, ensuring secure data transfer.

[0543] The server uses a generative artificial intelligence model to design the optimal educational program based on collected educational information and learner attribute data. During this process, prompt statements are input to the generative AI model to determine the necessary program content. An example of a specific prompt statement would be, "Please suggest a program for beginners who want to learn AI technology."

[0544] Furthermore, the server utilizes an emotion analysis engine to evaluate the learner's emotional state. By analyzing the text and behavioral patterns entered by the learner, it can detect changes in emotions such as loss of interest or stress, and dynamically optimize the educational program. This ensures that learners are provided with the optimal learning pace and content, resulting in an effective learning experience.

[0545] The generated educational programs are delivered to learners via their devices. Learners use these devices to select programs and proceed with their studies. This enhances the individual learner's learning experience and maximizes learning effectiveness.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The server collects education-related information from educational institutions via the internet. Specifically, the server uses a REST API to retrieve data. The input is the API endpoint of the educational institution, and the output is education-related information in JSON format. This information is later stored in a database.

[0549] Step 2:

[0550] Users access the learning platform using their device and enter attribute data such as their educational background, work experience, learning objectives, and areas of interest into a form. The device encrypts the entered data using the HTTPS protocol and sends it to the server. The input is text data entered by the user, and the output is secure data communication passed to the server.

[0551] Step 3:

[0552] The server integrates collected educational information and attribute data received from users, and inputs it into a generative artificial intelligence model. Here, a prompt (e.g., "Please suggest a program for beginners who want to learn AI technology") is provided to the generative AI model. The input consists of educational information and user attribute information, and the output is the content of an optimized educational program.

[0553] Step 4:

[0554] The server analyzes user behavior data using an emotion analysis engine to evaluate the user's emotional state. Input consists of learning behavioral patterns and text data acquired from the device, while output is an analysis result representing the user's emotional state. This analysis dynamically optimizes the program's content and delivery pace.

[0555] Step 5:

[0556] The server delivers the generated educational program to the terminal. The user selects this program using the terminal and begins learning. The input is the program data generated by the server, and the output is the program content displayed on the terminal.

[0557] Step 6:

[0558] After completing the program, users fill out feedback on their terminal and send it to the server. This feedback consists of evaluations of the program and suggestions for improvement. The server then uses this feedback data to adjust its generative model and further improve the educational program. The input is user feedback data, and the output is specific actions taken for improvement.

[0559] (Application Example 2)

[0560] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0561] In modern society, there is a need for individual learners to receive educational programs tailored to their own attributes and interests. Furthermore, there is a need to develop systems that enable dynamic educational delivery that takes into account the emotional state of learners. However, conventional systems have made it difficult to adjust educational plans to reflect emotional states, making it challenging for learners to obtain the optimal educational experience.

[0562] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0563] In this invention, the server includes means for collecting educational resources from multiple educational providers, means for acquiring attribute data of individual users, and means for generating educational plans using an artificial intelligence model, adjusting them according to the user's emotional state using an emotion recognition engine, and providing them. This makes it possible to provide personalized educational experiences based on the user's attributes and emotional state.

[0564] "Educational resources" refer to information and data such as curricula, teaching materials, and educational content collected from education providers.

[0565] "User attribute data" refers to information such as the educational background, work history, learning objectives, and areas of interest of individual learners.

[0566] An "artificial intelligence model" is a machine learning algorithm used to generate an optimal educational plan based on user attribute data and educational resources.

[0567] An "emotion recognition engine" is software that analyzes a user's behavior patterns and input data to understand their emotional state.

[0568] An "educational plan" is a learning program tailored to the user, generated by an artificial intelligence model and adjusted by an emotion recognition engine.

[0569] A "virtual system" refers to a platform that users can access online and purchase or use educational media and resources.

[0570] The invention describes embodiments for carrying out the invention. This invention collects educational resources from multiple educational providers onto a server, and users access it to provide an optimal educational plan for each individual learner.

[0571] The server connects with a database of educational providers via the internet to collect educational resources. The collected resources are stored in the server's database and used for later analysis. Users access the virtual system using a terminal and input their attribute data, including educational background, work experience, learning objectives, and areas of interest. The terminal then transmits the collected attribute data to the server.

[0572] The server generates an educational plan tailored to the user by running an artificial intelligence model using accumulated educational resources and user attribute data. In this process, it utilizes an emotion recognition engine to analyze the user's input data and behavioral patterns to understand their emotional state. Based on the emotional state obtained by the emotion recognition engine, the educational plan is dynamically adjusted to provide the user with an optimal learning experience.

[0573] A concrete example would be a user who wants to learn programming accessing a virtual system. In this case, the server would suggest a programming course for beginners and provide reassuring support by adjusting the learning pace if the user expresses concerns. This would allow the user to learn at their own pace.

[0574] An example of a prompt message used is: "User information: {'Education': 'High school graduate', 'Work experience': 'None', 'Learning objective': 'Career advancement', 'Areas of interest': 'Programming'} Emotional state: 'Anxious' Please provide the optimal educational program." This enables the use of a generative AI model to provide an educational plan tailored to the user.

[0575] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0576] Step 1:

[0577] The server collects educational resources from databases of multiple educational providers via the internet. It stores the retrieved educational content data locally and prepares it for analysis. The input is the query results from the educational provider databases, and the output is the educational resources recorded in the server's database.

[0578] Step 2:

[0579] Users access a virtual system through a terminal and input attribute data such as educational background, work experience, learning objectives, and areas of interest. This data is sent to the server in real time and stored for the next process. The input is attribute data from the user, and the output is user information transferred to the server.

[0580] Step 3:

[0581] The server uses the received user attribute data and stored educational resources to run a generative AI model and generate a new educational plan. The input is the user's attribute data and educational resources, and the output is the optimal educational plan. During the generation process, machine learning algorithms are applied to combine diverse data to construct an appropriate learning plan.

[0582] Step 4:

[0583] The server further utilizes an emotion recognition engine to analyze user input data and behavioral patterns to understand their emotional state. Input consists of user behavior logs and reaction data, providing information about their emotional state. Output is analytical data regarding the user's emotional state.

[0584] Step 5:

[0585] Based on the output of the emotion recognition engine, the server dynamically adjusts the educational plan to prevent stress and loss of interest. The input is the educational plan and emotional state data, and the output is the adjusted educational plan. Specifically, this involves readjusting the learning pace and changing the content balance.

[0586] Step 6:

[0587] The server provides the adjusted educational plan to the terminal and prepares the environment for the user to begin learning. The user can then take the educational program and learn based on this plan. The input is the adjusted educational plan, and the output is the learning content provided to the user.

[0588] Step 7:

[0589] Users send learning progress and feedback from their devices to the server. The server then uses this feedback to further improve the educational plan. The input is user feedback data, and the output is improvement data that can be used to inform the next educational plan.

[0590] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0591] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0592] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0593] [Fourth Embodiment]

[0594] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0595] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0596] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0597] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0598] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0599] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0600] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0601] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0602] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0603] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0604] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0605] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0606] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0607] The system of the present invention consists of the processes of collecting information from educational providers, acquiring user information, generating and providing educational programs using a generative model, processing feedback, and monetizing through advertising. The following describes specific embodiments of this system.

[0608] The server connects to databases of multiple education providers via the internet to retrieve the latest educational course information. This information is integrated and stored in a database on the server.

[0609] Users access the educational platform using their devices and enter attribute information such as their educational background, skills, and learning objectives. This information is securely transmitted from the device to the server.

[0610] The server executes a generative model based on the received user attribute information and the information from educational providers that it has stored on its own. This model generates an educational program optimized for the user's needs and attributes, and makes it available to the user.

[0611] The generated educational program is delivered to the user via their device. The user can view this program, select the courses offered as needed, and take them.

[0612] Furthermore, users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback information and uses it to create future programs and improve the system.

[0613] From a monetization perspective, the server displays advertisements on the platform and generates revenue from them. A portion of this revenue is returned to users as points, which can then be used for discounts and benefits when selecting courses.

[0614] As a concrete example, consider a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and wishes to specialize in data science. After the user enters the necessary information, the server uses a generative model to analyze the latest data science-related courses and proposes an educational program that includes short-term intensive courses and lectures focusing on specific AI technologies. In this way, a personalized program tailored to individual needs and career goals is provided.

[0615] The following describes the processing flow.

[0616] Step 1:

[0617] The server periodically collects the latest educational course information from multiple educational provider platforms via APIs and web scraping. This includes details such as course name, curriculum, target audience, fees, and start date. The collected information is organized and stored in a database.

[0618] Step 2:

[0619] Users access the learning platform using their device and enter their educational background, work experience, skill level, areas of interest, and learning objectives. The detailed information provided is encrypted and transmitted to the server securely.

[0620] Step 3:

[0621] The server uses a generative model to design the optimal educational program based on collected educational information and user attribute information. This model selects the appropriate combination of courses and learning paths while taking into account the user's goals and interests.

[0622] Step 4:

[0623] The server individually customizes the content of the generated educational program and sends it to the terminal. Users can review this program through their terminal and view detailed information about recommended courses and suggested plans.

[0624] Step 5:

[0625] Users register for courses of interest based on the provided program and begin taking the courses. A feature is also provided to provide feedback on learning progress and results for the courses taken.

[0626] Step 6:

[0627] User feedback is sent from the device to the server. The server analyzes this feedback and uses it to improve the generation model and suggestions so that the feedback can be reflected in the next program generation.

[0628] Step 7:

[0629] The server manages the advertisements displayed on the platform and tracks their revenue. A portion of the revenue earned is returned to users as points that can be used for future educational program registrations or service usage.

[0630] (Example 1)

[0631] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0632] Modern education systems are required to respond quickly to rapidly changing learner needs and technological advancements. Furthermore, there is a need to establish methods for dynamically and efficiently delivering educational content best suited to individual users. However, traditional systems have limitations in providing optimal learning experiences because the processes of collecting educational data, generating content tailored to user characteristics, and delivering content to users are partial and lack integration. Moreover, the introduction of new monetization methods is a crucial challenge for the sustainable operation of platforms.

[0633] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0634] In this invention, the server includes means for collecting educational data obtained from educational institutions, means for acquiring user characteristic information, and means for creating educational content using a generation algorithm based on the educational data and user characteristic information. This makes it possible to provide educational content tailored to the needs of individual users and to enhance the sustainability of the platform operation through the monetization of commercial information.

[0635] An "educational institution" refers to an organization or group that provides various educational data and information.

[0636] "Educational data" refers to information collected from educational institutions, including course information and detailed curriculum information.

[0637] "Users" refers to individuals or organizations that use an educational platform to receive learning content.

[0638] "Characteristic information" refers to information about an individual's characteristics, such as educational background, skills, and learning objectives, provided by the user.

[0639] A "generative algorithm" refers to a computational method used to create optimal educational content based on user characteristics and educational data.

[0640] "Educational content" refers to learning materials and courses provided to users, which are created using generative algorithms.

[0641] "Commercial information" refers to advertisements and marketing information displayed on the platform that are relevant to the user.

[0642] "Monetization" refers to the process of generating revenue through the display of commercial information on a platform.

[0643] The system implementing this invention consists of a server operating via the internet, a terminal that accepts user input, and a generative AI model that generates educational content based on educational data and user information. This system acquires educational data from educational institutions in real time, collects characteristic information for each user, and analyzes it comprehensively to provide personalized educational content that meets user needs.

[0644] The server accesses databases from multiple educational institutions, retrieves the latest educational data using APIs, and stores it in its own database. This data includes course names, instructors, dates, and content summaries. Users access the system using their devices and input their educational background, skills, and learning objectives. The device encrypts this information and sends it to the server, where it is securely stored.

[0645] The server uses an AI-powered generative model to generate appropriate educational content based on collected educational data and user characteristic information. This generative AI model is built using machine learning algorithms and automatically selects and combines courses that meet user needs. The generated educational content is immediately delivered to the user's device, allowing the user to view, select, and take courses.

[0646] To give a concrete example, imagine a user interested in the field of AI accessing an educational platform. Suppose this user has a foundation in computer science and desires a course specializing in data science. The server can use a generative AI model to provide a personalized educational program, including short, intensive data science courses and lectures related to AI technology.

[0647] An example of a prompt message would be, "Please suggest a short, intensive data science course to advance my career in the AI ​​field." By sending a message tailored to the user's specific learning needs to the server, the system can automatically generate optimal educational content.

[0648] This system allows users to access optimal educational resources that quickly address their individual needs, enabling them to have an efficient learning experience.

[0649] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0650] Step 1:

[0651] The server accesses databases of multiple educational institutions and retrieves the latest educational data using APIs. It uses API keys and connection information as input, and based on this, collects educational information such as course names, instructors, and content from the institutions' databases. The collected information is stored in a database on the server, and data processing, such as duplicate checks, is performed to ensure data consistency.

[0652] Step 2:

[0653] Users access the educational platform via their devices and enter personal attribute information such as their educational background, skills, and learning objectives into a login form. The device receives this information as input and then securely transmits it to the server after an encryption process. As output, the server stores the user's characteristic information.

[0654] Step 3:

[0655] The server takes collected educational data and user characteristic information as input and runs a generative AI model. This model uses machine learning algorithms to select the optimal educational content according to the user's needs. The model's calculations generate courses that match the user's interests and career goals. This generation process involves data calculations, and the output is a personalized educational program.

[0656] Step 4:

[0657] The server organizes the generated educational programs and sends them to the terminal. The terminal receives them and displays the program and course information in a user-friendly format. Users can evaluate and select the displayed content as input and decide which courses to take. As output, the user's selection history and course progress are recorded as logs.

[0658] Step 5:

[0659] Users send feedback about the courses they have taken to the server as input from their device. The device receives this feedback data, quantifies the information entered in the feedback form, encrypts it, and sends it to the server. The server analyzes this information and performs data calculations so that it can be used to improve future educational content.

[0660] Step 6:

[0661] The server dynamically displays commercial information, i.e., advertisements, related to the user's profile on the system. Based on the display of commercial information, revenue is generated, and a portion of the resources obtained is returned to the user as points. This allows the user to use the points as a discount when selecting a course next time.

[0662] (Application Example 1)

[0663] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0664] It is not easy for users to find the educational program that best suits them, and it is particularly difficult to provide educational programs that cater to the diverse learning needs and goals of each user. Furthermore, there is a need for a system that individually optimizes educational programs based on users' interests and goals, thereby effectively and efficiently improving the learning experience. Additionally, there are challenges such as the difficulty of accessing user-friendly interfaces using smart devices, and a lack of features to maintain learning motivation and continuity.

[0665] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0666] In this invention, the server includes means for collecting educational information from multiple educational providers, means for acquiring attribute information of individual users, means for constructing educational programs using generative models, means for optimizing educational programs based on interests and goals input by users, and means for providing a user-friendly interface using smart devices. This makes it possible to provide personalized educational programs that meet the learning needs of each user, thereby realizing an effective learning experience.

[0667] An "education provider" is an organization or individual that generates and provides educational information to learners.

[0668] "Educational information" refers to content and materials necessary for learners to acquire specific subjects or skills.

[0669] A "user" is an individual learner who receives an educational program and utilizes its services.

[0670] "Attribute information" refers to information about an individual, including their educational background, skills, interests, and learning goals.

[0671] A "generative model" is an algorithm that generates the optimal educational program based on input educational information and user attribute information.

[0672] "Optimization" is the process of customizing educational programs according to the user's interests and goals to maximize learning effectiveness.

[0673] A "smart device" is a portable electronic device that has computing capabilities and can connect to a network.

[0674] A "user-friendly interface" is a user interface for a computer program that is designed to allow users to operate it intuitively.

[0675] A "personalized education program" is educational content optimized for the specific needs and objectives of a particular user.

[0676] This section describes an embodiment for carrying out the invention. The system that realizes this application collects educational information from various educational providers and generates an optimal educational program using a generative AI model based on the user's attribute information. The server retrieves the latest educational information from the database of educational providers via the internet and stores it in the database. The user accesses the educational platform using a terminal and inputs attribute information such as academic background, skills, and learning goals. This information is securely transmitted from the terminal to the server.

[0677] The server generates educational programs by executing a generative AI model based on collected educational information and user attribute information. This generation process utilizes machine learning frameworks such as TensorFlow and PyTorch. The generated educational programs are then delivered to the user's device. Through the smart device's interface, users can intuitively view and participate in the programs.

[0678] Users can send feedback about the programs they have taken from their devices to the server. The server analyzes this feedback and uses it to create future programs and improve the system. Advertisements are displayed on the platform, and a portion of the revenue is returned to users as points that can be used for further learning.

[0679] As a concrete example, consider a scenario where a user inputs "I want to deepen my knowledge of machine learning" into the app. The system proposes a curriculum that starts with the basics of Python programming and then progresses to detailed lectures on machine learning algorithms. An example of a prompt message would be, "I am interested in machine learning, but I am a beginner in programming. Please propose a curriculum that will allow me to learn efficiently."

[0680] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0681] Step 1:

[0682] The server connects to a database of educational providers via the internet. It collects the latest educational information from these providers and integrates and stores it in the server's database. The input consists of various educational content provided by the providers, and the output is a database of integrated educational information. This process involves data collection, format conversion, and storage in a standardized format.

[0683] Step 2:

[0684] Users access the educational platform from their devices and enter attribute information such as educational background, skills, and learning objectives. This information is sent to the server using secure protocols such as NI. Based on the input from the device, the server updates the user database. The input is user attribute information, and the output is the updated user database. Data validation and encoding are also performed.

[0685] Step 3:

[0686] The server provides integrated educational information and user attribute information as input to a generative AI model. The generative AI model operates using TensorFlow or PyTorch and generates an optimized educational program. The input is integrated educational content and user attribute information, and the output is a customized educational program. This step involves data analysis and algorithmic inference.

[0687] Step 4:

[0688] The server delivers the generated educational program to the user's device. Users can view the educational program through an intuitive interface via their smart device. The input is the data of the generated educational program, and the output is the educational content provided to the user. Data transmission and UI rendering take place here.

[0689] Step 5:

[0690] Users send feedback about the educational programs they have taken from their terminals to the server. The server receives this feedback and analyzes the data to generate future programs and improve the system. The input is the user's feedback, and the output is the analyzed data. In this step, the feedback is analyzed and the feedback data is integrated into the learning model.

[0691] Step 6:

[0692] The server manages advertisements on the platform and generates revenue. A portion of the advertising revenue is returned to users as points, which are recorded in the user database as available rewards. The input is ad viewing data, and the output is point information. Revenue data management and point system updates are performed here.

[0693] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0694] The system of the present invention collects educational information, acquires user information, and generates and provides educational programs by combining a generative model and an emotion engine. Specific embodiments thereof are described below.

[0695] The server connects with databases of multiple education providers via the internet to collect information about educational courses. This collected information is stored in a database on the server and used for later analysis.

[0696] Users access the learning platform using their devices and enter attribute information such as their educational background, work experience, learning objectives, and areas of interest. The device then sends this information to the server.

[0697] The server executes a generative model based on the user's attribute and educational information to design an optimal educational program for the user. In this process, it utilizes an emotion engine to analyze the user's input data and behavioral patterns to understand the user's emotional state.

[0698] The emotional state of the user, as recognized by the emotion engine, is used to optimize the educational program. For example, if a user expresses a loss of interest in learning, the server can suggest more stimulating and engaging content. Similarly, for users experiencing stress, a relaxing learning plan can be created.

[0699] The generated educational programs are delivered to the user via a terminal. The user can select and actually take part in these programs. During learning, the emotion engine continuously monitors the user's emotional state based on their actions and inputs, and dynamically adjusts the program as needed.

[0700] Users send feedback about the programs they have taken from their devices to the server. The server combines this feedback with the results of the emotion engine's analysis to improve the educational programs and fine-tune the generative model. This improves the accuracy of the next educational program recommendations.

[0701] As a concrete example, consider a case where a user interested in AI technology and wanting to learn programming accesses the system. Based on the user's input information and the emotion engine's analysis, the server generates an interactive program that will capture the user's interest. If the emotion engine determines that the user is feeling anxious, it adjusts the learning pace and provides reassuring support. In this way, the user experience is improved and the learning effect is maximized.

[0702] The following describes the processing flow.

[0703] Step 1:

[0704] The server collects educational information from educational providers using APIs and other data acquisition methods. This information includes the content, target audience, fees, and teaching methods of each educational course. The server stores this information in a database and updates it periodically as needed.

[0705] Step 2:

[0706] Users access the learning platform via their device and enter their educational background, work experience, current skills, and areas of interest. They also enter their learning objectives and long-term career goals, and transmit this information from their device to the server.

[0707] Step 3:

[0708] After receiving user attribute information, the server activates the emotion engine to analyze the user's emotional state from the input data. The server uses indicators such as keyboard input speed and selected content patterns to infer the user's psychological state.

[0709] Step 4:

[0710] The server runs a generative model, combining collected educational information, user attribute information, and evaluations from the emotion engine to create an optimal educational program for the user. For example, a user identified as experiencing stress will be offered a more flexible learning plan.

[0711] Step 5:

[0712] The server sends the generated educational program to the terminal and displays it visually to the user. The user can review the provided program, select the course that best suits their needs, and begin learning.

[0713] Step 6:

[0714] The user provides continuous feedback by having their device capture changes in their emotions during learning and their reactions to the tasks they complete. This allows the emotion engine to perform real-time emotion analysis and send it to the server.

[0715] Step 7:

[0716] The server dynamically adjusts the educational program as needed based on the new sentiment analysis results. This makes it possible to rearrange the order of content or add new supplementary materials to engage learners.

[0717] Step 8:

[0718] After completing the learning process, the user sends comprehensive feedback on the entire learning program to the server via their device. The server then continuously optimizes the educational program and generative model based on this feedback and data from the emotion engine.

[0719] (Example 2)

[0720] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] Traditional educational programs often fail to adequately consider the individual needs and emotional states of learners, resulting in low learning effectiveness and satisfaction. Furthermore, the fixed content and delivery methods of these programs make it difficult to incorporate learner feedback for improvement.

[0722] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0723] In this invention, the server includes means for collecting education-related information from multiple educational institutions, means for acquiring attribute data of individual learners, means for designing an educational program using a generative artificial intelligence model based on the education-related information and the learner's attribute data, means for evaluating the learner's emotional state using an emotion analysis engine and optimizing the educational program, and means for receiving feedback from learners and reflecting it in improving the educational program and adjusting the generative model. This makes it possible to provide effective and flexible educational programs tailored to the needs of individual learners.

[0724] An "educational provider" refers to an organization or group that provides information and programs related to learning and training.

[0725] "Education-related information" includes all data related to learning, such as course content, teaching materials, and instructor information for educational programs.

[0726] A "learner" refers to an individual who participates in an educational program with the aim of acquiring specific knowledge or skills.

[0727] "Attribute data" refers to personal information about learners, including educational background, work experience, learning objectives, and areas of interest.

[0728] A "generative artificial intelligence model" refers to an algorithm or system that generates an output that conforms to a specific purpose based on the input information.

[0729] An "emotion analysis engine" refers to a technology or system used to analyze and evaluate an individual's emotional state from input data.

[0730] "Feedback" refers to information provided by participants regarding their opinions, evaluations, and suggestions for improvement regarding the program and learning experience.

[0731] "Learner needs" refer to the knowledge and skills that learners are trying to achieve, as well as their learning objectives and goals.

[0732] Embodiments of the present invention are systems for collecting education-related information, acquiring learner attribute data, and generating and providing educational programs by combining a generative artificial intelligence model and an emotion analysis engine.

[0733] The server collects educational information from multiple educational institutions via the internet. Specifically, the server uses a REST API to connect, retrieves data on educational courses in JSON format, and stores it in a database. This allows for the accumulation of a wealth of educational information, which can then be used for analysis and program design.

[0734] The terminal is operated by the learner and provides a means of accessing the learning platform. The learner inputs attribute data such as their educational background, work experience, learning objectives, and areas of interest, and transmits this information to the server via the terminal. The HTTPS protocol is used for this communication, ensuring secure data transfer.

[0735] The server uses a generative artificial intelligence model to design the optimal educational program based on collected educational information and learner attribute data. During this process, prompt statements are input to the generative AI model to determine the necessary program content. An example of a specific prompt statement would be, "Please suggest a program for beginners who want to learn AI technology."

[0736] Furthermore, the server utilizes an emotion analysis engine to evaluate the learner's emotional state. By analyzing the text and behavioral patterns entered by the learner, it can detect changes in emotions such as loss of interest or stress, and dynamically optimize the educational program. This ensures that learners are provided with the optimal learning pace and content, resulting in an effective learning experience.

[0737] The generated educational programs are delivered to learners via their devices. Learners use these devices to select programs and proceed with their studies. This enhances the individual learner's learning experience and maximizes learning effectiveness.

[0738] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0739] Step 1:

[0740] The server collects education-related information from educational institutions via the internet. Specifically, the server uses a REST API to retrieve data. The input is the API endpoint of the educational institution, and the output is education-related information in JSON format. This information is later stored in a database.

[0741] Step 2:

[0742] Users access the learning platform using their device and enter attribute data such as their educational background, work experience, learning objectives, and areas of interest into a form. The device encrypts the entered data using the HTTPS protocol and sends it to the server. The input is text data entered by the user, and the output is secure data communication passed to the server.

[0743] Step 3:

[0744] The server integrates collected educational information and attribute data received from users, and inputs it into a generative artificial intelligence model. Here, a prompt (e.g., "Please suggest a program for beginners who want to learn AI technology") is provided to the generative AI model. The input consists of educational information and user attribute information, and the output is the content of an optimized educational program.

[0745] Step 4:

[0746] The server analyzes user behavior data using an emotion analysis engine to evaluate the user's emotional state. Input consists of learning behavioral patterns and text data acquired from the device, while output is an analysis result representing the user's emotional state. This analysis dynamically optimizes the program's content and delivery pace.

[0747] Step 5:

[0748] The server delivers the generated educational program to the terminal. The user selects this program using the terminal and begins learning. The input is the program data generated by the server, and the output is the program content displayed on the terminal.

[0749] Step 6:

[0750] After completing the program, users fill out feedback on their terminal and send it to the server. This feedback consists of evaluations of the program and suggestions for improvement. The server then uses this feedback data to adjust its generative model and further improve the educational program. The input is user feedback data, and the output is specific actions taken for improvement.

[0751] (Application Example 2)

[0752] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0753] In modern society, there is a need for individual learners to receive educational programs tailored to their own attributes and interests. Furthermore, there is a need to develop systems that enable dynamic educational delivery that takes into account the emotional state of learners. However, conventional systems have made it difficult to adjust educational plans to reflect emotional states, making it challenging for learners to obtain the optimal educational experience.

[0754] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0755] In this invention, the server includes means for collecting educational resources from multiple educational providers, means for acquiring attribute data of individual users, and means for generating educational plans using an artificial intelligence model, adjusting them according to the user's emotional state using an emotion recognition engine, and providing them. This makes it possible to provide personalized educational experiences based on the user's attributes and emotional state.

[0756] "Educational resources" refer to information and data such as curricula, teaching materials, and educational content collected from education providers.

[0757] "User attribute data" refers to information such as the educational background, work history, learning objectives, and areas of interest of individual learners.

[0758] An "artificial intelligence model" is a machine learning algorithm used to generate an optimal educational plan based on user attribute data and educational resources.

[0759] An "emotion recognition engine" is software that analyzes a user's behavior patterns and input data to understand their emotional state.

[0760] An "educational plan" is a learning program tailored to the user, generated by an artificial intelligence model and adjusted by an emotion recognition engine.

[0761] A "virtual system" refers to a platform that users can access online and purchase or use educational media and resources.

[0762] The invention describes embodiments for carrying out the invention. This invention collects educational resources from multiple educational providers onto a server, and users access it to provide an optimal educational plan for each individual learner.

[0763] The server connects with a database of educational providers via the internet to collect educational resources. The collected resources are stored in the server's database and used for later analysis. Users access the virtual system using a terminal and input their attribute data, including educational background, work experience, learning objectives, and areas of interest. The terminal then transmits the collected attribute data to the server.

[0764] The server generates an educational plan tailored to the user by running an artificial intelligence model using accumulated educational resources and user attribute data. In this process, it utilizes an emotion recognition engine to analyze the user's input data and behavioral patterns to understand their emotional state. Based on the emotional state obtained by the emotion recognition engine, the educational plan is dynamically adjusted to provide the user with an optimal learning experience.

[0765] A concrete example would be a user who wants to learn programming accessing a virtual system. In this case, the server would suggest a programming course for beginners and provide reassuring support by adjusting the learning pace if the user expresses concerns. This would allow the user to learn at their own pace.

[0766] An example of a prompt message used is: "User information: {'Education': 'High school graduate', 'Work experience': 'None', 'Learning objective': 'Career advancement', 'Areas of interest': 'Programming'} Emotional state: 'Anxious' Please provide the optimal educational program." This enables the use of a generative AI model to provide an educational plan tailored to the user.

[0767] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0768] Step 1:

[0769] The server collects educational resources from databases of multiple educational providers via the internet. It stores the retrieved educational content data locally and prepares it for analysis. The input is the query results from the educational provider databases, and the output is the educational resources recorded in the server's database.

[0770] Step 2:

[0771] Users access a virtual system through a terminal and input attribute data such as educational background, work experience, learning objectives, and areas of interest. This data is sent to the server in real time and stored for the next process. The input is attribute data from the user, and the output is user information transferred to the server.

[0772] Step 3:

[0773] The server uses the received user attribute data and stored educational resources to run a generative AI model and generate a new educational plan. The input is the user's attribute data and educational resources, and the output is the optimal educational plan. During the generation process, machine learning algorithms are applied to combine diverse data to construct an appropriate learning plan.

[0774] Step 4:

[0775] The server further utilizes an emotion recognition engine to analyze user input data and behavioral patterns to understand their emotional state. Input consists of user behavior logs and reaction data, providing information about their emotional state. Output is analytical data regarding the user's emotional state.

[0776] Step 5:

[0777] Based on the output of the emotion recognition engine, the server dynamically adjusts the educational plan to prevent stress and loss of interest. The input is the educational plan and emotional state data, and the output is the adjusted educational plan. Specifically, this involves readjusting the learning pace and changing the content balance.

[0778] Step 6:

[0779] The server provides the adjusted educational plan to the terminal and prepares the environment for the user to begin learning. The user can then take the educational program and learn based on this plan. The input is the adjusted educational plan, and the output is the learning content provided to the user.

[0780] Step 7:

[0781] Users send learning progress and feedback from their devices to the server. The server then uses this feedback to further improve the educational plan. The input is user feedback data, and the output is improvement data that can be used to inform the next educational plan.

[0782] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0783] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0784] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0785] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0786] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0787] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0788] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0789] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0790] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0791] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0792] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0793] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0794] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0795] 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.

[0796] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0797] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0798] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0799] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0800] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0801] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0802] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0803] The following is further disclosed regarding the embodiments described above.

[0804] (Claim 1)

[0805] Means of collecting educational information from multiple educational providers,

[0806] A means of obtaining attribute information for individual users,

[0807] A means for generating an educational program using a generative model based on the aforementioned educational information and user attribute information,

[0808] Means for providing the generated educational program to the user,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, which receives user feedback and incorporates it into improvements to the educational program.

[0812] (Claim 3)

[0813] The system according to claim 1, which returns a portion of the funds obtained through advertising revenue to users as points.

[0814] "Example 1"

[0815] (Claim 1)

[0816] Means of collecting educational data obtained from educational institutions,

[0817] Means for obtaining user characteristic information,

[0818] A means for creating educational content using a generation algorithm based on the aforementioned educational data and user characteristic information,

[0819] A means of presenting the aforementioned created educational content to users,

[0820] A means for dynamically displaying relevant commercial information to the user,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, which receives user feedback and uses it to improve educational content.

[0824] (Claim 3)

[0825] The system according to claim 1, which provides users with a portion of the resources obtained through revenue from commercial information as compensation.

[0826] "Application Example 1"

[0827] (Claim 1)

[0828] Means of collecting educational information from multiple educational providers,

[0829] A means of obtaining attribute information of individual users,

[0830] A means for constructing an educational program using a generative model based on the aforementioned educational information and user attribute information,

[0831] Means for providing the generated educational program to users,

[0832] A means of optimizing educational programs based on user inputs of interests and goals,

[0833] A means of providing a user-friendly interface using smart devices,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, which receives feedback from users and incorporates it into improvements to the educational program.

[0837] (Claim 3)

[0838] The system according to claim 1, which returns a portion of the funds obtained through advertising revenue to users as points.

[0839] "Example 2 of combining an emotion engine"

[0840] (Claim 1)

[0841] Means of collecting education-related information from multiple educational institutions,

[0842] A means of obtaining attribute data for individual learners,

[0843] A means for designing an educational program using a generative artificial intelligence model based on the aforementioned educational information and learner attribute data,

[0844] A means of evaluating learners' emotional states using an emotion analysis engine and optimizing educational programs,

[0845] Means for providing the generated educational program to learners,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, which receives feedback from learners and uses it to improve the educational program and adjust the generative model.

[0849] (Claim 3)

[0850] The system according to claim 1, wherein a portion of the funds obtained through advertising revenue is returned to learners as compensation.

[0851] "Application example 2 of combining emotional engines"

[0852] (Claim 1)

[0853] Means of collecting educational resources from multiple educational providers,

[0854] A means of obtaining attribute data for individual users,

[0855] A means for generating an educational plan using an artificial intelligence model based on the aforementioned educational resources and user attribute data,

[0856] A means for adjusting and providing the aforementioned generated educational plan according to the user's emotional state using an emotion recognition engine,

[0857] A means of recommending appropriate educational media within a virtual system,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system described in claim 1, which receives feedback from users and incorporates it into improvements to the educational plan.

[0861] (Claim 3)

[0862] The system according to claim 1, wherein a portion of the assets obtained through profits is returned to the users as a reward. [Explanation of Symbols]

[0863] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting educational information from multiple educational providers, A means of obtaining attribute information for individual users, A means for generating an educational program using a generative model based on the aforementioned educational information and user attribute information, Means for providing the generated educational program to the user, A system that includes this.

2. The system according to claim 1, which receives user feedback and incorporates it into improvements to the educational program.

3. The system according to claim 1, which returns a portion of the funds obtained through advertising revenue to users as points.

Images