system

Abstract

Provide a system. 【Solution means】 An information storage means for storing educator information, A receiving means for receiving learning desire information from learners, An analysis means for analyzing the learning desire information of learners using generative AI and selecting the most suitable educator for the learners, A matching means for matching the selected educator and the learner, A plan providing means for creating a learning plan and providing the plan to the learner, A communication means for conducting online education between the learner and the educator, A feedback collection means for collecting feedback from learners and storing it in a database, A system including the above.

Description

Technical Field

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, in order to meet diversified learning needs, it is necessary to provide specialized education according to the wishes and purposes of individual learners. However, it is difficult to effectively match appropriate educators with learners, and there are limitations in selecting appropriate content from a vast amount of educational information. Furthermore, since it is not easy to individualize and dynamically adjust online learning plans, a mechanism for maximizing learning effects is required.

Means for Solving the Problems

[0005] This invention collects learner needs by providing information storage means for storing educator information and receiving means for receiving learning preference information from learners. It includes analysis means that analyze learners' learning preference information using generation AI to select the most suitable educator for the learner and matching means that match the selected educator with the learner. It also includes plan provision means that creates and provides a learning plan to the learner, and communication means that conducts online education between learners and educators, thereby providing an individualized learning environment. Furthermore, by including feedback collection means that collect feedback from learners and store it in a database, it becomes possible to dynamically adjust learning content and plans and enhance learning effectiveness.

[0006] "Educator information" refers to detailed information about the person who will be providing instruction to the learners, such as their area of ​​expertise, teaching experience, and available teaching times.

[0007] "Information storage means" refers to databases and storage systems for securely and efficiently storing information about educators and learners.

[0008] A "receiving means" refers to an interface or function for receiving learning request information from learners and processing it within the system.

[0009] "Generative AI" refers to an algorithm or system that uses artificial intelligence technology to analyze data and gain a detailed understanding of the learner's needs.

[0010] "Analysis methods" refer to the processes and techniques used to analyze received learning preference information and select appropriate educators.

[0011] A "matching method" is a mechanism or process for effectively connecting learners and educators based on the results of analysis.

[0012] A "plan delivery method" refers to a system or method for creating a learning plan based on the learner's needs and presenting its contents to the learner.

[0013] "Communication methods" refer to the technical infrastructure and means that enable learners and educators to communicate with each other in an online environment.

[0014] A "feedback collection method" refers to a function or process for collecting, accumulating, and analyzing opinions and evaluations from learners. [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 a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[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 disks (e.g., hard disks), or magnetic tapes, 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 describes a system that effectively matches educators and learners and provides an individualized learning environment online. The program processing of this system is described below.

[0037] This system begins with learners sending their personal information and learning preferences to a server via a terminal. The server stores the received information in a database, gaining a detailed understanding of the learners' needs.

[0038] Next, the server stores information such as the educators' areas of expertise and teaching history in a database to build educator profiles. These profiles are used as foundational data for the generating AI to select the most suitable educator for each learner.

[0039] The generating AI analyzes information received from learners and selects appropriate educators based on their learning goals and desired learning content. The server matches the selected educators with the learners and creates individualized learning plans based on this matching. These plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0040] The device will present this learning plan to the learner and enable them to participate in online lessons with the educator. It will utilize communication methods to conduct real-time video conferencing, allowing for active communication between both parties.

[0041] After class, users provide feedback via their devices, and the server collects, analyzes, and stores this information in a database. This data is used to improve the overall system performance.

[0042] For example, if a user wishes to improve their "foreign language conversation skills," the server will select a foreign language education expert and provide a learning plan tailored to the user. Following this plan, the user can participate in online sessions with the foreign language teacher and efficiently improve their skills through practical conversation practice.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The device displays a registration form to the user. The user enters information such as their name, email address, desired subjects to study, and goals. After completion, the device sends this data to the server.

[0046] Step 2:

[0047] The server stores the received user information in a database. During storage, it also generates an initial dataset for analyzing the learner's needs.

[0048] Step 3:

[0049] The terminal presents a registration form to the educator. The educator enters information such as their area of ​​expertise, teaching experience, and available time slots. The terminal then sends this information to the server.

[0050] Step 4:

[0051] The server stores educator information in a database and builds educator profiles. These profiles are used to match educators with learners.

[0052] Step 5:

[0053] The server activates the generation AI and analyzes the user's learning preferences. Based on the analysis results, it selects the most suitable educator candidate for the learner.

[0054] Step 6:

[0055] The server matches selected educators with learners and creates individualized learning plans. These plans include learning objectives, relevant materials, and assessment methods.

[0056] Step 7:

[0057] The device notifies the learner of this learning plan and allows them to review the details. If the learner agrees to the plan, the online lesson schedule is set.

[0058] Step 8:

[0059] When the scheduled class time arrives, users connect to the online platform using their devices. These devices provide features that enable real-time video conversations and chat.

[0060] Step 9:

[0061] After the class ends, users enter feedback on the class via their device. The device then sends the feedback to the server.

[0062] Step 10:

[0063] The server collects the submitted feedback and stores it in a database. This data helps improve future matching accuracy and learning plans.

[0064] (Example 1)

[0065] 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."

[0066] Traditional online education systems have struggled to efficiently select educators based on individual learners' needs, making it difficult to maximize educational effectiveness. Furthermore, they have faced challenges in efficiently collecting learner progress and feedback, and dynamically adjusting educational plans. As a result, providing appropriate, individualized education to learners has been difficult.

[0067] 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.

[0068] In this invention, the server includes a storage means for storing information, a receiving means for receiving learning preference information, and an analysis means for analyzing the learning preference information using generative artificial intelligence technology and selecting an appropriate educator. This makes it possible to appropriately provide individualized learning plans to learners and achieve optimal matching between educators and learners.

[0069] "Means for storing information" refers to devices or methods for storing information using databases or storage devices.

[0070] A "receiving means for receiving learning request information" refers to a means of delivering learning-related information entered by learners to a server.

[0071] "Generative artificial intelligence technology" refers to machine learning models and artificial intelligence technologies used to analyze received data and make appropriate judgments and choices.

[0072] "Analysis means" refers to a process or apparatus for analyzing learning target information using generating artificial intelligence technology.

[0073] "Means for combining selected educators and learners" refers to a method or device for selecting appropriate educators and connecting them with learners based on analyzed information.

[0074] "A means of creating and providing individualized learning plans to learners" refers to a means of designing learning plans tailored to the learners' needs and communicating them to the learners.

[0075] "Communication methods" refer to communication technologies that enable learners and educators to interact online and conduct educational activities in real time.

[0076] "Information gathering means" refers to methods and devices for collecting and storing feedback from learners and data related to lessons.

[0077] This invention uses an information processing system to effectively match learners and educators online and provide an individualized learning environment.

[0078] The server receives learning preference information entered by learners via their devices. This learning preference information includes the learner's personal needs, goals, and preferred learning style. Learners enter this information using a web browser or mobile app and send it to the server. This data is transmitted securely using the HTTPS protocol and stored in a database on the server side.

[0079] Next, the server retrieves information such as the educator's area of ​​expertise, teaching experience, and qualifications, and records this information in a database. At this stage, generative artificial intelligence technology is used to construct a profile of the educator. This profile information becomes the basic data for optimal matching between learners and educators.

[0080] The generative AI model runs on a server, analyzing learners' needs and selecting the most suitable educators. Text processing techniques are used for the analysis. Based on the analysis results, the server effectively matches educators and learners and creates individualized learning plans. These learning plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0081] The device presents this learning plan to the learner. The learner receives instruction from the educator in real time using a video conferencing tool (e.g., common online meeting software). This allows for practical and efficient learning.

[0082] After the lesson ends, users send feedback to the server via their devices. The server collects this feedback and analyzes the data again using a generative AI model. The results of this analysis are used to improve the quality of education.

[0083] For example, if a user wishes to improve their "foreign language conversation skills," the server will select an expert in that field and provide a learning plan suitable for the user. An example of a prompt to the generating AI model would be, "Please suggest a method for matching me with an online educator to improve my foreign language conversation skills." This prompt allows the system to quickly select an educator that meets the user's needs.

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

[0085] Step 1:

[0086] Users enter learning information using their device. This includes personal information, learning objectives, and preferred learning style. The entered data is sent from the device to the server. The HTTPS protocol is used for this transmission to ensure security.

[0087] Step 2:

[0088] The server receives learning request information sent from the terminal. The received data is validated to check data accuracy and converted to an appropriate format. Only accurate data is then stored in the database.

[0089] Step 3:

[0090] The server collects information from educators, such as their areas of expertise and teaching experience. This includes information gathering through automated forms and email. The collected information is stored in a database as profile data.

[0091] Step 4:

[0092] The generative AI model runs on a server and analyzes learner needs and educator profiles. The AI ​​applies text analysis techniques to compare learning preferences with educator expertise and select the most suitable educator. Learning preferences and profile data are used as input, and a list of appropriate educators is generated as a selection result.

[0093] Step 5:

[0094] The server creates a customized individual learning plan based on the educator list generated in step 4. This plan includes specific teaching materials, teaching methods, and evaluation criteria. The learning plan is dynamically optimized using analysis results from generative artificial intelligence technology.

[0095] Step 6:

[0096] The device receives the learning plan provided by the server and presents it to the user. Simultaneously, links to video conferencing tools and class schedule information are also sent to the user. The device supports real-time communication technology to maintain connectivity.

[0097] Step 7:

[0098] Users participate in online classes based on the information provided. During classes, interaction with educators takes place via the device, and high-quality audio and video data is streamed. This enhances the educational experience.

[0099] Step 8:

[0100] After the lesson ends, users provide feedback using their devices. The feedback is collected in the form of a multifaceted question and sent from the device to the server.

[0101] Step 9:

[0102] The server analyzes the received feedback. A generative AI model uses this data to evaluate and identify areas for improvement in the quality of education and individual adjustments. The analysis results are recorded in a database and used to create future learning plans.

[0103] (Application Example 1)

[0104] 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."

[0105] In online education environments, matching learners with educators who meet their individual needs and efficiently providing suitable educational resources are key challenges. Traditional systems struggle to find the optimal combination of learner and educator, sometimes resulting in decreased learning efficiency. Furthermore, providing educational resources in a way that is easily accessible to learners is not yet fully realized.

[0106] 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.

[0107] In this invention, the server includes information storage means for storing educator information, receiving means for receiving learning preference information from learners, analysis means for analyzing learners' learning preference information using generating AI and selecting the most suitable educator for the learner, matching means for matching the selected educator with the learner, plan provision means for creating a learning plan and providing the plan to the learner, communication means for conducting online education between learners and educators, feedback collection means for collecting feedback from learners and storing it in a database, optimization provision means for optimizing educational resources based on the learner's profile and providing them in streaming format, and operation simplification means for simplifying access to educational resources through an interface on the user terminal. This enables learners to be effectively matched with educators best suited to their individual learning needs and provides easily accessible and personalized educational resources.

[0108] An "information storage device" is a device for storing information about educators in digital format.

[0109] A "receiving mechanism" is a system for receiving learning preference information provided by learners into the server.

[0110] "Analysis methods" refer to the process of using generative AI to analyze in detail the information provided by learners and select the most suitable educator to meet their needs.

[0111] A "matching method" is a system designed to appropriately connect selected educators with learners.

[0112] A "plan delivery method" is a method for presenting a designed learning plan to learners.

[0113] "Communication means" refers to the communication infrastructure that enables learners and educators to receive education online.

[0114] A "feedback collection method" refers to a method for collecting opinions and evaluations from learners after class and storing them in a database.

[0115] An "optimized delivery method" is a system for optimizing and delivering educational resources based on the learner's profile.

[0116] "Means of simplifying operation" are mechanisms that allow learners to easily access educational resources through user-friendly interfaces.

[0117] The system based on this invention is designed to achieve personalized education and is implemented using the following hardware and software. The system mainly consists of a server, terminals, and users.

[0118] The server is equipped with database software as a means of storing information, and stores educator information. A form-based interface is provided to receive learning preference information from users, and this information is stored in the server's database. The analysis method, which uses generative AI, analyzes users' learning preferences and constructs machine learning algorithms to select appropriate educators. This incorporates text mining utilizing natural language processing technology.

[0119] The learning plan is delivered online to learners via a plan delivery system, and the learning based on it is conducted using communication methods. Video streaming services such as the Zoom SDK are integrated, enabling real-time education. The resulting feedback is efficiently collected from users through a feedback collection system.

[0120] Furthermore, the optimized delivery method uses AI-based algorithms to optimize educational resources based on the learner's profile and delivers them in streaming format. This process is supported by database technologies such as Firebase. The simplified operation method allows learners to easily access educational resources through interfaces installed on smartphones and other devices. The user interface is designed for intuitive operation.

[0121] For example, if a learner wishes to improve their second language skills, the server selects an educator tailored to the learner's specific goals and preferences, and presents appropriate materials and a learning plan. In online sessions, the selected educator and learner interact using Zoom or similar platforms, and the feedback is used to adjust the next lesson's approach.

[0122] Example of a prompt:

[0123] "This student is 10 years old and struggles with math. Please recommend a teacher with teaching experience who can teach them gently."

[0124] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0125] Step 1:

[0126] Users input their learning preferences using devices such as smartphones or PCs. This includes information such as the subjects they want to study and their preferred learning style. The entered information is sent to the server via a receiving device and stored in a database.

[0127] Step 2:

[0128] The server activates an analysis tool to analyze the received learning preference information. It incorporates the prompt "Recommend an educator that matches the learner's needs" into the generating AI model. The AI ​​uses natural language processing technology to analyze the input data and select the most suitable educator profile for the learner.

[0129] Step 3:

[0130] Based on the selected educator information, the server uses a matching mechanism to create pairs of learners and educators. This process also takes into account the schedules and compatibility of both parties. The optimal pairing is then performed based on the results of data calculations performed by the generative AI.

[0131] Step 4:

[0132] The server creates a learning plan for the selected educators and provides it to the terminal via a plan delivery system. This plan includes the teaching materials and methods to be used. The learning plan is dynamically adjusted based on real-time data analysis.

[0133] Step 5:

[0134] The device initiates an online session using communication methods. It supports real-time lessons through video conferencing services such as the Zoom SDK. Users (learners) interact with educators and receive instruction towards set goals.

[0135] Step 6:

[0136] After the lesson ends, the device receives feedback from the user. The server stores this feedback in a database and uses it to improve the overall system performance. The collected data is used to improve the AI ​​algorithms.

[0137] Step 7:

[0138] The server uses an optimized delivery mechanism to stream educational resources based on the user's profile information. This allows learners to immediately access optimized resources in their next online session.

[0139] 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.

[0140] This invention combines a system that effectively matches educators and learners and provides an online learning environment with an emotion engine that recognizes the user's emotions.

[0141] First, learners input their learning preferences through a terminal and send them to the server. The server stores educator information, such as the educator's area of ​​expertise and teaching methods, in a database and uses a generative AI and an emotion engine to analyze the learner's information in detail. The generative AI analyzes the learner's learning preferences and goals, while the emotion engine also evaluates the learner's emotional data in real time and analyzes their current emotional state.

[0142] Based on the analysis results, the server selects the most suitable educator for the learner and creates a learning plan tailored to the learner's needs and emotions. This plan incorporates the most appropriate teaching materials and methods based on the learner's condition, taking into account the data provided by the emotion engine. For example, if the emotion engine indicates that the learner has a high level of concentration, it can suggest more challenging tasks.

[0143] The learning plan is displayed on the device, and the user reviews its contents. Once the user agrees to the plan, the device schedules the lessons and guides the user to the online learning platform. During the lessons, an emotion engine monitors the user's facial expressions and voice, and provides real-time feedback to the server on changes in their emotions during learning. The server can use this data to instruct educators to adjust their teaching methods.

[0144] After the lesson ends, users input feedback via their devices and send it to the server. This feedback and emotion engine data are stored in a database and used to help plan future lessons and select educators.

[0145] For example, if a user wishes to acquire a specific skill and experiences stress during a lesson, the emotion engine detects this state, and the server adjusts the difficulty level of the skill acquisition or suggests a relaxing teaching method to the educator. In this way, a learning experience best suited to the learner's emotional state can be provided.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The device presents the user with a form to enter their learning objectives and desired content. The user enters their name, email address, target skills, etc., and presses the submit button. The device sends this information to the server.

[0149] Step 2:

[0150] The server stores the received user information in a database. Furthermore, it collects educator information, including the educator's area of ​​expertise and teaching experience, and stores it in the database as well.

[0151] Step 3:

[0152] The server uses a generation AI to analyze the user's learning preferences and lists suitable educators. During this process, it analyzes the characteristics of educators necessary for the user to achieve their goals.

[0153] Step 4:

[0154] The device presents the user with suitable educator candidates and prompts them to make a selection. The user chooses an educator and checks the learning schedule.

[0155] Step 5:

[0156] The server activates the emotion engine and monitors the user's emotions in real time. When a user participates in an online lesson, the device transmits facial expressions and voice data to the emotion engine via its camera and microphone.

[0157] Step 6:

[0158] The emotion engine analyzes the user's emotional data and reports their current emotional state to the server. This includes information such as whether the user is focused or stressed.

[0159] Step 7:

[0160] The server dynamically adjusts the learning plan based on emotional state data. If necessary, it sends suggestions to educators to modify the teaching content.

[0161] Step 8:

[0162] After the lesson ends, users enter feedback on the lesson via their device and send it to the server. This feedback will be referenced when customizing the lesson for the next time.

[0163] Step 9:

[0164] The server stores feedback and sentiment data in a database, which is used to improve the user experience and enhance the accuracy of educator selection in the future. This process optimizes the user's learning effectiveness.

[0165] (Example 2)

[0166] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0167] Online education systems are required to provide education that is tailored to the individual needs and emotional state of learners. However, existing systems only consider the learning content that learners desire, and there is a challenge in suggesting the most suitable educator and learning plan that reflects their emotions and condition.

[0168] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0169] In this invention, the server includes a storage means for storing educator information, an input means for receiving learner learning preference information, and an emotion evaluation means for analyzing emotion data in real time and evaluating the learner's emotional state. This makes it possible to select the optimal educator, taking into account the learner's learning preference and emotional state, and to provide a learning plan based on that.

[0170] "Educator information" refers to data that includes attributes such as the educator's area of ​​expertise, teaching experience, and teaching style.

[0171] "Memory devices" refer to devices and methods for storing information, such as databases and storage systems.

[0172] "Learning preference information" refers to data that includes the skills and goals that learners want to acquire, as well as their preferred learning style.

[0173] "Input means" refers to interfaces and communication methods for receiving learner information.

[0174] "Generative AI" is an artificial intelligence technology that uses machine learning techniques to analyze data and support decision-making.

[0175] "Evaluation methods" refer to functions that use generative AI models to analyze learner information and select the most suitable educator.

[0176] "Emotional assessment tools" are technologies that analyze emotional data in real time and evaluate the emotional state of learners.

[0177] "Combination means" refers to the methods or processes used to combine the most suitable educators and learners.

[0178] "Means of providing a learning plan" refers to the functions and processes for formulating a learning plan based on the learner's needs and feelings, and for presenting it to the learner.

[0179] "Means of communication" refers to networks and communication technologies that enable communication between learners and educators.

[0180] "Monitoring means" refers to the process of monitoring the learner's status in real time during learning and feeding that information back to the server.

[0181] "Methods for gathering feedback" refer to methods and systems for collecting feedback from learners and storing it in an information base.

[0182] This invention provides a system for online education that offers optimal education based on the individual needs and emotional state of learners.

[0183] First, the user enters their learning preferences through their device. A dedicated user interface is provided for this input, allowing the user to record their learning goals and preferred learning style in detail through voice recognition or text input. This information is then transmitted to a server via the internet.

[0184] The server stores the received learner information in storage. This data includes the educator's area of ​​expertise and teaching experience, and a structured database is used for efficient storage and retrieval of the information. The server also analyzes the learner information using a generative AI model. This model employs natural language processing techniques and implements algorithms that interpret the learner's desired content in detail. Furthermore, it utilizes an emotion engine to analyze emotional information obtained from user signals in real time. This makes it possible to accurately assess the learner's current emotional state.

[0185] For example, if a user sets a learning goal of "I want to acquire English conversation skills," the generating AI model will suggest relevant learning materials and educators. An example of a prompt might be, "Please suggest a plan to improve listening skills using high school level English. The learner currently has high concentration and a positive learning attitude."

[0186] After a learning plan is created, the plan received from the server is displayed on the device. The user reviews and agrees to the plan, and scheduling is completed. During lessons, the user's facial expressions and voice are monitored through the device's built-in camera and microphone, and the data obtained is sent to the server in real time. This feedback information is used by educators to adjust lessons, ensuring that learners receive the best possible educational experience.

[0187] Thus, by combining a generative AI model with emotion evaluation technology, the present invention realizes education that is tailored to the individual needs and emotions of learners, and provides a more flexible and effective online learning environment.

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

[0189] Step 1:

[0190] Users input their learning preferences using a device. Specifically, they enter the skills they want to learn, their goals, and their preferred learning style through text or voice input via the user interface. This data is sent to the server in a structured format.

[0191] Step 2:

[0192] The server stores the received learning preference information in its storage device. Simultaneously, it invokes a generative AI model to analyze the received data. Specifically, it provides the generative AI model with prompts and performs natural language processing analysis. This analysis allows it to generate data on educators and learning materials related to the learner's preferences. The analysis results are stored in a temporary database.

[0193] Step 3:

[0194] The server uses an emotion engine to evaluate the learner's emotional state from their input data. Specifically, it analyzes certain keywords and contextual information within the input data to quantify the learner's current emotional state (e.g., concentration level, stress level, etc.). This information is then incorporated as an important factor in creating a learning plan.

[0195] Step 4:

[0196] Based on the analysis results and emotional state, the server selects the most suitable educator from the database and develops a learning plan. Specifically, it processes the aggregated data using a Python script to determine the suggested teaching materials and methods. This plan is then saved back to the database and sent to the terminal.

[0197] Step 5:

[0198] The device displays the learning plan received from the server in the user interface. Once the user reviews and agrees to the learning plan, the device automatically sets the schedule. Specifically, it uses a calendar application to create appointments and set reminders.

[0199] Step 6:

[0200] During lessons, the device monitors the user's state in real time through its camera and microphone. This includes an emotion engine analyzing data obtained from the user's facial expressions and voice, and sending it to a server. This data is then fed back to the educator, allowing them to adjust teaching methods as needed.

[0201] Step 7:

[0202] After the lesson ends, users input feedback via their devices. Specifically, they enter text feedback regarding the quality of the lesson and their level of understanding, and send it to the server. This data is used to improve future learning plans and is stored in a database.

[0203] (Application Example 2)

[0204] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0205] In online learning environments, there is a need to effectively match learners with educators and flexibly optimize the learning experience in response to the individual state of the learner, especially changes in their emotions. However, current systems find it difficult to analyze emotions in real time and dynamically adjust learning plans and content based on that analysis. As a result, it is difficult to accurately provide learning content that is appropriate for the learner's level of concentration and fatigue.

[0206] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0207] In this invention, the server includes an information storage means for storing educator information, an emotion analysis means for analyzing learners' emotions in real time and dynamically adjusting learning content, and a content optimization means for optimizing learning content according to the learner's concentration level and fatigue level. This enables the matching of learners with the most suitable educators and the flexible provision of content according to the learners' emotional state.

[0208] "Educator information" refers to attribute information such as the educator's area of ​​expertise and teaching methods.

[0209] "Information storage means" refers to servers and databases used to store information about educators.

[0210] "Learning preference information" refers to information that includes the learning content and goals that the learner desires.

[0211] "Receiving means" refers to an interface for receiving learning preference information sent by learners.

[0212] "Generative AI" refers to artificial intelligence technology that analyzes learning preferences and generates the optimal learning plan.

[0213] "Analysis method" refers to the process of using generative AI to analyze learners' preferences and select the most suitable educator.

[0214] "Matching method" refers to a mechanism for connecting educators and learners selected through analysis.

[0215] "Plan delivery means" refers to a system for presenting generated learning plans to learners.

[0216] "Communication methods" refer to technologies that enable learners and educators to exchange information online.

[0217] "Feedback collection methods" refer to functions for collecting feedback and opinions from learners and storing them in a database.

[0218] "Emotion analysis methods" refer to technologies that analyze a learner's emotions from their facial expressions and voice, and understand their state in real time.

[0219] "Content optimization means" refers to a mechanism for dynamically adjusting the learning content provided according to the learner's emotional state.

[0220] To implement this invention, it is necessary to construct an online learning system centered on a server. First, learners use a terminal to input their learning preferences and send them to the server. This terminal can be a smartphone, computer, or head-mounted display. The server is equipped with information storage means for storing the educators' areas of expertise and teaching methods.

[0221] The received information is analyzed by a generative AI. This generative AI utilizes, for example, the GPT model from OpenAI®. The generative AI analyzes the learning preference information in detail and selects the most suitable educator. The server further uses emotion analysis tools to grasp the learner's real-time emotional state from their facial expression and voice data. For this purpose, it uses, for example, the emotion recognition API from Microsoft® Azure®.

[0222] After the most suitable educator is selected, the server connects the learner with the educator using a matching mechanism. Then, using a plan provision mechanism, it creates an individualized learning plan tailored to the learner's current emotional state. This plan is displayed on the learner's device, allowing the learner to review it.

[0223] During lessons, the server monitors changes in learners' emotions through emotion analysis tools. Based on this data, the server utilizes content optimization tools to dynamically adjust learning content according to the learners' concentration levels and fatigue levels. For example, if a learner is highly focused, a more challenging task is provided; if they are feeling fatigued, relaxation content is presented.

[0224] After class, students input feedback via their devices, and the server saves this data to a database using a feedback collection system. This data is then used to plan future lessons.

[0225] As a concrete example, if the emotion analysis system detects fatigue in a learner who wants to study English, the server will suggest a relaxation video to maintain the learner's motivation. Another example of a prompt for the generative AI model is, "Please suggest an English learning plan that takes into account the user's concentration and fatigue level. Please add simple exercises where relaxation is needed."

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

[0227] Step 1:

[0228] The user uses a terminal to input information about their learning preferences and sends it to the server. This data includes the areas they want to study and their specific goals. The server receives this information and stores it in a database. This prepares the learning preference information for use in the next process.

[0229] Step 2:

[0230] The server sends the received learning preference information to the generating AI. The generating AI analyzes this information and uses specific prompts to select an educator suitable for the user. The generating AI analyzes the text data to find educators whose expertise and teaching methods match the user's needs. The selection results are output as educator information.

[0231] Step 3:

[0232] The server uses emotion analysis tools to collect real-time facial and voice data from the user. The server sends this data to an emotion recognition API to analyze the user's emotional state. The analysis results in emotional parameters such as the user's current concentration level and stress level.

[0233] Step 4:

[0234] The server generates an optimal learning plan for the learner based on the obtained educator information and emotional parameters. This plan includes challenging content if the learner is highly focused, and relaxation content if fatigue is observed. The generated learning plan is sent to the terminal.

[0235] Step 5:

[0236] Users review their learning plan on their device, and if they agree to the plan, the lesson begins. During the lesson, the server optimizes the content as needed, providing a learning experience tailored to the learner's emotional state. This optimization is performed dynamically based on emotional changes, maximizing the user's learning effectiveness.

[0237] Step 6:

[0238] After the lesson ends, users input feedback about their learning experience from their device and send it to the server. The server collects this feedback information and stores it in a database to help plan future learning sessions. Along with the feedback, sentiment data is also stored and used in future optimization processes.

[0239] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0240] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0241] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0242] [Second Embodiment]

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

[0244] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0245] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0246] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0247] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0248] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0249] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0250] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0251] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0252] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0253] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0254] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0255] This invention describes a system that effectively matches educators and learners and provides an individualized learning environment online. The program processing of this system is described below.

[0256] This system begins with learners sending their personal information and learning preferences to a server via a terminal. The server stores the received information in a database, gaining a detailed understanding of the learners' needs.

[0257] Next, the server stores information such as the educators' areas of expertise and teaching history in a database, building profiles of the educators. These profiles are used as foundational data for the generating AI to select the most suitable educators for learners.

[0258] The generating AI analyzes information received from learners and selects appropriate educators based on their learning goals and desired learning content. The server matches the selected educators with the learners and creates individualized learning plans based on this matching. These plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0259] The device will present this learning plan to the learner and enable them to participate in online lessons with the educator. It will utilize communication methods to conduct real-time video conferencing, allowing for active communication between both parties.

[0260] After class, users provide feedback via their devices, and the server collects, analyzes, and stores this information in a database. This data is used to improve the overall system performance.

[0261] For example, if a user wishes to improve their "foreign language conversation skills," the server will select a foreign language education expert and provide a learning plan tailored to the user. Following this plan, the user can participate in online sessions with the foreign language teacher and efficiently improve their skills through practical conversation practice.

[0262] The following describes the processing flow.

[0263] Step 1:

[0264] The device displays a registration form to the user. The user enters information such as their name, email address, desired subjects to study, and goals. After completion, the device sends this data to the server.

[0265] Step 2:

[0266] The server stores the received user information in a database. During storage, it also generates an initial dataset for analyzing the learner's needs.

[0267] Step 3:

[0268] The terminal presents a registration form to the educator. The educator enters information such as their area of ​​expertise, teaching experience, and available time slots. The terminal then sends this information to the server.

[0269] Step 4:

[0270] The server stores educator information in a database and builds educator profiles. These profiles are used to match educators with learners.

[0271] Step 5:

[0272] The server activates the generation AI and analyzes the user's learning preferences. Based on the analysis results, it selects the most suitable educator candidate for the learner.

[0273] Step 6:

[0274] The server matches selected educators with learners and creates individualized learning plans. These plans include learning objectives, relevant materials, and assessment methods.

[0275] Step 7:

[0276] The device notifies the learner of this learning plan and allows them to review the details. If the learner agrees to the plan, the online lesson schedule is set.

[0277] Step 8:

[0278] When the scheduled class time arrives, the user connects to the online platform using the terminal. The terminal provides functions that enable real-time video conferencing and chatting.

[0279] Step 9:

[0280] After the class, the user inputs feedback on the class through the terminal. The terminal sends the feedback to the server.

[0281] Step 10:

[0282] The server collects the sent feedback and stores it in the database. This data is useful for improving future matching accuracy and learning plans.

[0283] (Example 1)

[0284] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In conventional online education systems, it was difficult to efficiently select educators based on the individual needs of learners, and it was difficult to maximize the educational effect. There was also a problem in that it was difficult to efficiently collect the progress and feedback of learners and dynamically adjust the educational plan. As a result, it was difficult to provide appropriate individualized education to learners.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0287] In this invention, the server includes a storage means for storing information, a receiving means for receiving learning desire information, and an analysis means for analyzing the learning desire information using generative artificial intelligence technology and selecting an appropriate educator. As a result, it becomes possible to appropriately provide an individual learning plan to the learner and realize an optimal matching between the educator and the learner.

[0288] "Means for storing information" refers to devices or methods for storing information using databases or storage devices.

[0289] A "receiving means for receiving learning request information" refers to a means of delivering learning-related information entered by learners to a server.

[0290] "Generative artificial intelligence technology" refers to machine learning models and artificial intelligence technologies used to analyze received data and make appropriate judgments and choices.

[0291] "Analysis means" refers to a process or apparatus for analyzing learning target information using generating artificial intelligence technology.

[0292] "Means for combining selected educators and learners" refers to a method or device for selecting appropriate educators and connecting them with learners based on analyzed information.

[0293] "A means of creating and providing individualized learning plans to learners" refers to a means of designing learning plans tailored to the learners' needs and communicating them to the learners.

[0294] "Communication methods" refer to communication technologies that enable learners and educators to interact online and conduct educational activities in real time.

[0295] "Information gathering means" refers to methods and devices for collecting and storing feedback from learners and data related to lessons.

[0296] This invention uses an information processing system to effectively match learners and educators online and provide an individualized learning environment.

[0297] The server receives learning preference information entered by learners via their devices. This learning preference information includes the learner's personal needs, goals, and preferred learning style. Learners enter this information using a web browser or mobile app and send it to the server. This data is transmitted securely using the HTTPS protocol and stored in a database on the server side.

[0298] Next, the server retrieves information such as the educator's area of ​​expertise, teaching experience, and qualifications, and records this information in a database. At this stage, generative artificial intelligence technology is used to construct a profile of the educator. This profile information becomes the basic data for optimal matching between learners and educators.

[0299] The generative AI model runs on a server, analyzing learners' needs and selecting the most suitable educators. Text processing techniques are used for the analysis. Based on the analysis results, the server effectively matches educators and learners and creates individualized learning plans. These learning plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0300] The device presents this learning plan to the learner. The learner receives instruction from the educator in real time using a video conferencing tool (e.g., common online meeting software). This allows for practical and efficient learning.

[0301] After the lesson ends, users send feedback to the server via their devices. The server collects this feedback and analyzes the data again using a generative AI model. The results of this analysis are used to improve the quality of education.

[0302] As a specific example, when a user wishes to improve their "foreign language conversation skills", the server selects an expert in the relevant field and provides a learning plan suitable for the user. An example of a prompt sentence for the generative AI model is "Please propose a method for matching with an online educator to improve foreign language conversation skills". With this prompt, the system can quickly select an educator that meets the user's needs.

[0303] The flow of the specific process in Example 1 will be described using FIG. 11.

[0304] Step 1:

[0305] The user uses the terminal to input learning desire information. This includes personal information, learning objectives, desired learning styles, etc. The input data is sent from the terminal to the server. For this transmission, the HTTPS protocol is used to ensure security.

[0306] Step 2:

[0307] The server receives the learning desire information sent from the terminal. The received data is verified to confirm data accuracy and converted into an appropriate format. Thereafter, only the accurate data is stored in the database.

[0308] Step 3:

[0309] The server collects information such as the specialized fields and teaching experience provided by the educators. This includes information collection using automatic form input and emails. The collected information is stored in the database as profile data.

[0310] Step 4:

[0311] The generative AI model runs on a server and analyzes learner needs and educator profiles. The AI ​​applies text analysis techniques to compare learning preferences with educator expertise and select the most suitable educator. Learning preferences and profile data are used as input, and a list of appropriate educators is generated as a selection result.

[0312] Step 5:

[0313] The server creates a customized individual learning plan based on the educator list generated in step 4. This plan includes specific teaching materials, teaching methods, and evaluation criteria. The learning plan is dynamically optimized using analysis results from generative artificial intelligence technology.

[0314] Step 6:

[0315] The device receives the learning plan provided by the server and presents it to the user. Simultaneously, links to video conferencing tools and class schedule information are also sent to the user. The device supports real-time communication technology to maintain connectivity.

[0316] Step 7:

[0317] Users participate in online classes based on the information provided. During classes, interaction with educators takes place via the device, and high-quality audio and video data is streamed. This enhances the educational experience.

[0318] Step 8:

[0319] After the lesson ends, users provide feedback using their devices. The feedback is collected in the form of a multifaceted question and sent from the device to the server.

[0320] Step 9:

[0321] The server analyzes the received feedback. A generative AI model uses this data to evaluate and identify areas for improvement in the quality of education and individual adjustments. The analysis results are recorded in a database and used to create future learning plans.

[0322] (Application Example 1)

[0323] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0324] In online education environments, matching learners with educators who meet their individual needs and efficiently providing suitable educational resources are key challenges. Traditional systems struggle to find the optimal combination of learner and educator, sometimes resulting in decreased learning efficiency. Furthermore, providing educational resources in a way that is easily accessible to learners is not yet fully realized.

[0325] 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.

[0326] In this invention, the server includes information storage means for storing educator information, receiving means for receiving learning preference information from learners, analysis means for analyzing learners' learning preference information using generating AI and selecting the most suitable educator for the learner, matching means for matching the selected educator with the learner, plan provision means for creating a learning plan and providing the plan to the learner, communication means for conducting online education between learners and educators, feedback collection means for collecting feedback from learners and storing it in a database, optimization provision means for optimizing educational resources based on the learner's profile and providing them in streaming format, and operation simplification means for simplifying access to educational resources through an interface on the user terminal. This enables learners to be effectively matched with educators best suited to their individual learning needs and provides easily accessible and personalized educational resources.

[0327] An "information storage device" is a device for storing information about educators in digital format.

[0328] A "receiving mechanism" is a system for receiving learning preference information provided by learners into the server.

[0329] "Analysis methods" refer to the process of using generative AI to analyze in detail the information provided by learners and select the most suitable educator to meet their needs.

[0330] A "matching method" is a system designed to appropriately connect selected educators with learners.

[0331] A "plan delivery method" is a method for presenting a designed learning plan to learners.

[0332] "Communication means" refers to the communication infrastructure that enables learners and educators to receive education online.

[0333] A "feedback collection method" refers to a method for collecting opinions and evaluations from learners after class and storing them in a database.

[0334] An "optimized delivery method" is a system for optimizing and delivering educational resources based on the learner's profile.

[0335] "Means of simplifying operation" are mechanisms that allow learners to easily access educational resources through user-friendly interfaces.

[0336] The system based on this invention is designed to achieve personalized education and is implemented using the following hardware and software. The system mainly consists of a server, terminals, and users.

[0337] The server is equipped with database software as a means of storing information, and stores educator information. A form-based interface is provided to receive learning preference information from users, and this information is stored in the server's database. The analysis method, which uses generative AI, analyzes users' learning preferences and constructs machine learning algorithms to select appropriate educators. This incorporates text mining utilizing natural language processing technology.

[0338] The learning plan is delivered online to learners via a plan delivery system, and the learning based on it is conducted using communication methods. Video streaming services such as the Zoom SDK are integrated, enabling real-time education. The resulting feedback is efficiently collected from users through a feedback collection system.

[0339] Furthermore, the optimized delivery method uses AI-based algorithms to optimize educational resources based on the learner's profile and delivers them in streaming format. This process is supported by database technologies such as Firebase. The simplified operation method allows learners to easily access educational resources through interfaces installed on smartphones and other devices. The user interface is designed for intuitive operation.

[0340] For example, if a learner wishes to improve their second language skills, the server selects an educator tailored to the learner's specific goals and preferences, and presents appropriate materials and a learning plan. In online sessions, the selected educator and learner interact using Zoom or similar platforms, and the feedback is used to adjust the next lesson's approach.

[0341] Example of a prompt:

[0342] "This student is 10 years old and struggles with math. Please recommend a teacher with teaching experience who can teach them gently."

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

[0344] Step 1:

[0345] Users input their learning preferences using devices such as smartphones or PCs. This includes information such as the subjects they want to study and their preferred learning style. The entered information is sent to the server via a receiving device and stored in a database.

[0346] Step 2:

[0347] The server activates an analysis tool to analyze the received learning preference information. It incorporates the prompt "Recommend an educator that matches the learner's needs" into the generating AI model. The AI ​​uses natural language processing technology to analyze the input data and select the most suitable educator profile for the learner.

[0348] Step 3:

[0349] Based on the selected educator information, the server uses a matching mechanism to create pairs of learners and educators. This process also takes into account the schedules and compatibility of both parties. The optimal pairing is then performed based on the results of data calculations performed by the generative AI.

[0350] Step 4:

[0351] The server creates a learning plan for the selected educators and provides it to the terminal via a plan delivery system. This plan includes the teaching materials and methods to be used. The learning plan is dynamically adjusted based on real-time data analysis.

[0352] Step 5:

[0353] The device initiates an online session using communication methods. It supports real-time lessons through video conferencing services such as the Zoom SDK. Users (learners) interact with educators and receive instruction towards set goals.

[0354] Step 6:

[0355] After the lesson ends, the device receives feedback from the user. The server stores this feedback in a database and uses it to improve the overall system performance. The collected data is used to improve the AI ​​algorithms.

[0356] Step 7:

[0357] The server uses an optimized delivery mechanism to stream educational resources based on the user's profile information. This allows learners to immediately access optimized resources in their next online session.

[0358] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0359] This invention combines a system that effectively matches educators and learners and provides an online learning environment with an emotion engine that recognizes the user's emotions.

[0360] First, learners input their learning preferences through a terminal and send them to the server. The server stores educator information, such as the educator's area of ​​expertise and teaching methods, in a database and uses a generative AI and an emotion engine to analyze the learner's information in detail. The generative AI analyzes the learner's learning preferences and goals, while the emotion engine also evaluates the learner's emotional data in real time and analyzes their current emotional state.

[0361] Based on the analysis results, the server selects the most suitable educator for the learner and creates a learning plan tailored to the learner's needs and emotions. This plan incorporates the most appropriate teaching materials and methods based on the learner's condition, taking into account the data provided by the emotion engine. For example, if the emotion engine indicates that the learner has a high level of concentration, it can suggest more challenging tasks.

[0362] The learning plan is displayed on the device, and the user reviews its contents. Once the user agrees to the plan, the device schedules the lessons and guides the user to the online learning platform. During the lessons, an emotion engine monitors the user's facial expressions and voice, and provides real-time feedback to the server on changes in their emotions during learning. The server can use this data to instruct educators to adjust their teaching methods.

[0363] After the lesson ends, users input feedback via their devices and send it to the server. This feedback and emotion engine data are stored in a database and used to help plan future lessons and select educators.

[0364] For example, if a user wishes to acquire a specific skill and experiences stress during a lesson, the emotion engine detects this state, and the server adjusts the difficulty level of the skill acquisition or suggests a relaxing teaching method to the educator. In this way, a learning experience best suited to the learner's emotional state can be provided.

[0365] The following describes the processing flow.

[0366] Step 1:

[0367] The device presents the user with a form to enter their learning objectives and desired content. The user enters their name, email address, target skills, etc., and presses the submit button. The device sends this information to the server.

[0368] Step 2:

[0369] The server stores the received user information in a database. Furthermore, it collects educator information, including the educator's area of ​​expertise and teaching experience, and stores it in the database as well.

[0370] Step 3:

[0371] The server uses a generation AI to analyze the user's learning preferences and lists suitable educators. During this process, it analyzes the characteristics of educators necessary for the user to achieve their goals.

[0372] Step 4:

[0373] The device presents the user with suitable educator candidates and prompts them to make a selection. The user chooses an educator and checks the learning schedule.

[0374] Step 5:

[0375] The server activates the emotion engine and monitors the user's emotions in real time. When a user participates in an online lesson, the device transmits facial expressions and voice data to the emotion engine via its camera and microphone.

[0376] Step 6:

[0377] The emotion engine analyzes the user's emotional data and reports their current emotional state to the server. This includes information such as whether the user is focused or stressed.

[0378] Step 7:

[0379] The server dynamically adjusts the learning plan based on emotional state data. If necessary, it sends suggestions to educators to modify the teaching content.

[0380] Step 8:

[0381] After the lesson ends, users enter feedback on the lesson via their device and send it to the server. This feedback will be referenced when customizing the lesson for the next time.

[0382] Step 9:

[0383] The server stores feedback and sentiment data in a database, which is used to improve the user experience and enhance the accuracy of educator selection in the future. This process optimizes the user's learning effectiveness.

[0384] (Example 2)

[0385] 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".

[0386] Online education systems are required to provide education that is tailored to the individual needs and emotional state of learners. However, existing systems only consider the learning content that learners desire, and there is a challenge in suggesting the most suitable educator and learning plan that reflects their emotions and condition.

[0387] 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.

[0388] In this invention, the server includes a storage means for storing educator information, an input means for receiving learner learning preference information, and an emotion evaluation means for analyzing emotion data in real time and evaluating the learner's emotional state. This makes it possible to select the optimal educator, taking into account the learner's learning preference and emotional state, and to provide a learning plan based on that.

[0389] "Educator information" refers to data that includes attributes such as the educator's area of ​​expertise, teaching experience, and teaching style.

[0390] "Memory devices" refer to devices and methods for storing information, such as databases and storage systems.

[0391] "Learning preference information" refers to data that includes the skills and goals that learners want to acquire, as well as their preferred learning style.

[0392] "Input means" refers to interfaces and communication methods for receiving learner information.

[0393] "Generative AI" is an artificial intelligence technology that uses machine learning techniques to analyze data and support decision-making.

[0394] "Evaluation methods" refer to functions that use generative AI models to analyze learner information and select the most suitable educator.

[0395] "Emotional assessment tools" are technologies that analyze emotional data in real time and evaluate the emotional state of learners.

[0396] "Combination means" refers to the methods or processes used to combine the most suitable educators and learners.

[0397] "Means of providing a learning plan" refers to the functions and processes for formulating a learning plan based on the learner's needs and feelings, and for presenting it to the learner.

[0398] "Means of communication" refers to networks and communication technologies that enable communication between learners and educators.

[0399] "Monitoring means" refers to the process of monitoring the learner's status in real time during learning and feeding that information back to the server.

[0400] "Methods for gathering feedback" refer to methods and systems for collecting feedback from learners and storing it in an information base.

[0401] This invention provides a system for online education that offers optimal education based on the individual needs and emotional state of learners.

[0402] First, the user enters their learning preferences through their device. A dedicated user interface is provided for this input, allowing the user to record their learning goals and preferred learning style in detail through voice recognition or text input. This information is then transmitted to a server via the internet.

[0403] The server stores the received learner information in storage. This data includes the educator's area of ​​expertise and teaching experience, and a structured database is used for efficient storage and retrieval of the information. The server also analyzes the learner information using a generative AI model. This model employs natural language processing techniques and implements algorithms that interpret the learner's desired content in detail. Furthermore, it utilizes an emotion engine to analyze emotional information obtained from user signals in real time. This makes it possible to accurately assess the learner's current emotional state.

[0404] For example, if a user sets a learning goal of "I want to acquire English conversation skills," the generating AI model will suggest relevant learning materials and educators. An example of a prompt might be, "Please suggest a plan to improve listening skills using high school level English. The learner currently has high concentration and a positive learning attitude."

[0405] After a learning plan is created, the plan received from the server is displayed on the device. The user reviews and agrees to the plan, and scheduling is completed. During lessons, the user's facial expressions and voice are monitored through the device's built-in camera and microphone, and the data obtained is sent to the server in real time. This feedback information is used by educators to adjust lessons, ensuring that learners receive the best possible educational experience.

[0406] Thus, by combining a generative AI model with emotion evaluation technology, the present invention realizes education that is tailored to the individual needs and emotions of learners, and provides a more flexible and effective online learning environment.

[0407] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0408] Step 1:

[0409] Users input their learning preferences using a device. Specifically, they enter the skills they want to learn, their goals, and their preferred learning style through text or voice input via the user interface. This data is sent to the server in a structured format.

[0410] Step 2:

[0411] The server stores the received learning preference information in its storage device. Simultaneously, it invokes a generative AI model to analyze the received data. Specifically, it provides the generative AI model with prompts and performs natural language processing analysis. This analysis allows it to generate data on educators and learning materials related to the learner's preferences. The analysis results are stored in a temporary database.

[0412] Step 3:

[0413] The server uses an emotion engine to evaluate the learner's emotional state from their input data. Specifically, it analyzes certain keywords and contextual information within the input data to quantify the learner's current emotional state (e.g., concentration level, stress level, etc.). This information is then incorporated as an important factor in creating a learning plan.

[0414] Step 4:

[0415] Based on the analysis results and emotional state, the server selects the most suitable educator from the database and develops a learning plan. Specifically, it processes the aggregated data using a Python script to determine the suggested teaching materials and methods. This plan is then saved back to the database and sent to the terminal.

[0416] Step 5:

[0417] The device displays the learning plan received from the server in the user interface. Once the user reviews and agrees to the learning plan, the device automatically sets the schedule. Specifically, it uses a calendar application to create appointments and set reminders.

[0418] Step 6:

[0419] During lessons, the device monitors the user's state in real time through its camera and microphone. This includes an emotion engine analyzing data obtained from the user's facial expressions and voice, and sending it to a server. This data is then fed back to the educator, allowing them to adjust teaching methods as needed.

[0420] Step 7:

[0421] After the lesson ends, users input feedback via their devices. Specifically, they enter text feedback regarding the quality of the lesson and their level of understanding, and send it to the server. This data is used to improve future learning plans and is stored in a database.

[0422] (Application Example 2)

[0423] 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".

[0424] In online learning environments, there is a need to effectively match learners with educators and flexibly optimize the learning experience in response to the individual state of the learner, especially changes in their emotions. However, current systems find it difficult to analyze emotions in real time and dynamically adjust learning plans and content based on that analysis. As a result, it is difficult to accurately provide learning content that is appropriate for the learner's level of concentration and fatigue.

[0425] 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.

[0426] In this invention, the server includes an information storage means for storing educator information, an emotion analysis means for analyzing learners' emotions in real time and dynamically adjusting learning content, and a content optimization means for optimizing learning content according to the learner's concentration level and fatigue level. This enables the matching of learners with the most suitable educators and the flexible provision of content according to the learners' emotional state.

[0427] "Educator information" refers to attribute information such as the educator's area of ​​expertise and teaching methods.

[0428] "Information storage means" refers to servers and databases used to store information about educators.

[0429] "Learning preference information" refers to information that includes the learning content and goals that the learner desires.

[0430] "Receiving means" refers to an interface for receiving learning preference information sent by learners.

[0431] "Generative AI" refers to artificial intelligence technology that analyzes learning preferences and generates the optimal learning plan.

[0432] "Analysis method" refers to the process of using generative AI to analyze learners' preferences and select the most suitable educator.

[0433] "Matching method" refers to a mechanism for connecting educators and learners selected through analysis.

[0434] "Plan delivery means" refers to a system for presenting generated learning plans to learners.

[0435] "Communication methods" refer to technologies that enable learners and educators to exchange information online.

[0436] "Feedback collection methods" refer to functions for collecting feedback and opinions from learners and storing them in a database.

[0437] "Emotion analysis methods" refer to technologies that analyze a learner's emotions from their facial expressions and voice, and understand their state in real time.

[0438] "Content optimization means" refers to a mechanism for dynamically adjusting the learning content provided according to the learner's emotional state.

[0439] To implement this invention, it is necessary to construct an online learning system centered on a server. First, learners use a terminal to input their learning preferences and send them to the server. This terminal can be a smartphone, computer, or head-mounted display. The server is equipped with information storage means for storing the educators' areas of expertise and teaching methods.

[0440] The received information is analyzed by a generative AI. This generative AI utilizes, for example, OpenAI's GPT model. The generative AI analyzes the learning preference information in detail and selects the most suitable educator. The server further uses emotion analysis tools to grasp the learner's real-time emotional state from their facial expression and voice data. For this purpose, for example, Microsoft Azure's emotion recognition API is used.

[0441] After the most suitable educator is selected, the server connects the learner with the educator using a matching mechanism. Then, using a plan provision mechanism, it creates an individualized learning plan tailored to the learner's current emotional state. This plan is displayed on the learner's device, allowing the learner to review it.

[0442] During lessons, the server monitors changes in learners' emotions through emotion analysis tools. Based on this data, the server utilizes content optimization tools to dynamically adjust learning content according to the learners' concentration levels and fatigue levels. For example, if a learner is highly focused, a more challenging task is provided; if they are feeling fatigued, relaxation content is presented.

[0443] After class, students input feedback via their devices, and the server saves this data to a database using a feedback collection system. This data is then used to plan future lessons.

[0444] As a concrete example, if the emotion analysis system detects fatigue in a learner who wants to study English, the server will suggest a relaxation video to maintain the learner's motivation. Another example of a prompt for the generative AI model is, "Please suggest an English learning plan that takes into account the user's concentration and fatigue level. Please add simple exercises where relaxation is needed."

[0445] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0446] Step 1:

[0447] The user uses a terminal to input information about their learning preferences and sends it to the server. This data includes the areas they want to study and their specific goals. The server receives this information and stores it in a database. This prepares the learning preference information for use in the next process.

[0448] Step 2:

[0449] The server sends the received learning preference information to the generating AI. The generating AI analyzes this information and uses specific prompts to select an educator suitable for the user. The generating AI analyzes the text data to find educators whose expertise and teaching methods match the user's needs. The selection results are output as educator information.

[0450] Step 3:

[0451] The server uses emotion analysis tools to collect real-time facial and voice data from the user. The server sends this data to an emotion recognition API to analyze the user's emotional state. The analysis results in emotional parameters such as the user's current concentration level and stress level.

[0452] Step 4:

[0453] The server generates an optimal learning plan for the learner based on the obtained educator information and emotional parameters. This plan includes challenging content if the learner is highly focused, and relaxation content if fatigue is observed. The generated learning plan is sent to the terminal.

[0454] Step 5:

[0455] Users review their learning plan on their device, and if they agree to the plan, the lesson begins. During the lesson, the server optimizes the content as needed, providing a learning experience tailored to the learner's emotional state. This optimization is performed dynamically based on emotional changes, maximizing the user's learning effectiveness.

[0456] Step 6:

[0457] After the lesson ends, users input feedback about their learning experience from their device and send it to the server. The server collects this feedback information and stores it in a database to help plan future learning sessions. Along with the feedback, sentiment data is also stored and used in future optimization processes.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Third Embodiment]

[0462] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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".

[0474] This invention describes a system that effectively matches educators and learners and provides an individualized learning environment online. The program processing of this system is described below.

[0475] This system begins with learners sending their personal information and learning preferences to a server via a terminal. The server stores the received information in a database, gaining a detailed understanding of the learners' needs.

[0476] Next, the server stores information such as the educators' areas of expertise and teaching history in a database, building profiles of the educators. These profiles are used as foundational data for the generating AI to select the most suitable educators for learners.

[0477] The generating AI analyzes information received from learners and selects appropriate educators based on their learning goals and desired learning content. The server matches the selected educators with the learners and creates individualized learning plans based on this matching. These plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0478] The device will present this learning plan to the learner and enable them to participate in online lessons with the educator. It will utilize communication methods to conduct real-time video conferencing, allowing for active communication between both parties.

[0479] After class, users provide feedback via their devices, and the server collects, analyzes, and stores this information in a database. This data is used to improve the overall system performance.

[0480] For example, if a user wishes to improve their "foreign language conversation skills," the server will select a foreign language education expert and provide a learning plan tailored to the user. Following this plan, the user can participate in online sessions with the foreign language teacher and efficiently improve their skills through practical conversation practice.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The device displays a registration form to the user. The user enters information such as their name, email address, desired subjects to study, and goals. After completion, the device sends this data to the server.

[0484] Step 2:

[0485] The server stores the received user information in a database. During storage, it also generates an initial dataset for analyzing the learner's needs.

[0486] Step 3:

[0487] The terminal presents a registration form to the educator. The educator enters information such as their area of ​​expertise, teaching experience, and available time slots. The terminal then sends this information to the server.

[0488] Step 4:

[0489] The server stores educator information in a database and builds educator profiles. These profiles are used to match educators with learners.

[0490] Step 5:

[0491] The server activates the generation AI and analyzes the user's learning preferences. Based on the analysis results, it selects the most suitable educator candidate for the learner.

[0492] Step 6:

[0493] The server matches selected educators with learners and creates individualized learning plans. These plans include learning objectives, relevant materials, and assessment methods.

[0494] Step 7:

[0495] The device notifies the learner of this learning plan and allows them to review the details. If the learner agrees to the plan, the online lesson schedule is set.

[0496] Step 8:

[0497] When the scheduled class time arrives, users connect to the online platform using their devices. These devices provide features that enable real-time video conversations and chat.

[0498] Step 9:

[0499] After the class ends, users enter feedback on the class via their device. The device then sends the feedback to the server.

[0500] Step 10:

[0501] The server collects the submitted feedback and stores it in a database. This data helps improve future matching accuracy and learning plans.

[0502] (Example 1)

[0503] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0504] Traditional online education systems have struggled to efficiently select educators based on individual learners' needs, making it difficult to maximize educational effectiveness. Furthermore, they have faced challenges in efficiently collecting learner progress and feedback, and dynamically adjusting educational plans. As a result, providing appropriate, individualized education to learners has been difficult.

[0505] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0506] In this invention, the server includes a storage means for storing information, a receiving means for receiving learning preference information, and an analysis means for analyzing the learning preference information using generative artificial intelligence technology and selecting an appropriate educator. This makes it possible to appropriately provide individualized learning plans to learners and achieve optimal matching between educators and learners.

[0507] "Means for storing information" refers to devices or methods for storing information using databases or storage devices.

[0508] A "receiving means for receiving learning request information" refers to a means of delivering learning-related information entered by learners to a server.

[0509] "Generative artificial intelligence technology" refers to machine learning models and artificial intelligence technologies used to analyze received data and make appropriate judgments and choices.

[0510] "Analysis means" refers to a process or apparatus for analyzing learning target information using generating artificial intelligence technology.

[0511] "Means for combining selected educators and learners" refers to a method or device for selecting appropriate educators and connecting them with learners based on analyzed information.

[0512] "Means of providing individualized learning plans" refers to means of designing learning plans tailored to the learner's needs and communicating them to the learner.

[0513] "Communication methods" refer to communication technologies that enable learners and educators to interact online and conduct educational activities in real time.

[0514] "Information gathering means" refers to methods and devices for collecting and storing feedback from learners and data related to lessons.

[0515] This invention uses an information processing system to effectively match learners and educators online and provide an individualized learning environment.

[0516] The server receives learning preference information entered by learners via their devices. This learning preference information includes the learner's personal needs, goals, and preferred learning style. Learners enter this information using a web browser or mobile app and send it to the server. This data is transmitted securely using the HTTPS protocol and stored in a database on the server side.

[0517] Next, the server retrieves information such as the educator's area of ​​expertise, teaching experience, and qualifications, and records this information in a database. At this stage, generative artificial intelligence technology is used to construct a profile of the educator. This profile information becomes the basic data for optimal matching between learners and educators.

[0518] The generative AI model runs on a server, analyzing learners' needs and selecting the most suitable educators. Text processing techniques are used for the analysis. Based on the analysis results, the server effectively matches educators and learners and creates individualized learning plans. These learning plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0519] The device presents this learning plan to the learner. The learner receives instruction from the educator in real time using a video conferencing tool (e.g., common online meeting software). This allows for practical and efficient learning.

[0520] After the lesson ends, users send feedback to the server via their devices. The server collects this feedback and analyzes the data again using a generative AI model. The results of this analysis are used to improve the quality of education.

[0521] For example, if a user wishes to improve their "foreign language conversation skills," the server will select an expert in that field and provide a learning plan suitable for the user. An example of a prompt to the generating AI model would be, "Please suggest a method for matching me with an online educator to improve my foreign language conversation skills." This prompt allows the system to quickly select an educator that meets the user's needs.

[0522] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0523] Step 1:

[0524] Users enter learning information using their device. This includes personal information, learning objectives, and preferred learning style. The entered data is sent from the device to the server. The HTTPS protocol is used for this transmission to ensure security.

[0525] Step 2:

[0526] The server receives learning request information sent from the terminal. The received data is validated to check data accuracy and converted to an appropriate format. Only accurate data is then stored in the database.

[0527] Step 3:

[0528] The server collects information from educators, such as their areas of expertise and teaching experience. This includes information gathering through automated forms and email. The collected information is stored in a database as profile data.

[0529] Step 4:

[0530] The generative AI model runs on a server and analyzes learner needs and educator profiles. The AI ​​applies text analysis techniques to compare learning preferences with educator expertise and select the most suitable educator. Learning preferences and profile data are used as input, and a list of appropriate educators is generated as a selection result.

[0531] Step 5:

[0532] The server creates a customized individual learning plan based on the educator list generated in step 4. This plan includes specific teaching materials, teaching methods, and assessment criteria. The learning plan is dynamically optimized using analysis results from generative artificial intelligence technology.

[0533] Step 6:

[0534] The device receives the learning plan provided by the server and presents it to the user. Simultaneously, links to video conferencing tools and class schedule information are also sent to the user. The device supports real-time communication technology to maintain connectivity.

[0535] Step 7:

[0536] Users participate in online classes based on the information provided. During classes, interaction with educators takes place via the device, and high-quality audio and video data is streamed. This enhances the educational experience.

[0537] Step 8:

[0538] After the lesson ends, users provide feedback using their devices. The feedback is collected in the form of a multifaceted question and sent from the device to the server.

[0539] Step 9:

[0540] The server analyzes the received feedback. A generative AI model uses this data to evaluate and identify areas for improvement in the quality of education and individual adjustments. The analysis results are recorded in a database and used to create future learning plans.

[0541] (Application Example 1)

[0542] 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."

[0543] In online education environments, matching learners with educators who meet their individual needs and efficiently providing suitable educational resources are key challenges. Traditional systems struggle to find the optimal combination of learner and educator, sometimes resulting in decreased learning efficiency. Furthermore, providing educational resources in a way that is easily accessible to learners is not yet fully realized.

[0544] 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.

[0545] In this invention, the server includes information storage means for storing educator information, receiving means for receiving learning preference information from learners, analysis means for analyzing learners' learning preference information using generating AI and selecting the most suitable educator for the learner, matching means for matching the selected educator with the learner, plan provision means for creating a learning plan and providing the plan to the learner, communication means for conducting online education between learners and educators, feedback collection means for collecting feedback from learners and storing it in a database, optimization provision means for optimizing educational resources based on the learner's profile and providing them in streaming format, and operation simplification means for simplifying access to educational resources through an interface on the user terminal. This enables learners to be effectively matched with educators best suited to their individual learning needs and provides easily accessible and personalized educational resources.

[0546] An "information storage device" is a device for storing information about educators in digital format.

[0547] A "receiving mechanism" is a system for receiving learning preference information provided by learners into the server.

[0548] "Analysis methods" refer to the process of using generative AI to analyze in detail the information provided by learners and select the most suitable educator to meet their needs.

[0549] A "matching method" is a system designed to appropriately connect selected educators with learners.

[0550] A "plan delivery method" is a method for presenting a designed learning plan to learners.

[0551] "Communication means" refers to the communication infrastructure that enables learners and educators to receive education online.

[0552] A "feedback collection method" refers to a method for collecting opinions and evaluations from learners after class and storing them in a database.

[0553] An "optimized delivery method" is a system for optimizing and delivering educational resources based on the learner's profile.

[0554] "Means of simplifying operation" are mechanisms that allow learners to easily access educational resources through user-friendly interfaces.

[0555] The system based on this invention is designed to achieve personalized education and is implemented using the following hardware and software. The system mainly consists of a server, terminals, and users.

[0556] The server is equipped with database software as a means of storing information, and stores educator information. A form-based interface is provided to receive learning preference information from users, and this information is stored in the server's database. The analysis method, which uses generative AI, analyzes users' learning preferences and constructs machine learning algorithms to select appropriate educators. This incorporates text mining utilizing natural language processing technology.

[0557] The learning plan is delivered online to learners via a plan delivery system, and the learning based on it is conducted using communication methods. Video streaming services such as the Zoom SDK are integrated, enabling real-time education. The resulting feedback is efficiently collected from users through a feedback collection system.

[0558] Furthermore, the optimized delivery method uses AI-based algorithms to optimize educational resources based on the learner's profile and delivers them in streaming format. This process is supported by database technologies such as Firebase. The simplified operation method allows learners to easily access educational resources through interfaces installed on smartphones and other devices. The user interface is designed for intuitive operation.

[0559] For example, if a learner wishes to improve their second language skills, the server selects an educator tailored to the learner's specific goals and preferences, and presents appropriate materials and a learning plan. In online sessions, the selected educator and learner interact using Zoom or similar platforms, and the feedback is used to adjust the next lesson's approach.

[0560] Example of a prompt:

[0561] "This student is 10 years old and struggles with math. Please recommend a teacher with teaching experience who can teach them gently."

[0562] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0563] Step 1:

[0564] Users input their learning preferences using devices such as smartphones or PCs. This includes information such as the subjects they want to study and their preferred learning style. The entered information is sent to the server via a receiving device and stored in a database.

[0565] Step 2:

[0566] The server activates an analysis tool to analyze the received learning preference information. It incorporates the prompt "Recommend an educator that matches the learner's needs" into the generating AI model. The AI ​​uses natural language processing technology to analyze the input data and select the most suitable educator profile for the learner.

[0567] Step 3:

[0568] Based on the selected educator information, the server uses a matching mechanism to create pairs of learners and educators. This process also takes into account the schedules and compatibility of both parties. The optimal pairing is then performed based on the results of data calculations performed by the generative AI.

[0569] Step 4:

[0570] The server creates a learning plan for the selected educators and provides it to the terminal via a plan delivery system. This plan includes the teaching materials and methods to be used. The learning plan is dynamically adjusted based on real-time data analysis.

[0571] Step 5:

[0572] The device initiates an online session using communication methods. It supports real-time lessons through video conferencing services such as the Zoom SDK. Users (learners) interact with educators and receive education towards set goals.

[0573] Step 6:

[0574] After the lesson ends, the device receives feedback from the user. The server stores this feedback in a database and uses it to improve the overall system performance. The collected data is used to improve the AI ​​algorithms.

[0575] Step 7:

[0576] The server uses an optimized delivery mechanism to stream educational resources based on the user's profile information. This allows learners to immediately access optimized resources in their next online session.

[0577] 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.

[0578] This invention combines a system that effectively matches educators and learners and provides an online learning environment with an emotion engine that recognizes the user's emotions.

[0579] First, learners input their learning preferences through a terminal and send them to the server. The server stores educator information, such as the educator's area of ​​expertise and teaching methods, in a database and uses a generative AI and an emotion engine to analyze the learner's information in detail. The generative AI analyzes the learner's learning preferences and goals, while the emotion engine also evaluates the learner's emotional data in real time and analyzes their current emotional state.

[0580] Based on the analysis results, the server selects the most suitable educator for the learner and creates a learning plan tailored to the learner's needs and emotions. This plan incorporates the most appropriate teaching materials and methods based on the learner's condition, taking into account the data provided by the emotion engine. For example, if the emotion engine indicates that the learner has a high level of concentration, it can suggest more challenging tasks.

[0581] The learning plan is displayed on the device, and the user reviews its contents. Once the user agrees to the plan, the device schedules the lessons and guides the user to the online learning platform. During the lessons, an emotion engine monitors the user's facial expressions and voice, and provides real-time feedback to the server on changes in their emotions during learning. The server can use this data to instruct educators to adjust their teaching methods.

[0582] After the lesson ends, users input feedback via their devices and send it to the server. This feedback and emotion engine data are stored in a database and used to help plan future lessons and select educators.

[0583] For example, if a user wishes to acquire a specific skill and experiences stress during a lesson, the emotion engine detects this state, and the server adjusts the difficulty level of the skill acquisition or suggests a relaxing teaching method to the educator. In this way, a learning experience best suited to the learner's emotional state can be provided.

[0584] The following describes the processing flow.

[0585] Step 1:

[0586] The device presents the user with a form to enter their learning objectives and desired content. The user enters their name, email address, target skills, etc., and presses the submit button. The device sends this information to the server.

[0587] Step 2:

[0588] The server stores the received user information in a database. Furthermore, it collects educator information, including the educator's area of ​​expertise and teaching experience, and stores it in the database as well.

[0589] Step 3:

[0590] The server uses a generation AI to analyze the user's learning preferences and lists suitable educators. During this process, it analyzes the characteristics of educators necessary for the user to achieve their goals.

[0591] Step 4:

[0592] The device presents the user with suitable educator candidates and prompts them to make a selection. The user chooses an educator and checks the learning schedule.

[0593] Step 5:

[0594] The server activates the emotion engine and monitors the user's emotions in real time. When a user participates in an online lesson, the device transmits facial expressions and voice data to the emotion engine via its camera and microphone.

[0595] Step 6:

[0596] The emotion engine analyzes the user's emotional data and reports their current emotional state to the server. This includes information such as whether the user is focused or stressed.

[0597] Step 7:

[0598] The server dynamically adjusts the learning plan based on emotional state data. If necessary, it sends suggestions to educators to modify the teaching content.

[0599] Step 8:

[0600] After the lesson ends, users enter feedback on the lesson via their device and send it to the server. This feedback will be referenced when customizing the lesson for the next time.

[0601] Step 9:

[0602] The server stores feedback and sentiment data in a database, which is used to improve the user experience and enhance the accuracy of educator selection in the future. This process optimizes the user's learning effectiveness.

[0603] (Example 2)

[0604] 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."

[0605] Online education systems are required to provide education that is tailored to the individual needs and emotional state of learners. However, existing systems only consider the learning content that learners desire, and there is a challenge in suggesting the most suitable educator and learning plan that reflects their emotions and condition.

[0606] 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.

[0607] In this invention, the server includes a storage means for storing educator information, an input means for receiving learner learning preference information, and an emotion evaluation means for analyzing emotion data in real time and evaluating the learner's emotional state. This makes it possible to select the optimal educator, taking into account the learner's learning preference and emotional state, and to provide a learning plan based on that.

[0608] "Educator information" refers to data that includes attributes such as the educator's area of ​​expertise, teaching experience, and teaching style.

[0609] "Memory devices" refer to devices and methods for storing information, such as databases and storage systems.

[0610] "Learning preference information" refers to data that includes the skills and goals that learners want to acquire, as well as their preferred learning style.

[0611] "Input means" refers to interfaces and communication methods for receiving learner information.

[0612] "Generative AI" is an artificial intelligence technology that uses machine learning techniques to analyze data and support decision-making.

[0613] "Evaluation methods" refer to functions that use generative AI models to analyze learner information and select the most suitable educator.

[0614] "Emotional assessment tools" are technologies that analyze emotional data in real time and evaluate the emotional state of learners.

[0615] "Combination means" refers to the methods or processes used to combine the most suitable educators and learners.

[0616] "Means of providing a learning plan" refers to the functions and processes for formulating a learning plan based on the learner's needs and feelings, and for presenting it to the learner.

[0617] "Means of communication" refers to networks and communication technologies that enable communication between learners and educators.

[0618] "Monitoring means" refers to the process of monitoring the learner's status in real time during learning and feeding that information back to the server.

[0619] "Methods for gathering feedback" refer to methods and systems for collecting feedback from learners and storing it in an information base.

[0620] This invention provides a system for online education that offers optimal education based on the individual needs and emotional state of learners.

[0621] First, the user enters their learning preferences through their device. A dedicated user interface is provided for this input, allowing the user to record their learning goals and preferred learning style in detail through voice recognition or text input. This information is then transmitted to a server via the internet.

[0622] The server stores the received learner information in storage. This data includes the educator's area of ​​expertise and teaching experience, and a structured database is used for efficient storage and retrieval of the information. The server also analyzes the learner information using a generative AI model. This model employs natural language processing techniques and implements algorithms that interpret the learner's desired content in detail. Furthermore, it utilizes an emotion engine to analyze emotional information obtained from user signals in real time. This makes it possible to accurately assess the learner's current emotional state.

[0623] For example, if a user sets a learning goal of "I want to acquire English conversation skills," the generating AI model will suggest relevant learning materials and educators. An example of a prompt might be, "Please suggest a plan to improve listening skills using high school level English. The learner currently has high concentration and a positive learning attitude."

[0624] After a learning plan is created, the plan received from the server is displayed on the device. The user reviews and agrees to the plan, and scheduling is completed. During lessons, the user's facial expressions and voice are monitored through the device's built-in camera and microphone, and the data obtained is sent to the server in real time. This feedback information is used by educators to adjust lessons, ensuring that learners receive the best possible educational experience.

[0625] Thus, by combining a generative AI model with emotion evaluation technology, the present invention realizes education that is tailored to the individual needs and emotions of learners, and provides a more flexible and effective online learning environment.

[0626] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0627] Step 1:

[0628] Users input their learning preferences using a device. Specifically, they enter the skills they want to learn, their goals, and their preferred learning style through text or voice input via the user interface. This data is sent to the server in a structured format.

[0629] Step 2:

[0630] The server stores the received learning preference information in its storage device. Simultaneously, it invokes a generative AI model to analyze the received data. Specifically, it provides the generative AI model with prompts and performs natural language processing analysis. This analysis allows it to generate data on educators and learning materials related to the learner's preferences. The analysis results are stored in a temporary database.

[0631] Step 3:

[0632] The server uses an emotion engine to evaluate the learner's emotional state from their input data. Specifically, it analyzes certain keywords and contextual information within the input data to quantify the learner's current emotional state (e.g., concentration level, stress level, etc.). This information is then incorporated as an important factor in creating a learning plan.

[0633] Step 4:

[0634] Based on the analysis results and emotional state, the server selects the most suitable educator from the database and develops a learning plan. Specifically, it processes the aggregated data using a Python script to determine the suggested teaching materials and methods. This plan is then saved back to the database and sent to the terminal.

[0635] Step 5:

[0636] The device displays the learning plan received from the server in the user interface. Once the user reviews and agrees to the learning plan, the device automatically sets the schedule. Specifically, it uses a calendar application to create appointments and set reminders.

[0637] Step 6:

[0638] During lessons, the device monitors the user's state in real time through its camera and microphone. This includes an emotion engine analyzing data obtained from the user's facial expressions and voice, and sending it to a server. This data is then fed back to the educator, allowing them to adjust teaching methods as needed.

[0639] Step 7:

[0640] After the lesson ends, users input feedback via their devices. Specifically, they enter text feedback regarding the quality of the lesson and their level of understanding, and send it to the server. This data is used to improve future learning plans and is stored in a database.

[0641] (Application Example 2)

[0642] 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."

[0643] In online learning environments, there is a need to effectively match learners with educators and flexibly optimize the learning experience in response to the individual state of the learner, especially changes in their emotions. However, current systems find it difficult to analyze emotions in real time and dynamically adjust learning plans and content based on that analysis. As a result, it is difficult to accurately provide learning content that is appropriate for the learner's level of concentration and fatigue.

[0644] 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.

[0645] In this invention, the server includes an information storage means for storing educator information, an emotion analysis means for analyzing learners' emotions in real time and dynamically adjusting learning content, and a content optimization means for optimizing learning content according to the learner's concentration level and fatigue level. This enables the matching of learners with the most suitable educators and the flexible provision of content according to the learners' emotional state.

[0646] "Educator information" refers to attribute information such as the educator's area of ​​expertise and teaching methods.

[0647] "Information storage means" refers to servers and databases used to store information about educators.

[0648] "Learning preference information" refers to information that includes the learning content and goals that the learner desires.

[0649] "Receiving means" refers to an interface for receiving learning preference information sent by learners.

[0650] "Generative AI" refers to artificial intelligence technology that analyzes learning preferences and generates the optimal learning plan.

[0651] "Analysis method" refers to the process of using generative AI to analyze learners' preferences and select the most suitable educator.

[0652] "Matching method" refers to a mechanism for connecting educators and learners selected through analysis.

[0653] "Plan delivery means" refers to a system for presenting generated learning plans to learners.

[0654] "Communication methods" refer to technologies that enable learners and educators to exchange information online.

[0655] "Feedback collection methods" refer to functions for collecting feedback and opinions from learners and storing them in a database.

[0656] "Emotion analysis methods" refer to technologies that analyze a learner's emotions from their facial expressions and voice, and understand their state in real time.

[0657] "Content optimization means" refers to a mechanism for dynamically adjusting the learning content provided according to the learner's emotional state.

[0658] To implement this invention, it is necessary to construct an online learning system centered on a server. First, learners use a terminal to input their learning preferences and send them to the server. This terminal can be a smartphone, computer, or head-mounted display. The server is equipped with information storage means for storing the educators' areas of expertise and teaching methods.

[0659] The received information is analyzed by a generative AI. This generative AI utilizes, for example, OpenAI's GPT model. The generative AI analyzes the learning preference information in detail and selects the most suitable educator. The server further uses emotion analysis tools to grasp the learner's real-time emotional state from their facial expression and voice data. For this purpose, for example, Microsoft Azure's emotion recognition API is used.

[0660] After the most suitable educator is selected, the server connects the learner with the educator using a matching mechanism. Then, using a plan provision mechanism, it creates an individualized learning plan tailored to the learner's current emotional state. This plan is displayed on the learner's device, allowing the learner to review it.

[0661] During lessons, the server monitors changes in learners' emotions through emotion analysis tools. Based on this data, the server utilizes content optimization tools to dynamically adjust learning content according to the learners' concentration levels and fatigue levels. For example, if a learner is highly focused, a more challenging task is provided; if they are feeling fatigued, relaxation content is presented.

[0662] After class, students input feedback via their devices, and the server saves this data to a database using a feedback collection system. This data is then used to plan future lessons.

[0663] As a concrete example, if the emotion analysis system detects fatigue in a learner who wants to study English, the server will suggest a relaxation video to maintain the learner's motivation. Another example of a prompt for the generative AI model is, "Please suggest an English learning plan that takes into account the user's concentration and fatigue level. Please add simple exercises where relaxation is needed."

[0664] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0665] Step 1:

[0666] The user uses a terminal to input information about their learning preferences and sends it to the server. This data includes the subject area they wish to study and their specific goals. The server receives this information and stores it in a database. This prepares the learning preference information for use in subsequent processes.

[0667] Step 2:

[0668] The server sends the received learning preference information to the generating AI. The generating AI analyzes this information and uses specific prompts to select an educator suitable for the user. The generating AI analyzes the text data to find educators whose expertise and teaching methods match the user's needs. The selection results are output as educator information.

[0669] Step 3:

[0670] The server uses emotion analysis tools to collect real-time facial and voice data from the user. The server sends this data to an emotion recognition API to analyze the user's emotional state. The analysis results in emotional parameters such as the user's current concentration level and stress level.

[0671] Step 4:

[0672] The server generates an optimal learning plan for the learner based on the obtained educator information and emotional parameters. This plan includes challenging content if the learner is highly focused, and relaxation content if fatigue is observed. The generated learning plan is sent to the terminal.

[0673] Step 5:

[0674] Users review their learning plan on their device, and if they agree to the plan, the lesson begins. During the lesson, the server optimizes the content as needed, providing a learning experience tailored to the learner's emotional state. This optimization is performed dynamically based on emotional changes, maximizing the user's learning effectiveness.

[0675] Step 6:

[0676] After the lesson ends, users input feedback about their learning experience from their device and send it to the server. The server collects this feedback information and stores it in a database to help plan future learning sessions. Along with the feedback, sentiment data is also stored and used in future optimization processes.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] [Fourth Embodiment]

[0681] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0682] 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.

[0683] 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).

[0684] 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.

[0685] 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.

[0686] 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).

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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".

[0694] This invention describes a system that effectively matches educators and learners and provides an individualized learning environment online. The program processing of this system is described below.

[0695] This system begins with learners sending their personal information and learning preferences to a server via a terminal. The server stores the received information in a database, gaining a detailed understanding of the learners' needs.

[0696] Next, the server stores information such as the educators' areas of expertise and teaching history in a database to build educator profiles. These profiles are used as foundational data for the generating AI to select the most suitable educator for each learner.

[0697] The generating AI analyzes information received from learners and selects appropriate educators based on their learning goals and desired learning content. The server matches the selected educators with the learners and creates individualized learning plans based on this matching. These plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0698] The device will present this learning plan to the learner and enable them to participate in online lessons with the educator. It will also utilize communication methods to conduct real-time video conferencing, allowing for active communication between both parties.

[0699] After class, users provide feedback via their devices, and the server collects, analyzes, and stores this information in a database. This data is used to improve the overall system performance.

[0700] For example, if a user wishes to improve their "foreign language conversation skills," the server will select a foreign language education expert and provide a learning plan tailored to the user. Following this plan, the user can participate in online sessions with the foreign language teacher and efficiently improve their skills through practical conversation practice.

[0701] The following describes the processing flow.

[0702] Step 1:

[0703] The device displays a registration form to the user. The user enters information such as their name, email address, desired subjects to study, and goals. After completion, the device sends this data to the server.

[0704] Step 2:

[0705] The server stores the received user information in a database. During storage, it also generates an initial dataset for analyzing the learner's needs.

[0706] Step 3:

[0707] The terminal presents a registration form to the educator. The educator enters information such as their area of ​​expertise, teaching experience, and available time slots. The terminal then sends this information to the server.

[0708] Step 4:

[0709] The server stores educator information in a database and builds educator profiles. These profiles are used to match educators with learners.

[0710] Step 5:

[0711] The server activates the generation AI and analyzes the user's learning preferences. Based on the analysis results, it selects the most suitable educator candidate for the learner.

[0712] Step 6:

[0713] The server matches selected educators with learners and creates individualized learning plans. These plans include learning objectives, relevant materials, and assessment methods.

[0714] Step 7:

[0715] The device notifies the learner of this learning plan and allows them to review the details. If the learner agrees to the plan, the online lesson schedule is set.

[0716] Step 8:

[0717] When the scheduled class time arrives, users connect to the online platform using their devices. These devices provide features that enable real-time video conversations and chat.

[0718] Step 9:

[0719] After the class ends, users enter feedback on the class via their device. The device then sends the feedback to the server.

[0720] Step 10:

[0721] The server collects the submitted feedback and stores it in a database. This data helps improve future matching accuracy and learning plans.

[0722] (Example 1)

[0723] 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".

[0724] Traditional online education systems have struggled to efficiently select educators based on individual learners' needs, making it difficult to maximize educational effectiveness. Furthermore, they have faced challenges in efficiently collecting learner progress and feedback, and dynamically adjusting educational plans. As a result, providing appropriate, individualized education to learners has been difficult.

[0725] 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.

[0726] In this invention, the server includes a storage means for storing information, a receiving means for receiving learning preference information, and an analysis means for analyzing the learning preference information using generative artificial intelligence technology and selecting an appropriate educator. This makes it possible to appropriately provide individualized learning plans to learners and achieve optimal matching between educators and learners.

[0727] "Means for storing information" refers to devices or methods for storing information using databases or storage devices.

[0728] A "receiving means for receiving learning request information" refers to a means of delivering learning-related information entered by learners to a server.

[0729] "Generative artificial intelligence technology" refers to machine learning models and artificial intelligence technologies used to analyze received data and make appropriate judgments and choices.

[0730] "Analysis means" refers to a process or apparatus for analyzing learning target information using generating artificial intelligence technology.

[0731] "Means for combining selected educators and learners" refers to a method or device for selecting appropriate educators and connecting them with learners based on analyzed information.

[0732] "A means of creating and providing individualized learning plans to learners" refers to a means of designing learning plans tailored to the learners' needs and communicating them to the learners.

[0733] "Communication methods" refer to communication technologies that enable learners and educators to interact online and conduct educational activities in real time.

[0734] "Information gathering means" refers to methods and devices for collecting and storing feedback from learners and data related to lessons.

[0735] This invention uses an information processing system to effectively match learners and educators online and provide an individualized learning environment.

[0736] The server receives learning preference information entered by learners via their devices. This learning preference information includes the learner's personal needs, goals, and preferred learning style. Learners enter this information using a web browser or mobile app and send it to the server. This data is transmitted securely using the HTTPS protocol and stored in a database on the server side.

[0737] Next, the server retrieves information such as the educator's area of ​​expertise, teaching experience, and qualifications, and records this information in a database. At this stage, generative artificial intelligence technology is used to construct a profile of the educator. This profile information becomes the basic data for optimal matching between learners and educators.

[0738] The generative AI model runs on a server, analyzing learners' needs and selecting the most suitable educators. Text processing techniques are used for the analysis. Based on the analysis results, the server effectively matches educators and learners and creates individualized learning plans. These learning plans include specific teaching materials, teaching methods, and methods for evaluating learning progress.

[0739] The device presents this learning plan to the learner. The learner receives instruction from the educator in real time using a video conferencing tool (e.g., common online meeting software). This allows for practical and efficient learning.

[0740] After the lesson ends, users send feedback to the server via their devices. The server collects this feedback and analyzes the data again using a generative AI model. The results of this analysis are used to improve the quality of education.

[0741] For example, if a user wishes to improve their "foreign language conversation skills," the server will select an expert in that field and provide a learning plan suitable for the user. An example of a prompt to the generating AI model would be, "Please suggest a method for matching me with an online educator to improve my foreign language conversation skills." This prompt allows the system to quickly select an educator that meets the user's needs.

[0742] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0743] Step 1:

[0744] Users enter learning information using their device. This includes personal information, learning objectives, and preferred learning style. The entered data is sent from the device to the server. The HTTPS protocol is used for this transmission to ensure security.

[0745] Step 2:

[0746] The server receives learning request information sent from the terminal. The received data is validated to check data accuracy and converted to an appropriate format. Only accurate data is then stored in the database.

[0747] Step 3:

[0748] The server collects information from educators, such as their areas of expertise and teaching experience. This includes information gathering through automated forms and email. The collected information is stored in a database as profile data.

[0749] Step 4:

[0750] The generative AI model runs on a server and analyzes learner needs and educator profiles. The AI ​​applies text analysis techniques to compare learning preferences with educator expertise and select the most suitable educator. Learning preferences and profile data are used as input, and a list of appropriate educators is generated as a selection result.

[0751] Step 5:

[0752] The server creates a customized individual learning plan based on the educator list generated in step 4. This plan includes specific teaching materials, teaching methods, and evaluation criteria. The learning plan is dynamically optimized using analysis results from generative artificial intelligence technology.

[0753] Step 6:

[0754] The device receives the learning plan provided by the server and presents it to the user. Simultaneously, links to video conferencing tools and class schedule information are also sent to the user. The device supports real-time communication technology to maintain connectivity.

[0755] Step 7:

[0756] Users participate in online classes based on the information provided. During classes, interaction with educators takes place via the device, and high-quality audio and video data is streamed. This enhances the educational experience.

[0757] Step 8:

[0758] After the lesson ends, users provide feedback using their devices. The feedback is collected in the form of a multifaceted question and sent from the device to the server.

[0759] Step 9:

[0760] The server analyzes the received feedback. A generative AI model uses this data to evaluate and identify areas for improvement in the quality of education and individual adjustments. The analysis results are recorded in a database and used to create future learning plans.

[0761] (Application Example 1)

[0762] 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".

[0763] In online education environments, matching learners with educators who meet their individual needs and efficiently providing suitable educational resources are key challenges. Traditional systems struggle to find the optimal combination of learner and educator, sometimes resulting in decreased learning efficiency. Furthermore, providing educational resources in a way that is easily accessible to learners is not yet fully realized.

[0764] 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.

[0765] In this invention, the server includes information storage means for storing educator information, receiving means for receiving learning preference information from learners, analysis means for analyzing learners' learning preference information using generating AI and selecting the most suitable educator for the learner, matching means for matching the selected educator with the learner, plan provision means for creating a learning plan and providing the plan to the learner, communication means for conducting online education between learners and educators, feedback collection means for collecting feedback from learners and storing it in a database, optimization provision means for optimizing educational resources based on the learner's profile and providing them in streaming format, and operation simplification means for simplifying access to educational resources through an interface on the user terminal. This enables learners to be effectively matched with educators best suited to their individual learning needs and provides easily accessible and personalized educational resources.

[0766] An "information storage device" is a device for storing information about educators in digital format.

[0767] A "receiving mechanism" is a system for receiving learning preference information provided by learners into the server.

[0768] "Analysis methods" refer to the process of using generative AI to analyze in detail the information provided by learners and select the most suitable educator to meet their needs.

[0769] A "matching method" is a system designed to appropriately connect selected educators with learners.

[0770] A "plan delivery method" is a method for presenting a designed learning plan to learners.

[0771] "Communication means" refers to the communication infrastructure that enables learners and educators to receive education online.

[0772] A "feedback collection method" refers to a method for collecting opinions and evaluations from learners after class and storing them in a database.

[0773] An "optimized delivery method" is a system for optimizing and delivering educational resources based on the learner's profile.

[0774] "Means of simplifying operation" are mechanisms that allow learners to easily access educational resources through user-friendly interfaces.

[0775] The system based on this invention is designed to achieve personalized education and is implemented using the following hardware and software. The system mainly consists of a server, terminals, and users.

[0776] The server is equipped with database software as a means of storing information, and stores educator information. A form-based interface is provided to receive learning preference information from users, and this information is stored in the server's database. The analysis method, which uses generative AI, analyzes users' learning preferences and constructs machine learning algorithms to select appropriate educators. This incorporates text mining utilizing natural language processing technology.

[0777] The learning plan is delivered online to learners via a plan delivery system, and the learning based on it is conducted using communication methods. Video streaming services such as the Zoom SDK are integrated, enabling real-time education. The resulting feedback is efficiently collected from users through a feedback collection system.

[0778] Furthermore, the optimized delivery method uses AI-based algorithms to optimize educational resources based on the learner's profile and delivers them in streaming format. This process is supported by database technologies such as Firebase. The simplified operation method allows learners to easily access educational resources through interfaces installed on smartphones and other devices. The user interface is designed for intuitive operation.

[0779] For example, if a learner wishes to improve their second language skills, the server selects an educator tailored to the learner's specific goals and preferences, and presents appropriate materials and a learning plan. In online sessions, the selected educator and learner interact using Zoom or similar platforms, and the feedback is used to adjust the next lesson's approach.

[0780] Example of a prompt:

[0781] "This student is 10 years old and struggles with math. Please recommend a teacher with teaching experience who can teach them gently."

[0782] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0783] Step 1:

[0784] Users input their learning preferences using devices such as smartphones or PCs. This includes information such as the subjects they want to study and their preferred learning style. The entered information is sent to the server via a receiving device and stored in a database.

[0785] Step 2:

[0786] The server activates an analysis tool to analyze the received learning preference information. It incorporates the prompt "Recommend an educator that matches the learner's needs" into the generating AI model. The AI ​​uses natural language processing technology to analyze the input data and select the most suitable educator profile for the learner.

[0787] Step 3:

[0788] Based on the selected educator information, the server uses a matching mechanism to create pairs of learners and educators. This process also takes into account the schedules and compatibility of both parties. The optimal pairing is then performed based on the results of data calculations performed by the generative AI.

[0789] Step 4:

[0790] The server creates a learning plan for the selected educators and provides it to the terminal via a plan delivery system. This plan includes the teaching materials and methods to be used. The learning plan is dynamically adjusted based on real-time data analysis.

[0791] Step 5:

[0792] The device initiates an online session using communication methods. It supports real-time lessons through video conferencing services such as the Zoom SDK. Users (learners) interact with educators and receive instruction towards set goals.

[0793] Step 6:

[0794] After the lesson ends, the device receives feedback from the user. The server stores this feedback in a database and uses it to improve the overall system performance. The collected data is used to improve the AI ​​algorithms.

[0795] Step 7:

[0796] The server uses an optimized delivery mechanism to stream educational resources based on the user's profile information. This allows learners to immediately access optimized resources in their next online session.

[0797] 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.

[0798] This invention combines a system that effectively matches educators and learners and provides an online learning environment with an emotion engine that recognizes the user's emotions.

[0799] First, learners input their learning preferences through a terminal and send them to the server. The server stores educator information, such as the educator's area of ​​expertise and teaching methods, in a database and uses a generative AI and an emotion engine to analyze the learner's information in detail. The generative AI analyzes the learner's learning preferences and goals, while the emotion engine also evaluates the learner's emotional data in real time and analyzes their current emotional state.

[0800] Based on the analysis results, the server selects the most suitable educator for the learner and creates a learning plan tailored to the learner's needs and emotions. This plan incorporates the most appropriate teaching materials and methods based on the learner's condition, taking into account the data provided by the emotion engine. For example, if the emotion engine indicates that the learner has a high level of concentration, it can suggest more challenging tasks.

[0801] The learning plan is displayed on the device, and the user reviews its contents. Once the user agrees to the plan, the device schedules the lessons and guides the user to the online learning platform. During the lessons, an emotion engine monitors the user's facial expressions and voice, and provides real-time feedback to the server on changes in their emotions during learning. The server can use this data to instruct educators to adjust their teaching methods.

[0802] After the lesson ends, users input feedback via their devices and send it to the server. This feedback and emotion engine data are stored in a database and used to plan future lessons and select educators.

[0803] For example, if a user wishes to acquire a specific skill and experiences stress during a lesson, the emotion engine detects this state, and the server adjusts the difficulty level of the skill acquisition or suggests a relaxing teaching method to the educator. In this way, a learning experience best suited to the learner's emotional state can be provided.

[0804] The following describes the processing flow.

[0805] Step 1:

[0806] The device presents the user with a form to enter their learning objectives and desired content. The user enters their name, email address, target skills, etc., and presses the submit button. The device sends this information to the server.

[0807] Step 2:

[0808] The server stores the received user information in a database. Furthermore, it collects educator information, including the educator's area of ​​expertise and teaching experience, and stores it in the database as well.

[0809] Step 3:

[0810] The server uses a generation AI to analyze the user's learning preferences and lists suitable educators. During this process, it analyzes the characteristics of educators necessary for the user to achieve their goals.

[0811] Step 4:

[0812] The device presents the user with suitable educator candidates and prompts them to make a selection. The user chooses an educator and checks the learning schedule.

[0813] Step 5:

[0814] The server activates the emotion engine and monitors the user's emotions in real time. When a user participates in an online lesson, the device transmits facial expressions and voice data to the emotion engine via its camera and microphone.

[0815] Step 6:

[0816] The emotion engine analyzes the user's emotional data and reports their current emotional state to the server. This includes information such as whether the user is focused or stressed.

[0817] Step 7:

[0818] The server dynamically adjusts the learning plan based on emotional state data. If necessary, it sends suggestions to educators to modify the teaching content.

[0819] Step 8:

[0820] After the lesson ends, users enter feedback on the lesson via their device and send it to the server. This feedback will be referenced when customizing the lesson for the next time.

[0821] Step 9:

[0822] The server stores feedback and sentiment data in a database, which is used to improve the user experience and enhance the accuracy of educator selection in the future. This process optimizes the user's learning effectiveness.

[0823] (Example 2)

[0824] 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".

[0825] Online education systems are required to provide education that is tailored to the individual needs and emotional state of learners. However, existing systems only consider the learning content that learners desire, and there is a challenge in suggesting the most suitable educator and learning plan that reflects their emotions and condition.

[0826] 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.

[0827] In this invention, the server includes a storage means for storing educator information, an input means for receiving learner learning preference information, and an emotion evaluation means for analyzing emotion data in real time and evaluating the learner's emotional state. This makes it possible to select the optimal educator, taking into account the learner's learning preference and emotional state, and to provide a learning plan based on that.

[0828] "Educator information" refers to data that includes attributes such as the educator's area of ​​expertise, teaching experience, and teaching style.

[0829] "Memory devices" refer to devices and methods for storing information, such as databases and storage systems.

[0830] "Learning preference information" refers to data that includes the skills and goals that learners want to acquire, as well as their preferred learning style.

[0831] "Input means" refers to interfaces and communication methods for receiving learner information.

[0832] "Generative AI" is an artificial intelligence technology that uses machine learning techniques to analyze data and support decision-making.

[0833] "Evaluation methods" refer to functions that use generative AI models to analyze learner information and select the most suitable educator.

[0834] "Emotional assessment tools" are technologies that analyze emotional data in real time and evaluate the emotional state of learners.

[0835] "Combination means" refers to the methods or processes used to combine the most suitable educators and learners.

[0836] "Means of providing a learning plan" refers to the functions and processes for formulating a learning plan based on the learner's needs and feelings, and for presenting it to the learner.

[0837] "Means of communication" refers to networks and communication technologies that enable communication between learners and educators.

[0838] "Monitoring means" refers to the process of monitoring the learner's status in real time during learning and feeding that information back to the server.

[0839] "Methods for gathering feedback" refer to methods and systems for collecting feedback from learners and storing it in an information base.

[0840] This invention provides a system for online education that offers optimal education based on the individual needs and emotional state of learners.

[0841] First, the user enters their learning preferences through their device. A dedicated user interface is provided for this input, allowing the user to record their learning goals and preferred learning style in detail through voice recognition or text input. This information is then transmitted to a server via the internet.

[0842] The server stores the received learner information in storage. This data includes the educator's area of ​​expertise and teaching experience, and a structured database is used for efficient storage and retrieval of the information. The server also analyzes the learner information using a generative AI model. This model employs natural language processing techniques and implements algorithms that interpret the learner's desired content in detail. Furthermore, it utilizes an emotion engine to analyze emotional information obtained from user signals in real time. This makes it possible to accurately assess the learner's current emotional state.

[0843] For example, if a user sets a learning goal of "I want to acquire English conversation skills," the generating AI model will suggest relevant learning materials and educators. An example of a prompt might be, "Please suggest a plan to improve listening skills using high school level English. The learner currently has high concentration and a positive learning attitude."

[0844] After a learning plan is created, the plan received from the server is displayed on the device. The user reviews and agrees to the plan, and scheduling is completed. During lessons, the user's facial expressions and voice are monitored through the device's built-in camera and microphone, and the data obtained is sent to the server in real time. This feedback information is used by educators to adjust lessons, ensuring that learners receive the best possible educational experience.

[0845] Thus, by combining a generative AI model with emotion evaluation technology, the present invention realizes education that is tailored to the individual needs and emotions of learners, and provides a more flexible and effective online learning environment.

[0846] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0847] Step 1:

[0848] Users input their learning preferences using a device. Specifically, they enter the skills they want to learn, their goals, and their preferred learning style through text or voice input via the user interface. This data is sent to the server in a structured format.

[0849] Step 2:

[0850] The server stores the received learning preference information in its storage device. Simultaneously, it invokes a generative AI model to analyze the received data. Specifically, it provides the generative AI model with prompts and performs natural language processing analysis. This analysis allows it to generate data on educators and learning materials related to the learner's preferences. The analysis results are stored in a temporary database.

[0851] Step 3:

[0852] The server uses an emotion engine to evaluate the learner's emotional state from their input data. Specifically, it analyzes certain keywords and contextual information within the input data to quantify the learner's current emotional state (e.g., concentration level, stress level, etc.). This information is then incorporated as an important factor in creating a learning plan.

[0853] Step 4:

[0854] Based on the analysis results and emotional state, the server selects the most suitable educator from the database and develops a learning plan. Specifically, it processes the aggregated data using a Python script to determine the suggested teaching materials and methods. This plan is then saved back to the database and sent to the terminal.

[0855] Step 5:

[0856] The device displays the learning plan received from the server in the user interface. Once the user reviews and agrees to the learning plan, the device automatically sets the schedule. Specifically, it uses a calendar application to create appointments and set reminders.

[0857] Step 6:

[0858] During lessons, the device monitors the user's state in real time through its camera and microphone. This includes an emotion engine analyzing data obtained from the user's facial expressions and voice, and sending it to a server. This data is then fed back to the educator, allowing them to adjust teaching methods as needed.

[0859] Step 7:

[0860] After the lesson ends, users input feedback via their devices. Specifically, they enter text feedback regarding the quality of the lesson and their level of understanding, and send it to the server. This data is used to improve future learning plans and is stored in a database.

[0861] (Application Example 2)

[0862] 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".

[0863] In online learning environments, there is a need to effectively match learners with educators and flexibly optimize the learning experience in response to the individual state of the learner, especially changes in their emotions. However, current systems find it difficult to analyze emotions in real time and dynamically adjust learning plans and content based on that analysis. As a result, it is difficult to accurately provide learning content that is appropriate for the learner's level of concentration and fatigue.

[0864] 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.

[0865] In this invention, the server includes an information storage means for storing educator information, an emotion analysis means for analyzing learners' emotions in real time and dynamically adjusting learning content, and a content optimization means for optimizing learning content according to the learner's concentration level and fatigue level. This enables the matching of learners with the most suitable educators and the flexible provision of content according to the learners' emotional state.

[0866] "Educator information" refers to attribute information such as the educator's area of ​​expertise and teaching methods.

[0867] "Information storage means" refers to servers and databases used to store information about educators.

[0868] "Learning preference information" refers to information that includes the learning content and goals that the learner desires.

[0869] "Receiving means" refers to an interface for receiving learning preference information sent by learners.

[0870] "Generative AI" refers to artificial intelligence technology that analyzes learning preferences and generates the optimal learning plan.

[0871] "Analysis method" refers to the process of using generative AI to analyze learners' preferences and select the most suitable educator.

[0872] "Matching method" refers to a mechanism for connecting educators and learners selected through analysis.

[0873] "Plan delivery means" refers to a system for presenting generated learning plans to learners.

[0874] "Communication methods" refer to technologies that enable learners and educators to exchange information online.

[0875] "Feedback collection methods" refer to functions for collecting feedback and opinions from learners and storing them in a database.

[0876] "Emotion analysis methods" refer to technologies that analyze a learner's emotions from their facial expressions and voice, and understand their state in real time.

[0877] "Content optimization means" refers to a mechanism for dynamically adjusting the learning content provided according to the learner's emotional state.

[0878] To implement this invention, it is necessary to construct an online learning system centered on a server. First, learners use a terminal to input their learning preferences and send them to the server. This terminal can be a smartphone, computer, or head-mounted display. The server is equipped with information storage means for storing the educators' areas of expertise and teaching methods.

[0879] The received information is analyzed by a generative AI. This generative AI utilizes, for example, OpenAI's GPT model. The generative AI analyzes the learning preference information in detail and selects the most suitable educator. The server further uses emotion analysis tools to grasp the learner's real-time emotional state from their facial expression and voice data. For this purpose, for example, Microsoft Azure's emotion recognition API is used.

[0880] After the most suitable educator is selected, the server connects learners with educators using a matching mechanism. Then, using a plan provision mechanism, it creates an individualized learning plan tailored to the learner's current emotional state. This plan is displayed on the learner's device, allowing them to review it.

[0881] During lessons, the server monitors changes in learners' emotions through emotion analysis tools. Based on this data, the server utilizes content optimization tools to dynamically adjust learning content according to the learners' concentration levels and fatigue levels. For example, if a learner is highly focused, a more challenging task is provided; if they are feeling fatigued, relaxation content is presented.

[0882] After class, students input feedback via their devices, and the server saves this data to a database using a feedback collection system. This data is then used to plan future lessons.

[0883] As a concrete example, if the emotion analysis system detects fatigue in a learner who wants to study English, the server will suggest a relaxation video to maintain the learner's motivation. Another example of a prompt for the generative AI model is, "Please suggest an English learning plan that takes into account the user's concentration and fatigue level. Please add simple exercises where relaxation is needed."

[0884] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0885] Step 1:

[0886] The user uses a terminal to input information about their learning preferences and sends it to the server. This data includes the subject area they wish to study and their specific goals. The server receives this information and stores it in a database. This prepares the learning preference information for use in subsequent processes.

[0887] Step 2:

[0888] The server sends the received learning preference information to the generating AI. The generating AI analyzes this information and uses specific prompts to select an educator suitable for the user. The generating AI analyzes the text data to find educators whose expertise and teaching methods match the user's needs. The selection results are output as educator information.

[0889] Step 3:

[0890] The server uses emotion analysis tools to collect real-time facial and voice data from the user. The server sends this data to an emotion recognition API to analyze the user's emotional state. The analysis results in emotional parameters such as the user's current concentration level and stress level.

[0891] Step 4:

[0892] The server generates an optimal learning plan for the learner based on the obtained educator information and emotional parameters. This plan includes challenging content if the learner is highly focused, and relaxation content if fatigue is observed. The generated learning plan is sent to the terminal.

[0893] Step 5:

[0894] Users review their learning plan on their device, and if they agree to the plan, the lesson begins. During the lesson, the server optimizes the content as needed, providing a learning experience tailored to the learner's emotional state. This optimization is performed dynamically based on emotional changes, maximizing the user's learning effectiveness.

[0895] Step 6:

[0896] After the lesson ends, users input feedback about their learning experience from their device and send it to the server. The server collects this feedback information and stores it in a database to help plan future learning sessions. Along with the feedback, sentiment data is also stored and used in future optimization processes.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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."

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] The following is further disclosed regarding the embodiments described above.

[0919] (Claim 1)

[0920] Information storage means for storing educator information,

[0921] A means of receiving learning request information from learners,

[0922] An analytical method that uses generative AI to analyze learners' learning preferences and selects the most suitable educator for each learner,

[0923] A matching method for matching selected educators with learners,

[0924] A means of providing a learning plan, which involves creating a learning plan and providing that plan to the learner.

[0925] Communication methods for conducting online education between learners and educators,

[0926] A feedback collection method that collects feedback from learners and stores it in a database,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, wherein the analysis means uses text mining technology to analyze the information to be learned in detail.

[0930] (Claim 3)

[0931] The system according to claim 1, wherein the plan provision means has a function to dynamically adjust individual learning plans in real time.

[0932] "Example 1"

[0933] (Claim 1)

[0934] A storage means for storing information,

[0935] A means of receiving learning request information,

[0936] An analytical means that uses generative artificial intelligence technology to analyze learning preference information and select an appropriate educator,

[0937] A means of combining selected educators and learners,

[0938] A means of creating individual learning plans and providing those plans to learners,

[0939] Communication means for conducting educational activities between learners and educators via communication,

[0940] Information gathering means for collecting information from learners and storing it in a memory device,

[0941] A system that includes this.

[0942] (Claim 2)

[0943] The system according to claim 1, wherein the analysis means uses text processing technology to analyze the learning target information in detail.

[0944] (Claim 3)

[0945] The system according to claim 1, wherein the plan provision means has a function to instantly and dynamically adjust the learning plan.

[0946] "Application Example 1"

[0947] (Claim 1)

[0948] Information storage means for storing educator information,

[0949] A means of receiving learning request information from learners,

[0950] An analytical method that uses generative AI to analyze learners' learning preferences and selects the most suitable educator for each learner,

[0951] A matching method for matching selected educators with learners,

[0952] A means of providing a learning plan, which involves creating a learning plan and providing that plan to the learner.

[0953] Communication methods for conducting online education between learners and educators,

[0954] A feedback collection method that collects feedback from learners and stores it in a database,

[0955] An optimized delivery method that optimizes educational resources based on learner profiles and provides them in streaming format,

[0956] A means of simplifying operation that simplifies access to educational resources through an interface on the user's terminal,

[0957] A system that includes this.

[0958] (Claim 2)

[0959] The system according to claim 1, wherein the analysis means uses text mining technology to analyze the information to be learned in detail.

[0960] (Claim 3)

[0961] The system according to claim 1, wherein the plan provision means has a function to dynamically adjust individual learning plans in real time.

[0962] "Example 2 of combining an emotion engine"

[0963] (Claim 1)

[0964] A memory means for storing educator information,

[0965] An input means for receiving learning preference information from learners,

[0966] An evaluation method that uses generative AI to analyze learners' learning preferences and select the most suitable educator,

[0967] An emotion assessment method that analyzes emotion data in real time and evaluates the emotional state of learners,

[0968] A means of combining selected educators and learners,

[0969] A means of providing a learning plan that develops a learning plan based on the learner's needs and feelings, and presents that plan to the learner.

[0970] A means of communication for conducting education electronically between learners and educators,

[0971] A monitoring system that uses emotion assessment tools to monitor the state of learners during class and provides real-time feedback to a server,

[0972] A means of collecting opinions from learners and storing them in an information base,

[0973] A system that includes this.

[0974] (Claim 2)

[0975] The system according to claim 1, wherein the evaluation means uses natural language processing to analyze the learning target information in detail.

[0976] (Claim 3)

[0977] The system according to claim 1, wherein the plan provision means has a function to dynamically adjust the individual learning plan based on the learner's emotional state.

[0978] "Application example 2 when combining with an emotional engine"

[0979] (Claim 1)

[0980] Information storage means for storing educator information,

[0981] A means of receiving learning request information from learners,

[0982] An analytical method that uses generative AI to analyze learners' learning preferences and selects the most suitable educator for each learner,

[0983] A matching method for matching selected educators with learners,

[0984] A means of providing a learning plan, which involves creating a learning plan and providing that plan to the learner.

[0985] Communication methods for conducting online education between learners and educators,

[0986] A feedback collection method that collects feedback from learners and stores it in a database,

[0987] A sentiment analysis tool that analyzes learners' emotions in real time and dynamically adjusts the learning content,

[0988] A content optimization method that optimizes learning content according to the learner's concentration and fatigue level,

[0989] A system that includes this.

[0990] (Claim 2)

[0991] The system according to claim 1, wherein the analysis means uses text mining technology to analyze learning preference information in detail, and the emotion analysis means uses facial expression and voice data.

[0992] (Claim 3)

[0993] The system according to claim 1, wherein the plan provision means dynamically adjusts individual learning plans in real time, and the content optimization means has the function of flexibly providing content according to the learner's emotional state. [Explanation of Symbols]

[0994] 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. Information storage means for storing educator information, A means of receiving learning request information from learners, An analytical method that uses generative AI to analyze learners' learning preferences and selects the most suitable educator for each learner, A matching method for matching selected educators with learners, A means of providing a learning plan, which involves creating a learning plan and providing that plan to the learner. Communication methods for conducting online education between learners and educators, A feedback collection method that collects feedback from learners and stores it in a database, A system that includes this.

2. The system according to claim 1, wherein the analysis means uses text mining technology to analyze the learning target information in detail.

3. The system according to claim 1, wherein the plan provision means has a function to dynamically adjust individual learning plans in real time.

Images