system

Abstract

We provide the system. [Solution] Means for collecting educational information and evaluating it based on reliability and accuracy, A means for receiving user learning requests and generating an optimal learning plan based on them, A means of calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information, A means for presenting an optimal educational plan in response to user input in an information processing device and adjusting the plan via an artificial intelligence agent, 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, 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 the modern educational environment, while there is a vast amount of educational content on the Internet, the uncertainty of its accuracy and reliability has become a factor hindering the educational progress of learners. Also, due to the decrease in educational providers and the increasing burden in the educational field, it has become difficult to consistently provide high-quality education. For this reason, the development of a system that can efficiently and reliably utilize various educational resources is required.

Means for Solving the Problems

[0005] This invention provides a means for evaluating educational content based on reliability and accuracy and collecting it centrally in a database. Furthermore, it includes a means for receiving individual learning requests from users and generating an optimal learning plan from the database accordingly, thereby addressing individual learning needs. In addition, it incorporates a means for monitoring usage and calculating rewards based on the frequency and conditions of use of selected content, thereby ensuring incentives for educational providers and realizing a sustainable educational ecosystem.

[0006] "Educational content" refers to teaching materials or collections of teaching materials used to impart knowledge and skills to learners, and includes a variety of formats such as videos, texts, and interactive exercises.

[0007] "Reliability" is an indicator of the quality of information and data, showing that they are accurate and do not cause errors or misunderstandings when used.

[0008] "Accuracy" is a characteristic that indicates how closely information or data matches the truth or facts, and it is the degree to which it guarantees that there are no errors or biases.

[0009] "Evaluation" is the act of analyzing and judging the value and quality of information or data based on specific criteria.

[0010] A "database" is a system that structures, records, and stores information in a digital format, making it searchable and accessible as needed.

[0011] "Learning requirements" refer to the unique needs of learners who seek to acquire specific knowledge or skills in order to achieve their educational goals.

[0012] A "learning plan" is a specific schedule or sequence that determines the optimal learning methods, materials, and time allocation for a learner to achieve their goals.

[0013] "Usage frequency" is a metric that measures how often a particular resource or service is used.

[0014] "Compensation" refers to the price or incentive paid for a particular action or contribution. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is an educational system that effectively collects and evaluates educational content and provides users with an optimal learning experience. This system is primarily realized through multi-layered interaction between servers, terminals, and users.

[0037] The server has the capability to collect educational content from the internet and internal databases. During this collection process, the server evaluates the collected content based on reliability and accuracy standards and automatically registers it in the database. This ensures that users have access to quality-assured educational resources.

[0038] The terminal receives input from the user, sends it to the server, and then presents the user with a learning plan based on that input. Specifically, when the user inputs what they want to learn and their goals into the terminal, the server selects the most suitable learning content from the database via an AI agent and generates a learning plan. This includes presenting learning materials tailored to the learner's learning style and arranging them in an appropriate order.

[0039] Users progress through their learning via their devices, following the provided learning plan. They can send feedback to their devices as needed, allowing the AI ​​agent to review and adjust the plan. The server also monitors the user's learning progress via the devices and stores the data.

[0040] This system also includes a reward management system that calculates and pays content providers rewards based on usage. For example, if a particular educational content meets a certain usage frequency, the provider will receive appropriate compensation, promoting the sustainable supply of educational resources.

[0041] As described above, the present invention provides a means to significantly improve the quality and efficiency of education, and realizes a highly convenient educational environment for both users and educators.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server connects to the internet and the company's internal database to collect educational content. During this process, it identifies and collects new information and updated resources.

[0045] Step 2:

[0046] The server performs a process to evaluate the reliability and accuracy of the educational content it collects. The content is filtered according to pre-defined criteria, and unsuitable content is excluded.

[0047] Step 3:

[0048] The server registers evaluated educational content in a database and adds metadata to enable efficient searching.

[0049] Step 4:

[0050] The user operates the device and inputs what they want to learn and their goals. This includes specific topics and desired learning periods.

[0051] Step 5:

[0052] The device sends user input to the server, and an AI agent is used to generate an optimal learning plan. Based on this request, the server selects relevant content from its database.

[0053] Step 6:

[0054] The server creates a customized learning plan, determining the order of learning materials and learning steps. This is then sent to the terminal and presented to the user.

[0055] Step 7:

[0056] The user progresses through the learning plan provided. During the learning process, the user can send progress updates and feedback via their device.

[0057] Step 8:

[0058] The server monitors learning progress and accumulates learning history data. This allows for the collection of data that can be used to improve the next learning plan.

[0059] Step 9:

[0060] The system analyzes data on the educational content used by the server and calculates compensation based on usage frequency. The calculated compensation is then paid to the content provider.

[0061] Step 10:

[0062] After the device completes the learning process, it provides feedback to the user on their learning outcomes and suggests the next learning content. This promotes continuous learning.

[0063] (Example 1)

[0064] 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."

[0065] While there is a need to manage the quality of educational information and provide flexible learning plans that meet the individual needs of learners, there is a lack of means to efficiently collect reliable content from a large amount of educational information and to improve the learning experience by utilizing the progress and feedback of individual users. Furthermore, paying educational information providers fair compensation based on the usage of educational information is also a challenge.

[0066] 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.

[0067] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for receiving users' learning requests and generating an optimal learning plan based on them, and means for calculating rewards for educational information selected from a large amount of information based on usage frequency and conditions. This enables the collection and evaluation of reliable information, the provision of learning plans based on individual learning styles, and the fair distribution of rewards for educational information.

[0068] "Educational information" refers to materials and data that enable learners to acquire the knowledge and skills they need, and includes teaching materials and course content.

[0069] "Reliability" is the characteristic that guarantees information is accurate and free from errors.

[0070] "Accuracy" refers to a state in which information is based on facts, is unambiguous, and serves its purpose.

[0071] "User learning requirements" refer to the goals that learners aim for, the skills they want to acquire, and their specific learning needs.

[0072] A "learning plan" is a plan that outlines an efficient learning flow and steps, tailored to the learner's objectives.

[0073] A "generative AI model" is a type of artificial intelligence that has the ability to generate new information and plans based on diverse data.

[0074] "Frequency of use" is an indicator that shows how often information or services are used within a specific period of time.

[0075] "Compensation" refers to monetary payment made to educational information providers based on the value and usage of their content.

[0076] "Feedback" refers to information about opinions and reactions obtained from learners, which is used to improve learning.

[0077] "Dynamic generation" refers to the process of adjusting and generating information and plans in real time according to the user's situation.

[0078] This invention includes a system for collecting and evaluating educational information and providing an optimized learning experience for individual learners. The overall process is primarily achieved through collaboration between a server, terminals, and users.

[0079] The server collects educational information using the internet and the company's internal database. This collection process uses software such as web crawlers to verify the source of each piece of information. The collected information is stored in temporary storage and then evaluated for reliability and accuracy using natural language processing algorithms. Once the evaluation is complete, the information is formally registered in the database.

[0080] The terminal receives learning requests from users and formats them into a data format for transmission to the server. At the same time, it provides an intuitive user interface to allow users to specifically set the content and goals they wish to learn.

[0081] Based on the received request, the server generates an optimal learning plan using a generative AI model. The AI ​​model utilizes learning algorithms to select relevant educational information and materials, dynamically creating a plan tailored to the user's learning style. This dynamic generation process is driven by instructions given to the AI ​​model via prompts. For example, a prompt might ask, "How do I generate the optimal learning plan based on the user's specified goals?"

[0082] Users can progress through their learning using the learning plan displayed on their device. Learning progress and user feedback are sent to the server via the device. The server analyzes this data, uses an AI agent to re-evaluate the plan, and makes adjustments as needed.

[0083] For example, if a user enters "I want to learn programming," the server searches its database for reliable programming learning materials, generates learning steps tailored to the user's progress level, and displays them on the terminal. In this way, it supports the learner in reaching their goals.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server collects educational information from the internet and internal databases. Input is educational information from the internet and internal databases, and output is raw data stored in temporary storage. Specifically, it uses a web crawler to visit specific educational pages, extracts the necessary information, and stores it temporarily.

[0087] Step 2:

[0088] The server evaluates the collected educational information. The input is raw data from temporary storage, and the output is information that has been evaluated for reliability and accuracy. The server uses natural language processing algorithms to analyze the source and content of the information, determine whether it meets the specified evaluation criteria, and register the approved information in the database.

[0089] Step 3:

[0090] The terminal receives learning requests from the user. The input is the user's learning objectives and requests, and the output is processing request data sent to the server. Specifically, the user inputs a request such as "I want to learn English conversation" through the user interface, and the terminal formats it into the appropriate format.

[0091] Step 4:

[0092] The server searches a database of educational information for relevant data based on the learning request it receives. The input is the user's request data, and the output is the relevant educational information. A generative AI model is used, given a prompt as input, to dynamically generate a learning plan suitable for the user. For example, the prompt "What plan would you recommend if I wanted to learn intermediate-level English?" might be used.

[0093] Step 5:

[0094] The terminal presents the generated learning plan to the user. The input is the learning plan sent from the server, and the output is the learning steps and learning material information displayed on the terminal screen. Specifically, the learning content is displayed on the screen in stages, allowing the user to progress while checking their progress.

[0095] Step 6:

[0096] As users progress through the learning process, they send feedback via their device. The input is user feedback information, and the output is adjustment request data sent to the server. Specifically, users input feedback such as "This chapter is difficult," and the device sends this to the server.

[0097] Step 7:

[0098] The server analyzes the received feedback and adjusts the learning plan. The input is the user's feedback data, and the output is the newly adjusted learning plan. An AI agent is used to analyze the feedback, reconstruct the plan, and send it to the device.

[0099] (Application Example 1)

[0100] 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."

[0101] Traditional education systems struggle to propose individualized learning plans and flexibly adjust plans according to learners' progress. Furthermore, they lack sufficient evaluation to enhance the reliability of educational information, making it difficult to access high-quality learning resources. Therefore, there is a need to provide users with the optimal learning experience and make access to reliable educational information easier.

[0102] 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.

[0103] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy; means for receiving the user's learning request and generating an optimal learning plan based thereon; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; and means for presenting an optimal educational plan in response to the user's input in an information processing device and adjusting the plan via an artificial intelligence agent. As a result, users can effectively utilize highly reliable educational information and receive a flexible learning plan that meets their individual learning needs.

[0104] "Educational information" refers to various data and materials used to enhance learners' knowledge and improve their skills.

[0105] "Reliability" refers to the characteristic that information and systems are accurate and can consistently deliver results that meet user expectations.

[0106] "Accuracy" refers to the degree to which information or data matches actual facts or standards.

[0107] "Learning requirements" refer to the content and goals that learners hope to achieve in order to acquire specific knowledge or skills.

[0108] A "learning plan" is a plan designed to help learners efficiently acquire knowledge and skills.

[0109] An "information processing device" refers to a digital device such as a computer or smartphone, which is used for collecting, processing, and displaying data.

[0110] An "artificial intelligence agent" refers to a program that makes autonomous decisions based on human instructions through machine learning and data analysis.

[0111] "Educational data" refers to information and numerical data related to education, which is used for evaluating and analyzing educational resources.

[0112] The server collects educational information extensively using the internet and internal databases, and evaluates the collected information based on its reliability and accuracy. This evaluation is based on factors such as the source of the information and its past usage history. The server stores the evaluated information and registers it in a database accessible to users.

[0113] The terminal accepts the user's learning requests as input. When a user enters a specific goal into the terminal, such as "I want to deeply understand trigonometric functions," that request is sent to the server. The server uses a generative AI model to generate the optimal learning plan from the database for that request. This generation process also takes into account the user's past learning history and progress. The generated learning plan is presented to the user via an information processing device.

[0114] As users progress through the learning plan presented via their device, they provide feedback to the device based on their progress and understanding. This feedback information is sent to a server, where an artificial intelligence agent analyzes it and flexibly adjusts the learning plan as needed. The server also has a function to calculate rewards based on the frequency and conditions of use of educational data and pay appropriate compensation to educational information providers.

[0115] For example, if a high school student enters into the app that they "want to deeply understand trigonometry," the system will provide a series of learning plans, including suitable materials and assignments, based on that request. As the user progresses through their daily studies using the plan, they can provide feedback on areas where their understanding is insufficient, and the AI ​​agent will optimize the plan accordingly, enabling effective learning.

[0116] An example of a prompt message would be, "What to learn next week: Trigonometry. Suggest a learning level and update the plan based on your progress. Allow users to manage their own pace." This allows you to provide a learning experience optimized for the user.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server collects educational information from the internet and internal databases. Input data consists of information from websites and online resources, while output is educational information evaluated for reliability and accuracy. Specifically, the server uses scraping techniques to organize and store the information as structured data.

[0120] Step 2:

[0121] The user inputs learning requests into the device. These requests specify what the user wants to learn and their goals, and the output is request data based on these requests. For example, the user might input text such as "I want to understand trigonometry in depth" into the smartphone app.

[0122] Step 3:

[0123] The server uses a generative AI model to generate the optimal learning plan from the database. The input is the user's request data and past learning history, and the output is a learning plan tailored to each user. The server uses the AI ​​model to filter educational information and select content suitable for the user.

[0124] Step 4:

[0125] The device presents the generated learning plan to the user. The input is the learning plan data sent from the server, and the output is the user's viewing. Specifically, the device's app displays the plan in an easy-to-understand manner, and the user proceeds with their learning based on it.

[0126] Step 5:

[0127] Users input their learning progress into their device and provide feedback. Input is text or progress metrics based on their learning status, and output is feedback data sent to the server. Through the progress screen, users fill in their level of understanding and areas they find difficult.

[0128] Step 6:

[0129] The server analyzes feedback data and adjusts the learning plan using an artificial intelligence agent. Inputs are user feedback and learning scores, and output is the updated learning plan. The server uses machine learning algorithms to modify the difficulty level and order of learning materials as needed.

[0130] Step 7:

[0131] The server analyzes the frequency of use of educational information and calculates rewards. The input is historical data on the use of educational information, and the output is the reward amount. Specifically, the server uses a statistical model to evaluate the value of the educational information.

[0132] 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.

[0133] This invention relates to a system for collecting and evaluating educational content and generating learning plans tailored to users' learning needs. A key feature of this system is the incorporation of an emotion engine that recognizes the user's emotions and optimizes the learning experience based on those emotions. Specifically, the system includes a server, a terminal, and the emotion engine.

[0134] The server collects educational content through the internet and internal data sources. The collected content is evaluated based on reliability and accuracy and registered in a database. Furthermore, the server assigns metadata to this content, enabling efficient searching and selection.

[0135] The device receives learning requests from the user and sends them to the server. During this process, the emotion engine recognizes the user's current emotional state and reflects it in the learning plan. For example, if the user is feeling stressed, the emotion engine will make adjustments such as suggesting content with a relaxing effect.

[0136] As a concrete example, a user inputs "I want to learn probability theory in mathematics" via their device. The emotion engine uses cameras and sensors to analyze the user's facial expressions and voice. If the user appears calm, it presents standard learning materials; if the user shows signs of anxiety, it presents materials with a lower difficulty level or interactive practice problems.

[0137] The emotion engine continuously monitors user emotional data, which is recorded in a database along with learning progress. This data is used to optimize future learning plans, providing a personalized learning environment for each user.

[0138] By incorporating an emotion engine in this way, it becomes possible to provide educational content tailored to the individual emotions of users, thereby maximizing learning efficiency. Furthermore, it has a function to calculate rewards based on the frequency and conditions of use of learning content, promoting the sustainable provision of educational resources. Thus, this invention provides an innovative educational system that flexibly responds to diverse learning needs.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server periodically collects educational content from the internet and internal databases. During collection, the content is categorized by format and content, and evaluated based on reliability and accuracy criteria. Inappropriate content is excluded during this process.

[0142] Step 2:

[0143] The server registers evaluated educational content in a database and adds metadata, enabling efficient searching.

[0144] Step 3:

[0145] The user uses their device to input the topics and goals they want to learn. For example, the user might input, "I want to learn the basics of programming."

[0146] Step 4:

[0147] The device's built-in emotion engine uses the camera and microphone to analyze the user's facial expressions and voice tone in real time to determine their current emotional state. If the system determines that the user is relaxed, it will then analyze the user's emotional state.

[0148] Step 5:

[0149] The device sends the emotion data recognized by the emotion engine and the user's request to the server.

[0150] Step 6:

[0151] The server considers emotional data to select the most suitable learning content from the database. For example, if the user is relaxed, it might suggest a fast-paced video lecture.

[0152] Step 7:

[0153] The server generates a customized learning plan that includes selected learning content and sends it to the device.

[0154] Step 8:

[0155] The device will display a learning plan to the user, allowing them to manage their progress step by step.

[0156] Step 9:

[0157] The user progresses through the learning process via their device. During the learning process, the emotion engine monitors the user's emotional state again, and if stress levels increase, it makes adjustments such as inserting easier practice problems.

[0158] Step 10:

[0159] After the learning session is complete, the device collects user feedback and sends it to the server. The server records this data to be used in the next learning plan.

[0160] Step 11:

[0161] Based on usage data collected by the server, the frequency of use of educational content is analyzed, and compensation is calculated and paid to content providers accordingly.

[0162] Step 12:

[0163] At the end of each session, the device provides the user with feedback on their learning achievements and progress, and offers learning suggestions for the next session. This provides users with a learning environment that allows for continuous growth.

[0164] (Example 2)

[0165] 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".

[0166] Traditional education systems have struggled to provide flexible and personalized educational experiences that respond to users' learning needs and emotional states. Furthermore, the selection and evaluation of collected educational information, the improvement of search efficiency, and the calculation of rewards have not been optimal, resulting in a failure to maximize learning efficiency.

[0167] 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.

[0168] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for recognizing the user's emotional state and optimizing educational activities based on that state, and means for providing educational information adapted to the user according to the generated learning plan. This makes it possible to provide an optimal educational experience that is tailored to each user's individual learning needs and emotional state.

[0169] "Educational information" refers to all educational materials and content intended for use by learners, and is collected after being evaluated for reliability and accuracy.

[0170] A "learning plan" refers to a set of procedures and strategies for providing educational information that are optimized based on the user's learning needs and emotional state.

[0171] "User emotional state" refers to information that indicates the learner's psychological and emotional condition and is used to optimize the learning plan.

[0172] "Feature data" refers to classification tags and attribute information assigned to collected educational information, and its purpose is to improve the efficiency of searches.

[0173] "Reward" refers to the value or benefit calculated based on the frequency and conditions of use of educational information selected from a large amount of data.

[0174] The system implementing this invention primarily consists of a server, terminals, and an emotion engine. The server collects educational information through the internet and internal data sources. This information is evaluated based on reliability and accuracy and registered in a database. Specifically, the server periodically accesses online educational platforms and open databases via APIs to obtain the latest information.

[0175] The terminal is a device that receives learning requests from users and sends data entered via the user interface to the server. For example, if a user enters "I want to learn probability theory in mathematics," that information is sent to the server and processed.

[0176] The emotion engine uses hardware such as cameras and microphones to analyze the user's facial expressions and voice, and to identify their emotional state. This allows the server to generate an optimized learning plan based on the user's emotional state and adjust the learning content as needed.

[0177] Based on the generated learning plan, the device provides personalized educational information to the user. Learning progress and emotional data are seamlessly monitored through the emotion engine, and feedback is provided as needed. This cycle continuously optimizes the user's learning experience.

[0178] Based on this embodiment, it becomes possible to provide educational experiences tailored to the individual user's requirements and emotions. The innovativeness of this system lies in its dynamic content delivery powered by an emotion engine and its promotion of efficient learning.

[0179] A concrete example of a prompt is: "If a user wants to learn probability theory in mathematics but is currently feeling insecure, what kind of learning materials would be most effective to suggest?" Such prompts can be used with generative AI models to optimize learning plans.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The server collects educational information from the internet and internal data sources. Inputs include source URLs and API keys for educational information, while output is raw educational data. Specifically, the server periodically accesses designated information sources and runs programs to automate data collection.

[0183] Step 2:

[0184] The server evaluates the collected educational information. The input is the raw educational data collected in Step 1, and its reliability and accuracy are evaluated. The output is the evaluation result, which is registered in the database. Specifically, an algorithm is used to analyze the source of the information and past reliability evaluation scores, and high-rated content is selected.

[0185] Step 3:

[0186] The server assigns feature data to evaluated educational information. The input is evaluated educational data, and the output is educational content with specific feature data assigned to it. In this process, tagging, categorization, and difficulty levels are added to organize the information and improve subsequent search efficiency.

[0187] Step 4:

[0188] The terminal receives learning requests from the user. The input is the learning request entered by the user, such as a specific request like "I want to learn probability theory in mathematics." The output is the request data sent to the server. In operation, the request data is input via the terminal's user interface and sent to the server in a formatted form.

[0189] Step 5:

[0190] The device recognizes the user's emotional state and transmits it to the server. Input is the user's voice and facial expression data, and output is analyzed emotional data. Specifically, it collects emotional data using a camera and microphone, and this data is analyzed in real time by an emotion engine.

[0191] Step 6:

[0192] The server generates a learning plan based on the user's learning needs and emotional state. The input is the learning needs and emotional data, and the output is a customized learning plan. The server utilizes a generative AI model to design the optimal learning path for each user. Prompts and other prompts may be used in this process.

[0193] Step 7:

[0194] The terminal presents educational information to the user according to the learning plan received from the server. The input is the customized learning plan, and the output is the educational content displayed to the user. Interactive learning materials and videos are used here to specifically support the user's learning experience.

[0195] (Application Example 2)

[0196] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0197] In education, it is difficult to provide an optimal educational experience tailored to the emotional state of individual users. Furthermore, the recommendation of content that meets diverse educational needs is not efficient, and there is a lack of effective means to promote individualized learning. As a result, improvements in educational efficiency are hindered, potentially leading to a decline in users' motivation to learn.

[0198] 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.

[0199] In this invention, the server includes means for collecting educational data and evaluating it based on reliability and accuracy; means for accepting the user's educational requests and generating an optimal educational plan based on them; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; means for recognizing emotions and optimizing the educational experience; a program for analyzing visual and auditory data to identify the user's emotional state; and means for recommending educational data that corresponds to the user's emotions. This makes it possible to provide an effective and personalized educational experience that corresponds to the user's emotions.

[0200] "Educational data" refers to all information used for educational purposes for individual users, and its reliability and accuracy are the criteria for evaluation.

[0201] "Educational requirements" refer to the user's desires regarding the knowledge and skills they seek in their learning.

[0202] An "educational plan" refers to a program designed to optimize the learning flow and methods based on the user's learning needs.

[0203] "Massive amounts of information" refers to the vast amount of education-related information collected via the internet and internal databases.

[0204] "Frequency of use" indicates how often a particular piece of educational data is used.

[0205] "Conditions" refer to the specific circumstances or factors under which educational data is used.

[0206] "Rewards" refer to evaluations or points calculated based on the frequency and conditions of use of educational data.

[0207] "Recognizing emotions" is the process of analyzing the user's facial expressions and voice data to identify their current emotional state.

[0208] "Visual and auditory data" refers to various data formats, including the user's facial expressions and voice, and is used for emotion recognition.

[0209] A "program" refers to a set of instructions or procedures designed to achieve a specific purpose.

[0210] "Educational experience" refers to the overall experience that individual users gain through educational content.

[0211] "Optimization" refers to adjusting and improving the educational experience in the most effective way for the user.

[0212] "Recommendation" means suggesting the most suitable educational data and content for the user.

[0213] The system in this invention mainly consists of a server, a terminal, and a program incorporating an emotion recognition engine. The server collects educational data via a wide range of internet resources and an internal database, and evaluates its reliability and accuracy. The hardware to be used is assumed to be a server with a high-performance processor and large-capacity storage. The software includes a database management system (e.g., MySQL®) for data analysis and management.

[0214] Next, the device accepts the user's educational requests and sends them to the server. It also uses the camera and microphone to acquire the user's visual and audio data, which is then analyzed in real time by an emotion recognition engine. This engine incorporates algorithms to identify emotional states using machine learning libraries (e.g., TENSORFLOW®).

[0215] Once the user's emotional state is analyzed, optimized educational data is recommended. For example, if a user inputs "I want to learn basic chemistry" and displays a stable emotional state, the system will suggest content of normal difficulty. On the other hand, if the system detects that the user is agitated, it will provide more interactive learning materials. A concrete example of a prompt might be, "If the user's facial expression indicates they are relaxed, present them with a slideshow about basic chemistry."

[0216] This allows for the automatic recommendation of educational programs tailored to individual users, thereby improving the quality of the learning experience.

[0217] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0218] Step 1:

[0219] The server collects educational data from the internet and internal data sources. Input consists of information from various online resources and databases, which are integrated to create an educational database. Data analysis techniques are used to assess reliability and accuracy, and inappropriate data is filtered out to produce curated educational information.

[0220] Step 2:

[0221] The terminal receives educational requests from the user. The user inputs the content they want to learn as text, and this is recorded by the terminal. This request is then forwarded from the terminal to the server, which selects appropriate educational data based on the user's request and develops an educational plan. This is where data mining techniques by the server are utilized.

[0222] Step 3:

[0223] The device acquires the user's visual and auditory data. Using the camera and microphone, it captures changes in facial expressions and voice in real time. This data serves as input for analysis by the emotion engine.

[0224] Step 4:

[0225] The emotion engine analyzes visual and audio data transmitted from the device. Using machine learning models, it identifies the user's emotional state, and the data is output as emotion tags. These tags are then used to recommend educational data.

[0226] Step 5:

[0227] The server recommends educational data based on the user's educational needs and sentiment tags. The input consists of educational needs and sentiment tags, which are used to execute a search algorithm and output the most suitable educational content.

[0228] Step 6:

[0229] The terminal presents the user with recommended data received from the server. It displays the educational data in the format most suitable for the user (e.g., interactive materials or videos) and initiates the educational experience. Here, prompt messages are used to specify the content to be presented.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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".

[0246] This invention is an educational system that effectively collects and evaluates educational content and provides users with an optimal learning experience. This system is primarily realized through multi-layered interaction between servers, terminals, and users.

[0247] The server has the capability to collect educational content from the internet and internal databases. During this collection process, the server evaluates the collected content based on reliability and accuracy standards and automatically registers it in the database. This ensures that users have access to quality-assured educational resources.

[0248] The terminal receives input from the user, sends it to the server, and then presents the user with a learning plan based on that input. Specifically, when the user inputs what they want to learn and their goals into the terminal, the server selects the most suitable learning content from the database via an AI agent and generates a learning plan. This includes presenting learning materials tailored to the learner's learning style and arranging them in an appropriate order.

[0249] Users progress through their learning via their devices, following the provided learning plan. They can send feedback to their devices as needed, allowing the AI ​​agent to review and adjust the plan. The server also monitors the user's learning progress via the devices and stores the data.

[0250] This system also includes a reward management system that calculates and pays content providers rewards based on usage. For example, if a particular educational content meets a certain usage frequency, the provider will receive appropriate compensation, promoting the sustainable supply of educational resources.

[0251] As described above, the present invention provides a means to significantly improve the quality and efficiency of education, and realizes a highly convenient educational environment for both users and educators.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server connects to the internet and the company's internal database to collect educational content. During this process, it identifies and collects new information and updated resources.

[0255] Step 2:

[0256] The server performs a process to evaluate the reliability and accuracy of the educational content it collects. The content is filtered according to pre-defined criteria, and unsuitable content is excluded.

[0257] Step 3:

[0258] The server registers evaluated educational content in a database and adds metadata to enable efficient searching.

[0259] Step 4:

[0260] The user operates the device and inputs what they want to learn and their goals. This includes specific topics and desired learning periods.

[0261] Step 5:

[0262] The device sends user input to the server, and an AI agent is used to generate an optimal learning plan. Based on this request, the server selects relevant content from its database.

[0263] Step 6:

[0264] The server creates a customized learning plan, determining the order of learning materials and learning steps. This is then sent to the terminal and presented to the user.

[0265] Step 7:

[0266] The user progresses through the learning plan provided. During the learning process, the user can send progress updates and feedback via their device.

[0267] Step 8:

[0268] The server monitors learning progress and accumulates learning history data. This allows for the collection of data that can be used to improve the next learning plan.

[0269] Step 9:

[0270] The system analyzes data on the educational content used by the server and calculates compensation based on usage frequency. The calculated compensation is then paid to the content provider.

[0271] Step 10:

[0272] After the device completes the learning process, it provides feedback to the user on their learning outcomes and suggests the next learning content. This promotes continuous learning.

[0273] (Example 1)

[0274] 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."

[0275] While there is a need to manage the quality of educational information and provide flexible learning plans that meet the individual needs of learners, there is a lack of means to efficiently collect reliable content from a large amount of educational information and to improve the learning experience by utilizing the progress and feedback of individual users. Furthermore, paying educational information providers fair compensation based on the usage of educational information is also a challenge.

[0276] 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.

[0277] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for receiving users' learning requests and generating an optimal learning plan based on them, and means for calculating rewards for educational information selected from a large amount of information based on usage frequency and conditions. This enables the collection and evaluation of reliable information, the provision of learning plans based on individual learning styles, and the fair distribution of rewards for educational information.

[0278] "Educational information" refers to materials and data for learners to acquire the knowledge and skills they need, including teaching materials and course content.

[0279] "Reliability" is a characteristic that guarantees that information is accurate and free from errors.

[0280] "Accuracy" refers to the state where information is based on facts and meets the purpose without causing misunderstandings.

[0281] "Learner's learning requirements" mean the goals learners aim for, the skills they want to acquire, and their specific needs in learning.

[0282] "Learning plan" refers to a plan that shows an efficient learning process and steps configured according to the purposes of learners.

[0283] "Generative AI model" is a type of artificial intelligence that has the ability to generate new information and plans based on various data.

[0284] "Usage frequency" is an indicator that shows how much information and services are used within a specific period.

[0285] "Remuneration" refers to the monetary consideration paid to educational information providers according to the value and usage status of their content.

[0286] "Feedback" is information on opinions and reactions obtained from learners and is utilized to improve learning.

[0287] "Dynamic generation" refers to the process of adjusting and generating information and plans in real time according to the situation of users.

[0288] This invention includes a system that collects and evaluates educational information and provides an optimized learning experience for individual learners. The overall process is mainly realized through the cooperation among servers, terminals, and users.

[0289] The server collects educational information using the internet and the company's internal database. This collection process uses software such as web crawlers to verify the source of each piece of information. The collected information is stored in temporary storage and then evaluated for reliability and accuracy using natural language processing algorithms. Once the evaluation is complete, the information is formally registered in the database.

[0290] The terminal receives learning requests from users and formats them into a data format for transmission to the server. At the same time, it provides an intuitive user interface to allow users to specifically set the content and goals they wish to learn.

[0291] Based on the received request, the server generates an optimal learning plan using a generative AI model. The AI ​​model utilizes learning algorithms to select relevant educational information and materials, dynamically creating a plan tailored to the user's learning style. This dynamic generation process is driven by instructions given to the AI ​​model via prompts. For example, a prompt might ask, "How do I generate the optimal learning plan based on the user's specified goals?"

[0292] Users can progress through their learning using the learning plan displayed on their device. Learning progress and user feedback are sent to the server via the device. The server analyzes this data, uses an AI agent to re-evaluate the plan, and makes adjustments as needed.

[0293] For example, if a user enters "I want to learn programming," the server searches its database for reliable programming learning materials, generates learning steps tailored to the user's progress level, and displays them on the terminal. In this way, it supports the learner in reaching their goals.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The server collects educational information from the internet and internal databases. Input is educational information from the internet and internal databases, and output is raw data stored in temporary storage. Specifically, it uses a web crawler to visit specific educational pages, extracts the necessary information, and stores it temporarily.

[0297] Step 2:

[0298] The server evaluates the collected educational information. The input is raw data from temporary storage, and the output is information that has been evaluated for reliability and accuracy. The server uses natural language processing algorithms to analyze the source and content of the information, determine whether it meets the specified evaluation criteria, and register the approved information in the database.

[0299] Step 3:

[0300] The terminal receives learning requests from the user. The input is the user's learning objectives and requests, and the output is processing request data sent to the server. Specifically, the user inputs a request such as "I want to learn English conversation" through the user interface, and the terminal formats it into the appropriate format.

[0301] Step 4:

[0302] The server searches a database of educational information for relevant data based on the learning request it receives. The input is the user's request data, and the output is the relevant educational information. A generative AI model is used, given a prompt as input, to dynamically generate a learning plan suitable for the user. For example, the prompt "What plan would you recommend if I wanted to learn intermediate-level English?" might be used.

[0303] Step 5:

[0304] The terminal presents the generated learning plan to the user. The input is the learning plan sent from the server, and the output is the learning steps and teaching material information displayed on the terminal screen. As a specific operation, the learning content that progresses step by step is displayed on the screen, and the user can proceed with the learning while checking the progress.

[0305] Step 6:

[0306] While proceeding with the learning, the user sends feedback through the terminal. The input is the feedback information from the user, and the output is the adjustment request data sent to the server. Specifically, feedback such as "This chapter is difficult" is input, and the terminal sends this to the server.

[0307] Step 7:

[0308] The server analyzes the received feedback and adjusts the learning plan. The input is the user's feedback data, and the output is the newly adjusted learning plan. An AI agent is utilized to analyze the feedback, reconstruct the plan, and send it to the terminal.

[0309] (Application Example 1)

[0310] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0311] In the conventional education system, it is difficult to propose an individualized learning plan and flexibly adjust the plan according to the progress of the learner. Furthermore, there are issues such as insufficient evaluation to enhance the reliability of educational information and difficulty in accessing high-quality learning resources. Therefore, it is required to provide the user with an optimal learning experience and make it easier to access reliable educational information.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0313] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy; means for receiving the user's learning request and generating an optimal learning plan based thereon; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; and means for presenting an optimal educational plan in response to the user's input in an information processing device and adjusting the plan via an artificial intelligence agent. As a result, users can effectively utilize highly reliable educational information and receive a flexible learning plan that meets their individual learning needs.

[0314] "Educational information" refers to various data and materials used to enhance learners' knowledge and improve their skills.

[0315] "Reliability" refers to the characteristic that information and systems are accurate and can consistently deliver results that meet user expectations.

[0316] "Accuracy" refers to the degree to which information or data matches actual facts or standards.

[0317] "Learning requirements" refer to the content and goals that learners hope to achieve in order to acquire specific knowledge or skills.

[0318] A "learning plan" is a plan designed to help learners efficiently acquire knowledge and skills.

[0319] An "information processing device" refers to a digital device such as a computer or smartphone, which is used for collecting, processing, and displaying data.

[0320] An "artificial intelligence agent" refers to a program that makes autonomous decisions based on human instructions through machine learning and data analysis.

[0321] "Educational data" refers to information and numerical data related to education, which is used for evaluating and analyzing educational resources.

[0322] The server collects educational information extensively using the internet and internal databases, and evaluates the collected information based on its reliability and accuracy. This evaluation is based on factors such as the source of the information and its past usage history. The server stores the evaluated information and registers it in a database accessible to users.

[0323] The terminal accepts the user's learning requests as input. When a user enters a specific goal into the terminal, such as "I want to deeply understand trigonometric functions," that request is sent to the server. The server uses a generative AI model to generate the optimal learning plan from the database for that request. This generation process also takes into account the user's past learning history and progress. The generated learning plan is presented to the user via an information processing device.

[0324] As users progress through the learning plan presented via their device, they provide feedback to the device based on their progress and understanding. This feedback information is sent to a server, where an artificial intelligence agent analyzes it and flexibly adjusts the learning plan as needed. The server also has a function to calculate rewards based on the frequency and conditions of use of educational data and pay appropriate compensation to educational information providers.

[0325] For example, if a high school student enters into the app that they "want to deeply understand trigonometry," the system will provide a series of learning plans, including suitable materials and assignments, based on that request. As the user progresses through their daily studies using the plan, they can provide feedback on areas where their understanding is insufficient, and the AI ​​agent will optimize the plan accordingly, enabling effective learning.

[0326] An example of a prompt message would be, "What to learn next week: Trigonometry. Suggest a learning level and update the plan based on your progress. Allow users to manage their own pace." This allows you to provide a learning experience optimized for the user.

[0327] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0328] Step 1:

[0329] The server collects educational information from the internet and internal databases. Input data consists of information from websites and online resources, while output is educational information evaluated for reliability and accuracy. Specifically, the server uses scraping techniques to organize and store the information as structured data.

[0330] Step 2:

[0331] The user inputs learning requests into the device. These requests specify what the user wants to learn and their goals, and the output is request data based on these requests. For example, the user might input text such as "I want to understand trigonometry in depth" into the smartphone app.

[0332] Step 3:

[0333] The server uses a generative AI model to generate the optimal learning plan from the database. The input is the user's request data and past learning history, and the output is a learning plan tailored to each user. The server uses the AI ​​model to filter educational information and select content suitable for the user.

[0334] Step 4:

[0335] The device presents the generated learning plan to the user. The input is the learning plan data sent from the server, and the output is the user's viewing. Specifically, the device's app displays the plan in an easy-to-understand manner, and the user proceeds with their learning based on it.

[0336] Step 5:

[0337] Users input their learning progress into their device and provide feedback. Input is text or progress metrics based on their learning status, and output is feedback data sent to the server. Through the progress screen, users fill in their level of understanding and areas they find difficult.

[0338] Step 6:

[0339] The server analyzes feedback data and adjusts the learning plan using an artificial intelligence agent. Inputs are user feedback and learning scores, and output is the updated learning plan. The server uses machine learning algorithms to modify the difficulty level and order of learning materials as needed.

[0340] Step 7:

[0341] The server analyzes the frequency of use of educational information and calculates rewards. The input is historical data on the use of educational information, and the output is the reward amount. Specifically, the server uses a statistical model to evaluate the value of the educational information.

[0342] 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.

[0343] This invention relates to a system for collecting and evaluating educational content and generating learning plans tailored to users' learning needs. A key feature of this system is the incorporation of an emotion engine that recognizes the user's emotions and optimizes the learning experience based on those emotions. Specifically, the system includes a server, a terminal, and the emotion engine.

[0344] The server collects educational content through the internet and internal data sources. The collected content is evaluated based on reliability and accuracy and registered in a database. Furthermore, the server assigns metadata to this content, enabling efficient searching and selection.

[0345] The device receives learning requests from the user and sends them to the server. During this process, the emotion engine recognizes the user's current emotional state and reflects it in the learning plan. For example, if the user is feeling stressed, the emotion engine will make adjustments such as suggesting content with a relaxing effect.

[0346] As a concrete example, a user inputs "I want to learn probability theory in mathematics" via their device. The emotion engine uses cameras and sensors to analyze the user's facial expressions and voice. If the user appears calm, it presents standard learning materials; if the user shows signs of anxiety, it presents materials with a lower difficulty level or interactive practice problems.

[0347] The emotion engine continuously monitors user emotional data, which is recorded in a database along with learning progress. This data is used to optimize future learning plans, providing a personalized learning environment for each user.

[0348] By incorporating an emotion engine in this way, it becomes possible to provide educational content tailored to the individual emotions of users, thereby maximizing learning efficiency. Furthermore, it has a function to calculate rewards based on the frequency and conditions of use of learning content, promoting the sustainable provision of educational resources. Thus, this invention provides an innovative educational system that flexibly responds to diverse learning needs.

[0349] The following describes the processing flow.

[0350] Step 1:

[0351] The server periodically collects educational content from the internet and internal databases. During collection, the content is categorized by format and content, and evaluated based on reliability and accuracy criteria. Inappropriate content is excluded during this process.

[0352] Step 2:

[0353] The server registers evaluated educational content in a database and adds metadata, enabling efficient searching.

[0354] Step 3:

[0355] The user uses their device to input the topics and goals they want to learn. For example, the user might input, "I want to learn the basics of programming."

[0356] Step 4:

[0357] The device's built-in emotion engine uses the camera and microphone to analyze the user's facial expressions and voice tone in real time to determine their current emotional state. If the system determines that the user is relaxed, it will then analyze the user's emotional state.

[0358] Step 5:

[0359] The device sends the emotion data recognized by the emotion engine and the user's request to the server.

[0360] Step 6:

[0361] The server considers emotional data to select the most suitable learning content from the database. For example, if the user is relaxed, it might suggest a fast-paced video lecture.

[0362] Step 7:

[0363] The server generates a customized learning plan that includes selected learning content and sends it to the device.

[0364] Step 8:

[0365] The device will display a learning plan to the user, allowing them to manage their progress step by step.

[0366] Step 9:

[0367] The user progresses through the learning process via their device. During the learning process, the emotion engine monitors the user's emotional state again, and if stress levels increase, it makes adjustments such as inserting easier practice problems.

[0368] Step 10:

[0369] After the learning session is complete, the device collects user feedback and sends it to the server. The server records this data to be used in the next learning plan.

[0370] Step 11:

[0371] Based on usage data collected by the server, the frequency of use of educational content is analyzed, and compensation is calculated and paid to content providers accordingly.

[0372] Step 12:

[0373] At the end of each session, the device provides the user with feedback on their learning achievements and progress, and offers learning suggestions for the next session. This provides users with a learning environment that allows for continuous growth.

[0374] (Example 2)

[0375] 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".

[0376] Traditional education systems have struggled to provide flexible and personalized educational experiences that respond to users' learning needs and emotional states. Furthermore, the selection and evaluation of collected educational information, the improvement of search efficiency, and the calculation of rewards have not been optimal, resulting in a failure to maximize learning efficiency.

[0377] 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.

[0378] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for recognizing the user's emotional state and optimizing educational activities based on that state, and means for providing educational information adapted to the user according to the generated learning plan. This makes it possible to provide an optimal educational experience that is tailored to each user's individual learning needs and emotional state.

[0379] "Educational information" refers to all educational materials and content intended for use by learners, and is collected after being evaluated for reliability and accuracy.

[0380] A "learning plan" refers to a set of procedures and strategies for providing educational information that are optimized based on the user's learning needs and emotional state.

[0381] "User emotional state" refers to information that indicates the learner's psychological and emotional condition and is used to optimize the learning plan.

[0382] "Feature data" refers to classification tags and attribute information assigned to collected educational information, and its purpose is to improve the efficiency of searches.

[0383] "Reward" refers to the value or benefit calculated based on the frequency and conditions of use of educational information selected from a large amount of data.

[0384] The system implementing this invention primarily consists of a server, terminals, and an emotion engine. The server collects educational information through the internet and internal data sources. This information is evaluated based on reliability and accuracy and registered in a database. Specifically, the server periodically accesses online educational platforms and open databases via APIs to obtain the latest information.

[0385] The terminal is a device that receives learning requests from users and sends data entered via the user interface to the server. For example, if a user enters "I want to learn probability theory in mathematics," that information is sent to the server and processed.

[0386] The emotion engine uses hardware such as cameras and microphones to analyze the user's facial expressions and voice, and to identify their emotional state. This allows the server to generate an optimized learning plan based on the user's emotional state and adjust the learning content as needed.

[0387] Based on the generated learning plan, the device provides personalized educational information to the user. Learning progress and emotional data are seamlessly monitored through the emotion engine, and feedback is provided as needed. This cycle continuously optimizes the user's learning experience.

[0388] Based on this embodiment, it becomes possible to provide educational experiences tailored to the individual user's requirements and emotions. The innovativeness of this system lies in its dynamic content delivery powered by an emotion engine and its promotion of efficient learning.

[0389] A concrete example of a prompt is: "If a user wants to learn probability theory in mathematics but is currently feeling insecure, what kind of learning materials would be most effective to suggest?" Such prompts can be used with generative AI models to optimize learning plans.

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The server collects educational information from the internet and internal data sources. Inputs include source URLs and API keys for educational information, while output is raw educational data. Specifically, the server periodically accesses designated information sources and runs programs to automate data collection.

[0393] Step 2:

[0394] The server evaluates the collected educational information. The input is the raw educational data collected in Step 1, and its reliability and accuracy are evaluated. The output is the evaluation result, which is registered in the database. Specifically, an algorithm is used to analyze the source of the information and past reliability evaluation scores, and high-rated content is selected.

[0395] Step 3:

[0396] The server assigns feature data to evaluated educational information. The input is evaluated educational data, and the output is educational content with specific feature data assigned to it. In this process, tagging, categorization, and difficulty levels are added to organize the information and improve subsequent search efficiency.

[0397] Step 4:

[0398] The terminal receives learning requests from the user. The input is the learning request entered by the user, such as a specific request like "I want to learn probability theory in mathematics." The output is the request data sent to the server. In operation, the request data is input via the terminal's user interface and sent to the server in a formatted form.

[0399] Step 5:

[0400] The device recognizes the user's emotional state and transmits it to the server. Input is the user's voice and facial expression data, and output is analyzed emotional data. Specifically, it collects emotional data using a camera and microphone, and this data is analyzed in real time by an emotion engine.

[0401] Step 6:

[0402] The server generates a learning plan based on the user's learning needs and emotional state. The input is the learning needs and emotional data, and the output is a customized learning plan. The server utilizes a generative AI model to design the optimal learning path for each user. Prompts and other prompts may be used in this process.

[0403] Step 7:

[0404] The terminal presents educational information to the user according to the learning plan received from the server. The input is the customized learning plan, and the output is the educational content displayed to the user. Interactive learning materials and videos are used here to specifically support the user's learning experience.

[0405] (Application Example 2)

[0406] 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".

[0407] In education, it is difficult to provide an optimal educational experience tailored to the emotional state of individual users. Furthermore, the recommendation of content that meets diverse educational needs is not efficient, and there is a lack of effective means to promote individualized learning. As a result, improvements in educational efficiency are hindered, potentially leading to a decline in users' motivation to learn.

[0408] 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.

[0409] In this invention, the server includes means for collecting educational data and evaluating it based on reliability and accuracy; means for accepting the user's educational requests and generating an optimal educational plan based on them; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; means for recognizing emotions and optimizing the educational experience; a program for analyzing visual and auditory data to identify the user's emotional state; and means for recommending educational data that corresponds to the user's emotions. This makes it possible to provide an effective and personalized educational experience that corresponds to the user's emotions.

[0410] "Educational data" refers to all information used for educational purposes for individual users, and its reliability and accuracy are the criteria for evaluation.

[0411] "Educational requirements" refer to the user's desires regarding the knowledge and skills they seek in their learning.

[0412] An "educational plan" refers to a program designed to optimize the learning flow and methods based on the user's learning needs.

[0413] "Massive amounts of information" refers to the vast amount of education-related information collected via the internet and internal databases.

[0414] "Frequency of use" indicates how often a particular piece of educational data is used.

[0415] "Conditions" refer to the specific circumstances or factors under which educational data is used.

[0416] "Rewards" refer to evaluations or points calculated based on the frequency and conditions of use of educational data.

[0417] "Recognizing emotions" is the process of analyzing the user's facial expressions and voice data to identify their current emotional state.

[0418] "Visual and auditory data" refers to various data formats, including the user's facial expressions and voice, and is used for emotion recognition.

[0419] A "program" refers to a set of instructions or procedures designed to achieve a specific purpose.

[0420] "Educational experience" refers to the overall experience that individual users gain through educational content.

[0421] "Optimization" refers to adjusting and improving the educational experience in the most effective way for the user.

[0422] "Recommendation" means suggesting the most suitable educational data and content for the user.

[0423] The system in this invention mainly consists of a server, a terminal, and a program incorporating an emotion recognition engine. The server collects educational data via a wide range of internet resources and an internal database, and evaluates its reliability and accuracy. The hardware to be used is assumed to be a server with a high-performance processor and large-capacity storage. The software includes a database management system (e.g., MySQL) for data analysis and management.

[0424] Next, the device accepts the user's educational requests and sends them to the server. It also uses the camera and microphone to acquire the user's visual and audio data, which is then analyzed in real time by an emotion recognition engine. This engine incorporates algorithms to identify emotional states using machine learning libraries (e.g., TensorFlow).

[0425] Once the user's emotional state is analyzed, optimized educational data is recommended. For example, if a user inputs "I want to learn basic chemistry" and displays a stable emotional state, the system will suggest content of normal difficulty. On the other hand, if the system detects that the user is agitated, it will provide more interactive learning materials. A concrete example of a prompt might be, "If the user's facial expression indicates they are relaxed, present them with a slideshow about basic chemistry."

[0426] This allows for the automatic recommendation of educational programs tailored to individual users, thereby improving the quality of the learning experience.

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The server collects educational data from the internet and internal data sources. Input consists of information from various online resources and databases, which are integrated to create an educational database. Data analysis techniques are used to assess reliability and accuracy, and inappropriate data is filtered out to produce curated educational information.

[0430] Step 2:

[0431] The terminal receives educational requests from the user. The user inputs the content they want to learn as text, and this is recorded by the terminal. This request is then forwarded from the terminal to the server, which selects appropriate educational data based on the user's request and develops an educational plan. This is where data mining techniques by the server are utilized.

[0432] Step 3:

[0433] The device acquires the user's visual and auditory data. Using the camera and microphone, it captures changes in facial expressions and voice in real time. This data serves as input for analysis by the emotion engine.

[0434] Step 4:

[0435] The emotion engine analyzes visual and audio data transmitted from the device. Using machine learning models, it identifies the user's emotional state, and the data is output as emotion tags. These tags are then used to recommend educational data.

[0436] Step 5:

[0437] The server recommends educational data based on the user's educational needs and sentiment tags. The input consists of educational needs and sentiment tags, which are used to execute a search algorithm and output the most suitable educational content.

[0438] Step 6:

[0439] The terminal presents the user with recommended data received from the server. It displays the educational data in the format most suitable for the user (e.g., interactive materials or videos) and initiates the educational experience. Here, prompt messages are used to specify the content to be presented.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Third Embodiment]

[0444] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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".

[0456] This invention is an educational system that effectively collects and evaluates educational content and provides users with an optimal learning experience. This system is primarily realized through multi-layered interaction between servers, terminals, and users.

[0457] The server has the capability to collect educational content from the internet and internal databases. During this collection process, the server evaluates the collected content based on reliability and accuracy standards and automatically registers it in the database. This ensures that users have access to quality-assured educational resources.

[0458] The terminal receives input from the user, sends it to the server, and then presents the user with a learning plan based on that input. Specifically, when the user inputs what they want to learn and their goals into the terminal, the server selects the most suitable learning content from the database via an AI agent and generates a learning plan. This includes presenting learning materials tailored to the learner's learning style and arranging them in an appropriate order.

[0459] Users progress through their learning via their devices, following the provided learning plan. They can send feedback to their devices as needed, allowing the AI ​​agent to review and adjust the plan. The server also monitors the user's learning progress via the devices and stores the data.

[0460] This system also includes a reward management system that calculates and pays content providers rewards based on usage. For example, if a particular educational content meets a certain usage frequency, the provider will receive appropriate compensation, promoting the sustainable supply of educational resources.

[0461] As described above, the present invention provides a means to significantly improve the quality and efficiency of education, and realizes a highly convenient educational environment for both users and educators.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The server connects to the internet and the company's internal database to collect educational content. During this process, it identifies and collects new information and updated resources.

[0465] Step 2:

[0466] The server performs a process to evaluate the reliability and accuracy of the educational content it collects. The content is filtered according to pre-defined criteria, and unsuitable content is excluded.

[0467] Step 3:

[0468] The server registers evaluated educational content in a database and adds metadata to enable efficient searching.

[0469] Step 4:

[0470] The user operates the device and inputs what they want to learn and their goals. This includes specific topics and desired learning periods.

[0471] Step 5:

[0472] The device sends user input to the server, and an AI agent is used to generate an optimal learning plan. Based on this request, the server selects relevant content from its database.

[0473] Step 6:

[0474] The server creates a customized learning plan, determining the order of learning materials and learning steps. This is then sent to the terminal and presented to the user.

[0475] Step 7:

[0476] The user progresses through the learning plan provided. During the learning process, the user can send progress updates and feedback via their device.

[0477] Step 8:

[0478] The server monitors learning progress and accumulates learning history data. This allows for the collection of data that can be used to improve the next learning plan.

[0479] Step 9:

[0480] The system analyzes data on the educational content used by the server and calculates compensation based on usage frequency. The calculated compensation is then paid to the content provider.

[0481] Step 10:

[0482] After the device completes the learning process, it provides feedback to the user on their learning outcomes and suggests the next learning content. This promotes continuous learning.

[0483] (Example 1)

[0484] 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."

[0485] While there is a need to manage the quality of educational information and provide flexible learning plans that meet the individual needs of learners, there is a lack of means to efficiently collect reliable content from a large amount of educational information and to improve the learning experience by utilizing the progress and feedback of individual users. Furthermore, paying educational information providers fair compensation based on the usage of educational information is also a challenge.

[0486] 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.

[0487] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for receiving users' learning requests and generating an optimal learning plan based on them, and means for calculating rewards for educational information selected from a large amount of information based on usage frequency and conditions. This enables the collection and evaluation of reliable information, the provision of learning plans based on individual learning styles, and the fair distribution of rewards for educational information.

[0488] "Educational information" refers to materials and data that enable learners to acquire the knowledge and skills they need, and includes teaching materials and course content.

[0489] "Reliability" is the characteristic that guarantees information is accurate and free from errors.

[0490] "Accuracy" refers to a state in which information is based on facts, is unambiguous, and serves its purpose.

[0491] "User learning requirements" refer to the goals that learners aim for, the skills they want to acquire, and their specific learning needs.

[0492] A "learning plan" is a plan that outlines an efficient learning flow and steps, tailored to the learner's objectives.

[0493] A "generative AI model" is a type of artificial intelligence that has the ability to generate new information and plans based on diverse data.

[0494] "Frequency of use" is an indicator that shows how often information or services are used within a specific period of time.

[0495] "Compensation" refers to monetary payment made to educational information providers based on the value and usage of their content.

[0496] "Feedback" refers to information about opinions and reactions obtained from learners, which is used to improve learning.

[0497] "Dynamic generation" refers to the process of adjusting and generating information and plans in real time according to the user's situation.

[0498] This invention includes a system for collecting and evaluating educational information and providing an optimized learning experience for individual learners. The overall process is primarily achieved through collaboration between a server, terminals, and users.

[0499] The server collects educational information using the internet and the company's internal database. This collection process uses software such as web crawlers to verify the source of each piece of information. The collected information is stored in temporary storage and then evaluated for reliability and accuracy using natural language processing algorithms. Once the evaluation is complete, the information is formally registered in the database.

[0500] The terminal receives learning requests from users and formats them into a data format for transmission to the server. At the same time, it provides an intuitive user interface to allow users to specifically set the content and goals they wish to learn.

[0501] Based on the received request, the server generates an optimal learning plan using a generative AI model. The AI ​​model utilizes learning algorithms to select relevant educational information and materials, dynamically creating a plan tailored to the user's learning style. This dynamic generation process is driven by instructions given to the AI ​​model via prompts. For example, a prompt might ask, "How do I generate the optimal learning plan based on the user's specified goals?"

[0502] Users can progress through their learning using the learning plan displayed on their device. Learning progress and user feedback are sent to the server via the device. The server analyzes this data, uses an AI agent to re-evaluate the plan, and makes adjustments as needed.

[0503] For example, if a user enters "I want to learn programming," the server searches its database for reliable programming learning materials, generates learning steps tailored to the user's progress level, and displays them on the terminal. In this way, it supports the learner in reaching their goals.

[0504] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0505] Step 1:

[0506] The server collects educational information from the internet and internal databases. Input is educational information from the internet and internal databases, and output is raw data stored in temporary storage. Specifically, it uses a web crawler to visit specific educational pages, extracts the necessary information, and stores it temporarily.

[0507] Step 2:

[0508] The server evaluates the collected educational information. The input is raw data from temporary storage, and the output is information that has been evaluated for reliability and accuracy. The server uses natural language processing algorithms to analyze the source and content of the information, determine whether it meets the specified evaluation criteria, and register the approved information in the database.

[0509] Step 3:

[0510] The terminal receives learning requests from the user. The input is the user's learning objectives and requests, and the output is processing request data sent to the server. Specifically, the user inputs a request such as "I want to learn English conversation" through the user interface, and the terminal formats it into the appropriate format.

[0511] Step 4:

[0512] The server searches a database of educational information for relevant data based on the learning request it receives. The input is the user's request data, and the output is the relevant educational information. A generative AI model is used, given a prompt as input, to dynamically generate a learning plan suitable for the user. For example, the prompt "What plan would you recommend if I wanted to learn intermediate-level English?" might be used.

[0513] Step 5:

[0514] The terminal presents the generated learning plan to the user. The input is the learning plan sent from the server, and the output is the learning steps and learning material information displayed on the terminal screen. Specifically, the learning content is displayed on the screen in stages, allowing the user to progress while checking their progress.

[0515] Step 6:

[0516] As users progress through the learning process, they send feedback via their device. The input is user feedback information, and the output is adjustment request data sent to the server. Specifically, users input feedback such as "This chapter is difficult," and the device sends this to the server.

[0517] Step 7:

[0518] The server analyzes the received feedback and adjusts the learning plan. The input is the user's feedback data, and the output is the newly adjusted learning plan. An AI agent is used to analyze the feedback, reconstruct the plan, and send it to the device.

[0519] (Application Example 1)

[0520] 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."

[0521] Traditional education systems struggle to propose individualized learning plans and flexibly adjust plans according to learners' progress. Furthermore, they lack sufficient evaluation to enhance the reliability of educational information, making it difficult to access high-quality learning resources. Therefore, there is a need to provide users with the optimal learning experience and make access to reliable educational information easier.

[0522] 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.

[0523] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy; means for receiving the user's learning request and generating an optimal learning plan based thereon; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; and means for presenting an optimal educational plan in response to the user's input in an information processing device and adjusting the plan via an artificial intelligence agent. As a result, users can effectively utilize highly reliable educational information and receive a flexible learning plan that meets their individual learning needs.

[0524] "Educational information" refers to various data and materials used to enhance learners' knowledge and improve their skills.

[0525] "Reliability" refers to the characteristic that information and systems are accurate and can consistently deliver results that meet user expectations.

[0526] "Accuracy" refers to the degree to which information or data matches actual facts or standards.

[0527] "Learning requirements" refer to the content and goals that learners hope to achieve in order to acquire specific knowledge or skills.

[0528] A "learning plan" is a plan designed to help learners efficiently acquire knowledge and skills.

[0529] An "information processing device" refers to a digital device such as a computer or smartphone, which is used for collecting, processing, and displaying data.

[0530] An "artificial intelligence agent" refers to a program that makes autonomous decisions based on human instructions through machine learning and data analysis.

[0531] "Educational data" refers to information and numerical data related to education, which is used for evaluating and analyzing educational resources.

[0532] The server collects educational information extensively using the internet and internal databases, and evaluates the collected information based on its reliability and accuracy. This evaluation is based on factors such as the source of the information and its past usage history. The server stores the evaluated information and registers it in a database accessible to users.

[0533] The terminal accepts the user's learning requests as input. When a user enters a specific goal into the terminal, such as "I want to deeply understand trigonometric functions," that request is sent to the server. The server uses a generative AI model to generate the optimal learning plan from the database for that request. This generation process also takes into account the user's past learning history and progress. The generated learning plan is presented to the user via an information processing device.

[0534] As users progress through the learning plan presented via their device, they provide feedback to the device based on their progress and understanding. This feedback information is sent to a server, where an artificial intelligence agent analyzes it and flexibly adjusts the learning plan as needed. The server also has a function to calculate rewards based on the frequency and conditions of use of educational data and pay appropriate compensation to educational information providers.

[0535] For example, if a high school student enters into the app that they "want to deeply understand trigonometry," the system will provide a series of learning plans, including suitable materials and assignments, based on that request. As the user progresses through their daily studies using the plan, they can provide feedback on areas where their understanding is insufficient, and the AI ​​agent will optimize the plan accordingly, enabling effective learning.

[0536] An example of a prompt message would be, "What to learn next week: Trigonometry. Suggest a learning level and update the plan based on your progress. Allow users to manage their own pace." This allows you to provide a learning experience optimized for the user.

[0537] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0538] Step 1:

[0539] The server collects educational information from the internet and internal databases. Input data consists of information from websites and online resources, while output is educational information evaluated for reliability and accuracy. Specifically, the server uses scraping techniques to organize and store the information as structured data.

[0540] Step 2:

[0541] The user inputs learning requests into the device. These requests specify what the user wants to learn and their goals, and the output is request data based on these requests. For example, the user might input text such as "I want to understand trigonometry in depth" into the smartphone app.

[0542] Step 3:

[0543] The server uses a generative AI model to generate the optimal learning plan from the database. The input is the user's request data and past learning history, and the output is a learning plan tailored to each user. The server uses the AI ​​model to filter educational information and select content suitable for the user.

[0544] Step 4:

[0545] The device presents the generated learning plan to the user. The input is the learning plan data sent from the server, and the output is the user's viewing. Specifically, the device's app displays the plan in an easy-to-understand manner, and the user proceeds with their learning based on it.

[0546] Step 5:

[0547] Users input their learning progress into their device and provide feedback. Input is text or progress metrics based on their learning status, and output is feedback data sent to the server. Through the progress screen, users fill in their level of understanding and areas they find difficult.

[0548] Step 6:

[0549] The server analyzes feedback data and adjusts the learning plan using an artificial intelligence agent. Inputs are user feedback and learning scores, and output is the updated learning plan. The server uses machine learning algorithms to modify the difficulty level and order of learning materials as needed.

[0550] Step 7:

[0551] The server analyzes the frequency of use of educational information and calculates rewards. The input is historical data on the use of educational information, and the output is the reward amount. Specifically, the server uses a statistical model to evaluate the value of the educational information.

[0552] 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.

[0553] This invention relates to a system for collecting and evaluating educational content and generating learning plans tailored to users' learning needs. A key feature of this system is the incorporation of an emotion engine that recognizes the user's emotions and optimizes the learning experience based on those emotions. Specifically, the system includes a server, a terminal, and the emotion engine.

[0554] The server collects educational content through the internet and internal data sources. The collected content is evaluated based on reliability and accuracy and registered in a database. Furthermore, the server assigns metadata to this content, enabling efficient searching and selection.

[0555] The device receives learning requests from the user and sends them to the server. During this process, the emotion engine recognizes the user's current emotional state and reflects it in the learning plan. For example, if the user is feeling stressed, the emotion engine will make adjustments such as suggesting content with a relaxing effect.

[0556] As a concrete example, a user inputs "I want to learn probability theory in mathematics" via their device. The emotion engine uses cameras and sensors to analyze the user's facial expressions and voice. If the user appears calm, it presents standard learning materials; if the user shows signs of anxiety, it presents materials with a lower difficulty level or interactive practice problems.

[0557] The emotion engine continuously monitors user emotional data, which is recorded in a database along with learning progress. This data is used to optimize future learning plans, providing a personalized learning environment for each user.

[0558] By incorporating an emotion engine in this way, it becomes possible to provide educational content tailored to the individual emotions of users, thereby maximizing learning efficiency. Furthermore, it has a function to calculate rewards based on the frequency and conditions of use of learning content, promoting the sustainable provision of educational resources. Thus, this invention provides an innovative educational system that flexibly responds to diverse learning needs.

[0559] The following describes the processing flow.

[0560] Step 1:

[0561] The server periodically collects educational content from the internet and internal databases. During collection, the content is categorized by format and content, and evaluated based on reliability and accuracy criteria. Inappropriate content is excluded during this process.

[0562] Step 2:

[0563] The server registers evaluated educational content in a database and adds metadata, enabling efficient searching.

[0564] Step 3:

[0565] The user uses their device to input the topics and goals they want to learn. For example, the user might input, "I want to learn the basics of programming."

[0566] Step 4:

[0567] The device's built-in emotion engine uses the camera and microphone to analyze the user's facial expressions and voice tone in real time to determine their current emotional state. If the system determines that the user is relaxed, it will then analyze the user's emotional state.

[0568] Step 5:

[0569] The device sends the emotion data recognized by the emotion engine and the user's request to the server.

[0570] Step 6:

[0571] The server considers emotional data to select the most suitable learning content from the database. For example, if the user is relaxed, it might suggest a fast-paced video lecture.

[0572] Step 7:

[0573] The server generates a customized learning plan that includes selected learning content and sends it to the device.

[0574] Step 8:

[0575] The device will display a learning plan to the user, allowing them to manage their progress step by step.

[0576] Step 9:

[0577] The user progresses through the learning process via their device. During the learning process, the emotion engine monitors the user's emotional state again, and if stress levels increase, it makes adjustments such as inserting easier practice problems.

[0578] Step 10:

[0579] After the learning session is complete, the device collects user feedback and sends it to the server. The server records this data to be used in the next learning plan.

[0580] Step 11:

[0581] Based on usage data collected by the server, the frequency of use of educational content is analyzed, and compensation is calculated and paid to content providers accordingly.

[0582] Step 12:

[0583] At the end of each session, the device provides the user with feedback on their learning achievements and progress, and offers learning suggestions for the next session. This provides users with a learning environment that allows for continuous growth.

[0584] (Example 2)

[0585] 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."

[0586] Traditional education systems have struggled to provide flexible and personalized educational experiences that respond to users' learning needs and emotional states. Furthermore, the selection and evaluation of collected educational information, the improvement of search efficiency, and the calculation of rewards have not been optimal, resulting in a failure to maximize learning efficiency.

[0587] 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.

[0588] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for recognizing the user's emotional state and optimizing educational activities based on that state, and means for providing educational information adapted to the user according to the generated learning plan. This makes it possible to provide an optimal educational experience that is tailored to each user's individual learning needs and emotional state.

[0589] "Educational information" refers to all educational materials and content intended for use by learners, and is collected after being evaluated for reliability and accuracy.

[0590] A "learning plan" refers to a set of procedures and strategies for providing educational information that are optimized based on the user's learning needs and emotional state.

[0591] "User emotional state" refers to information that indicates the learner's psychological and emotional condition and is used to optimize the learning plan.

[0592] "Feature data" refers to classification tags and attribute information assigned to collected educational information, and its purpose is to improve the efficiency of searches.

[0593] "Reward" refers to the value or benefit calculated based on the frequency and conditions of use of educational information selected from a large amount of data.

[0594] The system implementing this invention primarily consists of a server, terminals, and an emotion engine. The server collects educational information through the internet and internal data sources. This information is evaluated based on reliability and accuracy and registered in a database. Specifically, the server periodically accesses online educational platforms and open databases via APIs to obtain the latest information.

[0595] The terminal is a device that receives learning requests from users and sends data entered via the user interface to the server. For example, if a user enters "I want to learn probability theory in mathematics," that information is sent to the server and processed.

[0596] The emotion engine uses hardware such as cameras and microphones to analyze the user's facial expressions and voice, and to identify their emotional state. This allows the server to generate an optimized learning plan based on the user's emotional state and adjust the learning content as needed.

[0597] Based on the generated learning plan, the device provides personalized educational information to the user. Learning progress and emotional data are seamlessly monitored through the emotion engine, and feedback is provided as needed. This cycle continuously optimizes the user's learning experience.

[0598] Based on this embodiment, it becomes possible to provide educational experiences tailored to the individual user's requirements and emotions. The innovativeness of this system lies in its dynamic content delivery powered by an emotion engine and its promotion of efficient learning.

[0599] A concrete example of a prompt is: "If a user wants to learn probability theory in mathematics but is currently feeling insecure, what kind of learning materials would be most effective to suggest?" Such prompts can be used with generative AI models to optimize learning plans.

[0600] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0601] Step 1:

[0602] The server collects educational information from the internet and internal data sources. Inputs include source URLs and API keys for educational information, while output is raw educational data. Specifically, the server periodically accesses designated information sources and runs programs to automate data collection.

[0603] Step 2:

[0604] The server evaluates the collected educational information. The input is the raw educational data collected in Step 1, and its reliability and accuracy are evaluated. The output is the evaluation result, which is registered in the database. Specifically, an algorithm is used to analyze the source of the information and past reliability evaluation scores, and high-rated content is selected.

[0605] Step 3:

[0606] The server assigns feature data to evaluated educational information. The input is evaluated educational data, and the output is educational content with specific feature data assigned to it. In this process, tagging, categorization, and difficulty levels are added to organize the information and improve subsequent search efficiency.

[0607] Step 4:

[0608] The terminal receives learning requests from the user. The input is the learning request entered by the user, such as a specific request like "I want to learn probability theory in mathematics." The output is the request data sent to the server. In operation, the request data is input via the terminal's user interface and sent to the server in a formatted form.

[0609] Step 5:

[0610] The device recognizes the user's emotional state and transmits it to the server. Input is the user's voice and facial expression data, and output is analyzed emotional data. Specifically, it collects emotional data using a camera and microphone, and this data is analyzed in real time by an emotion engine.

[0611] Step 6:

[0612] The server generates a learning plan based on the user's learning needs and emotional state. The input is the learning needs and emotional data, and the output is a customized learning plan. The server utilizes a generative AI model to design the optimal learning path for each user. Prompts and other prompts may be used in this process.

[0613] Step 7:

[0614] The terminal presents educational information to the user according to the learning plan received from the server. The input is the customized learning plan, and the output is the educational content displayed to the user. Interactive learning materials and videos are used here to specifically support the user's learning experience.

[0615] (Application Example 2)

[0616] 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."

[0617] In education, it is difficult to provide an optimal educational experience tailored to the emotional state of individual users. Furthermore, the recommendation of content that meets diverse educational needs is not efficient, and there is a lack of effective means to promote individualized learning. As a result, improvements in educational efficiency are hindered, potentially leading to a decline in users' motivation to learn.

[0618] 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.

[0619] In this invention, the server includes means for collecting educational data and evaluating it based on reliability and accuracy; means for accepting the user's educational requests and generating an optimal educational plan based on them; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; means for recognizing emotions and optimizing the educational experience; a program for analyzing visual and auditory data to identify the user's emotional state; and means for recommending educational data that corresponds to the user's emotions. This makes it possible to provide an effective and personalized educational experience that corresponds to the user's emotions.

[0620] "Educational data" refers to all information used for educational purposes for individual users, and its reliability and accuracy are the criteria for evaluation.

[0621] "Educational requirements" refer to the user's desires regarding the knowledge and skills they seek in their learning.

[0622] An "educational plan" refers to a program designed to optimize the learning flow and methods based on the user's learning needs.

[0623] "Massive amounts of information" refers to the vast amount of education-related information collected via the internet and internal databases.

[0624] "Frequency of use" indicates how often a particular piece of educational data is used.

[0625] "Conditions" refer to the specific circumstances or factors under which educational data is used.

[0626] "Rewards" refer to evaluations or points calculated based on the frequency and conditions of use of educational data.

[0627] "Recognizing emotions" is the process of analyzing the user's facial expressions and voice data to identify their current emotional state.

[0628] "Visual and auditory data" refers to various data formats, including the user's facial expressions and voice, and is used for emotion recognition.

[0629] A "program" refers to a set of instructions or procedures designed to achieve a specific purpose.

[0630] "Educational experience" refers to the overall experience that individual users gain through educational content.

[0631] "Optimization" refers to adjusting and improving the educational experience in the most effective way for the user.

[0632] "Recommendation" means suggesting the most suitable educational data and content for the user.

[0633] The system in this invention mainly consists of a server, a terminal, and a program incorporating an emotion recognition engine. The server collects educational data via a wide range of internet resources and an internal database, and evaluates its reliability and accuracy. The hardware to be used is assumed to be a server with a high-performance processor and large-capacity storage. The software includes a database management system (e.g., MySQL) for data analysis and management.

[0634] Next, the device accepts the user's educational requests and sends them to the server. It also uses the camera and microphone to acquire the user's visual and audio data, which is then analyzed in real time by an emotion recognition engine. This engine incorporates algorithms to identify emotional states using machine learning libraries (e.g., TensorFlow).

[0635] Once the user's emotional state is analyzed, optimized educational data is recommended. For example, if a user inputs "I want to learn basic chemistry" and displays a stable emotional state, the system will suggest content of normal difficulty. On the other hand, if the system detects that the user is agitated, it will provide more interactive learning materials. A concrete example of a prompt might be, "If the user's facial expression indicates they are relaxed, present them with a slideshow about basic chemistry."

[0636] This allows for the automatic recommendation of educational programs tailored to individual users, thereby improving the quality of the learning experience.

[0637] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0638] Step 1:

[0639] The server collects educational data from the internet and internal data sources. Input consists of information from various online resources and databases, which are integrated to create an educational database. Data analysis techniques are used to assess reliability and accuracy, and inappropriate data is filtered out to produce curated educational information.

[0640] Step 2:

[0641] The terminal receives educational requests from the user. The user inputs the content they want to learn as text, and this is recorded by the terminal. This request is then forwarded from the terminal to the server, which selects appropriate educational data based on the user's request and develops an educational plan. This is where data mining techniques by the server are utilized.

[0642] Step 3:

[0643] The device acquires the user's visual and auditory data. Using the camera and microphone, it captures changes in facial expressions and voice in real time. This data serves as input for analysis by the emotion engine.

[0644] Step 4:

[0645] The emotion engine analyzes visual and audio data transmitted from the device. Using machine learning models, it identifies the user's emotional state, and the data is output as emotion tags. These tags are then used to recommend educational data.

[0646] Step 5:

[0647] The server recommends educational data based on the user's educational needs and sentiment tags. The input consists of educational needs and sentiment tags, which are used to execute a search algorithm and output the most suitable educational content.

[0648] Step 6:

[0649] The terminal presents the user with recommended data received from the server. It displays the educational data in the format most suitable for the user (e.g., interactive materials or videos) and initiates the educational experience. Here, prompt messages are used to specify the content to be presented.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] [Fourth Embodiment]

[0654] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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".

[0667] This invention is an educational system that effectively collects and evaluates educational content and provides users with an optimal learning experience. This system is primarily realized through multi-layered interaction between servers, terminals, and users.

[0668] The server has the capability to collect educational content from the internet and internal databases. During this collection process, the server evaluates the collected content based on reliability and accuracy standards and automatically registers it in the database. This ensures that users have access to quality-assured educational resources.

[0669] The terminal receives input from the user, sends it to the server, and then presents the user with a learning plan based on that input. Specifically, when the user inputs what they want to learn and their goals into the terminal, the server selects the most suitable learning content from the database via an AI agent and generates a learning plan. This includes presenting learning materials tailored to the learner's learning style and arranging them in an appropriate order.

[0670] Users progress through their learning via their devices, following the provided learning plan. They can send feedback to their devices as needed, allowing the AI ​​agent to review and adjust the plan. The server also monitors the user's learning progress via the devices and stores the data.

[0671] This system also includes a reward management system that calculates and pays content providers rewards based on usage. For example, if a particular educational content meets a certain usage frequency, the provider will receive appropriate compensation, promoting the sustainable supply of educational resources.

[0672] As described above, the present invention provides a means to significantly improve the quality and efficiency of education, and realizes a highly convenient educational environment for both users and educators.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] The server connects to the internet and the company's internal database to collect educational content. During this process, it identifies and collects new information and updated resources.

[0676] Step 2:

[0677] The server performs a process to evaluate the reliability and accuracy of the educational content it collects. The content is filtered according to pre-defined criteria, and unsuitable content is excluded.

[0678] Step 3:

[0679] The server registers evaluated educational content in a database and adds metadata to enable efficient searching.

[0680] Step 4:

[0681] The user operates the device and inputs what they want to learn and their goals. This includes specific topics and desired learning periods.

[0682] Step 5:

[0683] The device sends user input to the server, and an AI agent is used to generate an optimal learning plan. Based on this request, the server selects relevant content from its database.

[0684] Step 6:

[0685] The server creates a customized learning plan, determining the order of learning materials and learning steps. This is then sent to the terminal and presented to the user.

[0686] Step 7:

[0687] The user progresses through the learning plan provided. During the learning process, the user can send progress updates and feedback via their device.

[0688] Step 8:

[0689] The server monitors learning progress and accumulates learning history data. This allows for the collection of data that can be used to improve the next learning plan.

[0690] Step 9:

[0691] The system analyzes data on the educational content used by the server and calculates compensation based on usage frequency. The calculated compensation is then paid to the content provider.

[0692] Step 10:

[0693] After the device completes the learning process, it provides feedback to the user on their learning outcomes and suggests the next learning content. This promotes continuous learning.

[0694] (Example 1)

[0695] 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".

[0696] While there is a need to manage the quality of educational information and provide flexible learning plans that meet the individual needs of learners, there is a lack of means to efficiently collect reliable content from a large amount of educational information and to improve the learning experience by utilizing the progress and feedback of individual users. Furthermore, paying educational information providers fair compensation based on the usage of educational information is also a challenge.

[0697] 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.

[0698] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for receiving users' learning requests and generating an optimal learning plan based on them, and means for calculating rewards for educational information selected from a large amount of information based on usage frequency and conditions. This enables the collection and evaluation of reliable information, the provision of learning plans based on individual learning styles, and the fair distribution of rewards for educational information.

[0699] "Educational information" refers to materials and data that enable learners to acquire the knowledge and skills they need, and includes teaching materials and course content.

[0700] "Reliability" is the characteristic that guarantees information is accurate and free from errors.

[0701] "Accuracy" refers to a state in which information is based on facts, is unambiguous, and serves its purpose.

[0702] "User learning requirements" refer to the goals that learners aim for, the skills they want to acquire, and their specific learning needs.

[0703] A "learning plan" is a plan that outlines an efficient learning flow and steps, tailored to the learner's objectives.

[0704] A "generative AI model" is a type of artificial intelligence that has the ability to generate new information and plans based on diverse data.

[0705] "Frequency of use" is an indicator that shows how often information or services are used within a specific period of time.

[0706] "Compensation" refers to monetary payment made to educational information providers based on the value and usage of their content.

[0707] "Feedback" refers to information about opinions and reactions obtained from learners, which is used to improve learning.

[0708] "Dynamic generation" refers to the process of adjusting and generating information and plans in real time according to the user's situation.

[0709] This invention includes a system for collecting and evaluating educational information and providing an optimized learning experience for individual learners. The overall process is primarily achieved through collaboration between a server, terminals, and users.

[0710] The server collects educational information using the internet and the company's internal database. This collection process uses software such as web crawlers to verify the source of each piece of information. The collected information is stored in temporary storage and then evaluated for reliability and accuracy using natural language processing algorithms. Once the evaluation is complete, the information is formally registered in the database.

[0711] The terminal receives learning requests from users and formats them into a data format for transmission to the server. At the same time, it provides an intuitive user interface to allow users to specifically set the content and goals they wish to learn.

[0712] Based on the received request, the server generates an optimal learning plan using a generative AI model. The AI ​​model utilizes learning algorithms to select relevant educational information and materials, dynamically creating a plan tailored to the user's learning style. This dynamic generation process is driven by instructions given to the AI ​​model via prompts. For example, a prompt might ask, "How do I generate the optimal learning plan based on the user's specified goals?"

[0713] Users can progress through their learning using the learning plan displayed on their device. Learning progress and user feedback are sent to the server via the device. The server analyzes this data, uses an AI agent to re-evaluate the plan, and makes adjustments as needed.

[0714] For example, if a user enters "I want to learn programming," the server searches its database for reliable programming learning materials, generates learning steps tailored to the user's progress level, and displays them on the terminal. In this way, it supports the learner in reaching their goals.

[0715] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0716] Step 1:

[0717] The server collects educational information from the internet and internal databases. Input is educational information from the internet and internal databases, and output is raw data stored in temporary storage. Specifically, it uses a web crawler to visit specific educational pages, extracts the necessary information, and stores it temporarily.

[0718] Step 2:

[0719] The server evaluates the collected educational information. The input is raw data from temporary storage, and the output is information that has been evaluated for reliability and accuracy. The server uses natural language processing algorithms to analyze the source and content of the information, determine whether it meets the specified evaluation criteria, and register the approved information in the database.

[0720] Step 3:

[0721] The terminal receives learning requests from the user. The input is the user's learning objectives and requests, and the output is processing request data sent to the server. Specifically, the user inputs a request such as "I want to learn English conversation" through the user interface, and the terminal formats it into the appropriate format.

[0722] Step 4:

[0723] The server searches a database of educational information for relevant data based on the learning request it receives. The input is the user's request data, and the output is the relevant educational information. A generative AI model is used, given a prompt as input, to dynamically generate a learning plan suitable for the user. For example, the prompt "What plan would you recommend if I wanted to learn intermediate-level English?" might be used.

[0724] Step 5:

[0725] The terminal presents the generated learning plan to the user. The input is the learning plan sent from the server, and the output is the learning steps and learning material information displayed on the terminal screen. Specifically, the learning content is displayed on the screen in stages, allowing the user to progress while checking their progress.

[0726] Step 6:

[0727] As users progress through the learning process, they send feedback via their device. The input is user feedback information, and the output is adjustment request data sent to the server. Specifically, users input feedback such as "This chapter is difficult," and the device sends this to the server.

[0728] Step 7:

[0729] The server analyzes the received feedback and adjusts the learning plan. The input is the user's feedback data, and the output is the newly adjusted learning plan. An AI agent is used to analyze the feedback, reconstruct the plan, and send it to the device.

[0730] (Application Example 1)

[0731] 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".

[0732] Traditional education systems struggle to propose individualized learning plans and flexibly adjust plans according to learners' progress. Furthermore, they lack sufficient evaluation to enhance the reliability of educational information, making it difficult to access high-quality learning resources. Therefore, there is a need to provide users with the optimal learning experience and make access to reliable educational information easier.

[0733] 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.

[0734] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy; means for receiving the user's learning request and generating an optimal learning plan based thereon; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; and means for presenting an optimal educational plan in response to the user's input in an information processing device and adjusting the plan via an artificial intelligence agent. As a result, users can effectively utilize highly reliable educational information and receive a flexible learning plan that meets their individual learning needs.

[0735] "Educational information" refers to various data and materials used to enhance learners' knowledge and improve their skills.

[0736] "Reliability" refers to the characteristic that information and systems are accurate and can consistently deliver results that meet user expectations.

[0737] "Accuracy" refers to the degree to which information or data matches actual facts or standards.

[0738] "Learning requirements" refer to the content and goals that learners hope to achieve in order to acquire specific knowledge or skills.

[0739] A "learning plan" is a plan designed to help learners efficiently acquire knowledge and skills.

[0740] An "information processing device" refers to a digital device such as a computer or smartphone, which is used for collecting, processing, and displaying data.

[0741] An "artificial intelligence agent" refers to a program that makes autonomous decisions based on human instructions through machine learning and data analysis.

[0742] "Educational data" refers to information and numerical data related to education, which is used for evaluating and analyzing educational resources.

[0743] The server collects educational information extensively using the internet and internal databases, and evaluates the collected information based on its reliability and accuracy. This evaluation is based on factors such as the source of the information and its past usage history. The server stores the evaluated information and registers it in a database accessible to users.

[0744] The terminal accepts the user's learning requests as input. When a user enters a specific goal into the terminal, such as "I want to deeply understand trigonometric functions," that request is sent to the server. The server uses a generative AI model to generate the optimal learning plan from the database for that request. This generation process also takes into account the user's past learning history and progress. The generated learning plan is presented to the user via an information processing device.

[0745] As users progress through the learning plan presented via their device, they provide feedback to the device based on their progress and understanding. This feedback information is sent to a server, where an artificial intelligence agent analyzes it and flexibly adjusts the learning plan as needed. The server also has a function to calculate rewards based on the frequency and conditions of use of educational data and pay appropriate compensation to educational information providers.

[0746] For example, if a high school student enters into the app that they "want to deeply understand trigonometry," the system will provide a series of learning plans, including suitable materials and assignments, based on that request. As the user progresses through their daily studies using the plan, they can provide feedback on areas where their understanding is insufficient, and the AI ​​agent will optimize the plan accordingly, enabling effective learning.

[0747] An example of a prompt message would be, "What to learn next week: Trigonometry. Suggest a learning level and update the plan based on your progress. Allow users to manage their own pace." This allows you to provide a learning experience optimized for the user.

[0748] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0749] Step 1:

[0750] The server collects educational information from the internet and internal databases. Input data consists of information from websites and online resources, while output is educational information evaluated for reliability and accuracy. Specifically, the server uses scraping techniques to organize and store the information as structured data.

[0751] Step 2:

[0752] The user inputs learning requests into the device. These requests specify what the user wants to learn and their goals, and the output is request data based on these requests. For example, the user might input text such as "I want to understand trigonometry in depth" into the smartphone app.

[0753] Step 3:

[0754] The server uses a generative AI model to generate the optimal learning plan from the database. The input is the user's request data and past learning history, and the output is a learning plan tailored to each user. The server uses the AI ​​model to filter educational information and select content suitable for the user.

[0755] Step 4:

[0756] The device presents the generated learning plan to the user. The input is the learning plan data sent from the server, and the output is the user's viewing. Specifically, the device's app displays the plan in an easy-to-understand manner, and the user proceeds with their learning based on it.

[0757] Step 5:

[0758] Users input their learning progress into their device and provide feedback. Input is text or progress metrics based on their learning status, and output is feedback data sent to the server. Through the progress screen, users fill in their level of understanding and areas they find difficult.

[0759] Step 6:

[0760] The server analyzes feedback data and adjusts the learning plan using an artificial intelligence agent. Inputs are user feedback and learning scores, and output is the updated learning plan. The server uses machine learning algorithms to modify the difficulty level and order of learning materials as needed.

[0761] Step 7:

[0762] The server analyzes the frequency of use of educational information and calculates rewards. The input is historical data on the use of educational information, and the output is the reward amount. Specifically, the server uses a statistical model to evaluate the value of the educational information.

[0763] 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.

[0764] This invention relates to a system for collecting and evaluating educational content and generating learning plans tailored to users' learning needs. A key feature of this system is the incorporation of an emotion engine that recognizes the user's emotions and optimizes the learning experience based on those emotions. Specifically, the system includes a server, a terminal, and the emotion engine.

[0765] The server collects educational content through the internet and internal data sources. The collected content is evaluated based on reliability and accuracy and registered in a database. Furthermore, the server assigns metadata to this content, enabling efficient searching and selection.

[0766] The device receives learning requests from the user and sends them to the server. During this process, the emotion engine recognizes the user's current emotional state and reflects it in the learning plan. For example, if the user is feeling stressed, the emotion engine will make adjustments such as suggesting content with a relaxing effect.

[0767] As a concrete example, a user inputs "I want to learn probability theory in mathematics" via their device. The emotion engine uses cameras and sensors to analyze the user's facial expressions and voice. If the user appears calm, it presents standard learning materials; if the user shows signs of anxiety, it presents materials with a lower difficulty level or interactive practice problems.

[0768] The emotion engine continuously monitors user emotional data, which is recorded in a database along with learning progress. This data is used to optimize future learning plans, providing a personalized learning environment for each user.

[0769] By incorporating an emotion engine in this way, it becomes possible to provide educational content tailored to the individual emotions of users, thereby maximizing learning efficiency. Furthermore, it has a function to calculate rewards based on the frequency and conditions of use of learning content, promoting the sustainable provision of educational resources. Thus, this invention provides an innovative educational system that flexibly responds to diverse learning needs.

[0770] The following describes the processing flow.

[0771] Step 1:

[0772] The server periodically collects educational content from the internet and internal databases. During collection, the content is categorized by format and content, and evaluated based on reliability and accuracy criteria. Inappropriate content is excluded during this process.

[0773] Step 2:

[0774] The server registers evaluated educational content in a database and adds metadata, enabling efficient searching.

[0775] Step 3:

[0776] The user uses their device to input the topics and goals they want to learn. For example, the user might input, "I want to learn the basics of programming."

[0777] Step 4:

[0778] The device's built-in emotion engine uses the camera and microphone to analyze the user's facial expressions and voice tone in real time to determine their current emotional state. If the system determines that the user is relaxed, it will then analyze the user's emotional state.

[0779] Step 5:

[0780] The device sends the emotion data recognized by the emotion engine and the user's request to the server.

[0781] Step 6:

[0782] The server considers emotional data to select the most suitable learning content from the database. For example, if the user is relaxed, it might suggest a fast-paced video lecture.

[0783] Step 7:

[0784] The server generates a customized learning plan that includes selected learning content and sends it to the device.

[0785] Step 8:

[0786] The device will display a learning plan to the user, allowing them to manage their progress step by step.

[0787] Step 9:

[0788] The user progresses through the learning process via their device. During the learning process, the emotion engine monitors the user's emotional state again, and if stress levels increase, it makes adjustments such as inserting easier practice problems.

[0789] Step 10:

[0790] After the learning session is complete, the device collects user feedback and sends it to the server. The server records this data to be used in the next learning plan.

[0791] Step 11:

[0792] Based on usage data collected by the server, the frequency of use of educational content is analyzed, and compensation is calculated and paid to content providers accordingly.

[0793] Step 12:

[0794] At the end of each session, the device provides the user with feedback on their learning achievements and progress, and offers learning suggestions for the next session. This provides users with a learning environment that allows for continuous growth.

[0795] (Example 2)

[0796] 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".

[0797] Traditional education systems have struggled to provide flexible and personalized educational experiences that respond to users' learning needs and emotional states. Furthermore, the selection and evaluation of collected educational information, the improvement of search efficiency, and the calculation of rewards have not been optimal, resulting in a failure to maximize learning efficiency.

[0798] 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.

[0799] In this invention, the server includes means for collecting educational information and evaluating it based on reliability and accuracy, means for recognizing the user's emotional state and optimizing educational activities based on that state, and means for providing educational information adapted to the user according to the generated learning plan. This makes it possible to provide an optimal educational experience that is tailored to each user's individual learning needs and emotional state.

[0800] "Educational information" refers to all educational materials and content intended for use by learners, and is collected after being evaluated for reliability and accuracy.

[0801] A "learning plan" refers to a set of procedures and strategies for providing educational information that are optimized based on the user's learning needs and emotional state.

[0802] "User emotional state" refers to information that indicates the learner's psychological and emotional condition and is used to optimize the learning plan.

[0803] "Feature data" refers to classification tags and attribute information assigned to collected educational information, and its purpose is to improve the efficiency of searches.

[0804] "Reward" refers to the value or benefit calculated based on the frequency and conditions of use of educational information selected from a large amount of data.

[0805] The system implementing this invention primarily consists of a server, terminals, and an emotion engine. The server collects educational information through the internet and internal data sources. This information is evaluated based on reliability and accuracy and registered in a database. Specifically, the server periodically accesses online educational platforms and open databases via APIs to obtain the latest information.

[0806] The terminal is a device that receives learning requests from users and sends data entered via the user interface to the server. For example, if a user enters "I want to learn probability theory in mathematics," that information is sent to the server and processed.

[0807] The emotion engine uses hardware such as cameras and microphones to analyze the user's facial expressions and voice, and to identify their emotional state. This allows the server to generate an optimized learning plan based on the user's emotional state and adjust the learning content as needed.

[0808] Based on the generated learning plan, the device provides personalized educational information to the user. Learning progress and emotional data are seamlessly monitored through the emotion engine, and feedback is provided as needed. This cycle continuously optimizes the user's learning experience.

[0809] Based on this embodiment, it becomes possible to provide educational experiences tailored to the individual user's requirements and emotions. The innovativeness of this system lies in its dynamic content delivery powered by an emotion engine and its promotion of efficient learning.

[0810] A concrete example of a prompt is: "If a user wants to learn probability theory in mathematics but is currently feeling insecure, what kind of learning materials would be most effective to suggest?" Such prompts can be used with generative AI models to optimize learning plans.

[0811] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0812] Step 1:

[0813] The server collects educational information from the internet and internal data sources. Inputs include source URLs and API keys for educational information, while output is raw educational data. Specifically, the server periodically accesses designated information sources and runs programs to automate data collection.

[0814] Step 2:

[0815] The server evaluates the collected educational information. The input is the raw educational data collected in Step 1, and its reliability and accuracy are evaluated. The output is the evaluation result, which is registered in the database. Specifically, an algorithm is used to analyze the source of the information and past reliability evaluation scores, and high-rated content is selected.

[0816] Step 3:

[0817] The server assigns feature data to evaluated educational information. The input is evaluated educational data, and the output is educational content with specific feature data assigned to it. In this process, tagging, categorization, and difficulty levels are added to organize the information and improve subsequent search efficiency.

[0818] Step 4:

[0819] The terminal receives learning requests from the user. The input is the learning request entered by the user, such as a specific request like "I want to learn probability theory in mathematics." The output is the request data sent to the server. In operation, the request data is input via the terminal's user interface and sent to the server in a formatted form.

[0820] Step 5:

[0821] The device recognizes the user's emotional state and transmits it to the server. Input is the user's voice and facial expression data, and output is analyzed emotional data. Specifically, it collects emotional data using a camera and microphone, and this data is analyzed in real time by an emotion engine.

[0822] Step 6:

[0823] The server generates a learning plan based on the user's learning needs and emotional state. The input is the learning needs and emotional data, and the output is a customized learning plan. The server utilizes a generative AI model to design the optimal learning path for each user. Prompts and other prompts may be used in this process.

[0824] Step 7:

[0825] The terminal presents educational information to the user according to the learning plan received from the server. The input is the customized learning plan, and the output is the educational content displayed to the user. Interactive learning materials and videos are used here to specifically support the user's learning experience.

[0826] (Application Example 2)

[0827] 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".

[0828] In education, it is difficult to provide an optimal educational experience tailored to the emotional state of individual users. Furthermore, the recommendation of content that meets diverse educational needs is not efficient, and there is a lack of effective means to promote individualized learning. As a result, improvements in educational efficiency are hindered, potentially leading to a decline in users' motivation to learn.

[0829] 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.

[0830] In this invention, the server includes means for collecting educational data and evaluating it based on reliability and accuracy; means for accepting the user's educational requests and generating an optimal educational plan based on them; means for calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information; means for recognizing emotions and optimizing the educational experience; a program for analyzing visual and auditory data to identify the user's emotional state; and means for recommending educational data that corresponds to the user's emotions. This makes it possible to provide an effective and personalized educational experience that corresponds to the user's emotions.

[0831] "Educational data" refers to all information used for educational purposes for individual users, and its reliability and accuracy are the criteria for evaluation.

[0832] "Educational requirements" refer to the user's desires regarding the knowledge and skills they seek in their learning.

[0833] An "educational plan" refers to a program designed to optimize the learning flow and methods based on the user's learning needs.

[0834] "Massive amounts of information" refers to the vast amount of education-related information collected via the internet and internal databases.

[0835] "Frequency of use" indicates how often a particular piece of educational data is used.

[0836] "Conditions" refer to the specific circumstances or factors under which educational data is used.

[0837] "Rewards" refer to evaluations or points calculated based on the frequency and conditions of use of educational data.

[0838] "Recognizing emotions" is the process of analyzing the user's facial expressions and voice data to identify their current emotional state.

[0839] "Visual and auditory data" refers to various data formats, including the user's facial expressions and voice, and is used for emotion recognition.

[0840] A "program" refers to a set of instructions or procedures designed to achieve a specific purpose.

[0841] "Educational experience" refers to the overall experience that individual users gain through educational content.

[0842] "Optimization" refers to adjusting and improving the educational experience in the most effective way for the user.

[0843] "Recommendation" means suggesting the most suitable educational data and content for the user.

[0844] The system in this invention mainly consists of a server, a terminal, and a program incorporating an emotion recognition engine. The server collects educational data via a wide range of internet resources and an internal database, and evaluates its reliability and accuracy. The hardware to be used is assumed to be a server with a high-performance processor and large-capacity storage. The software includes a database management system (e.g., MySQL) for data analysis and management.

[0845] Next, the device accepts the user's educational requests and sends them to the server. It also uses the camera and microphone to acquire the user's visual and audio data, which is then analyzed in real time by an emotion recognition engine. This engine incorporates algorithms to identify emotional states using machine learning libraries (e.g., TensorFlow).

[0846] Once the user's emotional state is analyzed, optimized educational data is recommended. For example, if a user inputs "I want to learn basic chemistry" and displays a stable emotional state, the system will suggest content of normal difficulty. On the other hand, if the system detects that the user is agitated, it will provide more interactive learning materials. A concrete example of a prompt might be, "If the user's facial expression indicates they are relaxed, present them with a slideshow about basic chemistry."

[0847] This allows for the automatic recommendation of educational programs tailored to individual users, thereby improving the quality of the learning experience.

[0848] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0849] Step 1:

[0850] The server collects educational data from the internet and internal data sources. Input consists of information from various online resources and databases, which are integrated to create an educational database. Data analysis techniques are used to assess reliability and accuracy, and inappropriate data is filtered out to produce curated educational information.

[0851] Step 2:

[0852] The terminal receives educational requests from the user. The user inputs the content they want to learn as text, and this is recorded by the terminal. This request is then forwarded from the terminal to the server, which selects appropriate educational data based on the user's request and develops an educational plan. This is where data mining techniques by the server are utilized.

[0853] Step 3:

[0854] The device acquires the user's visual and auditory data. Using the camera and microphone, it captures changes in facial expressions and voice in real time. This data serves as input for analysis by the emotion engine.

[0855] Step 4:

[0856] The emotion engine analyzes visual and audio data transmitted from the device. Using machine learning models, it identifies the user's emotional state, and the data is output as emotion tags. These tags are then used to recommend educational data.

[0857] Step 5:

[0858] The server recommends educational data based on the user's educational needs and sentiment tags. The input consists of educational needs and sentiment tags, which are used to execute a search algorithm and output the most suitable educational content.

[0859] Step 6:

[0860] The terminal presents the user with recommended data received from the server. It displays the educational data in the format most suitable for the user (e.g., interactive materials or videos) and initiates the educational experience. Here, prompt messages are used to specify the content to be presented.

[0861] 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.

[0862] 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.

[0863] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0864] 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.

[0865] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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."

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0882] The following is further disclosed regarding the embodiments described above.

[0883] (Claim 1)

[0884] Means for collecting educational content and evaluating it based on reliability and accuracy,

[0885] A means for receiving user learning requests and generating an optimal learning plan based on them,

[0886] A means for calculating rewards based on usage frequency and conditions for educational content selected from a large amount of data,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, comprising means for assigning metadata to collected educational content to facilitate searching.

[0890] (Claim 3)

[0891] The system according to claim 1, comprising means for monitoring the user's learning progress and obtaining and analyzing feedback.

[0892] "Example 1"

[0893] (Claim 1)

[0894] Means for collecting educational information and evaluating it based on reliability and accuracy,

[0895] A means for receiving user learning requests and generating an optimal learning plan based on them,

[0896] A means of calculating rewards based on the frequency and conditions of use of educational information selected from a large amount of information,

[0897] A means of dynamically generating and presenting a learning plan using a generative AI model,

[0898] A means to accumulate users' learning progress and reflect it in the next learning plan,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, comprising means for adding supplementary information to collected educational information and facilitating retrieval.

[0902] (Claim 3)

[0903] The system according to claim 1, comprising means for receiving and analyzing feedback from users and adaptively adjusting the learning plan.

[0904] "Application Example 1"

[0905] (Claim 1)

[0906] Means for collecting educational information and evaluating it based on reliability and accuracy,

[0907] A means for receiving user learning requests and generating an optimal learning plan based on them,

[0908] A means of calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information,

[0909] A means for presenting an optimal educational plan in response to user input in an information processing device and adjusting the plan via an artificial intelligence agent,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, comprising means for assigning metadata to collected educational information to facilitate searching.

[0913] (Claim 3)

[0914] The system according to claim 1, comprising means for monitoring the user's learning progress and obtaining and analyzing feedback.

[0915] "Example 2 of combining an emotion engine"

[0916] (Claim 1)

[0917] Means for collecting educational information and evaluating it based on reliability and accuracy,

[0918] A means for receiving user learning requests and generating an optimal learning plan based on them,

[0919] A means for calculating rewards based on the frequency and conditions of use of educational information selected from a large amount of information,

[0920] A means of recognizing the emotional state of users and optimizing educational activities based on that,

[0921] A means of providing educational information adapted to the user according to the generated learning plan,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, comprising means for assigning feature data to collected educational information and facilitating retrieval.

[0925] (Claim 3)

[0926] The system according to claim 1, comprising means for monitoring the user's learning progress and emotional state, and for obtaining and analyzing feedback.

[0927] "Application example 2 when combining with an emotional engine"

[0928] (Claim 1)

[0929] Means for collecting educational data and evaluating it based on reliability and accuracy,

[0930] A means of accepting the user's educational needs and generating an optimal educational plan based on them,

[0931] A means of calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information,

[0932] A means of recognizing emotions and optimizing the educational experience,

[0933] A program that analyzes visual and auditory data to identify the user's emotional state,

[0934] A means of recommending educational data that responds to the user's emotions,

[0935] A system that includes this.

[0936] (Claim 2)

[0937] The system according to claim 1, comprising means for assigning identification information to collected educational data and facilitating retrieval.

[0938] (Claim 3)

[0939] The system according to claim 1, comprising means for monitoring the user's educational progress and obtaining and analyzing feedback. [Explanation of symbols]

[0940] 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 for collecting educational information and evaluating it based on reliability and accuracy, A means for receiving user learning requests and generating an optimal learning plan based on them, A means of calculating rewards based on the frequency and conditions of use of educational data selected from a large amount of information, A means for presenting an optimal educational plan in response to user input in an information processing device and adjusting the plan via an artificial intelligence agent, A system that includes this.

2. The system according to claim 1, comprising means for assigning metadata to collected educational information to facilitate searching.

3. The system according to claim 1, comprising means for monitoring the user's learning progress and obtaining and analyzing feedback.

Images