system

Abstract

Provide a system. 【Solution means】 Means for receiving learning evaluation data input by a learner; Means for analyzing the learning evaluation data to identify the learning tendency of the learner; Means for generating learning resources based on the identified learning tendency of the learner; Means for providing the learning resources to the learner; Means for controlling an input device through which a user acquires learning content via a visual device; Means for analyzing data acquired from the visual device to generate additional information in real time; Means for displaying the additional information in a format according to the user's level of understanding; A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional learning systems, it has been difficult to automatically provide optimal learning resources according to the characteristics of individual learners, and in many cases, only uniform teaching materials have been provided. For this reason, learners have been unable to conduct efficient learning according to their own level of understanding and learning progress, and there has been a problem that it takes a long time to acquire sufficient knowledge. In addition, it has been difficult to objectively evaluate their own progress after learning, and as a result, it has often hindered the review of learning.

Means for Solving the Problems

[0005] To solve these problems, the present invention provides a system that identifies learning tendencies based on learning evaluation data entered by learners and generates optimized learning resources based on those tendencies. Specifically, it analyzes learning evaluation data sent by learners to identify learning tendencies such as the learners' strengths and weaknesses. Next, based on these identified learning tendencies, it generates learning resources with the optimal format and content and provides these resources to learners, thereby enabling personalized and effective learning. Furthermore, it generates a test to measure comprehension after applying the learning resources, allowing learners to evaluate their own learning progress. As a result, learners can learn efficiently at their own pace, reducing wasted time.

[0006] "Learning assessment data" refers to data used to evaluate the learning outcomes achieved by learners, and includes information such as test results and self-assessments.

[0007] "Learning tendencies" refer to characteristic patterns in a learner's strengths and weaknesses, or their learning methods.

[0008] "Learning resources" refer to educational materials and content provided to support learners' learning, and include formats such as text, video, and audio.

[0009] A "system" is a collection of hardware and software that work together to achieve a specific purpose.

[0010] "Analysis" is the process of examining data in detail and extracting specific information, and in this context, it is used to identify learning trends.

[0011] "Identifying" is the process of clarifying details based on information and distinguishing the subject from others.

[0012] "To generate" refers to the process of creating something new for a specific purpose. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

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

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

[0016] In the following embodiments, a tagged processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a tagged 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.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] In order to implement the present invention, a system is needed that collects learner input information and provides an individualized learning experience based on that information. The operation of this system will be described in detail below.

[0035] 1. User Roles

[0036] Users use a device to manage their learning progress. After completing specific assignments or tests, users enter their test results into the device and send them to the system. This input information becomes part of the formation of learning evaluation data.

[0037] 2. The role of the terminal

[0038] The terminal receives the test results entered by the user as image data or text data. After receiving, this data is interpreted and then transferred to the server. The terminal also provides the user with an interface to display learning resources and test results.

[0039] 3. Server Role

[0040] The server receives learning assessment data sent from the terminal. This data is analyzed by the server and used to identify learning trends. The server utilizes machine learning algorithms and databases to analyze learning trends based on the user's past learning history and current test scores.

[0041] Next, the server generates learning resources optimized for the user based on these analysis results. These resources can support diverse learning formats and include text, videos, audio, and more. This allows users to efficiently acquire knowledge in a way that suits their own learning style.

[0042] Furthermore, the server creates comprehension tests that allow users to assess their own understanding. These tests reflect the user's current learning progress and understanding in specific areas, providing feedback to help them effectively advance their learning plan.

[0043] Specific example

[0044] As a concrete example, consider the case of a student studying mathematics. The user takes a midterm exam for their mathematics course, takes a picture of the results with their smartphone, and uploads it to their device. The device sends this image to a server, which then begins analyzing the test.

[0045] The server uses OCR technology to extract usable data from images and determines whether the answers are correct or incorrect. It also analyzes which problems correspond to which mathematical topics and identifies the user's learning tendencies. In this case, it might be found that the user makes particularly many mistakes on differential calculus problems.

[0046] Based on this information, the server generates supplementary learning content specifically focused on differentiation, supporting user improvement through video lectures and interactive practice problems. It also provides comprehension tests focused on contributions related to differentiation, measuring learning effectiveness within the next test cycle.

[0047] In this way, the system provides personalized support tailored to the user's learning needs, thereby enabling an efficient learning experience.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] After the user completes the learning process, they enter their test results into the device. The user can either take a photo of the test paper or enter the test results directly using the keyboard.

[0051] Step 2:

[0052] The terminal receives the input test result data, formats the data, and prepares it for transmission to the server. In the case of images, it optimizes the resolution as needed.

[0053] Step 3:

[0054] The device sends the formatted learning evaluation data to the server via the internet. A secure data transfer protocol is used to ensure data security.

[0055] Step 4:

[0056] The server receives the transmitted learning evaluation data and uses OCR technology to extract text data from the images. If it is text data, it verifies the integrity of the content.

[0057] Step 5:

[0058] The server analyzes the extracted information and calculates the user's score. Furthermore, it identifies the learning area to which each question belongs and identifies the user's strengths and weaknesses.

[0059] Step 6:

[0060] The server retrieves past learning history from the database and analyzes overall learning trends. This includes using machine learning models to identify long-term learning patterns.

[0061] Step 7:

[0062] Based on the analysis results, the server generates learning resources optimized for the user's learning needs. The content and format can vary widely, including text, diagrams, audio files, and video presentations.

[0063] Step 8:

[0064] The server sends the generated learning resources to the terminal. In addition, it automatically generates and provides comprehension tests related to the learning resources.

[0065] Step 9:

[0066] The device provides an interface that displays received learning resources and comprehension tests to the user. The user can then progress through their learning using the provided content.

[0067] (Example 1)

[0068] 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."

[0069] Conventional learning support systems have the challenge of not adequately providing learning resources that cater to the individual learning tendencies of learners, making it difficult to achieve an efficient learning process. Furthermore, there is room for improvement in generating tests that appropriately assess learners' understanding.

[0070] 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.

[0071] In this invention, the server includes means for receiving evaluation data entered by the learner, means for analyzing the evaluation data and identifying the learner's tendencies, means for using a generative AI model to generate information based on the identified tendencies, and means for preparing comprehension tests and measuring the learner's level of comprehension. This makes it possible to provide learning resources optimized for the individual needs of the learner and to generate tests to accurately evaluate their level of comprehension.

[0072] A "learner" refers to an individual who learns specific material for the purpose of education, training, or proficiency.

[0073] "Evaluation data" refers to quantitative or qualitative information obtained as a result of learners engaging in learning activities.

[0074] "Trends" refer to learning patterns and characteristics that become apparent based on a learner's learning history and performance.

[0075] "Means" refers to the methods, techniques, or processes used to achieve a specific function or purpose.

[0076] "Information generation" refers to the process of creating learning materials or resources that are best suited to the learner, based on analyzed trends.

[0077] A "generative AI model" refers to a computational model that utilizes artificial intelligence technology to automatically generate optimized outputs from given data and conditions.

[0078] A "comprehension test" refers to an assessment tool designed to evaluate the extent to which learners understand and have acquired specific knowledge or skills.

[0079] In implementing the present invention, it is necessary to design a system that provides an individualized learning experience based on learner input information. This system consists of three main elements: a terminal, a server, and a user.

[0080] Users use their devices to manage their learning outcomes and progress. Specifically, they input the results of completed assignments and tests on their smartphones or PCs and send them to the system. For example, they might take a picture of their math test results with their device's camera and upload it as image data.

[0081] The terminal is a device that receives data provided by the user. If it is image data, it uses OCR (Optical Character Recognition) technology to extract characters and convert them into text data. It also has the function to transfer the resulting data to a server.

[0082] The server is responsible for receiving and analyzing evaluation data sent from the terminal. Using evaluation data and historical data, it employs machine learning algorithms to identify learner tendencies. Based on these learning tendencies, it utilizes generative AI models to generate optimized information. This includes text, videos, and audio specifically tailored to particular problem areas. As a result, users can access learning resources in a format suited to their learning style.

[0083] Furthermore, the server generates comprehension tests to assess the learner's current level of understanding. These tests are adaptive, customizing based on user input and past results. The generated test results clearly identify areas for improvement in the next learning cycle.

[0084] As a concrete example, consider a student studying mathematics. The user takes a midterm exam in their mathematics course and uploads the results to their device. The device processes this image data using OCR technology and sends it to a server. The server analyzes the data and uses an AI model to generate supplementary materials based on areas where the learner particularly struggles, such as differential calculus. Finally, it provides the user with a test to measure their level of understanding.

[0085] An example of a specific prompt to input into the generating AI model is as follows: "Analyze the results of the following math test to identify the user's learning strengths and weaknesses, and generate learning resources optimized for them. Test results: Attach image or text data."

[0086] In this way, the present invention provides support for users to engage in efficient and personalized learning by utilizing a variety of digital technologies.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] Users input learning assignments and test results using their devices. For example, a user might take a picture of their math midterm exam results with their smartphone and upload it as an image. This input includes image data of the answer sheet. As output, this information is temporarily stored on the device.

[0090] Step 2:

[0091] The terminal processes the image data received from the user and prepares it for transmission to the server. During this process, the terminal uses OCR technology to extract character information from the image data and converts it into text data. The converted text data is then output and ready for transfer to the server.

[0092] Step 3:

[0093] The terminal sends the converted text data to the server. The input is text data after OCR processing, and the server receives it as output, which is then analyzed within the system.

[0094] Step 4:

[0095] The server receives text data sent from the terminal and begins analysis. The server uses machine learning algorithms to analyze the text data and identify the user's learning tendencies. The input is text data, and the output is metadata indicating the user's learning tendencies.

[0096] Step 5:

[0097] The server utilizes a generative AI model to generate learning resources based on identified learning tendencies. In this process, the generative AI model automatically creates optimal learning materials to address the user's weaknesses. The input is learning tendency data obtained through analysis, and the output is uniquely customized learning content.

[0098] Step 6:

[0099] The server creates tests to assess the user's understanding. These tests aim to measure the user's comprehension after applying learning resources and are customized based on past data and current status. Inputs include the user's learning history and current evaluation data, and the output generates individual comprehension tests.

[0100] Step 7:

[0101] The terminal provides users with learning resources and comprehension tests received from the server. The terminal displays learning materials and tests clearly through a graphical user interface (GUI), enhancing user convenience. Input is the content generated from the server, and output is the visual and interactive presentation of that content to the user.

[0102] (Application Example 1)

[0103] 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."

[0104] While conventional learning support systems provided optimal learning resources based on learner input data, they lacked sufficient real-time supplementary learning support and dynamic information delivery tailored to the learner's level of understanding. Therefore, there was a need for a system that could maximize learner learning effectiveness in real time.

[0105] 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.

[0106] In this invention, the server includes means for receiving learning evaluation data entered by the learner, means for analyzing the learning evaluation data to identify the learner's learning tendencies, means for generating learning resources based on the learner's identified learning tendencies, means for controlling an input device through which the user acquires learning content via a visual device, means for analyzing data acquired from the visual device to generate additional information in real time, and means for displaying the additional information in a format appropriate to the user's level of understanding. As a result, learners can acquire supplementary information in real time via a visual device, thereby enhancing the learning effect.

[0107] "Learner-input learning evaluation data" refers to information that learners input into their devices regarding their learning progress and test results, and that data is used for analysis.

[0108] "Learner learning tendencies" refer to the characteristic learning patterns and comprehension trends of learners identified from the analysis of learning evaluation data.

[0109] "Learning resources" refer to information and materials that are generated based on a learner's identified learning tendencies and are designed to efficiently support their learning.

[0110] An "input device that allows users to acquire learning content through visual devices" is a device that allows learners to visually absorb lesson content and teaching materials through a device capable of acquiring visual information, such as glasses or a headset.

[0111] "Data acquired from visual devices" refers to image data and textual information obtained through visual devices, and additional information is generated based on this data.

[0112] "Generating additional information in real time" means instantly analyzing data acquired by visual devices and immediately generating and providing supplementary information and explanations tailored to the learner's level of understanding.

[0113] "Displaying information in a format appropriate to the user's level of understanding" means displaying acquired additional information on a visual device in a format suitable for the user's learning status and level of understanding, thereby efficiently supporting learning.

[0114] The system for implementing this invention consists mainly of a terminal used by learners and a server that processes the data. The terminal is a device such as smart glasses or a smartphone and is equipped with a camera for learners to visually acquire data. Taking smart glasses as an example, the camera in the glasses captures the lesson content and sends it to the server as image data.

[0115] The server uses OCR technology, such as Google's Cloud Vision API, to extract text information from image data. Furthermore, the extracted information is stored in a database, and machine learning algorithms analyze its learning tendencies. Based on these analysis results, supplementary information and learning resources necessary for the learner are generated.

[0116] The generated learning resources are displayed in real time on the device's screen, providing additional information to support the learner's understanding. For example, if an equation is displayed in a math lesson, related calculation steps and supplementary explanations are presented on the visual device.

[0117] As a concrete example, during a math class, the glasses could recognize an equation on the blackboard and send a prompt message to the server such as, "I want to know more about how to solve this equation." This prompt message is input into a generative AI model, and the learner is provided with content including a detailed explanation, enabling a deeper understanding.

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] While a user is taking a class using smart glasses, the glasses' camera captures images of the blackboard and materials, inputting them as image data. This image data is then preprocessed before being sent to the server. Specific operations include adjusting the image resolution and removing noise.

[0121] Step 2:

[0122] The server uses the Google Cloud Vision API to extract text information from the received image data. The input data is an image, and the output data is in text format. As part of the data processing, character recognition using OCR technology is performed.

[0123] Step 3:

[0124] The server receives the extracted text information and compares it with the learner's past learning evaluation history. The input is past learning data and extracted text, and the output is the result of identifying learning trends. Machine learning algorithms are used to perform data calculations and analyze the learner's level of understanding and trends.

[0125] Step 4:

[0126] The server generates supplementary information and learning materials optimized for the learner based on the analyzed learning trends. It utilizes a generative AI model and prompt statements to create further explanations and problem sets. Specifically, it generates example prompt statements and deploys learning resources.

[0127] Step 5:

[0128] The generated learning resources are sent from the server to the terminal and displayed in real time on the user's smart glasses. The input is the generated learning resources, and the output is the visual information on the glasses' display. This allows learners to check the information on the spot and deepen their understanding.

[0129] 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.

[0130] To implement the present invention, a system is needed that combines an emotion engine that collects input information from learners, recognizes the learners' emotional states, and provides a personalized learning experience based on these. The operation of this system will be described in detail below.

[0131] 1. User Roles

[0132] Users manage their own learning progress and input test and assignment results into the device. They also provide emotional information to the emotion engine through inputs such as voice and facial expressions. This information is analyzed along with learning evaluation data.

[0133] 2. The role of the terminal

[0134] The device receives test results and emotional information entered by the user. Test results may be entered as text data or captured as images. Emotional information is obtained by measuring facial expressions, voice tone, etc., using sensors and cameras built into the device. The device functions as an interface for sending this data to a server.

[0135] 3. Server Role

[0136] The server receives learning evaluation data and emotional information sent from the terminal. First, the server analyzes the learning evaluation data to identify learning trends. Next, it analyzes the emotional information obtained using the emotion engine to determine the user's psychological state in the current learning environment. Using these analysis results, the server generates optimal learning resources that correspond to the learner's learning trends as well as changes in their emotions.

[0137] Furthermore, the system dynamically adjusts the content and format of learning resources based on the learner's emotions recognized by the emotion engine. For example, if a learner is feeling stressed, it can select learning content presented in a simpler format or with a more relaxed approach. In addition, along with the presentation of learning resources, comprehension tests for the next learning step can be prepared to maximize learning effectiveness.

[0138] Specific example

[0139] As a concrete example, consider the case of a user learning a language. After the user completes a language test, they input the results into the device. The device's camera captures the user's facial expressions, and the microphone is used to extract emotional information from voice input.

[0140] The server receives this data, analyzes the information using OCR and speech analysis technologies, and determines the learning tendencies and emotional state. For example, if a user performs poorly on a comprehension test, it may be suggested that they are temporarily experiencing learning stress.

[0141] The server generates learning resources that promote positive emotions, such as soothing audio content and interactive mini-games, to help users relax. It also slightly eases the questions on the next test to increase user motivation and prevent it from becoming too burdensome.

[0142] Thus, in embodiments of the present invention, an emotion engine is used to further personalize the learning experience and realize an efficient and user-friendly learning environment.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] After completing the learning tasks, the user enters their test results on the device. Additionally, the device's built-in camera and microphone automatically capture the user's facial expressions and voice, collecting emotional information.

[0146] Step 2:

[0147] The device formats the test results received from the user as text data or images. It also converts the captured emotional information into digital data and prepares it for transmission to the server.

[0148] Step 3:

[0149] The device sends learning evaluation data and sentiment information to the server. This process uses a secure data transfer protocol to protect user privacy.

[0150] Step 4:

[0151] The server receives data sent from the terminal and uses OCR technology to analyze the text information on the learning evaluation data. This allows the user's score and incorrect answers to be identified.

[0152] Step 5:

[0153] The server analyzes emotional information using an emotion engine. It utilizes image processing and voice analysis technologies to identify emotions such as stress and joy from the user's facial expressions and tone of voice.

[0154] Step 6:

[0155] The server comprehensively assesses the user's learning tendencies and emotional state based on the analysis results. This allows the user to understand their difficulties with specific learning topics and their current psychological state.

[0156] Step 7:

[0157] The server generates learning resources based on the data obtained. Depending on the emotions the user is feeling, it selects relaxing content and motivating resources to provide a learning experience tailored to the user's needs.

[0158] Step 8:

[0159] The server generates tests to assess the user's understanding. It also takes emotions into account and adjusts the difficulty and format of the questions to avoid placing an excessive burden on the user.

[0160] Step 9:

[0161] The device displays personalized learning resources and comprehension tests sent from the server to the user. Through these, the user can learn at their own pace.

[0162] (Example 2)

[0163] 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".

[0164] Conventional learning support systems are limited to providing learning resources based on learner evaluation data, making it difficult to consider learners' emotions and psychological states. Therefore, there are limitations to maximizing learner motivation and learning effectiveness. In contrast, there is a need for a system that utilizes learners' emotional information to provide more appropriate learning resources.

[0165] 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.

[0166] In this invention, the server includes means for receiving learning evaluation data and emotional information entered by the learner, means for analyzing the learning evaluation data to identify the learner's learning tendencies, means for analyzing the emotional information to determine the learner's psychological state, and means for generating learning resources based on the learner's identified learning tendencies and emotional information. This makes it possible to provide a personalized learning experience that responds to the learner's emotions.

[0167] "Learning assessment data" refers to a collection of information that includes the results of tests and assignments taken by learners, as well as their progress.

[0168] "Emotional information" refers to data that indicates a learner's psychological state, obtained from their voice, facial expressions, and behavior.

[0169] "Means for identifying learning trends" refers to the processes and techniques used to analyze learning assessment data and determine trends in learners' abilities and comprehension.

[0170] "Means of determining psychological state" refers to processes and techniques for analyzing emotional information and evaluating the mental and emotional state of learners.

[0171] "Means of generating learning resources" refers to the processes and technologies for creating, selecting, and providing optimal content and learning materials based on learners' learning tendencies and emotional information.

[0172] This system is designed to personalize the learner's learning experience. Specifically, it generates and provides optimal learning resources based on learning evaluation data and sentiment information provided by the learner. This system mainly consists of users, terminals, and servers.

[0173] Users input information about their learning environment into the device. Specifically, they input data such as test results and assignment status, and provide emotional information through the camera and microphone. This allows the device to record the user's learning progress and current emotional state.

[0174] The device is responsible for organizing learning evaluation data and emotional information collected from users and sending it to the server. The camera and microphone on the device use sensor technology to record the user's facial expressions and voice tone in real time and convert them into an analyzable format.

[0175] The server uses OCR and speech analysis technologies to analyze learning evaluation data and emotional information received from the terminal. This allows for the identification of learning trends and the determination of emotional states. Based on the analysis results, the server uses a generative AI model to generate prompt sentences and dynamically formulate the most suitable learning resources for the learner. This ensures that content is provided that matches the learner's current emotional state.

[0176] For example, if a user learning a language is perceived as stressed based on their facial expression after a language test, the server can recommend relaxing audio content or playful, interactive learning resources. It can also adjust the content of the next test to avoid discouraging the user's motivation to learn.

[0177] An example of a prompt might be, "Based on the user's learning data and emotional information, please suggest appropriate content to alleviate stress and increase learning motivation." Based on this prompt, the generative AI model designs appropriate learning resources.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The user inputs learning evaluation data and emotional information into the device. Learning evaluation data includes numerical and textual information indicating test results and assignment completion, while emotional information is recorded using a microphone and camera to capture the user's voice tone and facial expressions. This data is stored on the device.

[0181] Step 2:

[0182] The terminal converts the learning evaluation data and emotional information acquired from the user into a format suitable for transmission to the server. Specifically, it uses OCR technology to convert image data into text data and speech analysis technology to extract emotional parameters from audio data. This generates a standardized data set, which is then sent to the server.

[0183] Step 3:

[0184] The server receives standardized data sent from the terminal. The received data is divided into learning evaluation data and sentiment information. For the learning evaluation data, statistical methods and machine learning algorithms are applied to identify learning trends. For the sentiment information, sentiment analysis algorithms are used to evaluate the user's psychological state.

[0185] Step 4:

[0186] The server inputs prompt messages into the AI ​​model based on the analysis results, generating optimal learning resources for the user. The prompt messages are structured to convey a message such as, "Based on the user's learning data and emotional information, please suggest content that will alleviate stress and increase learning motivation." The AI ​​model then dynamically designs the learning resources based on these prompts.

[0187] Step 5:

[0188] The server sends the generated learning resources to the terminal and provides them to the user. These learning resources include, for example, audio content designed to promote relaxation and interactive learning games. Users can then engage in a learning experience through these resources. This process enhances the user's motivation to learn and supports effective learning.

[0189] (Application Example 2)

[0190] 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".

[0191] Providing learners with an efficient and personalized learning experience is a crucial challenge. However, conventional learning systems have struggled to assess learners' real-time emotional states and dynamically adjust learning content based on those assessments. Furthermore, there has been a need for methods that utilize learners' emotional information as they progress to maximize their motivation.

[0192] 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.

[0193] In this invention, the server includes a device for receiving evaluation data entered by the learner, a device for analyzing the evaluation data and identifying the learner's tendencies, and a device for generating educational resources based on the learner's identified tendencies and emotional state. This makes it possible to provide an individualized learning experience that takes into account the learner's emotional state, thereby maintaining and improving the learner's motivation to learn.

[0194] A "learner" is an individual who receives educational resources and attempts to understand their content.

[0195] "Evaluation data" refers to information provided by learners through assignments and test results that indicates their learning progress and level of understanding.

[0196] "Tendencies" refer to the learning patterns and characteristics that learners exhibit, as well as characteristics that indicate their degree of adaptability to the learning content.

[0197] "Educational resources" refer to resources such as teaching materials, content, and interactive learning tools that are provided to support learners' learning processes.

[0198] "Emotional information" refers to information that indicates the learner's emotional state during learning, obtained from their facial expressions, voice, and behavioral data.

[0199] An "emotion engine" is a system that analyzes emotional information obtained from learners and evaluates their emotional state during the learning process.

[0200] A "server" is a central control unit that receives and analyzes data from learners and provides educational resources.

[0201] To implement this invention, a system consisting of a user, a terminal, and a server is used.

[0202] The user inputs evaluation data such as learning progress and test results into the device. The device uses its built-in camera and microphone to capture the user's facial expressions and voice as emotional information.

[0203] The terminal functions as an interface for sending collected evaluation data and sentiment information to the server.

[0204] The server analyzes the received data to identify the learner's tendencies. It evaluates the user's emotional state using facial recognition with OpenCV and Face++, and speech analysis with Google Cloud Speech-to-Text. Furthermore, it utilizes machine learning platforms such as TENSORFLOW® and PyTorch to generate learning resources based on emotional information.

[0205] The emotion engine adjusts the content of learning resources based on usage data, dynamically providing the most suitable educational resources. For example, if a user is feeling stressed, it can generate more relaxing content or interactive games, providing a learning experience that responds to the user's emotional state.

[0206] For example, when a user shows fatigue or confusion while solving a math problem, providing simple puzzle games or refreshing content to encourage a change of pace can improve learning efficiency.

[0207] An example of a prompt to input into a generative AI model would be, "Please tell me how to design an e-learning app that detects the user's emotional state in real time and suggests the most appropriate learning content accordingly."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] Users input evaluation data, such as learning progress and test results, into their devices. This input data includes evaluation information in text format, as well as emotional information from facial expressions and voices collected via the camera and microphone. The device temporarily stores this data.

[0211] Step 2:

[0212] The device transmits stored evaluation data and sentiment information to a server via the network. It uses a data package as input and transfers data to the server as output. During this process, the data is protected by a secure communication protocol.

[0213] Step 3:

[0214] The server analyzes the received evaluation data and sentiment information. Text mining techniques are used to identify learner patterns and tendencies in the evaluation data. Sentiment information is extracted from facial expressions and speech using OpenCV and Google Cloud Speech-to-Text. The input is evaluation data and sentiment information, and the output is the user's learning tendencies and sentiment state.

[0215] Step 4:

[0216] The server generates optimal educational resources based on the acquired learning tendencies and emotional states. This process uses machine learning models based on TensorFlow and PyTorch to select and generate content that is most suitable for the user. The input is the previously analyzed learning tendencies and emotional states, and the output is the generation of appropriate educational content.

[0217] Step 5:

[0218] The server sends the generated educational resources to the device. The device presents this content to the user and supports user interaction. Specific actions include presenting interactive quizzes and playing relaxing videos. Learning continues as the generated content is displayed on the user's device.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] In order to implement the present invention, a system is needed that collects learner input information and provides an individualized learning experience based on that information. The operation of this system will be described in detail below.

[0236] 1. User Roles

[0237] Users use a device to manage their learning progress. After completing specific assignments or tests, users enter their test results into the device and send them to the system. This input information becomes part of the formation of learning evaluation data.

[0238] 2. The role of the terminal

[0239] The terminal receives the test results entered by the user as image data or text data. After receiving, this data is interpreted and then transferred to the server. The terminal also provides the user with an interface to display learning resources and test results.

[0240] 3. Server Role

[0241] The server receives learning assessment data sent from the terminal. This data is analyzed by the server and used to identify learning trends. The server utilizes machine learning algorithms and databases to analyze learning trends based on the user's past learning history and current test scores.

[0242] Next, the server generates learning resources optimized for the user based on these analysis results. These resources can support diverse learning formats and include text, videos, audio, and more. This allows users to efficiently acquire knowledge in a way that suits their own learning style.

[0243] Furthermore, the server creates comprehension tests that allow users to assess their own understanding. These tests reflect the user's current learning progress and understanding in specific areas, providing feedback to help them effectively advance their learning plan.

[0244] Specific example

[0245] As a concrete example, consider the case of a student studying mathematics. The user takes a midterm exam for their mathematics course, takes a picture of the results with their smartphone, and uploads it to their device. The device sends this image to a server, which then begins analyzing the test.

[0246] The server uses OCR technology to extract usable data from images and determines whether the answers are correct or incorrect. It also analyzes which problems correspond to which mathematical topics and identifies the user's learning tendencies. In this case, it might be found that the user makes particularly many mistakes on differential calculus problems.

[0247] Based on this information, the server generates supplementary learning content specifically focused on differentiation, supporting user improvement through video lectures and interactive practice problems. It also provides comprehension tests focused on contributions related to differentiation, measuring learning effectiveness within the next test cycle.

[0248] In this way, the system provides personalized support tailored to the user's learning needs, thereby enabling an efficient learning experience.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] After the user completes the learning process, they enter their test results into the device. The user can either take a photo of the test paper or enter the test results directly using the keyboard.

[0252] Step 2:

[0253] The terminal receives the input test result data, formats the data, and prepares it for transmission to the server. In the case of images, it optimizes the resolution as needed.

[0254] Step 3:

[0255] The device sends the formatted learning evaluation data to the server via the internet. A secure data transfer protocol is used to ensure data security.

[0256] Step 4:

[0257] The server receives the transmitted learning evaluation data and uses OCR technology to extract text data from the images. If it is text data, it verifies the integrity of the content.

[0258] Step 5:

[0259] The server analyzes the extracted information and calculates the user's score. Furthermore, it identifies the learning area to which each question belongs and identifies the user's strengths and weaknesses.

[0260] Step 6:

[0261] The server retrieves past learning history from the database and analyzes overall learning trends. This includes using machine learning models to identify long-term learning patterns.

[0262] Step 7:

[0263] Based on the analysis results, the server generates learning resources optimized for the user's learning needs. The content and format can vary widely, including text, diagrams, audio files, and video presentations.

[0264] Step 8:

[0265] The server sends the generated learning resources to the terminal. In addition, it automatically generates and provides comprehension tests related to the learning resources.

[0266] Step 9:

[0267] The device provides an interface that displays received learning resources and comprehension tests to the user. The user can then progress through their learning using the provided content.

[0268] (Example 1)

[0269] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0270] Conventional learning support systems have the challenge of not adequately providing learning resources that cater to the individual learning tendencies of learners, making it difficult to achieve an efficient learning process. Furthermore, there is room for improvement in generating tests that appropriately assess learners' understanding.

[0271] 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.

[0272] In this invention, the server includes means for receiving evaluation data entered by the learner, means for analyzing the evaluation data and identifying the learner's tendencies, means for using a generative AI model to generate information based on the identified tendencies, and means for preparing comprehension tests and measuring the learner's level of comprehension. This makes it possible to provide learning resources optimized for the individual needs of the learner and to generate tests to accurately evaluate their level of comprehension.

[0273] A "learner" refers to an individual who learns specific material for the purpose of education, training, or proficiency.

[0274] "Evaluation data" refers to quantitative or qualitative information obtained as a result of learners engaging in learning activities.

[0275] "Trends" refer to learning patterns and characteristics that become apparent based on a learner's learning history and performance.

[0276] "Means" refers to the methods, techniques, or processes used to achieve a specific function or purpose.

[0277] "Information generation" refers to the process of creating learning materials or resources that are best suited to the learner, based on analyzed trends.

[0278] A "generative AI model" refers to a computational model that utilizes artificial intelligence technology to automatically generate optimized outputs from given data and conditions.

[0279] A "comprehension test" refers to an assessment tool designed to evaluate the extent to which learners understand and have acquired specific knowledge or skills.

[0280] In implementing the present invention, it is necessary to design a system that provides an individualized learning experience based on learner input information. This system consists of three main elements: a terminal, a server, and a user.

[0281] Users use their devices to manage their learning outcomes and progress. Specifically, they input the results of completed assignments and tests on their smartphones or PCs and send them to the system. For example, they might take a picture of their math test results with their device's camera and upload it as image data.

[0282] The terminal is a device that receives data provided by the user. If it is image data, it uses OCR (Optical Character Recognition) technology to extract characters and convert them into text data. It also has the function to transfer the resulting data to a server.

[0283] The server is responsible for receiving and analyzing evaluation data sent from the terminal. Using evaluation data and historical data, it employs machine learning algorithms to identify learner tendencies. Based on these learning tendencies, it utilizes generative AI models to generate optimized information. This includes text, videos, and audio specifically tailored to particular problem areas. As a result, users can access learning resources in a format suited to their learning style.

[0284] Furthermore, the server creates an understanding test and evaluates the learner's current understanding level. This test is adaptive and customized based on the data input by the user and past results. Through the generated test results, the improvement points for the next learning cycle are clarified.

[0285] As a specific example, consider the case of a student learning mathematics. The user takes an intermediate mathematics test and uploads the results to the terminal. The terminal processes this image data using OCR technology and sends it to the server. The server analyzes the data and generates supplementary teaching materials based on the areas where the learner is particularly weak, such as differentiation, using a generative AI model. Then, a test for measuring understanding is provided to the user.

[0286] Examples of specific prompt texts to input into the generative AI model are as follows. "Analyze the results of the following mathematics test, identify the learning trends and weaknesses of the user, and generate learning resources optimized for them. Test results: Attach image or text data."

[0287] In this way, the present invention provides support for users to perform efficient and individualized learning by utilizing various digital technologies.

[0288] The flow of the specific process in Example 1 will be described using FIG. 11.

[0289] Step 1:

[0290] The user uses the terminal to input the results of learning tasks and tests. The user takes a photo of the results of an intermediate mathematics test with a smartphone and uploads it as an image. This input includes the image data of the answer sheet for the questions. As output, this information is temporarily stored in the terminal.

[0291] Step 2:

[0292] The terminal processes the image data received from the user and prepares it for transmission to the server. During this process, the terminal uses OCR technology to extract character information from the image data and converts it into text data. The converted text data is then output and ready for transfer to the server.

[0293] Step 3:

[0294] The terminal sends the converted text data to the server. The input is text data after OCR processing, and the server receives it as output, which is then analyzed within the system.

[0295] Step 4:

[0296] The server receives text data sent from the terminal and begins analysis. The server uses machine learning algorithms to analyze the text data and identify the user's learning tendencies. The input is text data, and the output is metadata indicating the user's learning tendencies.

[0297] Step 5:

[0298] The server utilizes a generative AI model to generate learning resources based on identified learning tendencies. In this process, the generative AI model automatically creates optimal learning materials to address the user's weaknesses. The input is learning tendency data obtained through analysis, and the output is uniquely customized learning content.

[0299] Step 6:

[0300] The server creates tests to assess the user's understanding. These tests aim to measure the user's comprehension after applying learning resources and are customized based on past data and current status. Inputs include the user's learning history and current evaluation data, and the output generates individual comprehension tests.

[0301] Step 7:

[0302] The terminal provides the user with the learning resources and comprehension tests received from the server. The terminal uses the GUI to display teaching materials and tests clearly, enhancing the convenience for the user. The input is the content generated by the server, and the output is to visually and interactively provide this content to the user.

[0303] (Application Example 1)

[0304] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0305] In the conventional learning support system, although optimal learning resources were provided based on the learner's input data, real-time supplementary learning support and dynamic information provision according to the learner's comprehension level were insufficient. Therefore, there has been a demand for a mechanism that enables learners to maximize their learning effects in real time.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0307] In this invention, the server includes means for receiving the learning evaluation data input by the learner, means for analyzing the learning evaluation data to identify the learning tendency of the learner, means for generating learning resources based on the identified learning tendency of the learner, means for controlling an input device through which the user acquires learning content through a visual device, means for analyzing the data obtained from the visual device to generate additional information in real time, and means for displaying the additional information in a format corresponding to the user's comprehension level. As a result, the learner can acquire real-time supplementary information through the visual device, and the learning effect can be enhanced.

[0308] The "learning evaluation data input by the learner" is information used when the learner inputs their own learning situation and test results into the terminal for analysis.

[0309] "Learner learning tendencies" refer to the characteristic learning patterns and comprehension trends of learners identified from the analysis of learning evaluation data.

[0310] "Learning resources" refer to information and materials that are generated based on a learner's identified learning tendencies and are designed to efficiently support their learning.

[0311] An "input device that allows users to acquire learning content through visual devices" is a device that allows learners to visually absorb lesson content and teaching materials through a device capable of acquiring visual information, such as glasses or a headset.

[0312] "Data acquired from visual devices" refers to image data and textual information obtained through visual devices, and additional information is generated based on this data.

[0313] "Generating additional information in real time" means instantly analyzing data acquired by visual devices and immediately generating and providing supplementary information and explanations tailored to the learner's level of understanding.

[0314] "Displaying information in a format appropriate to the user's level of understanding" means displaying acquired additional information on a visual device in a format suitable for the user's learning status and level of understanding, thereby efficiently supporting learning.

[0315] The system for implementing this invention consists mainly of a terminal used by learners and a server that processes the data. The terminal is a device such as smart glasses or a smartphone and is equipped with a camera for learners to visually acquire data. Taking smart glasses as an example, the camera in the glasses captures the lesson content and sends it to the server as image data.

[0316] The server uses OCR technology, such as the Google Cloud Vision API, to extract text information from image data. Furthermore, the extracted information is stored in a database, and machine learning algorithms analyze its learning tendencies. Based on these analysis results, supplementary information and learning resources necessary for the learner are generated.

[0317] The generated learning resources are displayed in real time on the device's screen, providing additional information to support the learner's understanding. For example, if an equation is displayed in a math lesson, related calculation steps and supplementary explanations are presented on the visual device.

[0318] As a concrete example, during a math class, the glasses could recognize an equation on the blackboard and send a prompt message to the server such as, "I want to know more about how to solve this equation." This prompt message is input into a generative AI model, and the learner is provided with content including a detailed explanation, enabling a deeper understanding.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] While a user is taking a class using smart glasses, the glasses' camera captures images of the blackboard and materials, inputting them as image data. This image data is then preprocessed before being sent to the server. Specific operations include adjusting the image resolution and removing noise.

[0322] Step 2:

[0323] The server uses the Google Cloud Vision API to extract text information from the received image data. The input data is an image, and the output data is in text format. As part of the data processing, character recognition using OCR technology is performed.

[0324] Step 3:

[0325] The server receives the extracted text information and compares it with the learner's past learning evaluation history. The input is past learning data and extracted text, and the output is the result of identifying learning trends. Machine learning algorithms are used to perform data calculations and analyze the learner's level of understanding and trends.

[0326] Step 4:

[0327] The server generates supplementary information and learning materials optimized for the learner based on the analyzed learning trends. It utilizes a generative AI model and prompt statements to create further explanations and problem sets. Specifically, it generates example prompt statements and deploys learning resources.

[0328] Step 5:

[0329] The generated learning resources are sent from the server to the terminal and displayed in real time on the user's smart glasses. The input is the generated learning resources, and the output is the visual information on the glasses' display. This allows learners to check the information on the spot and deepen their understanding.

[0330] 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.

[0331] To implement the present invention, a system is needed that combines an emotion engine that collects input information from learners, recognizes the learners' emotional states, and provides a personalized learning experience based on these. The operation of this system will be described in detail below.

[0332] 1. User Roles

[0333] Users manage their own learning progress and input test and assignment results into the device. They also provide emotional information to the emotion engine through inputs such as voice and facial expressions. This information is analyzed along with learning evaluation data.

[0334] 2. The role of the terminal

[0335] The device receives test results and emotional information entered by the user. Test results may be entered as text data or captured as images. Emotional information is obtained by measuring facial expressions, voice tone, etc., using sensors and cameras built into the device. The device functions as an interface for sending this data to a server.

[0336] 3. Server Role

[0337] The server receives learning evaluation data and emotional information sent from the terminal. First, the server analyzes the learning evaluation data to identify learning trends. Next, it analyzes the emotional information obtained using the emotion engine to determine the user's psychological state in the current learning environment. Using these analysis results, the server generates optimal learning resources that correspond to the learner's learning trends as well as changes in their emotions.

[0338] Furthermore, the system dynamically adjusts the content and format of learning resources based on the learner's emotions recognized by the emotion engine. For example, if a learner is feeling stressed, it can select learning content presented in a simpler format or with a more relaxed approach. In addition, along with the presentation of learning resources, comprehension tests for the next learning step can be prepared to maximize learning effectiveness.

[0339] Specific example

[0340] As a concrete example, consider the case of a user learning a language. After the user completes a language test, they input the results into the device. The device's camera captures the user's facial expressions, and the microphone is used to extract emotional information from voice input.

[0341] The server receives this data, analyzes the information using OCR and speech analysis technologies, and determines the learning tendencies and emotional state. For example, if a user performs poorly on a comprehension test, it may be suggested that they are temporarily experiencing learning stress.

[0342] The server generates learning resources that promote positive emotions, such as soothing audio content and interactive mini-games, to help users relax. It also slightly eases the questions on the next test to increase user motivation and prevent it from becoming too burdensome.

[0343] Thus, in embodiments of the present invention, an emotion engine is used to further personalize the learning experience and realize an efficient and user-friendly learning environment.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] After completing the learning tasks, the user enters their test results on the device. Additionally, the device's built-in camera and microphone automatically capture the user's facial expressions and voice, collecting emotional information.

[0347] Step 2:

[0348] The device formats the test results received from the user as text data or images. It also converts the captured emotional information into digital data and prepares it for transmission to the server.

[0349] Step 3:

[0350] The device sends learning evaluation data and sentiment information to the server. This process uses a secure data transfer protocol to protect user privacy.

[0351] Step 4:

[0352] The server receives data sent from the terminal and uses OCR technology to analyze the text information on the learning evaluation data. This allows the user's score and incorrect answers to be identified.

[0353] Step 5:

[0354] The server analyzes emotional information using an emotion engine. It utilizes image processing and voice analysis technologies to identify emotions such as stress and joy from the user's facial expressions and tone of voice.

[0355] Step 6:

[0356] The server comprehensively assesses the user's learning tendencies and emotional state based on the analysis results. This allows the user to understand their difficulties with specific learning topics and their current psychological state.

[0357] Step 7:

[0358] The server generates learning resources based on the data obtained. Depending on the emotions the user is feeling, it selects relaxing content and motivating resources to provide a learning experience tailored to the user's needs.

[0359] Step 8:

[0360] The server generates tests to assess the user's understanding. It also takes emotions into account and adjusts the difficulty and format of the questions to avoid placing an excessive burden on the user.

[0361] Step 9:

[0362] The device displays personalized learning resources and comprehension tests sent from the server to the user. Through these, the user can learn at their own pace.

[0363] (Example 2)

[0364] 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".

[0365] Conventional learning support systems are limited to providing learning resources based on learner evaluation data, making it difficult to consider learners' emotions and psychological states. Therefore, there are limitations to maximizing learner motivation and learning effectiveness. In contrast, there is a need for a system that utilizes learners' emotional information to provide more appropriate learning resources.

[0366] 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.

[0367] In this invention, the server includes means for receiving learning evaluation data and emotional information entered by the learner, means for analyzing the learning evaluation data to identify the learner's learning tendencies, means for analyzing the emotional information to determine the learner's psychological state, and means for generating learning resources based on the learner's identified learning tendencies and emotional information. This makes it possible to provide a personalized learning experience that responds to the learner's emotions.

[0368] "Learning assessment data" refers to a collection of information that includes the results of tests and assignments taken by learners, as well as their progress.

[0369] "Emotional information" refers to data that indicates a learner's psychological state, obtained from their voice, facial expressions, and behavior.

[0370] "Means for identifying learning trends" refers to the processes and techniques used to analyze learning assessment data and determine trends in learners' abilities and comprehension.

[0371] "Means of determining psychological state" refers to processes and techniques for analyzing emotional information and evaluating the mental and emotional state of learners.

[0372] "Means of generating learning resources" refers to the processes and technologies for creating, selecting, and providing optimal content and learning materials based on learners' learning tendencies and emotional information.

[0373] This system is designed to personalize the learner's learning experience. Specifically, it generates and provides optimal learning resources based on learning evaluation data and sentiment information provided by the learner. This system mainly consists of users, terminals, and servers.

[0374] Users input information about their learning environment into the device. Specifically, they input data such as test results and assignment status, and provide emotional information through the camera and microphone. This allows the device to record the user's learning progress and current emotional state.

[0375] The device is responsible for organizing learning evaluation data and emotional information collected from users and sending it to the server. The camera and microphone on the device use sensor technology to record the user's facial expressions and voice tone in real time and convert them into an analyzable format.

[0376] The server uses OCR and speech analysis technologies to analyze learning evaluation data and emotional information received from the terminal. This allows for the identification of learning trends and the determination of emotional states. Based on the analysis results, the server uses a generative AI model to generate prompt sentences and dynamically formulate the most suitable learning resources for the learner. This ensures that content is provided that matches the learner's current emotional state.

[0377] For example, if a user learning a language is perceived as stressed based on their facial expression after a language test, the server can recommend relaxing audio content or playful, interactive learning resources. It can also adjust the content of the next test to avoid discouraging the user's motivation to learn.

[0378] An example of a prompt might be, "Based on the user's learning data and emotional information, please suggest appropriate content to alleviate stress and increase learning motivation." Based on this prompt, the generative AI model designs appropriate learning resources.

[0379] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0380] Step 1:

[0381] The user inputs learning evaluation data and emotional information into the device. Learning evaluation data includes numerical and textual information indicating test results and assignment completion, while emotional information is recorded using a microphone and camera to capture the user's voice tone and facial expressions. This data is stored on the device.

[0382] Step 2:

[0383] The terminal converts the learning evaluation data and emotional information acquired from the user into a format suitable for transmission to the server. Specifically, it uses OCR technology to convert image data into text data and speech analysis technology to extract emotional parameters from audio data. This generates a standardized data set, which is then sent to the server.

[0384] Step 3:

[0385] The server receives standardized data sent from the terminal. The received data is divided into learning evaluation data and sentiment information. For the learning evaluation data, statistical methods and machine learning algorithms are applied to identify learning trends. For the sentiment information, sentiment analysis algorithms are used to evaluate the user's psychological state.

[0386] Step 4:

[0387] The server inputs prompt messages into the AI ​​model based on the analysis results, generating optimal learning resources for the user. The prompt messages are structured to convey a message such as, "Based on the user's learning data and emotional information, please suggest content that will alleviate stress and increase learning motivation." The AI ​​model then dynamically designs the learning resources based on these prompts.

[0388] Step 5:

[0389] The server sends the generated learning resources to the terminal and provides them to the user. These learning resources include, for example, audio content designed to promote relaxation and interactive learning games. Users can then engage in a learning experience through these resources. This process enhances the user's motivation to learn and supports effective learning.

[0390] (Application Example 2)

[0391] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0392] Providing learners with an efficient and personalized learning experience is a crucial challenge. However, conventional learning systems have struggled to assess learners' real-time emotional states and dynamically adjust learning content based on those assessments. Furthermore, there has been a need for methods that utilize learners' emotional information as they progress to maximize their motivation.

[0393] 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.

[0394] In this invention, the server includes a device for receiving evaluation data entered by the learner, a device for analyzing the evaluation data and identifying the learner's tendencies, and a device for generating educational resources based on the learner's identified tendencies and emotional state. This makes it possible to provide an individualized learning experience that takes into account the learner's emotional state, thereby maintaining and improving the learner's motivation to learn.

[0395] A "learner" is an individual who receives educational resources and attempts to understand their content.

[0396] "Evaluation data" refers to information provided by learners through assignments and test results that indicates their learning progress and level of understanding.

[0397] "Tendencies" refer to the learning patterns and characteristics that learners exhibit, as well as characteristics that indicate their degree of adaptability to the learning content.

[0398] "Educational resources" refer to resources such as teaching materials, content, and interactive learning tools that are provided to support learners' learning processes.

[0399] "Emotional information" refers to information that indicates the learner's emotional state during learning, obtained from their facial expressions, voice, and behavioral data.

[0400] An "emotion engine" is a system that analyzes emotional information obtained from learners and evaluates their emotional state during the learning process.

[0401] A "server" is a central control unit that receives and analyzes data from learners and provides educational resources.

[0402] To implement this invention, a system consisting of a user, a terminal, and a server is used.

[0403] The user inputs evaluation data such as learning progress and test results into the device. The device uses its built-in camera and microphone to capture the user's facial expressions and voice as emotional information.

[0404] The terminal functions as an interface for sending collected evaluation data and sentiment information to the server.

[0405] The server analyzes the received data to identify the learner's tendencies. It evaluates the user's emotional state using facial recognition with OpenCV and Face++, and speech analysis with Google Cloud Speech-to-Text. Furthermore, it utilizes machine learning platforms such as TensorFlow and PyTorch to generate training resources based on emotional information.

[0406] The emotion engine adjusts the content of learning resources based on usage data, dynamically providing the most suitable educational resources. For example, if a user is feeling stressed, it can generate more relaxing content or interactive games, providing a learning experience that responds to the user's emotional state.

[0407] For example, when a user shows fatigue or confusion while solving a math problem, providing simple puzzle games or refreshing content to encourage a change of pace can improve learning efficiency.

[0408] An example of a prompt to input into a generative AI model would be, "Please tell me how to design an e-learning app that detects the user's emotional state in real time and suggests the most appropriate learning content accordingly."

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] Users input evaluation data, such as learning progress and test results, into their devices. This input data includes evaluation information in text format, as well as emotional information from facial expressions and voices collected via the camera and microphone. The device temporarily stores this data.

[0412] Step 2:

[0413] The device transmits stored evaluation data and sentiment information to a server via the network. It uses a data package as input and transfers data to the server as output. During this process, the data is protected by a secure communication protocol.

[0414] Step 3:

[0415] The server analyzes the received evaluation data and sentiment information. Text mining techniques are used to identify learner patterns and tendencies in the evaluation data. Sentiment information is extracted from facial expressions and speech using OpenCV and Google Cloud Speech-to-Text. The input is evaluation data and sentiment information, and the output is the user's learning tendencies and sentiment state.

[0416] Step 4:

[0417] The server generates optimal educational resources based on the acquired learning tendencies and emotional states. This process uses machine learning models based on TensorFlow and PyTorch to select and generate content that is most suitable for the user. The input is the previously analyzed learning tendencies and emotional states, and the output is the generation of appropriate educational content.

[0418] Step 5:

[0419] The server sends the generated educational resources to the device. The device presents this content to the user and supports user interaction. Specific actions include presenting interactive quizzes and playing relaxing videos. Learning continues as the generated content is displayed on the user's device.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] [Third Embodiment]

[0424] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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".

[0436] In order to implement the present invention, a system is needed that collects learner input information and provides an individualized learning experience based on that information. The operation of this system will be described in detail below.

[0437] 1. User Roles

[0438] Users use a device to manage their learning progress. After completing specific assignments or tests, users enter their test results into the device and send them to the system. This input information becomes part of the formation of learning evaluation data.

[0439] 2. The role of the terminal

[0440] The terminal receives the test results entered by the user as image data or text data. After receiving, this data is interpreted and then transferred to the server. The terminal also provides the user with an interface to display learning resources and test results.

[0441] 3. Server Role

[0442] The server receives learning assessment data sent from the terminal. This data is analyzed by the server and used to identify learning trends. The server utilizes machine learning algorithms and databases to analyze learning trends based on the user's past learning history and current test scores.

[0443] Next, the server generates learning resources optimized for the user based on these analysis results. These resources can support diverse learning formats and include text, videos, audio, and more. This allows users to efficiently acquire knowledge in a way that suits their own learning style.

[0444] Furthermore, the server creates comprehension tests that allow users to assess their own understanding. These tests reflect the user's current learning progress and understanding in specific areas, providing feedback to help them effectively advance their learning plan.

[0445] Specific example

[0446] As a concrete example, consider the case of a student studying mathematics. The user takes a midterm exam for their mathematics course, takes a picture of the results with their smartphone, and uploads it to their device. The device sends this image to a server, which then begins analyzing the test.

[0447] The server uses OCR technology to extract usable data from images and determines whether the answers are correct or incorrect. It also analyzes which problems correspond to which mathematical topics and identifies the user's learning tendencies. In this case, it might be found that the user makes particularly many mistakes on differential calculus problems.

[0448] Based on this information, the server generates supplementary learning content specifically focused on differentiation, supporting user improvement through video lectures and interactive practice problems. It also provides comprehension tests focused on contributions related to differentiation, measuring learning effectiveness within the next test cycle.

[0449] In this way, the system provides personalized support tailored to the user's learning needs, thereby enabling an efficient learning experience.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] After the user completes the learning process, they enter their test results into the device. The user can either take a photo of the test paper or enter the test results directly using the keyboard.

[0453] Step 2:

[0454] The terminal receives the input test result data, formats the data, and prepares it for transmission to the server. In the case of images, it optimizes the resolution as needed.

[0455] Step 3:

[0456] The device sends the formatted learning evaluation data to the server via the internet. A secure data transfer protocol is used to ensure data security.

[0457] Step 4:

[0458] The server receives the transmitted learning evaluation data and uses OCR technology to extract text data from the images. If it is text data, it verifies the integrity of the content.

[0459] Step 5:

[0460] The server analyzes the extracted information and calculates the user's score. Furthermore, it identifies the learning area to which each question belongs and identifies the user's strengths and weaknesses.

[0461] Step 6:

[0462] The server retrieves past learning history from the database and analyzes overall learning trends. This includes using machine learning models to identify long-term learning patterns.

[0463] Step 7:

[0464] Based on the analysis results, the server generates learning resources optimized for the user's learning needs. The content and format can vary widely, including text, diagrams, audio files, and video presentations.

[0465] Step 8:

[0466] The server sends the generated learning resources to the terminal. In addition, it automatically generates and provides comprehension tests related to the learning resources.

[0467] Step 9:

[0468] The device provides an interface that displays received learning resources and comprehension tests to the user. The user can then progress through their learning using the provided content.

[0469] (Example 1)

[0470] 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."

[0471] Conventional learning support systems have the challenge of not adequately providing learning resources that cater to the individual learning tendencies of learners, making it difficult to achieve an efficient learning process. Furthermore, there is room for improvement in generating tests that appropriately assess learners' understanding.

[0472] 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.

[0473] In this invention, the server includes means for receiving evaluation data entered by the learner, means for analyzing the evaluation data and identifying the learner's tendencies, means for using a generative AI model to generate information based on the identified tendencies, and means for preparing comprehension tests and measuring the learner's level of comprehension. This makes it possible to provide learning resources optimized for the individual needs of the learner and to generate tests to accurately evaluate their level of comprehension.

[0474] A "learner" refers to an individual who learns specific material for the purpose of education, training, or proficiency.

[0475] "Evaluation data" refers to quantitative or qualitative information obtained as a result of learners engaging in learning activities.

[0476] "Trends" refer to learning patterns and characteristics that become apparent based on a learner's learning history and performance.

[0477] "Means" refers to the methods, techniques, or processes used to achieve a specific function or purpose.

[0478] "Information generation" refers to the process of creating learning materials or resources that are best suited to the learner, based on analyzed trends.

[0479] A "generative AI model" refers to a computational model that utilizes artificial intelligence technology to automatically generate optimized outputs from given data and conditions.

[0480] A "comprehension test" refers to an assessment tool designed to evaluate the extent to which learners understand and have acquired specific knowledge or skills.

[0481] In implementing the present invention, it is necessary to design a system that provides an individualized learning experience based on learner input information. This system consists of three main elements: a terminal, a server, and a user.

[0482] Users use their devices to manage their learning outcomes and progress. Specifically, they input the results of completed assignments and tests on their smartphones or PCs and send them to the system. For example, they might take a picture of their math test results with their device's camera and upload it as image data.

[0483] The terminal is a device that receives data provided by the user. If it is image data, it uses OCR (Optical Character Recognition) technology to extract characters and convert them into text data. It also has the function to transfer the resulting data to a server.

[0484] The server is responsible for receiving and analyzing evaluation data sent from the terminal. Using evaluation data and historical data, it employs machine learning algorithms to identify learner tendencies. Based on these learning tendencies, it utilizes generative AI models to generate optimized information. This includes text, videos, and audio specifically tailored to particular problem areas. As a result, users can access learning resources in a format suited to their learning style.

[0485] Furthermore, the server generates comprehension tests to assess the learner's current level of understanding. These tests are adaptive, customizing based on user input and past results. The generated test results clearly identify areas for improvement in the next learning cycle.

[0486] As a concrete example, consider a student studying mathematics. The user takes a midterm exam in their mathematics course and uploads the results to their device. The device processes this image data using OCR technology and sends it to a server. The server analyzes the data and uses an AI model to generate supplementary materials based on areas where the learner particularly struggles, such as differential calculus. Finally, it provides the user with a test to measure their level of understanding.

[0487] An example of a specific prompt to input into the generating AI model is as follows: "Analyze the results of the following math test to identify the user's learning strengths and weaknesses, and generate learning resources optimized for them. Test results: Attach image or text data."

[0488] In this way, the present invention provides support for users to engage in efficient and personalized learning by utilizing a variety of digital technologies.

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1:

[0491] Users input learning assignments and test results using their devices. For example, a user might take a picture of their math midterm exam results with their smartphone and upload it as an image. This input includes image data of the answer sheet. As output, this information is temporarily stored on the device.

[0492] Step 2:

[0493] The terminal processes the image data received from the user and prepares it for transmission to the server. During this process, the terminal uses OCR technology to extract character information from the image data and converts it into text data. The converted text data is then output and ready for transfer to the server.

[0494] Step 3:

[0495] The terminal sends the converted text data to the server. The input is text data after OCR processing, and the server receives it as output, which is then analyzed within the system.

[0496] Step 4:

[0497] The server receives text data sent from the terminal and begins analysis. The server uses machine learning algorithms to analyze the text data and identify the user's learning tendencies. The input is text data, and the output is metadata indicating the user's learning tendencies.

[0498] Step 5:

[0499] The server utilizes a generative AI model to generate learning resources based on identified learning tendencies. In this process, the generative AI model automatically creates optimal learning materials to address the user's weaknesses. The input is learning tendency data obtained through analysis, and the output is uniquely customized learning content.

[0500] Step 6:

[0501] The server creates tests to assess the user's understanding. These tests aim to measure the user's comprehension after applying learning resources and are customized based on past data and current status. Inputs include the user's learning history and current evaluation data, and the output generates individual comprehension tests.

[0502] Step 7:

[0503] The terminal provides users with learning resources and comprehension tests received from the server. The terminal displays learning materials and tests clearly through a graphical user interface (GUI), enhancing user convenience. Input is the content generated from the server, and output is the visual and interactive presentation of that content to the user.

[0504] (Application Example 1)

[0505] 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."

[0506] While conventional learning support systems provided optimal learning resources based on learner input data, they lacked sufficient real-time supplementary learning support and dynamic information delivery tailored to the learner's level of understanding. Therefore, there was a need for a system that could maximize learner learning effectiveness in real time.

[0507] 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.

[0508] In this invention, the server includes means for receiving learning evaluation data entered by the learner, means for analyzing the learning evaluation data to identify the learner's learning tendencies, means for generating learning resources based on the learner's identified learning tendencies, means for controlling an input device through which the user acquires learning content via a visual device, means for analyzing data acquired from the visual device to generate additional information in real time, and means for displaying the additional information in a format appropriate to the user's level of understanding. As a result, learners can acquire supplementary information in real time via a visual device, thereby enhancing the learning effect.

[0509] "Learner-input learning evaluation data" refers to information that learners input into their devices regarding their learning progress and test results, and that data is used for analysis.

[0510] "Learner learning tendencies" refer to the characteristic learning patterns and comprehension trends of learners identified from the analysis of learning evaluation data.

[0511] "Learning resources" refer to information and materials that are generated based on a learner's identified learning tendencies and are designed to efficiently support their learning.

[0512] An "input device that allows users to acquire learning content through visual devices" is a device that allows learners to visually absorb lesson content and teaching materials through a device capable of acquiring visual information, such as glasses or a headset.

[0513] "Data acquired from visual devices" refers to image data and textual information obtained through visual devices, and additional information is generated based on this data.

[0514] "Generating additional information in real time" means instantly analyzing data acquired by visual devices and immediately generating and providing supplementary information and explanations tailored to the learner's level of understanding.

[0515] "Displaying information in a format appropriate to the user's level of understanding" means displaying acquired additional information on a visual device in a format suitable for the user's learning status and level of understanding, thereby efficiently supporting learning.

[0516] The system for implementing this invention consists mainly of a terminal used by learners and a server that processes the data. The terminal is a device such as smart glasses or a smartphone and is equipped with a camera for learners to visually acquire data. Taking smart glasses as an example, the camera in the glasses captures the lesson content and sends it to the server as image data.

[0517] The server uses OCR technology, such as the Google Cloud Vision API, to extract text information from image data. Furthermore, the extracted information is stored in a database, and machine learning algorithms analyze its learning tendencies. Based on these analysis results, supplementary information and learning resources necessary for the learner are generated.

[0518] The generated learning resources are displayed in real time on the device's screen, providing additional information to support the learner's understanding. For example, if an equation is displayed in a math lesson, related calculation steps and supplementary explanations are presented on the visual device.

[0519] As a concrete example, during a math class, the glasses could recognize an equation on the blackboard and send a prompt message to the server such as, "I want to know more about how to solve this equation." This prompt message is input into a generative AI model, and the learner is provided with content including a detailed explanation, enabling a deeper understanding.

[0520] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0521] Step 1:

[0522] While a user is taking a class using smart glasses, the glasses' camera captures images of the blackboard and materials, inputting them as image data. This image data is then preprocessed before being sent to the server. Specific operations include adjusting the image resolution and removing noise.

[0523] Step 2:

[0524] The server uses the Google Cloud Vision API to extract text information from the received image data. The input data is an image, and the output data is in text format. As part of the data processing, character recognition using OCR technology is performed.

[0525] Step 3:

[0526] The server receives the extracted text information and compares it with the learner's past learning evaluation history. The input is past learning data and extracted text, and the output is the result of identifying learning trends. Machine learning algorithms are used to perform data calculations and analyze the learner's level of understanding and trends.

[0527] Step 4:

[0528] The server generates supplementary information and learning materials optimized for the learner based on the analyzed learning trends. It utilizes a generative AI model and prompt statements to create further explanations and problem sets. Specifically, it generates example prompt statements and deploys learning resources.

[0529] Step 5:

[0530] The generated learning resources are sent from the server to the terminal and displayed in real time on the user's smart glasses. The input is the generated learning resources, and the output is the visual information on the glasses' display. This allows learners to check the information on the spot and deepen their understanding.

[0531] 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.

[0532] To implement the present invention, a system is needed that combines an emotion engine that collects input information from learners, recognizes the learners' emotional states, and provides a personalized learning experience based on these. The operation of this system will be described in detail below.

[0533] 1. User Roles

[0534] Users manage their own learning progress and input test and assignment results into the device. They also provide emotional information to the emotion engine through inputs such as voice and facial expressions. This information is analyzed along with learning evaluation data.

[0535] 2. The role of the terminal

[0536] The device receives test results and emotional information entered by the user. Test results may be entered as text data or captured as images. Emotional information is obtained by measuring facial expressions, voice tone, etc., using sensors and cameras built into the device. The device functions as an interface for sending this data to a server.

[0537] 3. Server Role

[0538] The server receives learning evaluation data and emotional information sent from the terminal. First, the server analyzes the learning evaluation data to identify learning trends. Next, it analyzes the emotional information obtained using the emotion engine to determine the user's psychological state in the current learning environment. Using these analysis results, the server generates optimal learning resources that correspond to the learner's learning trends as well as changes in their emotions.

[0539] Furthermore, the system dynamically adjusts the content and format of learning resources based on the learner's emotions recognized by the emotion engine. For example, if a learner is feeling stressed, it can select learning content presented in a simpler format or with a more relaxed approach. In addition, along with the presentation of learning resources, comprehension tests for the next learning step can be prepared to maximize learning effectiveness.

[0540] Specific example

[0541] As a concrete example, consider the case of a user learning a language. After the user completes a language test, they input the results into the device. The device's camera captures the user's facial expressions, and the microphone is used to extract emotional information from voice input.

[0542] The server receives this data, analyzes the information using OCR and speech analysis technologies, and determines the learning tendencies and emotional state. For example, if a user performs poorly on a comprehension test, it may be suggested that they are temporarily experiencing learning stress.

[0543] The server generates learning resources that promote positive emotions, such as soothing audio content and interactive mini-games, to help users relax. It also slightly eases the questions on the next test to increase user motivation and prevent it from becoming too burdensome.

[0544] Thus, in embodiments of the present invention, an emotion engine is used to further personalize the learning experience and realize an efficient and user-friendly learning environment.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] After completing the learning tasks, the user enters their test results on the device. Additionally, the device's built-in camera and microphone automatically capture the user's facial expressions and voice, collecting emotional information.

[0548] Step 2:

[0549] The device formats the test results received from the user as text data or images. It also converts the captured emotional information into digital data and prepares it for transmission to the server.

[0550] Step 3:

[0551] The device sends learning evaluation data and sentiment information to the server. This process uses a secure data transfer protocol to protect user privacy.

[0552] Step 4:

[0553] The server receives data sent from the terminal and uses OCR technology to analyze the text information on the learning evaluation data. This allows the user's score and incorrect answers to be identified.

[0554] Step 5:

[0555] The server analyzes emotional information using an emotion engine. It utilizes image processing and voice analysis technologies to identify emotions such as stress and joy from the user's facial expressions and tone of voice.

[0556] Step 6:

[0557] The server comprehensively assesses the user's learning tendencies and emotional state based on the analysis results. This allows the user to understand their difficulties with specific learning topics and their current psychological state.

[0558] Step 7:

[0559] The server generates learning resources based on the data obtained. Depending on the emotions the user is feeling, it selects relaxing content and motivating resources to provide a learning experience tailored to the user's needs.

[0560] Step 8:

[0561] The server generates tests to assess the user's understanding. It also takes emotions into account and adjusts the difficulty and format of the questions to avoid placing an excessive burden on the user.

[0562] Step 9:

[0563] The device displays personalized learning resources and comprehension tests sent from the server to the user. Through these, the user can learn at their own pace.

[0564] (Example 2)

[0565] 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."

[0566] Conventional learning support systems are limited to providing learning resources based on learner evaluation data, making it difficult to consider learners' emotions and psychological states. Therefore, there are limitations to maximizing learner motivation and learning effectiveness. In contrast, there is a need for a system that utilizes learners' emotional information to provide more appropriate learning resources.

[0567] 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.

[0568] In this invention, the server includes means for receiving learning evaluation data and emotional information entered by the learner, means for analyzing the learning evaluation data to identify the learner's learning tendencies, means for analyzing the emotional information to determine the learner's psychological state, and means for generating learning resources based on the learner's identified learning tendencies and emotional information. This makes it possible to provide a personalized learning experience that responds to the learner's emotions.

[0569] "Learning assessment data" refers to a collection of information that includes the results of tests and assignments taken by learners, as well as their progress.

[0570] "Emotional information" refers to data that indicates a learner's psychological state, obtained from their voice, facial expressions, and behavior.

[0571] "Means for identifying learning trends" refers to the processes and techniques used to analyze learning assessment data and determine trends in learners' abilities and comprehension.

[0572] "Means of determining psychological state" refers to processes and techniques for analyzing emotional information and evaluating the mental and emotional state of learners.

[0573] "Means of generating learning resources" refers to the processes and technologies for creating, selecting, and providing optimal content and learning materials based on learners' learning tendencies and emotional information.

[0574] This system is designed to personalize the learner's learning experience. Specifically, it generates and provides optimal learning resources based on learning evaluation data and sentiment information provided by the learner. This system mainly consists of users, terminals, and servers.

[0575] Users input information about their learning environment into the device. Specifically, they input data such as test results and assignment status, and provide emotional information through the camera and microphone. This allows the device to record the user's learning progress and current emotional state.

[0576] The device is responsible for organizing learning evaluation data and emotional information collected from users and sending it to the server. The camera and microphone on the device use sensor technology to record the user's facial expressions and voice tone in real time and convert them into an analyzable format.

[0577] The server uses OCR and speech analysis technologies to analyze learning evaluation data and emotional information received from the terminal. This allows for the identification of learning trends and the determination of emotional states. Based on the analysis results, the server uses a generative AI model to generate prompt sentences and dynamically formulate the most suitable learning resources for the learner. This ensures that content is provided that matches the learner's current emotional state.

[0578] For example, if a user learning a language is perceived as stressed based on their facial expression after a language test, the server can recommend relaxing audio content or playful, interactive learning resources. It can also adjust the content of the next test to avoid discouraging the user's motivation to learn.

[0579] An example of a prompt might be, "Based on the user's learning data and emotional information, please suggest appropriate content to alleviate stress and increase learning motivation." Based on this prompt, the generative AI model designs appropriate learning resources.

[0580] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0581] Step 1:

[0582] The user inputs learning evaluation data and emotional information into the device. Learning evaluation data includes numerical and textual information indicating test results and assignment completion, while emotional information is recorded using a microphone and camera to capture the user's voice tone and facial expressions. This data is stored on the device.

[0583] Step 2:

[0584] The terminal converts the learning evaluation data and emotional information acquired from the user into a format suitable for transmission to the server. Specifically, it uses OCR technology to convert image data into text data and speech analysis technology to extract emotional parameters from audio data. This generates a standardized data set, which is then sent to the server.

[0585] Step 3:

[0586] The server receives standardized data sent from the terminal. The received data is divided into learning evaluation data and sentiment information. For the learning evaluation data, statistical methods and machine learning algorithms are applied to identify learning trends. For the sentiment information, sentiment analysis algorithms are used to evaluate the user's psychological state.

[0587] Step 4:

[0588] The server inputs prompt messages into the AI ​​model based on the analysis results, generating optimal learning resources for the user. The prompt messages are structured to convey a message such as, "Based on the user's learning data and emotional information, please suggest content that will alleviate stress and increase learning motivation." The AI ​​model then dynamically designs the learning resources based on these prompts.

[0589] Step 5:

[0590] The server sends the generated learning resources to the terminal and provides them to the user. These learning resources include, for example, audio content designed to promote relaxation and interactive learning games. Users can then engage in a learning experience through these resources. This process enhances the user's motivation to learn and supports effective learning.

[0591] (Application Example 2)

[0592] 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."

[0593] Providing learners with an efficient and personalized learning experience is a crucial challenge. However, conventional learning systems have struggled to assess learners' real-time emotional states and dynamically adjust learning content based on those assessments. Furthermore, there has been a need for methods that utilize learners' emotional information as they progress to maximize their motivation.

[0594] 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.

[0595] In this invention, the server includes a device for receiving evaluation data entered by the learner, a device for analyzing the evaluation data and identifying the learner's tendencies, and a device for generating educational resources based on the learner's identified tendencies and emotional state. This makes it possible to provide an individualized learning experience that takes into account the learner's emotional state, thereby maintaining and improving the learner's motivation to learn.

[0596] A "learner" is an individual who receives educational resources and attempts to understand their content.

[0597] "Evaluation data" refers to information provided by learners through assignments and test results that indicates their learning progress and level of understanding.

[0598] "Tendencies" refer to the learning patterns and characteristics that learners exhibit, as well as characteristics that indicate their degree of adaptability to the learning content.

[0599] "Educational resources" refer to resources such as teaching materials, content, and interactive learning tools that are provided to support learners' learning processes.

[0600] "Emotional information" refers to information that indicates the learner's emotional state during learning, obtained from their facial expressions, voice, and behavioral data.

[0601] An "emotion engine" is a system that analyzes emotional information obtained from learners and evaluates their emotional state during the learning process.

[0602] A "server" is a central control unit that receives and analyzes data from learners and provides educational resources.

[0603] To implement this invention, a system consisting of a user, a terminal, and a server is used.

[0604] The user inputs evaluation data such as learning progress and test results into the device. The device uses its built-in camera and microphone to capture the user's facial expressions and voice as emotional information.

[0605] The terminal functions as an interface for sending collected evaluation data and sentiment information to the server.

[0606] The server analyzes the received data to identify the learner's tendencies. It evaluates the user's emotional state using facial recognition with OpenCV and Face++, and speech analysis with Google Cloud Speech-to-Text. Furthermore, it utilizes machine learning platforms such as TensorFlow and PyTorch to generate training resources based on emotional information.

[0607] The emotion engine adjusts the content of learning resources based on usage data, dynamically providing the most suitable educational resources. For example, if a user is feeling stressed, it can generate more relaxing content or interactive games, providing a learning experience that responds to the user's emotional state.

[0608] For example, when a user shows fatigue or confusion while solving a math problem, providing simple puzzle games or refreshing content to encourage a change of pace can improve learning efficiency.

[0609] An example of a prompt to input into a generative AI model would be, "Please tell me how to design an e-learning app that detects the user's emotional state in real time and suggests the most appropriate learning content accordingly."

[0610] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0611] Step 1:

[0612] Users input evaluation data, such as learning progress and test results, into their devices. This input data includes evaluation information in text format, as well as emotional information from facial expressions and voices collected via the camera and microphone. The device temporarily stores this data.

[0613] Step 2:

[0614] The device transmits stored evaluation data and sentiment information to a server via the network. It uses a data package as input and transfers data to the server as output. During this process, the data is protected by a secure communication protocol.

[0615] Step 3:

[0616] The server analyzes the received evaluation data and sentiment information. Text mining techniques are used to identify learner patterns and tendencies in the evaluation data. Sentiment information is extracted from facial expressions and speech using OpenCV and Google Cloud Speech-to-Text. The input is evaluation data and sentiment information, and the output is the user's learning tendencies and sentiment state.

[0617] Step 4:

[0618] The server generates optimal educational resources based on the acquired learning tendencies and emotional states. This process uses machine learning models based on TensorFlow and PyTorch to select and generate content that is most suitable for the user. The input is the previously analyzed learning tendencies and emotional states, and the output is the generation of appropriate educational content.

[0619] Step 5:

[0620] The server sends the generated educational resources to the device. The device presents this content to the user and supports user interaction. Specific actions include presenting interactive quizzes and playing relaxing videos. Learning continues as the generated content is displayed on the user's device.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] [Fourth Embodiment]

[0625] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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".

[0638] In order to implement the present invention, a system is needed that collects learner input information and provides an individualized learning experience based on that information. The operation of this system will be described in detail below.

[0639] 1. User Roles

[0640] Users use a device to manage their learning progress. After completing specific assignments or tests, users enter their test results into the device and send them to the system. This input information becomes part of the formation of learning evaluation data.

[0641] 2. The role of the terminal

[0642] The terminal receives the test results entered by the user as image data or text data. After receiving, this data is interpreted and then transferred to the server. The terminal also provides the user with an interface to display learning resources and test results.

[0643] 3. Server Role

[0644] The server receives learning assessment data sent from the terminal. This data is analyzed by the server and used to identify learning trends. The server utilizes machine learning algorithms and databases to analyze learning trends based on the user's past learning history and current test scores.

[0645] Next, the server generates learning resources optimized for the user based on these analysis results. These resources can support diverse learning formats and include text, videos, audio, and more. This allows users to efficiently acquire knowledge in a way that suits their own learning style.

[0646] Furthermore, the server creates comprehension tests that allow users to assess their own understanding. These tests reflect the user's current learning progress and understanding in specific areas, providing feedback to help them effectively advance their learning plan.

[0647] Specific example

[0648] As a concrete example, consider the case of a student studying mathematics. The user takes a midterm exam for their mathematics course, takes a picture of the results with their smartphone, and uploads it to their device. The device sends this image to a server, which then begins analyzing the test.

[0649] The server uses OCR technology to extract usable data from images and determines whether the answers are correct or incorrect. It also analyzes which problems correspond to which mathematical topics and identifies the user's learning tendencies. In this case, it might be found that the user makes particularly many mistakes on differential calculus problems.

[0650] Based on this information, the server generates supplementary learning content specifically focused on differentiation, supporting user improvement through video lectures and interactive practice problems. It also provides comprehension tests focused on contributions related to differentiation, measuring learning effectiveness within the next test cycle.

[0651] In this way, the system provides personalized support tailored to the user's learning needs, thereby enabling an efficient learning experience.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] After the user completes the learning process, they enter their test results into the device. The user can either take a photo of the test paper or enter the test results directly using the keyboard.

[0655] Step 2:

[0656] The terminal receives the input test result data, formats the data, and prepares it for transmission to the server. In the case of images, it optimizes the resolution as needed.

[0657] Step 3:

[0658] The device sends the formatted learning evaluation data to the server via the internet. A secure data transfer protocol is used to ensure data security.

[0659] Step 4:

[0660] The server receives the transmitted learning evaluation data and uses OCR technology to extract text data from the images. If it is text data, it verifies the integrity of the content.

[0661] Step 5:

[0662] The server analyzes the extracted information and calculates the user's score. Furthermore, it identifies the learning area to which each question belongs and identifies the user's strengths and weaknesses.

[0663] Step 6:

[0664] The server retrieves past learning history from the database and analyzes overall learning trends. This includes using machine learning models to identify long-term learning patterns.

[0665] Step 7:

[0666] Based on the analysis results, the server generates learning resources optimized for the user's learning needs. The content and format can vary widely, including text, diagrams, audio files, and video presentations.

[0667] Step 8:

[0668] The server sends the generated learning resources to the terminal. In addition, it automatically generates and provides comprehension tests related to the learning resources.

[0669] Step 9:

[0670] The device provides an interface that displays received learning resources and comprehension tests to the user. The user can then progress through their learning using the provided content.

[0671] (Example 1)

[0672] 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".

[0673] Conventional learning support systems have the challenge of not adequately providing learning resources that cater to the individual learning tendencies of learners, making it difficult to achieve an efficient learning process. Furthermore, there is room for improvement in generating tests that appropriately assess learners' understanding.

[0674] 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.

[0675] In this invention, the server includes means for receiving evaluation data entered by the learner, means for analyzing the evaluation data and identifying the learner's tendencies, means for using a generative AI model to generate information based on the identified tendencies, and means for preparing comprehension tests and measuring the learner's level of comprehension. This makes it possible to provide learning resources optimized for the individual needs of the learner and to generate tests to accurately evaluate their level of comprehension.

[0676] A "learner" refers to an individual who learns specific material for the purpose of education, training, or proficiency.

[0677] "Evaluation data" refers to quantitative or qualitative information obtained as a result of learners engaging in learning activities.

[0678] "Trends" refer to learning patterns and characteristics that become apparent based on a learner's learning history and performance.

[0679] "Means" refers to the methods, techniques, or processes used to achieve a specific function or purpose.

[0680] "Information generation" refers to the process of creating learning materials or resources that are best suited to the learner, based on analyzed trends.

[0681] A "generative AI model" refers to a computational model that utilizes artificial intelligence technology to automatically generate optimized outputs from given data and conditions.

[0682] A "comprehension test" refers to an assessment tool designed to evaluate the extent to which learners understand and have acquired specific knowledge or skills.

[0683] In implementing the present invention, it is necessary to design a system that provides an individualized learning experience based on learner input information. This system consists of three main elements: a terminal, a server, and a user.

[0684] Users use their devices to manage their learning outcomes and progress. Specifically, they input the results of completed assignments and tests on their smartphones or PCs and send them to the system. For example, they might take a picture of their math test results with their device's camera and upload it as image data.

[0685] The terminal is a device that receives data provided by the user. If it is image data, it uses OCR (Optical Character Recognition) technology to extract characters and convert them into text data. It also has the function to transfer the resulting data to a server.

[0686] The server is responsible for receiving and analyzing evaluation data sent from the terminal. Using evaluation data and historical data, it employs machine learning algorithms to identify learner tendencies. Based on these learning tendencies, it utilizes generative AI models to generate optimized information. This includes text, videos, and audio specifically tailored to particular problem areas. As a result, users can access learning resources in a format suited to their learning style.

[0687] Furthermore, the server generates comprehension tests to assess the learner's current level of understanding. These tests are adaptive, customizing based on user input and past results. The generated test results clearly identify areas for improvement in the next learning cycle.

[0688] As a concrete example, consider a student studying mathematics. The user takes a midterm exam in their mathematics course and uploads the results to their device. The device processes this image data using OCR technology and sends it to a server. The server analyzes the data and uses an AI model to generate supplementary materials based on areas where the learner particularly struggles, such as differential calculus. Finally, it provides the user with a test to measure their level of understanding.

[0689] An example of a specific prompt to input into the generating AI model is as follows: "Analyze the results of the following math test to identify the user's learning strengths and weaknesses, and generate learning resources optimized for them. Test results: Attach image or text data."

[0690] In this way, the present invention provides support for users to engage in efficient and personalized learning by utilizing a variety of digital technologies.

[0691] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0692] Step 1:

[0693] Users input learning assignments and test results using their devices. For example, a user might take a picture of their math midterm exam results with their smartphone and upload it as an image. This input includes image data of the answer sheet. As output, this information is temporarily stored on the device.

[0694] Step 2:

[0695] The terminal processes the image data received from the user and prepares it for transmission to the server. During this process, the terminal uses OCR technology to extract character information from the image data and converts it into text data. The converted text data is then output and ready for transfer to the server.

[0696] Step 3:

[0697] The terminal sends the converted text data to the server. The input is text data after OCR processing, and the server receives it as output, which is then analyzed within the system.

[0698] Step 4:

[0699] The server receives text data sent from the terminal and begins analysis. The server uses machine learning algorithms to analyze the text data and identify the user's learning tendencies. The input is text data, and the output is metadata indicating the user's learning tendencies.

[0700] Step 5:

[0701] The server utilizes a generative AI model to generate learning resources based on identified learning tendencies. In this process, the generative AI model automatically creates optimal learning materials to address the user's weaknesses. The input is learning tendency data obtained through analysis, and the output is uniquely customized learning content.

[0702] Step 6:

[0703] The server creates tests to assess the user's understanding. These tests aim to measure the user's comprehension after applying learning resources and are customized based on past data and current status. Inputs include the user's learning history and current evaluation data, and the output generates individual comprehension tests.

[0704] Step 7:

[0705] The terminal provides users with learning resources and comprehension tests received from the server. The terminal displays learning materials and tests clearly through a graphical user interface (GUI), enhancing user convenience. Input is the content generated from the server, and output is the visual and interactive presentation of that content to the user.

[0706] (Application Example 1)

[0707] 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".

[0708] While conventional learning support systems provided optimal learning resources based on learner input data, they lacked sufficient real-time supplementary learning support and dynamic information delivery tailored to the learner's level of understanding. Therefore, there was a need for a system that could maximize learner learning effectiveness in real time.

[0709] 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.

[0710] In this invention, the server includes means for receiving learning evaluation data entered by the learner, means for analyzing the learning evaluation data to identify the learner's learning tendencies, means for generating learning resources based on the learner's identified learning tendencies, means for controlling an input device through which the user acquires learning content via a visual device, means for analyzing data acquired from the visual device to generate additional information in real time, and means for displaying the additional information in a format appropriate to the user's level of understanding. As a result, learners can acquire supplementary information in real time via a visual device, thereby enhancing the learning effect.

[0711] "Learner-input learning evaluation data" refers to information that learners input into their devices regarding their learning progress and test results, and that data is used for analysis.

[0712] "Learner learning tendencies" refer to the characteristic learning patterns and comprehension trends of learners identified from the analysis of learning evaluation data.

[0713] "Learning resources" refer to information and materials that are generated based on a learner's identified learning tendencies and are designed to efficiently support their learning.

[0714] An "input device that allows users to acquire learning content through visual devices" is a device that allows learners to visually absorb lesson content and teaching materials through a device capable of acquiring visual information, such as glasses or a headset.

[0715] "Data acquired from visual devices" refers to image data and textual information obtained through visual devices, and additional information is generated based on this data.

[0716] "Generating additional information in real time" means instantly analyzing data acquired by visual devices and immediately generating and providing supplementary information and explanations tailored to the learner's level of understanding.

[0717] "Displaying information in a format appropriate to the user's level of understanding" means displaying acquired additional information on a visual device in a format suitable for the user's learning status and level of understanding, thereby efficiently supporting learning.

[0718] The system for implementing this invention consists mainly of a terminal used by learners and a server that processes the data. The terminal is a device such as smart glasses or a smartphone and is equipped with a camera for learners to visually acquire data. Taking smart glasses as an example, the camera in the glasses captures the lesson content and sends it to the server as image data.

[0719] The server uses OCR technology, such as the Google Cloud Vision API, to extract text information from image data. Furthermore, the extracted information is stored in a database, and machine learning algorithms analyze its learning tendencies. Based on these analysis results, supplementary information and learning resources necessary for the learner are generated.

[0720] The generated learning resources are displayed in real time on the device's screen, providing additional information to support the learner's understanding. For example, if an equation is displayed in a math lesson, related calculation steps and supplementary explanations are presented on the visual device.

[0721] As a concrete example, during a math class, the glasses could recognize an equation on the blackboard and send a prompt message to the server such as, "I want to know more about how to solve this equation." This prompt message is input into a generative AI model, and the learner is provided with content including a detailed explanation, enabling a deeper understanding.

[0722] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0723] Step 1:

[0724] While a user is taking a class using smart glasses, the glasses' camera captures images of the blackboard and materials, inputting them as image data. This image data is then preprocessed before being sent to the server. Specific operations include adjusting the image resolution and removing noise.

[0725] Step 2:

[0726] The server uses the Google Cloud Vision API to extract text information from the received image data. The input data is an image, and the output data is in text format. As part of the data processing, character recognition using OCR technology is performed.

[0727] Step 3:

[0728] The server receives the extracted text information and compares it with the learner's past learning evaluation history. The input is past learning data and extracted text, and the output is the result of identifying learning trends. Machine learning algorithms are used to perform data calculations and analyze the learner's level of understanding and trends.

[0729] Step 4:

[0730] The server generates supplementary information and learning materials optimized for the learner based on the analyzed learning trends. It utilizes a generative AI model and prompt statements to create further explanations and problem sets. Specifically, it generates example prompt statements and deploys learning resources.

[0731] Step 5:

[0732] The generated learning resources are sent from the server to the terminal and displayed in real time on the user's smart glasses. The input is the generated learning resources, and the output is the visual information on the glasses' display. This allows learners to check the information on the spot and deepen their understanding.

[0733] 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.

[0734] To implement the present invention, a system is needed that combines an emotion engine that collects input information from learners, recognizes the learners' emotional states, and provides a personalized learning experience based on these. The operation of this system will be described in detail below.

[0735] 1. User Roles

[0736] Users manage their own learning progress and input test and assignment results into the device. They also provide emotional information to the emotion engine through inputs such as voice and facial expressions. This information is analyzed along with learning evaluation data.

[0737] 2. The role of the terminal

[0738] The device receives test results and emotional information entered by the user. Test results may be entered as text data or captured as images. Emotional information is obtained by measuring facial expressions, voice tone, etc., using sensors and cameras built into the device. The device functions as an interface for sending this data to a server.

[0739] 3. Server Role

[0740] The server receives learning evaluation data and emotional information sent from the terminal. First, the server analyzes the learning evaluation data to identify learning trends. Next, it analyzes the emotional information obtained using the emotion engine to determine the user's psychological state in the current learning environment. Using these analysis results, the server generates optimal learning resources that correspond to the learner's learning trends as well as changes in their emotions.

[0741] Furthermore, the system dynamically adjusts the content and format of learning resources based on the learner's emotions recognized by the emotion engine. For example, if a learner is feeling stressed, it can select learning content presented in a simpler format or with a more relaxed approach. In addition, along with the presentation of learning resources, comprehension tests for the next learning step can be prepared to maximize learning effectiveness.

[0742] Specific example

[0743] As a concrete example, consider the case of a user learning a language. After the user completes a language test, they input the results into the device. The device's camera captures the user's facial expressions, and the microphone is used to extract emotional information from voice input.

[0744] The server receives this data, analyzes the information using OCR and speech analysis technologies, and determines the learning tendencies and emotional state. For example, if a user performs poorly on a comprehension test, it may be suggested that they are temporarily experiencing learning stress.

[0745] The server generates learning resources that promote positive emotions, such as soothing audio content and interactive mini-games, to help users relax. It also slightly eases the questions on the next test to increase user motivation and prevent it from becoming too burdensome.

[0746] Thus, in embodiments of the present invention, an emotion engine is used to further personalize the learning experience and realize an efficient and user-friendly learning environment.

[0747] The following describes the processing flow.

[0748] Step 1:

[0749] After completing the learning tasks, the user enters their test results on the device. Additionally, the device's built-in camera and microphone automatically capture the user's facial expressions and voice, collecting emotional information.

[0750] Step 2:

[0751] The device formats the test results received from the user as text data or images. It also converts the captured emotional information into digital data and prepares it for transmission to the server.

[0752] Step 3:

[0753] The device sends learning evaluation data and sentiment information to the server. This process uses a secure data transfer protocol to protect user privacy.

[0754] Step 4:

[0755] The server receives data sent from the terminal and uses OCR technology to analyze the text information on the learning evaluation data. This allows the user's score and incorrect answers to be identified.

[0756] Step 5:

[0757] The server analyzes emotional information using an emotion engine. It utilizes image processing and voice analysis technologies to identify emotions such as stress and joy from the user's facial expressions and tone of voice.

[0758] Step 6:

[0759] The server comprehensively assesses the user's learning tendencies and emotional state based on the analysis results. This allows the user to understand their difficulties with specific learning topics and their current psychological state.

[0760] Step 7:

[0761] The server generates learning resources based on the data obtained. Depending on the emotions the user is feeling, it selects relaxing content and motivating resources to provide a learning experience tailored to the user's needs.

[0762] Step 8:

[0763] The server generates tests to assess the user's understanding. It also takes emotions into account and adjusts the difficulty and format of the questions to avoid placing an excessive burden on the user.

[0764] Step 9:

[0765] The device displays personalized learning resources and comprehension tests sent from the server to the user. Through these, the user can learn at their own pace.

[0766] (Example 2)

[0767] 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".

[0768] Conventional learning support systems are limited to providing learning resources based on learner evaluation data, making it difficult to consider learners' emotions and psychological states. Therefore, there are limitations to maximizing learner motivation and learning effectiveness. In contrast, there is a need for a system that utilizes learners' emotional information to provide more appropriate learning resources.

[0769] 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.

[0770] In this invention, the server includes means for receiving learning evaluation data and emotional information entered by the learner, means for analyzing the learning evaluation data to identify the learner's learning tendencies, means for analyzing the emotional information to determine the learner's psychological state, and means for generating learning resources based on the learner's identified learning tendencies and emotional information. This makes it possible to provide a personalized learning experience that responds to the learner's emotions.

[0771] "Learning assessment data" refers to a collection of information that includes the results of tests and assignments taken by learners, as well as their progress.

[0772] "Emotional information" refers to data that indicates a learner's psychological state, obtained from their voice, facial expressions, and behavior.

[0773] "Means for identifying learning trends" refers to the processes and techniques used to analyze learning assessment data and determine trends in learners' abilities and comprehension.

[0774] "Means of determining psychological state" refers to processes and techniques for analyzing emotional information and evaluating the mental and emotional state of learners.

[0775] "Means of generating learning resources" refers to the processes and technologies for creating, selecting, and providing optimal content and learning materials based on learners' learning tendencies and emotional information.

[0776] This system is designed to personalize the learner's learning experience. Specifically, it generates and provides optimal learning resources based on learning evaluation data and sentiment information provided by the learner. This system mainly consists of users, terminals, and servers.

[0777] Users input information about their learning environment into the device. Specifically, they input data such as test results and assignment status, and provide emotional information through the camera and microphone. This allows the device to record the user's learning progress and current emotional state.

[0778] The device is responsible for organizing learning evaluation data and emotional information collected from users and sending it to the server. The camera and microphone on the device use sensor technology to record the user's facial expressions and voice tone in real time and convert them into an analyzable format.

[0779] The server uses OCR and speech analysis technologies to analyze learning evaluation data and emotional information received from the terminal. This allows for the identification of learning trends and the determination of emotional states. Based on the analysis results, the server uses a generative AI model to generate prompt sentences and dynamically formulate the most suitable learning resources for the learner. This ensures that content is provided that matches the learner's current emotional state.

[0780] For example, if a user learning a language is perceived as stressed based on their facial expression after a language test, the server can recommend relaxing audio content or playful, interactive learning resources. It can also adjust the content of the next test to avoid discouraging the user's motivation to learn.

[0781] An example of a prompt might be, "Based on the user's learning data and emotional information, please suggest appropriate content to alleviate stress and increase learning motivation." Based on this prompt, the generative AI model designs appropriate learning resources.

[0782] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0783] Step 1:

[0784] The user inputs learning evaluation data and emotional information into the device. Learning evaluation data includes numerical and textual information indicating test results and assignment completion, while emotional information is recorded using a microphone and camera to capture the user's voice tone and facial expressions. This data is stored on the device.

[0785] Step 2:

[0786] The terminal converts the learning evaluation data and emotional information acquired from the user into a format suitable for transmission to the server. Specifically, it uses OCR technology to convert image data into text data and speech analysis technology to extract emotional parameters from audio data. This generates a standardized data set, which is then sent to the server.

[0787] Step 3:

[0788] The server receives standardized data sent from the terminal. The received data is divided into learning evaluation data and sentiment information. For the learning evaluation data, statistical methods and machine learning algorithms are applied to identify learning trends. For the sentiment information, sentiment analysis algorithms are used to evaluate the user's psychological state.

[0789] Step 4:

[0790] The server inputs prompt messages into the AI ​​model based on the analysis results, generating optimal learning resources for the user. The prompt messages are structured to convey a message such as, "Based on the user's learning data and emotional information, please suggest content that will alleviate stress and increase learning motivation." The AI ​​model then dynamically designs the learning resources based on these prompts.

[0791] Step 5:

[0792] The server sends the generated learning resources to the terminal and provides them to the user. These learning resources include, for example, audio content designed to promote relaxation and interactive learning games. Users can then engage in a learning experience through these resources. This process enhances the user's motivation to learn and supports effective learning.

[0793] (Application Example 2)

[0794] 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".

[0795] Providing learners with an efficient and personalized learning experience is a crucial challenge. However, conventional learning systems have struggled to assess learners' real-time emotional states and dynamically adjust learning content based on those assessments. Furthermore, there has been a need for methods that utilize learners' emotional information as they progress to maximize their motivation.

[0796] 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.

[0797] In this invention, the server includes a device for receiving evaluation data entered by the learner, a device for analyzing the evaluation data and identifying the learner's tendencies, and a device for generating educational resources based on the learner's identified tendencies and emotional state. This makes it possible to provide an individualized learning experience that takes into account the learner's emotional state, thereby maintaining and improving the learner's motivation to learn.

[0798] A "learner" is an individual who receives educational resources and attempts to understand their content.

[0799] "Evaluation data" refers to information provided by learners through assignments and test results that indicates their learning progress and level of understanding.

[0800] "Tendencies" refer to the learning patterns and characteristics that learners exhibit, as well as characteristics that indicate their degree of adaptability to the learning content.

[0801] "Educational resources" refer to resources such as teaching materials, content, and interactive learning tools that are provided to support learners' learning processes.

[0802] "Emotional information" refers to information that indicates the learner's emotional state during learning, obtained from their facial expressions, voice, and behavioral data.

[0803] An "emotion engine" is a system that analyzes emotional information obtained from learners and evaluates their emotional state during the learning process.

[0804] A "server" is a central control unit that receives and analyzes data from learners and provides educational resources.

[0805] To implement this invention, a system consisting of a user, a terminal, and a server is used.

[0806] The user inputs evaluation data such as learning progress and test results into the device. The device uses its built-in camera and microphone to capture the user's facial expressions and voice as emotional information.

[0807] The terminal functions as an interface for sending collected evaluation data and sentiment information to the server.

[0808] The server analyzes the received data to identify the learner's tendencies. It evaluates the user's emotional state using facial recognition with OpenCV and Face++, and speech analysis with Google Cloud Speech-to-Text. Furthermore, it utilizes machine learning platforms such as TensorFlow and PyTorch to generate training resources based on emotional information.

[0809] The emotion engine adjusts the content of learning resources based on usage data, dynamically providing the most suitable educational resources. For example, if a user is feeling stressed, it can generate more relaxing content or interactive games, providing a learning experience that responds to the user's emotional state.

[0810] For example, when a user shows fatigue or confusion while solving a math problem, providing simple puzzle games or refreshing content to encourage a change of pace can improve learning efficiency.

[0811] An example of a prompt to input into a generative AI model would be, "Please tell me how to design an e-learning app that detects the user's emotional state in real time and suggests the most appropriate learning content accordingly."

[0812] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0813] Step 1:

[0814] Users input evaluation data, such as learning progress and test results, into their devices. This input data includes evaluation information in text format, as well as emotional information from facial expressions and voices collected via the camera and microphone. The device temporarily stores this data.

[0815] Step 2:

[0816] The device transmits stored evaluation data and sentiment information to a server via the network. It uses a data package as input and transfers data to the server as output. During this process, the data is protected by a secure communication protocol.

[0817] Step 3:

[0818] The server analyzes the received evaluation data and sentiment information. Text mining techniques are used to identify learner patterns and tendencies in the evaluation data. Sentiment information is extracted from facial expressions and speech using OpenCV and Google Cloud Speech-to-Text. The input is evaluation data and sentiment information, and the output is the user's learning tendencies and sentiment state.

[0819] Step 4:

[0820] The server generates optimal educational resources based on the acquired learning tendencies and emotional states. This process uses machine learning models based on TensorFlow and PyTorch to select and generate content that is most suitable for the user. The input is the previously analyzed learning tendencies and emotional states, and the output is the generation of appropriate educational content.

[0821] Step 5:

[0822] The server sends the generated educational resources to the device. The device presents this content to the user and supports user interaction. Specific actions include presenting interactive quizzes and playing relaxing videos. Learning continues as the generated content is displayed on the user's device.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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."

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] The following is further disclosed regarding the embodiments described above.

[0845] (Claim 1)

[0846] A means for receiving learning evaluation data entered by learners,

[0847] A means for analyzing the learning evaluation data to identify the learner's learning tendencies,

[0848] A means for generating learning resources based on the identified learning tendencies of learners,

[0849] Means for providing the learning resources to learners,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, further comprising means for more precisely identifying learning tendencies using the learner's past learning evaluation history.

[0853] (Claim 3)

[0854] The system according to claim 1, further comprising means for generating a test to evaluate the learner's level of understanding after the application of learning resources.

[0855] "Example 1"

[0856] (Claim 1)

[0857] A means of receiving evaluation data entered by learners,

[0858] A means of analyzing evaluation data to identify learner tendencies,

[0859] A means of using a generative AI model to generate information based on identified trends,

[0860] Means for providing the generated information to learners,

[0861] A means of measuring learners' understanding by preparing comprehension tests,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, comprising means for precisely identifying learning trends using evaluation data and past history.

[0865] (Claim 3)

[0866] The system according to claim 1, comprising means for generating a new test to evaluate the learner's understanding after applying the information provided to the learner.

[0867] "Application Example 1"

[0868] (Claim 1)

[0869] A means for receiving learning evaluation data entered by learners,

[0870] A means for analyzing the learning evaluation data to identify the learner's learning tendencies,

[0871] A means for generating learning resources based on the identified learning tendencies of learners,

[0872] Means for providing the learning resources to learners,

[0873] A means for controlling an input device that allows the user to acquire learning content through a visual device,

[0874] A means of analyzing data acquired from a visual device to generate additional information in real time,

[0875] A means for displaying the additional information in a format that suits the user's level of understanding,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, further comprising means for more precisely identifying learning tendencies using the learner's past learning evaluation history.

[0879] (Claim 3)

[0880] The system according to claim 1, further comprising means for generating a test to evaluate the learner's level of understanding after the application of learning resources.

[0881] "Example 2 of combining an emotion engine"

[0882] (Claim 1)

[0883] A means for receiving learning evaluation data and sentiment information entered by learners,

[0884] A means for analyzing the learning evaluation data to identify the learner's learning tendencies,

[0885] A means of analyzing emotional information to determine the learner's psychological state,

[0886] A means for generating learning resources based on the learner's identified learning tendencies and emotional information,

[0887] Means for providing the learning resources to learners,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, comprising means for precisely identifying learning tendencies using past learning evaluation history and sentiment information.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for generating a test to evaluate the learner's level of understanding after the application of learning resources.

[0893] "Application example 2 when combining with an emotional engine"

[0894] (Claim 1)

[0895] A device that receives evaluation data entered by learners,

[0896] A device that analyzes the evaluation data and identifies the learner's tendencies,

[0897] A device that generates educational resources based on the identified tendencies and emotional states of learners,

[0898] A device for providing the educational resources to learners,

[0899] A device equipped with an emotion engine for acquiring and analyzing learners' emotional information, which dynamically adjusts educational resources according to the learners' emotional state,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, further comprising a device for more precisely identifying learning tendencies using the learner's past evaluation history and emotional history.

[0903] (Claim 3)

[0904] The system according to claim 1, comprising a device that generates a test to evaluate the learner's level of understanding after providing educational resources, and adjusts the content of the test based on the learner's emotional state. [Explanation of symbols]

[0905] 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. A means for receiving learning evaluation data entered by learners, A means for analyzing the learning evaluation data to identify the learner's learning tendencies, A means for generating learning resources based on the identified learning tendencies of learners, Means for providing the learning resources to learners, A means for controlling an input device that allows the user to acquire learning content through a visual device, A means of analyzing data acquired from a visual device to generate additional information in real time, A means for displaying the additional information in a format that suits the user's level of understanding, A system that includes this.

2. The system according to claim 1, further comprising means for more precisely identifying learning tendencies using the learner's past learning evaluation history.

3. The system according to claim 1, further comprising means for generating a test to evaluate the learner's level of understanding after the application of learning resources.

Images