system

Abstract

We provide the system. [Solution] Visual data is acquired via an input device. A processing device that generates character information from visual data using optical character recognition, An analysis device that analyzes generated character information and identifies the user's error patterns, A task generation device that generates review tasks suitable for the user based on identified error patterns, A display device that provides users with generated review assignments and offers explanations and educational materials, A support device that provides additional learning support to users using audio or visual feedback, A system that includes this.

Description

Technical Field

[0004] , ,

[0005] , ,

[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 as a 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] <00000​​​​​​​To solve the above problems, the present invention provides a means for acquiring image data input by a user and generating text data from that image data using optical character recognition. It also employs an analysis means for analyzing the generated text data and identifying the user's tendency to make incorrect answers. Furthermore, it includes a question generation means for generating review questions that are optimal for the user based on the identified tendency to make incorrect answers. In addition, by incorporating a display means that provides the user with these generated review questions and visually displays the necessary explanations and learning materials, it is possible to efficiently support the user's learning.

[0006] "Input means" refers to devices or interfaces used to receive information or data from users.

[0007] "Image data" refers to visual information recorded in a format that can be processed by a computer.

[0008] Optical character recognition (OCR) is a technology that identifies characters from image data and converts them into digital text.

[0009] "Text data" refers to character information recorded in a format that can be processed by a computer.

[0010] "Analysis means" refers to devices and algorithms used to analyze given data and extract useful information from it.

[0011] "Incorrect answer tendencies" refer to patterns of errors that users repeatedly make.

[0012] "Problem generation means" refers to devices or programs used to create new problems according to the user's characteristics and needs.

[0013] "Display means" refers to screens or devices used to provide users with the results of computer processing. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The learning support system of the present invention is designed to efficiently review questions that the user answered incorrectly and to improve learning efficiency.

[0036] First, the user uses a device with a dedicated application installed. The user inputs the incorrectly answered question by taking a picture or screenshot of it with their smartphone or tablet, thereby creating image data. The device receives this image data and uses optical character recognition (OCR) technology to generate text data from the image data containing character information. The system is designed to accurately identify characters and, if necessary, process mathematical formulas and diagrams as well.

[0037] The generated text data is sent from the terminal to the server. The server analyzes the received text data and uses machine learning algorithms to identify the user's error patterns and common mistakes. By referring to the user's past learning data and data from other users, the server gains a more accurate understanding of the causes of errors.

[0038] Based on the analysis results, the server generates original review questions to aid the user's learning. Educational technology and problem design theory are applied to this question generation process to ensure the questions are of appropriate difficulty and deepen the user's understanding. The server also generates explanations for incorrect answers and related learning materials (such as links to lecture videos).

[0039] These generated materials and problems are sent to the device and made available to the user within the application. Users can re-solve the problems within the app and progress through their learning while reviewing the explanations. Data such as progress and accuracy rates are also recorded and reported to teachers or parents as needed.

[0040] For example, if a user makes a mistake on a quadratic function problem in a math test, the server will generate review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user. As a result, the user can learn based on their own tendencies for making mistakes, and receive support to deepen their understanding in a short period of time.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0044] Step 2:

[0045] The device performs optical character recognition (OCR) on the received image data, converting the text information within the image into text data. During this process, it ensures accurate conversion even if mathematical formulas or special symbols are included.

[0046] Step 3:

[0047] The terminal structures the generated text data, adds metadata such as subject, question type, and difficulty level, and sends it to the server.

[0048] Step 4:

[0049] The server analyzes the received text data and metadata, using an AI algorithm to identify characteristics and patterns of user errors. Past training data is also referenced to extract the causes of errors.

[0050] Step 5:

[0051] Based on the analysis results, the server automatically generates review questions tailored to the user's weak areas. These questions are adjusted to an appropriate difficulty level and content according to the user's understanding. Explanatory text and related learning materials are also generated simultaneously.

[0052] Step 6:

[0053] The server sends generated problems, explanations, and learning materials to the user's device. This allows the user to view these within the application and progress through their learning.

[0054] Step 7:

[0055] Users work on review questions and record their results within the application. The device feeds back the user's answers and progress as data to the server, which is then used to further support their learning.

[0056] (Example 1)

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

[0058] There is a need for a system that allows individual learners to efficiently review the areas where they made mistakes and improve their academic ability in a short period of time. However, current learning support technologies lack the functionality to accurately analyze learners' error patterns and automatically generate appropriate review questions based on that analysis. Furthermore, there is no system in place to properly manage learners' progress and allow teachers and parents to easily access that information.

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

[0060] In this invention, the server includes means for acquiring image information of test questions answered incorrectly by the user via an input medium; processing means for generating character information from the image information using optical character conversion; analysis means for analyzing the generated character information and identifying the user's error patterns; question generation means for generating review questions optimized for the user based on the identified error patterns; a display medium for providing the generated review questions, explanations, and learning materials to the user; and recording and reporting means for recording the user's learning progress and correct answer rate and notifying the user, teacher, or guardian. This enables effective review tailored to the needs of each learner, improving learning efficiency and facilitating the appropriate sharing of progress information.

[0061] "Input medium" refers to devices and methods for transmitting information from a user to a system, and in particular includes cameras and scanners for acquiring image information.

[0062] "Optical character conversion" refers to a technology for converting image information into text information, primarily using optical character recognition (OCR) to generate text data from image data.

[0063] "Processing means" refers to devices or algorithms that perform the process of analyzing input image information and converting it into text information.

[0064] "Analysis means" refers to technologies and devices used to analyze generated textual information and identify patterns of incorrect answers made by users, and includes machine learning algorithms, etc.

[0065] "Problem generation means" refers to a device or algorithm that automatically generates review questions optimized to maximize educational effectiveness based on the user's error patterns.

[0066] "Display medium" refers to devices and systems used to provide and display generated review questions, explanations, and learning materials to users, and this particularly includes displays and mobile devices.

[0067] "Recording and reporting means" refers to devices or software that have the function of saving the user's learning progress and correct answer rate, and notifying the user themselves, or, if necessary, teachers or guardians, of this information.

[0068] To implement this invention, the user begins by using a device with a dedicated application installed to take a picture of an incorrectly answered test question or capture an image of the question via a screenshot. The device then converts this image information into text information using optical character recognition (OCR), a type of optical character conversion technology. Specific examples of such technologies include Tesseract and cloud-based OCR services.

[0069] The terminal then sends the generated text information to the server. The server uses a machine learning algorithm to analyze this text information and identify the user's error patterns. The server then uses a generative AI model to generate review questions tailored to the user's needs, referencing past training data and other users' error records. This process applies theories from educational technology and problem design, aiming to deepen understanding at an appropriate difficulty level.

[0070] In addition, the server generates explanations for the user's incorrect answers and related learning materials, and sends them to the terminal. The terminal displays the generated review questions and learning materials within the application, allowing the user to continue their learning through them.

[0071] For example, if a user makes a mistake on a quadratic function problem in a math test, the server generates review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user, and provides them as learning material. As a result, users can effectively review based on their individual error patterns, supporting a deeper understanding in a short period of time.

[0072] An example of a prompt message for a generating AI model is: "I made a mistake in reading the graph of a quadratic function. Please generate review questions specifically for my weak areas. Please also refer to past incorrect answer data and add explanations to deepen my understanding."

[0073] Thus, this invention is a system that provides customized learning support based on each user's tendency to make mistakes, thereby improving learning efficiency.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] Users take photos or screenshots of incorrectly answered exam questions using a smartphone, tablet, or other device. The question data is then entered as image information. Users must ensure the question is clearly visible in the image.

[0077] Step 2:

[0078] The terminal uses OCR software to generate text information from acquired image information. In this process, image data is input and text data is output. For example, Tesseract is used to perform calculations to identify data containing characters and mathematical formulas as text.

[0079] Step 3:

[0080] The terminal sends the generated character data to the server. The input here is character data, and the output is notification information indicating that communication with the server has been established and data has been sent. The terminal uses protocols such as HTTPS to ensure secure data communication.

[0081] Step 4:

[0082] The server analyzes the received text data using a machine learning algorithm to identify patterns of user errors. The input is the transmitted text data, and the output is information about the error patterns. The analysis calculations are performed by referring to past learning history and other user data.

[0083] Step 5:

[0084] The server uses a generative AI model to create review questions and explanations based on incorrect answer patterns. The input in this step is incorrect answer pattern information, and the output is the generated review questions and explanation materials. Optimal questions and answers are designed based on educational technology theory.

[0085] Step 6:

[0086] The server sends the generated review questions and explanatory materials to the terminal. The input is the review questions and explanatory materials, and the output is the state in which this data has been transferred to the terminal. The terminal displays the information through a user-friendly interface.

[0087] Step 7:

[0088] Users solve review problems provided through their devices and deepen their understanding by checking the explanations. Input consists of problems and materials displayed on the device, while output consists of the user's answers and progress data for review. The system records the user's learning progress and reports it to educators and parents as needed.

[0089] (Application Example 1)

[0090] 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."

[0091] Traditional learning support systems have faced challenges in efficiently reviewing incorrect answers and addressing individual learning needs. Furthermore, they lacked dynamic learning support utilizing audio and visual feedback, making it difficult to provide users with the optimal educational experience. Additionally, teachers and parents had limited information to track users' learning progress and provide appropriate support.

[0092] 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.

[0093] In this invention, the server includes a processing device that acquires visual data via an input device and generates character information from the visual data using optical character recognition; an analysis device that analyzes the generated character information and identifies the user's error patterns; a task generation device that generates review tasks suitable for the user based on the identified error patterns; a display device that provides the generated review tasks to the user and provides explanations and educational materials; and a support device that provides additional learning support to the user using audio or visual feedback. This enables users to review optimally according to their individual error tendencies and enjoy an intuitive learning experience through audio and visual feedback. Furthermore, it enables more effective educational support by providing educators with progress information for each user and creating individually optimized prompt sentences using a generation AI model.

[0094] An "input device" is a device used to acquire visual data, such as a camera or scanner.

[0095] "Visual data" refers to data that includes visual information, such as images and videos, and is acquired by an input device.

[0096] Optical character recognition (OCR) is a technology that extracts character information from image data and converts it into text data.

[0097] A "processing unit" is a computer unit that converts visual data into textual information and performs the optical character recognition process.

[0098] "Character information" refers to text data generated by optical character recognition.

[0099] An "analysis device" is a computer unit that analyzes the user's error patterns based on the generated character information.

[0100] "Incorrect answer patterns" refer to the tendencies and characteristics of how users answer questions incorrectly.

[0101] A "task generation device" is a computer unit that creates appropriate review tasks based on the user's error patterns.

[0102] "Assignments" refer to problems and exercises presented to users to support their learning.

[0103] A "display device" is a device that provides users with generated review assignments, explanations, and educational materials visually or audibly.

[0104] "Voice feedback" is a technology that provides supplementary information or guidance to users through audio.

[0105] "Visual feedback" is a technique that supplements or instructs users on learning content through visual information.

[0106] A "support device" is a device that provides additional learning support, such as audio or visual feedback.

[0107] To realize this invention, the system is configured as follows: First, the user takes a picture of a problem on paper using an input device, such as a tablet with a camera. The captured visual data is collected by the terminal and converted into text information by optical character recognition software, such as an OCR engine like Tesseract. Through this process, the visual data becomes digital text.

[0108] Next, the server receives the processed character information and analyzes the error patterns. The analysis device uses machine learning algorithms to analyze the user's past answer data and similar data from other users. In this phase, machine learning libraries such as scikit-learn are utilized to identify the user's learning needs based on the error patterns.

[0109] Based on identified error patterns, the server uses a task generator to create personalized review tasks for each user. These tasks include questions designed to reinforce areas where the user frequently makes mistakes, as well as exercises to deepen understanding. The generated tasks, explanations, and related educational materials are provided to the user via the terminal's display device.

[0110] Furthermore, the support device utilizes audio and visual feedback to provide users with additional learning support. Users can systematically progress through learning while receiving feedback from support devices such as robots.

[0111] For example, if a child mispronounces a particular word while doing their English homework, this system can provide additional practice exercises to reinforce that word. Using a generative AI model, it's possible to provide prompts such as, "Please pronounce the following word correctly: 'develop'."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The user takes a picture of their homework or problem using an input device. The input is visual data, which is captured by the terminal. The captured visual data is then prepared for further processing.

[0115] Step 2:

[0116] The device uses optical character recognition (OCR) technology to generate character information from the captured visual data. In this step, the visual data is converted into text data, and the character information recognized by the OCR engine is output.

[0117] Step 3:

[0118] The terminal sends the generated character information to the server. The server receives this character information and begins analysis. The input is text data, and the output is the identification of incorrect answer patterns.

[0119] Step 4:

[0120] The server uses a machine learning model to analyze user error patterns. It compares past answers with data from other similar users to identify error trends. The input consists of text data and past learning history data, and the output is the user's error patterns.

[0121] Step 5:

[0122] Based on identified incorrect answer patterns, the server generates review tasks suitable for the user using a task generation device. The input is the incorrect answer patterns, and the output is the review tasks and explanations.

[0123] Step 6:

[0124] The generated review assignments and explanations are sent to the terminal and provided to the user via a display device. The input here is the review assignments and explanations, and the output is presented visually or audibly.

[0125] Step 7:

[0126] The terminal or assistive device provides the user with additional learning support using audio or visual feedback. Specifically, it provides audio guidance on how to solve problems or the correct pronunciation of incorrect words. The input for this step is audio instructions or visual data, and the output is direct educational support for the user.

[0127] Step 8:

[0128] Ultimately, a generative AI model is used to optimize prompts for the user. For example, it provides dynamic instructions such as, "Please pronounce the following word correctly: 'develop'." Based on the input, feedback tailored to the user's needs is output.

[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] The learning support system of the present invention aims to analyze the user's tendency to make incorrect answers, recognize the user's emotional state, and provide an appropriate learning experience based on that.

[0131] First, the user takes a picture of the question they answered incorrectly with their smartphone or tablet and inputs it as image data into the device through the application. The device then uses optical character recognition (OCR) technology to convert this image into text data. This text data is sent to a server and used to analyze the user's answering patterns.

[0132] The server utilizes an emotion engine to recognize the user's emotional state when analyzing received text data. Emotion recognition uses cameras and voice input to analyze the user's facial expressions, reactions, and tone of voice to extract emotional data. By combining emotional data with information on error tendencies, a deep understanding of each user's learning needs can be obtained.

[0133] Based on the analysis results, the server generates review questions that take into account the user's emotional state. For example, if the user is feeling frustrated, it will present relatively easy questions to give them a sense of accomplishment and increase their motivation to learn. It can also customize and provide explanations and learning materials based on the user's interests and concerns.

[0134] The generated problems and materials are provided to the user via their device. The user then proceeds with their learning based on these materials and checks their answers and feedback within the application. Furthermore, learning progress and emotional states are reported to teachers and parents, helping to deepen their understanding.

[0135] As a concrete example, suppose a user incorrectly answers an English grammar question and uploads a photo of the answer to the app. If the server detects that the user is fatigued, it will generate a slightly easier, more engaging review question. This allows the user to continue learning without feeling excessively stressed. Through such a mechanism, it becomes possible to provide more personalized learning support.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0139] Step 2:

[0140] The device receives image data and uses Optical Character Recognition (OCR) to convert the text information within the image into text data. During this process, the accuracy of character recognition is improved by correcting the image resolution and brightness.

[0141] Step 3:

[0142] The device sends the converted text data, along with user facial expression and audio data obtained during the capture, to the server. This data is used to identify the user's emotional state.

[0143] Step 4:

[0144] The server analyzes the received text data and uses an AI algorithm to identify patterns in the user's incorrect responses. Simultaneously, an emotion engine analyzes facial expression and voice data to recognize the user's emotional state (e.g., concentration, fatigue, frustration).

[0145] Step 5:

[0146] The server combines data on incorrect answer patterns and emotional states to generate review questions tailored to the user. For example, if a user is feeling fatigued, the server will either lower the difficulty level of the questions or create questions with more engaging content. It will also select appropriate explanations and reference materials to stimulate the user's motivation to learn.

[0147] Step 6:

[0148] The server sends the generated review questions and explanatory materials to the terminal. The terminal displays these within the application, taking care to ensure that the user can understand them intuitively.

[0149] Step 7:

[0150] Users solve the provided problems, review the explanations, and progress through their learning. Throughout this process, the user's facial expressions and reactions are continuously collected on the device and sent to the server as feedback. Data on learning progress and emotional state is also accumulated and used to support future learning.

[0151] (Example 2)

[0152] 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".

[0153] Conventional learning support systems lack sufficient analysis and response capabilities for user errors, making it difficult to provide a learning experience tailored to individual learners. Furthermore, a learning environment that disregards the user's emotional state can lead to decreased motivation and increased stress. There is a need to solve these problems and provide more effective and personalized learning support.

[0154] 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.

[0155] In this invention, the server includes means for acquiring image information via an input device, means for generating character information from the image information using character recognition technology, means for analyzing the generated character information to identify the user's tendency to make incorrect answers, means for generating review tasks suitable for the user based on the identified tendency to make incorrect answers, means for recognizing the user's emotional state and providing an appropriate learning experience, and means for providing the generated review tasks to the user and providing explanations and learning materials. This makes it possible to provide a more appropriate and personalized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0156] An "input device" is a general term for hardware or software used to acquire image information from a user as digital data.

[0157] "Character recognition technology" is a technology that extracts character information from image information and converts it into digital text.

[0158] A "processing device" is a device that analyzes input information and performs processing according to its purpose.

[0159] An "analysis device" is a device that analyzes collected data and identifies patterns and trends.

[0160] A "task generation device" is a device that creates review tasks tailored to the user based on identified trends in incorrect answers.

[0161] An "emotion analysis device" is a device that recognizes the user's emotional state and provides the necessary information to offer an appropriate learning experience.

[0162] A "display device" is a device that provides users with generated assignments and explanatory materials visually.

[0163] The embodiments of the invention described herein provide a detailed configuration for realizing a system that provides an individually customized learning experience by recognizing the user's tendency to make incorrect answers and their emotional state.

[0164] Users take photos of incorrectly answered learning questions using a device such as a smartphone or tablet, and input the image data into the device via an application. The device then converts the acquired image data into text information using, for example, OCR (Optical Character Recognition) software, also known as character recognition technology. A concrete example of this would be the use of general-purpose OCR software.

[0165] The converted text information is sent from the terminal to the server. The server analyzes the received text information and records it in a database to identify the user's tendency to make incorrect answers. For example, analysis software is used for this analysis. The server also utilizes emotion recognition technologies such as an Emotion Engine to evaluate the user's emotional state. In this process, additional audio and video data from the terminal can be used to include the user's facial expressions and tone of voice in the analysis.

[0166] Based on the analysis results, the server generates review tasks that take into account the user's current state. If the emotional state indicates frustration, it generates relatively easy and engaging review tasks to encourage a sense of accomplishment. It can also select explanations and additional materials tailored to the user's interests, providing extra learning opportunities.

[0167] The generated assignments and materials are sent back from the server to the terminal and presented to the user through the terminal. The user can use these as a reference to progress with their learning and check their answers and feedback within the application. Furthermore, the system reports the user's learning progress and emotional state to educators and parents via the server, which is used to support learning.

[0168] As a concrete example, consider a scenario where a user incorrectly answers an English grammar question, takes a picture of the question, and uploads it. In this case, the server analyzes the image data to identify the pattern of incorrect answers, and if it determines that the user is showing signs of fatigue, it sets up a simple and engaging review question. An example of a prompt message for the generating AI model would be, "Generate a simple English grammar review question to present when the user looks tired."

[0169] This enables efficient and personalized learning support without causing excessive stress to the user.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] Users take photos of incorrectly answered questions with their smartphones or tablets and input the image data into their devices via the application. Specifically, the user uses the camera function to capture an image of the question, and the image data is saved to a designated folder within the application. This allows the user to input the visual information of the incorrectly answered question into their device in digital format.

[0173] Step 2:

[0174] The device converts the input image data into text data using optical character recognition (OCR) technology. The input for this step is image data captured by the user, and the OCR software processes the data by detecting and identifying characters within the image. As output, text data is generated and stored in the device's memory as a readable string.

[0175] Step 3:

[0176] The terminal sends the converted text data to the server. This involves converting image data into text information, encrypting that text data, and then transferring it to the server. The transmission to the server is performed using a secure communication protocol, protecting the user's data.

[0177] Step 4:

[0178] The server analyzes the received text data to identify the user's tendency to make incorrect answers. The input for this step is the text data sent from the terminal. As part of the data calculation, the server uses statistical methods to perform pattern recognition while referring to a database of past incorrect answers, and the output is information that identifies the user's tendency to make incorrect answers.

[0179] Step 5:

[0180] The server uses emotion recognition technology to analyze additional user data (video and audio) and evaluate their emotional state. The input for this step is the video and audio data provided additionally via the terminal. Specifically, the server inputs this data into the emotion analysis engine and generates information indicating the user's emotional state as output.

[0181] Step 6:

[0182] The server generates review tasks tailored to the user based on their error tendencies and emotional state. Using error tendency information and emotional state information as input, a generative AI model is used to create prompts and perform data calculations to generate appropriate tasks. The output is a personalized review task.

[0183] Step 7:

[0184] The server sends the generated review assignments to the terminal, which then displays them to the user. At this stage, the review assignments are converted into a user-friendly format and delivered to the terminal via secure communication. The user can then receive them and proceed with their learning.

[0185] Step 8:

[0186] Users work on review assignments while checking their answers and feedback. Specifically, users answer assignments within the application on their device and receive feedback on their results through a confirmation screen.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0189] While conventional learning support systems could analyze users' error tendencies, they struggled to adjust learning content to take into account the user's emotional state. Furthermore, providing an optimal learning experience for each individual user requires real-time analysis of their emotional state and the provision of review questions based on those results, but achieving this has been a challenge.

[0190] 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.

[0191] In this invention, the server includes a conversion means that acquires visual data via an input device and generates character data from the visual data using optical character recognition; an analysis means that analyzes the generated character data and identifies the user's tendency to make incorrect answers; and an adaptation means that identifies the analyzed emotional state and generates problems adapted to the user's emotions. This makes it possible to provide a customized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0192] An "input device" refers to hardware or software used to acquire visual data from an external source and incorporate it into the system.

[0193] Optical character recognition (OCR) is a technology that identifies characters contained within an image and converts them into character data.

[0194] "Conversion means" refers to a device or program that performs the process of converting visual data into text data.

[0195] "Analysis means" refers to a device or program for analyzing the user's tendency to make incorrect answers based on the generated character data.

[0196] "User" refers to anyone who uses this system to learn.

[0197] "Incorrect answer tendency" refers to data that shows the types of questions that users repeatedly get wrong and the tendencies behind those mistakes.

[0198] "Emotional state" refers to the user's emotional response or mental state at that particular moment.

[0199] An "adaptive measure" is a device or program that generates problems adapted to the user's emotions based on analyzed data.

[0200] "Presentation means" refers to a device or program for providing generated review questions or educational materials to users visually or audibly.

[0201] The term "educator" refers to an individual or organization responsible for providing education and guidance to users.

[0202] "Learning progress" refers to data that shows the level of understanding and achievement a user has made as they progress through their learning.

[0203] This invention is a system for analyzing a user's error tendencies and emotional state to provide a personalized learning experience. In this system, the terminal uses an input device to acquire visual data of the problems the user has solved. The acquired data is converted into text data using optical character recognition (OCR) software. In this conversion, Pytesseract OCR software is often used.

[0204] The converted text data is then sent to a server for analysis. The server uses analysis tools to identify the user's tendency to make incorrect answers from the text data. It also analyzes real-time emotional data of the user acquired using a camera and microphone, and identifies the emotional state using an emotion recognition engine such as Emotion Recognizer. Based on the analysis results, an adaptation tool generates review questions that match the user's emotional state.

[0205] The generated problems are provided to the user through a presentation method. This presentation utilizes devices such as smartphones and tablets, providing educational materials and explanations visually or audibly. Furthermore, learning progress is reported to educators, enabling them to support the user's learning.

[0206] As a concrete example, suppose a user solves a math division problem and makes a mistake. The user takes a picture of the image with their device and uploads it to the system. If the camera detects that the user's facial expression indicates anxiety, the server, using its emotion recognition engine, generates and provides a simpler division problem to alleviate the anxiety. Then, it gradually moves the user to problems that improve their problem-solving skills. In this way, problems are provided that are tailored to the user's emotions and learning needs.

[0207] An example of a prompt message for a generative AI model might be: "The user's emotional state has been identified as anxious. Based on the incorrect answers and emotional state, please generate a math division problem that is easy but gradually increases in difficulty."

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

[0209] Step 1:

[0210] The terminal uses its camera, which is an input device, to capture images of questions that the user answered incorrectly. These images are incorporated into the system as visual data. The captured image of the question is obtained as input and is used for subsequent processing.

[0211] Step 2:

[0212] The device uses optical character recognition (OCR) software to convert acquired visual data into text data. Specifically, it uses OCR technology such as Pytesseract to recognize characters in an image and generate text data. The input is the image data obtained in step 1, and the output is text data.

[0213] Step 3:

[0214] The terminal sends the generated text data to the server. The server receives this text data as input and uses analysis tools to identify the user's tendency to make incorrect answers. Specifically, it refers to past incorrect answer data and other problem databases and performs data analysis to identify incorrect answer patterns. The output is data on the tendency to make incorrect answers.

[0215] Step 4:

[0216] The device acquires the user's emotional state using a camera and microphone and sends that data to a server. The server uses an emotion recognition engine (e.g., Emotion Recognizer) to identify the user's emotional state from the input audio and video data. The input is audio and facial expression data, and the output is the analyzed emotional state.

[0217] Step 5:

[0218] The server uses adaptive mechanisms to generate review questions tailored to the user, based on error tendency data and emotional state data. Here, a generative AI model is utilized to assemble an appropriate set of questions. Prompts may also be used to instruct the AI ​​to present questions in a way that suits it. The output consists of customized questions.

[0219] Step 6:

[0220] The server sends the generated questions and explanations back to the terminal. The terminal then presents this to the user, specifically displaying educational materials and explanations on the screen, and providing them in audio format as needed. The input is the questions and materials obtained in step 5, and the output is presentation via visual and auditory means.

[0221] Step 7:

[0222] The terminal sends the user's learning progress to the server. The progress data obtained here is reported to the educator, thereby promoting support for the user's learning. The server receives the progress information as input, generates a report for the educator, and outputs it.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] The learning support system of the present invention is designed to efficiently review questions that the user answered incorrectly and to improve learning efficiency.

[0240] First, the user uses a device with a dedicated application installed. The user inputs the incorrectly answered question by taking a picture or screenshot of it with their smartphone or tablet, thereby creating image data. The device receives this image data and uses optical character recognition (OCR) technology to generate text data from the image data containing character information. The system is designed to accurately identify characters and, if necessary, process mathematical formulas and diagrams as well.

[0241] The generated text data is sent from the terminal to the server. The server analyzes the received text data and uses machine learning algorithms to identify the user's error patterns and common mistakes. By referring to the user's past learning data and data from other users, the server gains a more accurate understanding of the causes of errors.

[0242] Based on the analysis results, the server generates original review questions to aid the user's learning. Educational technology and problem design theory are applied to this question generation process to ensure the questions are of appropriate difficulty and deepen the user's understanding. The server also generates explanations for incorrect answers and related learning materials (such as links to lecture videos).

[0243] These generated materials and problems are sent to the device and made available to the user within the application. Users can re-solve the problems within the app and progress through their learning while reviewing the explanations. Data such as progress and accuracy rates are also recorded and reported to teachers or parents as needed.

[0244] For example, if a user makes a mistake on a quadratic function problem in a math test, the server will generate review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user. As a result, the user can learn based on their own tendencies for making mistakes, and receive support to deepen their understanding in a short period of time.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0248] Step 2:

[0249] The device performs optical character recognition (OCR) on the received image data, converting the text information within the image into text data. During this process, it ensures accurate conversion even if mathematical formulas or special symbols are included.

[0250] Step 3:

[0251] The terminal structures the generated text data, adds metadata such as subject, question type, and difficulty level, and sends it to the server.

[0252] Step 4:

[0253] The server analyzes the received text data and metadata, using an AI algorithm to identify characteristics and patterns of user errors. Past training data is also referenced to extract the causes of errors.

[0254] Step 5:

[0255] Based on the analysis results, the server automatically generates review questions tailored to the user's weak areas. These questions are adjusted to an appropriate difficulty level and content according to the user's understanding. Explanatory text and related learning materials are also generated simultaneously.

[0256] Step 6:

[0257] The server sends generated problems, explanations, and learning materials to the user's device. This allows the user to view these within the application and progress through their learning.

[0258] Step 7:

[0259] Users work on review questions and record their results within the application. The device feeds back the user's answers and progress as data to the server, which is then used to further support their learning.

[0260] (Example 1)

[0261] 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."

[0262] There is a need for a system that allows individual learners to efficiently review the areas where they made mistakes and improve their academic ability in a short period of time. However, current learning support technologies lack the functionality to accurately analyze learners' error patterns and automatically generate appropriate review questions based on that analysis. Furthermore, there is no system in place to properly manage learners' progress and allow teachers and parents to easily access that information.

[0263] 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.

[0264] In this invention, the server includes means for acquiring image information of test questions answered incorrectly by the user via an input medium; processing means for generating character information from the image information using optical character conversion; analysis means for analyzing the generated character information and identifying the user's error patterns; question generation means for generating review questions optimized for the user based on the identified error patterns; a display medium for providing the generated review questions, explanations, and learning materials to the user; and recording and reporting means for recording the user's learning progress and correct answer rate and notifying the user, teacher, or guardian. This enables effective review tailored to the needs of each learner, improving learning efficiency and facilitating the appropriate sharing of progress information.

[0265] "Input medium" refers to devices and methods for transmitting information from a user to a system, and in particular includes cameras and scanners for acquiring image information.

[0266] "Optical character conversion" refers to a technology for converting image information into text information, primarily using optical character recognition (OCR) to generate text data from image data.

[0267] "Processing means" refers to devices or algorithms that perform the process of analyzing input image information and converting it into text information.

[0268] "Analysis means" refers to technologies and devices used to analyze generated textual information and identify patterns of incorrect answers made by users, and includes machine learning algorithms, etc.

[0269] "Problem generation means" refers to a device or algorithm that automatically generates review questions optimized to maximize educational effectiveness based on the user's error patterns.

[0270] "Display medium" refers to devices and systems used to provide and display generated review questions, explanations, and learning materials to users, and this particularly includes displays and mobile devices.

[0271] "Recording and reporting means" refers to devices or software that have the function of saving the user's learning progress and correct answer rate, and notifying the user themselves, or, if necessary, teachers or guardians, of this information.

[0272] To implement this invention, the user begins by using a device with a dedicated application installed to take a picture of an incorrectly answered test question or capture an image of the question via a screenshot. The device then converts this image information into text information using optical character recognition (OCR), a type of optical character conversion technology. Specific examples of such technologies include Tesseract and cloud-based OCR services.

[0273] The terminal then sends the generated text information to the server. The server uses a machine learning algorithm to analyze this text information and identify the user's error patterns. The server then uses a generative AI model to generate review questions tailored to the user's needs, referencing past training data and other users' error records. This process applies theories from educational technology and problem design, aiming to deepen understanding at an appropriate difficulty level.

[0274] In addition, the server generates explanations for the user's incorrect answers and related learning materials, and sends them to the terminal. The terminal displays the generated review questions and learning materials within the application, allowing the user to continue their learning through them.

[0275] For example, if a user makes a mistake on a quadratic function problem in a math test, the server generates review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user, and provides them as learning material. As a result, users can effectively review based on their individual error patterns, supporting a deeper understanding in a short period of time.

[0276] An example of a prompt message for a generating AI model is: "I made a mistake in reading the graph of a quadratic function. Please generate review questions specifically for my weak areas. Please also refer to past incorrect answer data and add explanations to deepen my understanding."

[0277] Thus, this invention is a system that provides customized learning support based on each user's tendency to make mistakes, thereby improving learning efficiency.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] Users take photos or screenshots of incorrectly answered exam questions using a smartphone, tablet, or other device. The question data is then entered as image information. Users must ensure the question is clearly visible in the image.

[0281] Step 2:

[0282] The terminal uses OCR software to generate character information from the acquired image information. In this process, image data is input and character data is output. For example, by using Tesseract, operations are performed to identify data including characters and formulas as text.

[0283] Step 3:

[0284] The terminal sends the generated character data to the server. The input here is character data, and the output is notification information indicating the establishment of communication with the server and the completion of data transmission. The terminal uses a protocol such as HTTPS for secure data communication.

[0285] Step 4:

[0286] The server analyzes the received character data using a machine learning algorithm to identify the user's incorrect answer patterns. The input is the transmitted character data, and the output is the pattern information of incorrect answers. Analytical calculations are also performed by referring to past learning histories and other user data.

[0287] Step 5:

[0288] The server uses the generated AI model to create review questions and explanations based on the incorrect answer patterns. The input in this step is the incorrect answer pattern information, and the output is the generated review questions and explanatory materials. Optimal questions and answers are designed based on the theory of educational engineering.

[0289] Step 6:

[0290] The server sends the generated review questions and explanatory materials to the terminal. The input is the review questions and explanatory materials, and the output is the state indicating that these data have been transferred to the terminal. The terminal displays them through an interface that is easy for the user to learn.

[0291] Step 7:

[0292] Users solve review problems provided through their devices and deepen their understanding by checking the explanations. Input consists of problems and materials displayed on the device, while output consists of the user's answers and progress data for review. The system records the user's learning progress and reports it to educators and parents as needed.

[0293] (Application Example 1)

[0294] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0295] Traditional learning support systems have faced challenges in efficiently reviewing incorrect answers and addressing individual learning needs. Furthermore, they lacked dynamic learning support utilizing audio and visual feedback, making it difficult to provide users with the optimal educational experience. Additionally, teachers and parents had limited information to track users' learning progress and provide appropriate support.

[0296] 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.

[0297] In this invention, the server includes a processing device that acquires visual data via an input device and generates character information from the visual data using optical character recognition; an analysis device that analyzes the generated character information and identifies the user's error patterns; a task generation device that generates review tasks suitable for the user based on the identified error patterns; a display device that provides the generated review tasks to the user and provides explanations and educational materials; and a support device that provides additional learning support to the user using audio or visual feedback. This enables users to review optimally according to their individual error tendencies and enjoy an intuitive learning experience through audio and visual feedback. Furthermore, it enables more effective educational support by providing educators with progress information for each user and creating individually optimized prompt sentences using a generation AI model.

[0298] The "input device" is a device for acquiring visual data, such as a camera or a scanner.

[0299] "Visual data" refers to data containing visual information such as images and videos, which is acquired by an input device.

[0300] "Optical character recognition" is a technology for extracting character information from image data and converting it into text data.

[0301] The "processing device" is a computer unit for converting visual data into character information and executing an optical character recognition process.

[0302] "Character information" is text data generated by optical character recognition.

[0303] The "analysis device" is a computer unit for analyzing the user's wrong answer pattern based on the generated character information.

[0304] The "wrong answer pattern" refers to the tendency and characteristics when the user answers a question incorrectly.

[0305] The "problem generation device" is a computer unit for creating suitable review problems based on the user's wrong answer pattern.

[0306] A "problem" refers to questions or exercises presented to the user to assist learning.

[0307] The "display device" is a device for visually or auditorily providing the generated review problems, explanations, and educational materials to the user.

[0308] "Voice feedback" is a technology for supplementing or guiding learning content to the user through voice.

[0309] "Visual feedback" is a technique that supplements or instructs users on learning content through visual information.

[0310] A "support device" is a device that provides additional learning support, such as audio or visual feedback.

[0311] To realize this invention, the system is configured as follows: First, the user takes a picture of a problem on paper using an input device, such as a tablet with a camera. The captured visual data is collected by the terminal and converted into text information by optical character recognition software, such as an OCR engine like Tesseract. Through this process, the visual data becomes digital text.

[0312] Next, the server receives the processed character information and analyzes the error patterns. The analysis device uses machine learning algorithms to analyze the user's past answer data and similar data from other users. In this phase, machine learning libraries such as scikit-learn are utilized to identify the user's learning needs based on the error patterns.

[0313] Based on identified error patterns, the server uses a task generator to create personalized review tasks for each user. These tasks include questions designed to reinforce areas where the user frequently makes mistakes, as well as exercises to deepen understanding. The generated tasks, explanations, and related educational materials are provided to the user via the terminal's display device.

[0314] Furthermore, the support device utilizes audio and visual feedback to provide additional learning support to the user. Users can systematically progress through learning while receiving feedback from support devices such as robots.

[0315] For example, if a child mispronounces a particular word while doing their English homework, this system can provide additional practice exercises to reinforce that word. Using a generative AI model, it's possible to provide prompts such as, "Please pronounce the following word correctly: 'develop'."

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] The user takes a picture of their homework or problem using an input device. The input is visual data, which is captured by the terminal. The captured visual data is then prepared for further processing.

[0319] Step 2:

[0320] The device uses optical character recognition (OCR) technology to generate character information from the captured visual data. In this step, the visual data is converted into text data, and the character information recognized by the OCR engine is output.

[0321] Step 3:

[0322] The terminal sends the generated character information to the server. The server receives this character information and begins analysis. The input is text data, and the output is the identification of incorrect answer patterns.

[0323] Step 4:

[0324] The server uses a machine learning model to analyze user error patterns. It compares past answers with data from other similar users to identify error trends. The input consists of text data and past learning history data, and the output is the user's error patterns.

[0325] Step 5:

[0326] Based on identified incorrect answer patterns, the server generates review tasks suitable for the user using a task generation device. The input is the incorrect answer patterns, and the output is the review tasks and explanations.

[0327] Step 6:

[0328] The generated review assignments and explanations are sent to the terminal and provided to the user via a display device. The input here is the review assignments and explanations, and the output is presented visually or audibly.

[0329] Step 7:

[0330] The terminal or assistive device provides the user with additional learning support using audio or visual feedback. Specifically, it provides audio guidance on how to solve problems or the correct pronunciation of incorrect words. The input for this step is audio instructions or visual data, and the output is direct educational support for the user.

[0331] Step 8:

[0332] Ultimately, a generative AI model is used to optimize prompts for the user. For example, it provides dynamic instructions such as, "Please pronounce the following word correctly: 'develop'." Based on the input, feedback tailored to the user's needs is output.

[0333] 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.

[0334] The learning support system of the present invention aims to analyze the user's tendency to make incorrect answers, recognize the user's emotional state, and provide an appropriate learning experience based on that.

[0335] First, the user takes a picture of the question they answered incorrectly with their smartphone or tablet and inputs it as image data into the device through the application. The device then uses optical character recognition (OCR) technology to convert this image into text data. This text data is sent to a server and used to analyze the user's answering patterns.

[0336] The server utilizes an emotion engine to recognize the user's emotional state when analyzing received text data. Emotion recognition uses cameras and voice input to analyze the user's facial expressions, reactions, and tone of voice to extract emotional data. By combining emotional data with information on error tendencies, a deep understanding of each user's learning needs can be obtained.

[0337] Based on the analysis results, the server generates review questions that take into account the user's emotional state. For example, if the user is feeling frustrated, it will present relatively easy questions to give them a sense of accomplishment and increase their motivation to learn. It can also customize and provide explanations and learning materials based on the user's interests and concerns.

[0338] The generated problems and materials are provided to the user via their device. The user then proceeds with their learning based on these materials and checks their answers and feedback within the application. Furthermore, learning progress and emotional states are reported to teachers and parents, helping to deepen their understanding.

[0339] As a concrete example, suppose a user incorrectly answers an English grammar question and uploads a photo of the answer to the app. If the server detects that the user is fatigued, it will generate a slightly easier, more engaging review question. This allows the user to continue learning without feeling excessively stressed. Through such a mechanism, it becomes possible to provide more personalized learning support.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0343] Step 2:

[0344] The device receives image data and uses Optical Character Recognition (OCR) to convert the text information within the image into text data. During this process, the accuracy of character recognition is improved by correcting the image resolution and brightness.

[0345] Step 3:

[0346] The device sends the converted text data, along with user facial expression and audio data obtained during the capture, to the server. This data is used to identify the user's emotional state.

[0347] Step 4:

[0348] The server analyzes the received text data and uses an AI algorithm to identify patterns in the user's incorrect responses. Simultaneously, an emotion engine analyzes facial expression and voice data to recognize the user's emotional state (e.g., concentration, fatigue, frustration).

[0349] Step 5:

[0350] The server combines data on incorrect answer patterns and emotional states to generate review questions tailored to the user. For example, if a user is feeling fatigued, the server will either lower the difficulty level of the questions or create questions with more engaging content. It will also select appropriate explanations and reference materials to stimulate the user's motivation to learn.

[0351] Step 6:

[0352] The server sends the generated review questions and explanatory materials to the terminal. The terminal displays these within the application, taking care to ensure that the user can understand them intuitively.

[0353] Step 7:

[0354] Users solve the provided problems, review the explanations, and progress through their learning. Throughout this process, the user's facial expressions and reactions are continuously collected on the device and sent to the server as feedback. Data on learning progress and emotional state is also accumulated and used to support future learning.

[0355] (Example 2)

[0356] 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".

[0357] Conventional learning support systems lack sufficient analysis and response capabilities for user errors, making it difficult to provide a learning experience tailored to individual learners. Furthermore, a learning environment that disregards the user's emotional state can lead to decreased motivation and increased stress. There is a need to solve these problems and provide more effective and personalized learning support.

[0358] 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.

[0359] In this invention, the server includes means for acquiring image information via an input device, means for generating character information from the image information using character recognition technology, means for analyzing the generated character information to identify the user's tendency to make incorrect answers, means for generating review tasks suitable for the user based on the identified tendency to make incorrect answers, means for recognizing the user's emotional state and providing an appropriate learning experience, and means for providing the generated review tasks to the user and providing explanations and learning materials. This makes it possible to provide a more appropriate and personalized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0360] An "input device" is a general term for hardware or software used to acquire image information from a user as digital data.

[0361] "Character recognition technology" is a technology that extracts character information from image information and converts it into digital text.

[0362] A "processing device" is a device that analyzes input information and performs processing according to its purpose.

[0363] An "analysis device" is a device that analyzes collected data and identifies patterns and trends.

[0364] A "task generation device" is a device that creates review tasks tailored to the user based on identified trends in incorrect answers.

[0365] An "emotion analysis device" is a device that recognizes the user's emotional state and provides the necessary information to offer an appropriate learning experience.

[0366] A "display device" is a device that provides users with generated assignments and explanatory materials visually.

[0367] The embodiments of the invention described herein provide a detailed configuration for realizing a system that provides an individually customized learning experience by recognizing the user's tendency to make incorrect answers and their emotional state.

[0368] Users take photos of incorrectly answered learning questions using a device such as a smartphone or tablet, and input the image data into the device via an application. The device then converts the acquired image data into text information using, for example, OCR (Optical Character Recognition) software, also known as character recognition technology. A concrete example of this would be the use of general-purpose OCR software.

[0369] The converted text information is sent from the terminal to the server. The server analyzes the received text information and records it in a database to identify the user's tendency to make incorrect answers. For example, analysis software is used for this analysis. The server also utilizes emotion recognition technologies such as an Emotion Engine to evaluate the user's emotional state. In this process, additional audio and video data from the terminal can be used to include the user's facial expressions and tone of voice in the analysis.

[0370] Based on the analysis results, the server generates review tasks that take into account the user's current state. If the emotional state indicates frustration, it generates relatively easy and engaging review tasks to encourage a sense of accomplishment. It can also select explanations and additional materials tailored to the user's interests, providing extra learning opportunities.

[0371] The generated assignments and materials are sent back from the server to the terminal and presented to the user through the terminal. The user can use these as a reference to progress with their learning and check their answers and feedback within the application. Furthermore, the system reports the user's learning progress and emotional state to educators and parents via the server, which is used to support learning.

[0372] As a concrete example, consider a scenario where a user incorrectly answers an English grammar question, takes a picture of the question, and uploads it. In this case, the server analyzes the image data to identify the pattern of incorrect answers, and if it determines that the user is showing signs of fatigue, it sets up a simple and engaging review question. An example of a prompt message for the generating AI model would be, "Generate a simple English grammar review question to present when the user looks tired."

[0373] This enables efficient and personalized learning support without causing excessive stress to the user.

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1:

[0376] Users take photos of incorrectly answered questions with their smartphones or tablets and input the image data into their devices via the application. Specifically, the user uses the camera function to capture an image of the question, and the image data is saved to a designated folder within the application. This allows the user to input the visual information of the incorrectly answered question into their device in digital format.

[0377] Step 2:

[0378] The device converts the input image data into text data using optical character recognition (OCR) technology. The input for this step is image data captured by the user, and the OCR software processes the data by detecting and identifying characters within the image. As output, text data is generated and stored in the device's memory as a readable string.

[0379] Step 3:

[0380] The terminal sends the converted text data to the server. This involves converting image data into text information, encrypting that text data, and then transferring it to the server. The transmission to the server is performed using a secure communication protocol, protecting the user's data.

[0381] Step 4:

[0382] The server analyzes the received text data to identify the user's tendency to make incorrect answers. The input for this step is the text data sent from the terminal. As part of the data calculation, the server uses statistical methods to perform pattern recognition while referring to a database of past incorrect answers, and the output is information that identifies the user's tendency to make incorrect answers.

[0383] Step 5:

[0384] The server uses emotion recognition technology to analyze additional user data (video and audio) and evaluate their emotional state. The input for this step is the video and audio data provided additionally via the terminal. Specifically, the server inputs this data into the emotion analysis engine and generates information indicating the user's emotional state as output.

[0385] Step 6:

[0386] The server generates review tasks tailored to the user based on their error tendencies and emotional state. Using error tendency information and emotional state information as input, a generative AI model is used to create prompts and perform data calculations to generate appropriate tasks. The output is a personalized review task.

[0387] Step 7:

[0388] The server sends the generated review assignments to the terminal, which then displays them to the user. At this stage, the review assignments are converted into a user-friendly format and delivered to the terminal via secure communication. The user can then receive them and proceed with their learning.

[0389] Step 8:

[0390] Users work on review assignments while checking their answers and feedback. Specifically, users answer assignments within the application on their device and receive feedback on their results through a confirmation screen.

[0391] (Application Example 2)

[0392] 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."

[0393] While conventional learning support systems could analyze users' error tendencies, they struggled to adjust learning content to take into account the user's emotional state. Furthermore, providing an optimal learning experience for each individual user requires real-time analysis of their emotional state and the provision of review questions based on those results, but achieving this has been a challenge.

[0394] 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.

[0395] In this invention, the server includes a conversion means that acquires visual data via an input device and generates character data from the visual data using optical character recognition; an analysis means that analyzes the generated character data and identifies the user's tendency to make incorrect answers; and an adaptation means that identifies the analyzed emotional state and generates problems adapted to the user's emotions. This makes it possible to provide a customized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0396] An "input device" refers to hardware or software used to acquire visual data from an external source and incorporate it into the system.

[0397] Optical character recognition (OCR) is a technology that identifies characters contained within an image and converts them into character data.

[0398] "Conversion means" refers to a device or program that performs the process of converting visual data into text data.

[0399] "Analysis means" refers to a device or program for analyzing the user's tendency to make incorrect answers based on the generated character data.

[0400] "User" refers to anyone who uses this system to learn.

[0401] "Incorrect answer tendency" refers to data that shows the types of questions that users repeatedly get wrong and the tendencies behind those mistakes.

[0402] "Emotional state" refers to the user's emotional response or mental state at that particular moment.

[0403] An "adaptive measure" is a device or program that generates problems adapted to the user's emotions based on analyzed data.

[0404] "Presentation means" refers to a device or program for providing generated review questions or educational materials to users visually or audibly.

[0405] The term "educator" refers to an individual or organization responsible for providing education and guidance to users.

[0406] "Learning progress" refers to data that shows the level of understanding and achievement a user has made as they progress through their learning.

[0407] This invention is a system for analyzing a user's error tendencies and emotional state to provide a personalized learning experience. In this system, the terminal uses an input device to acquire visual data of the problems the user has solved. The acquired data is converted into text data using optical character recognition (OCR) software. In this conversion, Pytesseract OCR software is often used.

[0408] The converted text data is then sent to a server for analysis. The server uses analysis tools to identify the user's tendency to make incorrect answers from the text data. It also analyzes real-time emotional data of the user acquired using a camera and microphone, and identifies the emotional state using an emotion recognition engine such as Emotion Recognizer. Based on the analysis results, an adaptation tool generates review questions that match the user's emotional state.

[0409] The generated problems are provided to the user through a presentation method. This presentation utilizes devices such as smartphones and tablets, providing educational materials and explanations visually or audibly. Furthermore, learning progress is reported to educators, enabling them to support the user's learning.

[0410] As a concrete example, suppose a user solves a math division problem and makes a mistake. The user takes a picture of the image with their device and uploads it to the system. If the camera detects that the user's facial expression indicates anxiety, the server, using its emotion recognition engine, generates and provides a simpler division problem to alleviate the anxiety. Then, it gradually moves the user to problems that improve their problem-solving skills. In this way, problems are provided that are tailored to the user's emotions and learning needs.

[0411] An example of a prompt message for a generative AI model might be: "The user's emotional state has been identified as anxious. Based on the incorrect answers and emotional state, please generate a math division problem that is easy but gradually increases in difficulty."

[0412] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0413] Step 1:

[0414] The terminal uses its camera, which is an input device, to capture images of questions that the user answered incorrectly. These images are incorporated into the system as visual data. The captured image of the question is obtained as input and is used for subsequent processing.

[0415] Step 2:

[0416] The device uses optical character recognition (OCR) software to convert acquired visual data into text data. Specifically, it uses OCR technology such as Pytesseract to recognize characters in an image and generate text data. The input is the image data obtained in step 1, and the output is text data.

[0417] Step 3:

[0418] The terminal sends the generated text data to the server. The server receives this text data as input and uses analysis tools to identify the user's tendency to make incorrect answers. Specifically, it refers to past incorrect answer data and other problem databases and performs data analysis to identify incorrect answer patterns. The output is data on the tendency to make incorrect answers.

[0419] Step 4:

[0420] The device acquires the user's emotional state using a camera and microphone and sends that data to a server. The server uses an emotion recognition engine (e.g., Emotion Recognizer) to identify the user's emotional state from the input audio and video data. The input is audio and facial expression data, and the output is the analyzed emotional state.

[0421] Step 5:

[0422] The server uses adaptive mechanisms to generate review questions tailored to the user, based on error tendency data and emotional state data. Here, a generative AI model is utilized to assemble an appropriate set of questions. Prompts may also be used to instruct the AI ​​to present questions in a way that suits it. The output consists of customized questions.

[0423] Step 6:

[0424] The server sends the generated questions and explanations back to the terminal. The terminal then presents this to the user, specifically displaying educational materials and explanations on the screen, and providing them in audio format as needed. The input is the questions and materials obtained in step 5, and the output is presentation via visual and auditory means.

[0425] Step 7:

[0426] The terminal sends the user's learning progress to the server. The progress data obtained here is reported to the educator, thereby promoting support for the user's learning. The server receives the progress information as input, generates a report for the educator, and outputs it.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] [Third Embodiment]

[0431] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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".

[0443] The learning support system of the present invention is designed to efficiently review questions that the user answered incorrectly and to improve learning efficiency.

[0444] First, the user uses a device with a dedicated application installed. The user inputs the incorrectly answered question by taking a picture or screenshot of it with their smartphone or tablet, thereby creating image data. The device receives this image data and uses optical character recognition (OCR) technology to generate text data from the image data containing character information. The system is designed to accurately identify characters and, if necessary, process mathematical formulas and diagrams as well.

[0445] The generated text data is sent from the terminal to the server. The server analyzes the received text data and uses machine learning algorithms to identify the user's error patterns and common mistakes. By referring to the user's past learning data and data from other users, the server gains a more accurate understanding of the causes of errors.

[0446] Based on the analysis results, the server generates original review questions to aid the user's learning. Educational technology and problem design theory are applied to this question generation process to ensure the questions are of appropriate difficulty and deepen the user's understanding. The server also generates explanations for incorrect answers and related learning materials (such as links to lecture videos).

[0447] These generated materials and problems are sent to the device and made available to the user within the application. Users can re-solve the problems within the app and progress through their learning while reviewing the explanations. Data such as progress and accuracy rates are also recorded and reported to teachers or parents as needed.

[0448] For example, if a user makes a mistake on a quadratic function problem in a math test, the server will generate review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user. As a result, the user can learn based on their own tendencies for making mistakes, and receive support to deepen their understanding in a short period of time.

[0449] The following describes the processing flow.

[0450] Step 1:

[0451] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0452] Step 2:

[0453] The device performs optical character recognition (OCR) on the received image data, converting the text information within the image into text data. During this process, it ensures accurate conversion even if mathematical formulas or special symbols are included.

[0454] Step 3:

[0455] The terminal structures the generated text data, adds metadata such as subject, question type, and difficulty level, and sends it to the server.

[0456] Step 4:

[0457] The server analyzes the received text data and metadata, using an AI algorithm to identify characteristics and patterns of user errors. Past training data is also referenced to extract the causes of errors.

[0458] Step 5:

[0459] Based on the analysis results, the server automatically generates review questions tailored to the user's weak areas. These questions are adjusted to an appropriate difficulty level and content according to the user's understanding. Explanatory text and related learning materials are also generated simultaneously.

[0460] Step 6:

[0461] The server sends generated problems, explanations, and learning materials to the user's device. This allows the user to view these within the application and progress through their learning.

[0462] Step 7:

[0463] Users work on review questions and record their results within the application. The device feeds back the user's answers and progress as data to the server, which is then used to further support their learning.

[0464] (Example 1)

[0465] 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."

[0466] There is a need for a system that allows individual learners to efficiently review the areas where they made mistakes and improve their academic ability in a short period of time. However, current learning support technologies lack the functionality to accurately analyze learners' error patterns and automatically generate appropriate review questions based on that analysis. Furthermore, there is no system in place to properly manage learners' progress and allow teachers and parents to easily access that information.

[0467] 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.

[0468] In this invention, the server includes means for acquiring image information of test questions answered incorrectly by the user via an input medium; processing means for generating character information from the image information using optical character conversion; analysis means for analyzing the generated character information and identifying the user's error patterns; question generation means for generating review questions optimized for the user based on the identified error patterns; a display medium for providing the generated review questions, explanations, and learning materials to the user; and recording and reporting means for recording the user's learning progress and correct answer rate and notifying the user, teacher, or guardian. This enables effective review tailored to the needs of each learner, improving learning efficiency and facilitating the appropriate sharing of progress information.

[0469] "Input medium" refers to devices and methods for transmitting information from a user to a system, and in particular includes cameras and scanners for acquiring image information.

[0470] "Optical character conversion" refers to a technology for converting image information into text information, primarily using optical character recognition (OCR) to generate text data from image data.

[0471] "Processing means" refers to devices or algorithms that perform the process of analyzing input image information and converting it into text information.

[0472] "Analysis means" refers to technologies and devices used to analyze generated textual information and identify patterns of incorrect answers made by users, and includes machine learning algorithms, etc.

[0473] "Problem generation means" refers to a device or algorithm that automatically generates review questions optimized to maximize educational effectiveness based on the user's error patterns.

[0474] "Display medium" refers to devices and systems used to provide and display generated review questions, explanations, and learning materials to users, and this particularly includes displays and mobile devices.

[0475] "Recording and reporting means" refers to devices or software that have the function of saving the user's learning progress and correct answer rate, and notifying the user themselves, or, if necessary, teachers or guardians, of this information.

[0476] To implement this invention, the user begins by using a device with a dedicated application installed to take a picture of an incorrectly answered test question or capture an image of the question via a screenshot. The device then converts this image information into text information using optical character recognition (OCR), a type of optical character conversion technology. Specific examples of such technologies include Tesseract and cloud-based OCR services.

[0477] The terminal then sends the generated text information to the server. The server uses a machine learning algorithm to analyze this text information and identify the user's error patterns. The server then uses a generative AI model to generate review questions tailored to the user's needs, referencing past training data and other users' error records. This process applies theories from educational technology and problem design, aiming to deepen understanding at an appropriate difficulty level.

[0478] In addition, the server generates explanations for the user's incorrect answers and related learning materials, and sends them to the terminal. The terminal displays the generated review questions and learning materials within the application, allowing the user to continue their learning through them.

[0479] For example, if a user makes a mistake on a quadratic function problem in a math test, the server generates review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user, and provides them as learning material. As a result, users can effectively review based on their individual error patterns, supporting a deeper understanding in a short period of time.

[0480] An example of a prompt message for a generating AI model is: "I made a mistake in reading the graph of a quadratic function. Please generate review questions specifically for my weak areas. Please also refer to past incorrect answer data and add explanations to deepen my understanding."

[0481] Thus, this invention is a system that provides customized learning support based on each user's tendency to make mistakes, thereby improving learning efficiency.

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] Users take photos or screenshots of incorrectly answered exam questions using a smartphone, tablet, or other device. The question data is then entered as image information. Users must ensure the question is clearly visible in the image.

[0485] Step 2:

[0486] The terminal uses OCR software to generate text information from acquired image information. In this process, image data is input and text data is output. For example, Tesseract is used to perform calculations to identify data containing characters and mathematical formulas as text.

[0487] Step 3:

[0488] The terminal sends the generated character data to the server. The input here is character data, and the output is notification information indicating that communication with the server has been established and data has been sent. The terminal uses protocols such as HTTPS to ensure secure data communication.

[0489] Step 4:

[0490] The server analyzes the received text data using a machine learning algorithm to identify patterns in the user's incorrect responses. The input is the transmitted text data, and the output is information about the incorrect response patterns. The analysis calculations are performed by referring to past learning history and other user data.

[0491] Step 5:

[0492] The server uses a generative AI model to create review questions and explanations based on incorrect answer patterns. The input in this step is incorrect answer pattern information, and the output is the generated review questions and explanation materials. Optimal questions and answers are designed based on educational technology theory.

[0493] Step 6:

[0494] The server sends the generated review questions and explanatory materials to the terminal. The input is the review questions and explanatory materials, and the output is the state in which this data has been transferred to the terminal. The terminal displays the information through a user-friendly interface.

[0495] Step 7:

[0496] Users solve review problems provided through their devices and deepen their understanding by checking the explanations. Input consists of problems and materials displayed on the device, while output consists of the user's answers and progress data for review. The system records the user's learning progress and reports it to educators and parents as needed.

[0497] (Application Example 1)

[0498] 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."

[0499] Traditional learning support systems have faced challenges in efficiently reviewing incorrect answers and addressing individual learning needs. Furthermore, they lacked dynamic learning support utilizing audio and visual feedback, making it difficult to provide users with the optimal educational experience. Additionally, teachers and parents had limited information to track users' learning progress and provide appropriate support.

[0500] 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.

[0501] In this invention, the server includes a processing device that acquires visual data via an input device and generates character information from the visual data using optical character recognition; an analysis device that analyzes the generated character information and identifies the user's error patterns; a task generation device that generates review tasks suitable for the user based on the identified error patterns; a display device that provides the generated review tasks to the user and provides explanations and educational materials; and a support device that provides additional learning support to the user using audio or visual feedback. This enables users to review optimally according to their individual error tendencies and enjoy an intuitive learning experience through audio and visual feedback. Furthermore, it enables more effective educational support by providing educators with progress information for each user and creating individually optimized prompt sentences using a generation AI model.

[0502] An "input device" is a device used to acquire visual data, such as a camera or scanner.

[0503] "Visual data" refers to data that includes visual information, such as images and videos, and is acquired by an input device.

[0504] Optical character recognition (OCR) is a technology that extracts character information from image data and converts it into text data.

[0505] A "processing unit" is a computer unit that converts visual data into textual information and performs the optical character recognition process.

[0506] "Character information" refers to text data generated by optical character recognition.

[0507] An "analysis device" is a computer unit that analyzes the user's error patterns based on the generated character information.

[0508] "Incorrect answer patterns" refer to the tendencies and characteristics of how users answer questions incorrectly.

[0509] A "task generation device" is a computer unit that creates appropriate review tasks based on the user's error patterns.

[0510] "Assignments" refer to problems or exercises presented to users to support their learning.

[0511] A "display device" is a device that provides users with generated review assignments, explanations, and educational materials visually or audibly.

[0512] "Voice feedback" is a technology that provides supplementary information or guidance to users through audio.

[0513] "Visual feedback" is a technique that supplements or instructs users on learning content through visual information.

[0514] A "support device" is a device that provides additional learning support, such as audio or visual feedback.

[0515] To realize this invention, the system is configured as follows: First, the user takes a picture of a problem on paper using an input device, such as a tablet with a camera. The captured visual data is collected by the terminal and converted into text information by optical character recognition software, such as an OCR engine like Tesseract. Through this process, the visual data becomes digital text.

[0516] Next, the server receives the processed character information and analyzes the error patterns. The analysis device uses machine learning algorithms to analyze the user's past answer data and similar data from other users. In this phase, machine learning libraries such as scikit-learn are utilized to identify the user's learning needs based on the error patterns.

[0517] Based on identified error patterns, the server uses a task generator to create personalized review tasks for each user. These tasks include questions designed to reinforce areas where the user frequently makes mistakes, as well as exercises to deepen understanding. The generated tasks, explanations, and related educational materials are provided to the user via the terminal's display device.

[0518] Furthermore, the support device utilizes audio and visual feedback to provide additional learning support to the user. Users can systematically progress through learning while receiving feedback from support devices such as robots.

[0519] For example, if a child mispronounces a particular word while doing their English homework, this system can provide additional practice exercises to reinforce that word. Using a generative AI model, it's possible to provide prompts such as, "Please pronounce the following word correctly: 'develop'."

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

[0521] Step 1:

[0522] The user takes a picture of their homework or problem using an input device. The input is visual data, which is captured by the terminal. The captured visual data is then prepared for further processing.

[0523] Step 2:

[0524] The device uses optical character recognition (OCR) technology to generate character information from the captured visual data. In this step, the visual data is converted into text data, and the character information recognized by the OCR engine is output.

[0525] Step 3:

[0526] The terminal sends the generated character information to the server. The server receives this character information and begins analysis. The input is text data, and the output is the identification of incorrect answer patterns.

[0527] Step 4:

[0528] The server uses a machine learning model to analyze user error patterns. It compares past answers with data from other similar users to identify error trends. The input consists of text data and past learning history data, and the output is the user's error patterns.

[0529] Step 5:

[0530] Based on identified incorrect answer patterns, the server generates review tasks suitable for the user using a task generation device. The input is the incorrect answer patterns, and the output is the review tasks and explanations.

[0531] Step 6:

[0532] The generated review assignments and explanations are sent to the terminal and provided to the user via a display device. The input here is the review assignments and explanations, and the output is presented visually or audibly.

[0533] Step 7:

[0534] The terminal or assistive device provides the user with additional learning support using audio or visual feedback. Specifically, it provides audio guidance on how to solve problems or the correct pronunciation of incorrect words. The input for this step is audio instructions or visual data, and the output is direct educational support for the user.

[0535] Step 8:

[0536] Ultimately, a generative AI model is used to optimize prompts for the user. For example, it provides dynamic instructions such as, "Please pronounce the following word correctly: 'develop'." Based on the input, feedback tailored to the user's needs is output.

[0537] 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.

[0538] The learning support system of the present invention aims to analyze the user's tendency to make incorrect answers, recognize the user's emotional state, and provide an appropriate learning experience based on that.

[0539] First, the user takes a picture of the question they answered incorrectly with their smartphone or tablet and inputs it as image data into the device through the application. The device then uses optical character recognition (OCR) technology to convert this image into text data. This text data is sent to a server and used to analyze the user's answering patterns.

[0540] The server utilizes an emotion engine to recognize the user's emotional state when analyzing received text data. Emotion recognition uses cameras and voice input to analyze the user's facial expressions, reactions, and tone of voice to extract emotional data. By combining emotional data with information on error tendencies, a deep understanding of each user's learning needs can be obtained.

[0541] Based on the analysis results, the server generates review questions that take into account the user's emotional state. For example, if the user is feeling frustrated, it will present relatively easy questions to give them a sense of accomplishment and increase their motivation to learn. It can also customize and provide explanations and learning materials based on the user's interests and concerns.

[0542] The generated problems and materials are provided to the user via their device. The user then proceeds with their learning based on these materials and checks their answers and feedback within the application. Furthermore, learning progress and emotional states are reported to teachers and parents, helping to deepen their understanding.

[0543] As a concrete example, suppose a user incorrectly answers an English grammar question and uploads a photo of the answer to the app. If the server detects that the user is fatigued, it will generate a slightly easier, more engaging review question. This allows the user to continue learning without feeling excessively stressed. Through such a mechanism, it becomes possible to provide more personalized learning support.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0547] Step 2:

[0548] The device receives image data and uses Optical Character Recognition (OCR) to convert the text information within the image into text data. During this process, the accuracy of character recognition is improved by correcting the image resolution and brightness.

[0549] Step 3:

[0550] The device sends the converted text data, along with user facial expression and audio data obtained during the capture, to the server. This data is used to identify the user's emotional state.

[0551] Step 4:

[0552] The server analyzes the received text data and uses an AI algorithm to identify patterns in the user's incorrect responses. Simultaneously, an emotion engine analyzes facial expression and voice data to recognize the user's emotional state (e.g., concentration, fatigue, frustration).

[0553] Step 5:

[0554] The server combines data on incorrect answer patterns and emotional states to generate review questions tailored to the user. For example, if a user is feeling fatigued, the server will either lower the difficulty level of the questions or create questions with more engaging content. It will also select appropriate explanations and reference materials to stimulate the user's motivation to learn.

[0555] Step 6:

[0556] The server sends the generated review questions and explanatory materials to the terminal. The terminal displays these within the application, taking care to ensure that the user can understand them intuitively.

[0557] Step 7:

[0558] Users solve the provided problems, review the explanations, and progress through their learning. Throughout this process, the user's facial expressions and reactions are continuously collected on the device and sent to the server as feedback. Data on learning progress and emotional state is also accumulated and used to support future learning.

[0559] (Example 2)

[0560] 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."

[0561] Conventional learning support systems lack sufficient analysis and response capabilities for user errors, making it difficult to provide a learning experience tailored to individual learners. Furthermore, a learning environment that disregards the user's emotional state can lead to decreased motivation and increased stress. There is a need to solve these problems and provide more effective and personalized learning support.

[0562] 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.

[0563] In this invention, the server includes means for acquiring image information via an input device, means for generating character information from the image information using character recognition technology, means for analyzing the generated character information to identify the user's tendency to make incorrect answers, means for generating review tasks suitable for the user based on the identified tendency to make incorrect answers, means for recognizing the user's emotional state and providing an appropriate learning experience, and means for providing the generated review tasks to the user and providing explanations and learning materials. This makes it possible to provide a more appropriate and personalized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0564] An "input device" is a general term for hardware or software used to acquire image information from a user as digital data.

[0565] "Character recognition technology" is a technology that extracts character information from image information and converts it into digital text.

[0566] A "processing device" is a device that analyzes input information and performs processing according to its purpose.

[0567] An "analysis device" is a device that analyzes collected data and identifies patterns and trends.

[0568] A "task generation device" is a device that creates review tasks tailored to the user based on identified trends in incorrect answers.

[0569] An "emotion analysis device" is a device that recognizes the user's emotional state and provides the necessary information to offer an appropriate learning experience.

[0570] A "display device" is a device that provides users with generated assignments and explanatory materials visually.

[0571] The embodiments of the invention described herein provide a detailed configuration for realizing a system that provides an individually customized learning experience by recognizing the user's tendency to make incorrect answers and their emotional state.

[0572] Users take photos of incorrectly answered learning questions using a device such as a smartphone or tablet, and input the image data into the device via an application. The device then converts the acquired image data into text information using, for example, OCR (Optical Character Recognition) software, also known as character recognition technology. A concrete example of this would be the use of general-purpose OCR software.

[0573] The converted text information is sent from the terminal to the server. The server analyzes the received text information and records it in a database to identify the user's tendency to make incorrect answers. For example, analysis software is used for this analysis. The server also utilizes emotion recognition technologies such as an Emotion Engine to evaluate the user's emotional state. In this process, additional audio and video data from the terminal can be used to include the user's facial expressions and tone of voice in the analysis.

[0574] Based on the analysis results, the server generates review tasks that take into account the user's current state. If the emotional state indicates frustration, it generates relatively easy and engaging review tasks to encourage a sense of accomplishment. It can also select explanations and additional materials tailored to the user's interests, providing extra learning opportunities.

[0575] The generated assignments and materials are sent back from the server to the terminal and presented to the user through the terminal. The user can use these as a reference to progress with their learning and check their answers and feedback within the application. Furthermore, the system reports the user's learning progress and emotional state to educators and parents via the server, which is used to support learning.

[0576] As a concrete example, consider a scenario where a user incorrectly answers an English grammar question, takes a picture of the question, and uploads it. In this case, the server analyzes the image data to identify the pattern of incorrect answers, and if it determines that the user is showing signs of fatigue, it sets up a simple and engaging review question. An example of a prompt message for the generating AI model would be, "Generate a simple English grammar review question to present when the user looks tired."

[0577] This enables efficient and personalized learning support without causing excessive stress to the user.

[0578] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0579] Step 1:

[0580] Users take photos of incorrectly answered questions with their smartphones or tablets and input the image data into their devices via the application. Specifically, the user uses the camera function to capture an image of the question, and the image data is saved to a designated folder within the application. This allows the user to input the visual information of the incorrectly answered question into their device in digital format.

[0581] Step 2:

[0582] The device converts the input image data into text data using optical character recognition (OCR) technology. The input for this step is image data captured by the user, and the OCR software processes the data by detecting and identifying characters within the image. As output, text data is generated and stored in the device's memory as a readable string.

[0583] Step 3:

[0584] The terminal sends the converted text data to the server. This involves converting image data into text information, encrypting that text data, and then transferring it to the server. The transmission to the server is performed using a secure communication protocol, protecting the user's data.

[0585] Step 4:

[0586] The server analyzes the received text data to identify the user's tendency to make incorrect answers. The input for this step is the text data sent from the terminal. As part of the data calculation, the server uses statistical methods to perform pattern recognition while referring to a database of past incorrect answers, and the output is information that identifies the user's tendency to make incorrect answers.

[0587] Step 5:

[0588] The server uses emotion recognition technology to analyze additional user data (video and audio) and evaluate their emotional state. The input for this step is the video and audio data provided additionally via the terminal. Specifically, the server inputs this data into the emotion analysis engine and generates information indicating the user's emotional state as output.

[0589] Step 6:

[0590] The server generates review tasks tailored to the user based on their error tendencies and emotional state. Using error tendency information and emotional state information as input, a generative AI model is used to create prompts and perform data calculations to generate appropriate tasks. The output is a personalized review task.

[0591] Step 7:

[0592] The server sends the generated review assignments to the terminal, which then displays them to the user. At this stage, the review assignments are converted into a user-friendly format and delivered to the terminal via secure communication. The user can then receive them and proceed with their learning.

[0593] Step 8:

[0594] Users work on review assignments while checking their answers and feedback. Specifically, users answer assignments within the application on their device and receive feedback on their results through a confirmation screen.

[0595] (Application Example 2)

[0596] 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."

[0597] While conventional learning support systems could analyze users' error tendencies, they struggled to adjust learning content to take into account the user's emotional state. Furthermore, providing an optimal learning experience for each individual user requires real-time analysis of their emotional state and the provision of review questions based on those results, but achieving this has been a challenge.

[0598] 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.

[0599] In this invention, the server includes a conversion means that acquires visual data via an input device and generates character data from the visual data using optical character recognition; an analysis means that analyzes the generated character data and identifies the user's tendency to make incorrect answers; and an adaptation means that identifies the analyzed emotional state and generates problems adapted to the user's emotions. This makes it possible to provide a customized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0600] An "input device" refers to hardware or software used to acquire visual data from an external source and incorporate it into the system.

[0601] Optical character recognition (OCR) is a technology that identifies characters contained within an image and converts them into character data.

[0602] "Conversion means" refers to a device or program that performs the process of converting visual data into text data.

[0603] "Analysis means" refers to a device or program for analyzing the user's tendency to make incorrect answers based on the generated character data.

[0604] "User" refers to anyone who uses this system to learn.

[0605] "Incorrect answer tendency" refers to data that shows the types of questions that users repeatedly get wrong and the tendencies behind those mistakes.

[0606] "Emotional state" refers to the user's emotional response or mental state at that particular moment.

[0607] An "adaptive measure" is a device or program that generates problems adapted to the user's emotions based on analyzed data.

[0608] "Presentation means" refers to a device or program for providing generated review questions or educational materials to users visually or audibly.

[0609] The term "educator" refers to an individual or organization responsible for providing education and guidance to users.

[0610] "Learning progress" refers to data that shows the level of understanding and achievement a user has made as they progress through their learning.

[0611] This invention is a system for analyzing a user's error tendencies and emotional state to provide a personalized learning experience. In this system, the terminal uses an input device to acquire visual data of the problems the user has solved. The acquired data is converted into text data using optical character recognition (OCR) software. In this conversion, Pytesseract OCR software is often used.

[0612] The converted text data is then sent to a server for analysis. The server uses analysis tools to identify the user's tendency to make incorrect answers from the text data. It also analyzes real-time emotional data of the user acquired using a camera and microphone, and identifies the emotional state using an emotion recognition engine such as Emotion Recognizer. Based on the analysis results, an adaptation tool generates review questions that match the user's emotional state.

[0613] The generated problems are provided to the user through a presentation method. This presentation utilizes devices such as smartphones and tablets, providing educational materials and explanations visually or audibly. Furthermore, learning progress is reported to educators, enabling them to support the user's learning.

[0614] As a concrete example, suppose a user solves a math division problem and makes a mistake. The user takes a picture of the image with their device and uploads it to the system. If the camera detects that the user's facial expression indicates anxiety, the server, using its emotion recognition engine, generates and provides a simpler division problem to alleviate the anxiety. Then, it gradually moves the user to problems that improve their problem-solving skills. In this way, problems are provided that are tailored to the user's emotions and learning needs.

[0615] An example of a prompt message for a generative AI model might be: "The user's emotional state has been identified as anxious. Based on the incorrect answers and emotional state, please generate a math division problem that is easy but gradually increases in difficulty."

[0616] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0617] Step 1:

[0618] The terminal uses its camera, which is an input device, to capture images of questions that the user answered incorrectly. These images are incorporated into the system as visual data. The captured image of the question is obtained as input and is used for subsequent processing.

[0619] Step 2:

[0620] The device uses optical character recognition (OCR) software to convert acquired visual data into text data. Specifically, it uses OCR technology such as Pytesseract to recognize characters in an image and generate text data. The input is the image data obtained in step 1, and the output is text data.

[0621] Step 3:

[0622] The terminal sends the generated text data to the server. The server receives this text data as input and uses analysis tools to identify the user's tendency to make incorrect answers. Specifically, it refers to past incorrect answer data and other problem databases and performs data analysis to identify incorrect answer patterns. The output is data on the tendency to make incorrect answers.

[0623] Step 4:

[0624] The device acquires the user's emotional state using a camera and microphone and sends that data to a server. The server uses an emotion recognition engine (e.g., Emotion Recognizer) to identify the user's emotional state from the input audio and video data. The input is audio and facial expression data, and the output is the analyzed emotional state.

[0625] Step 5:

[0626] The server uses adaptive mechanisms to generate review questions tailored to the user, based on error tendency data and emotional state data. Here, a generative AI model is utilized to assemble an appropriate set of questions. Prompts may also be used to instruct the AI ​​to present questions in a way that suits it. The output consists of customized questions.

[0627] Step 6:

[0628] The server sends the generated questions and explanations back to the terminal. The terminal then presents this to the user, specifically displaying educational materials and explanations on the screen, and providing them in audio format as needed. The input is the questions and materials obtained in step 5, and the output is presentation via visual and auditory means.

[0629] Step 7:

[0630] The terminal sends the user's learning progress to the server. The progress data obtained here is reported to the educator, thereby promoting support for the user's learning. The server receives the progress information as input, generates a report for the educator, and outputs it.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] [Fourth Embodiment]

[0635] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0636] 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.

[0637] 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).

[0638] 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.

[0639] 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.

[0640] 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).

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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".

[0648] The learning support system of the present invention is designed to efficiently review questions that the user answered incorrectly and to improve learning efficiency.

[0649] First, the user uses a device with a dedicated application installed. The user inputs the incorrectly answered question by taking a picture or screenshot of it with their smartphone or tablet, thereby creating image data. The device receives this image data and uses optical character recognition (OCR) technology to generate text data from the image data containing character information. The system is designed to accurately identify characters and, if necessary, process mathematical formulas and diagrams as well.

[0650] The generated text data is sent from the terminal to the server. The server analyzes the received text data and uses machine learning algorithms to identify the user's error patterns and common mistakes. By referring to the user's past learning data and data from other users, the server gains a more accurate understanding of the causes of errors.

[0651] Based on the analysis results, the server generates original review questions to aid the user's learning. Educational technology and problem design theory are applied to this question generation process to ensure the questions are of appropriate difficulty and deepen the user's understanding. The server also generates explanations for incorrect answers and related learning materials (such as links to lecture videos).

[0652] These generated materials and problems are sent to the device and made available to the user within the application. Users can re-solve the problems within the app and progress through their learning while reviewing the explanations. Data such as progress and accuracy rates are also recorded and reported to teachers or parents as needed.

[0653] For example, if a user makes a mistake on a quadratic function problem in a math test, the server will generate review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user. As a result, the user can learn based on their own tendencies for making mistakes, and receive support to deepen their understanding in a short period of time.

[0654] The following describes the processing flow.

[0655] Step 1:

[0656] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0657] Step 2:

[0658] The device performs optical character recognition (OCR) on the received image data, converting the text information within the image into text data. During this process, it ensures accurate conversion even if mathematical formulas or special symbols are included.

[0659] Step 3:

[0660] The terminal structures the generated text data, adds metadata such as subject, question type, and difficulty level, and sends it to the server.

[0661] Step 4:

[0662] The server analyzes the received text data and metadata, using an AI algorithm to identify characteristics and patterns of user errors. Past training data is also referenced to extract the causes of errors.

[0663] Step 5:

[0664] Based on the analysis results, the server automatically generates review questions tailored to the user's weak areas. These questions are adjusted to an appropriate difficulty level and content according to the user's understanding. Explanatory text and related learning materials are also generated simultaneously.

[0665] Step 6:

[0666] The server sends generated problems, explanations, and learning materials to the user's device. This allows the user to view these within the application and progress through their learning.

[0667] Step 7:

[0668] Users work on review questions and record their results within the application. The device feeds back the user's answers and progress as data to the server, which is then used to further support their learning.

[0669] (Example 1)

[0670] 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".

[0671] There is a need for a system that allows individual learners to efficiently review the areas where they made mistakes and improve their academic ability in a short period of time. However, current learning support technologies lack the functionality to accurately analyze learners' error patterns and automatically generate appropriate review questions based on that analysis. Furthermore, there is no system in place to properly manage learners' progress and allow teachers and parents to easily access that information.

[0672] 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.

[0673] In this invention, the server includes means for acquiring image information of test questions answered incorrectly by the user via an input medium; processing means for generating character information from the image information using optical character conversion; analysis means for analyzing the generated character information and identifying the user's error patterns; question generation means for generating review questions optimized for the user based on the identified error patterns; a display medium for providing the generated review questions, explanations, and learning materials to the user; and recording and reporting means for recording the user's learning progress and correct answer rate and notifying the user, teacher, or guardian. This enables effective review tailored to the needs of each learner, improving learning efficiency and facilitating the appropriate sharing of progress information.

[0674] "Input medium" refers to devices and methods for transmitting information from a user to a system, and in particular includes cameras and scanners for acquiring image information.

[0675] "Optical character conversion" refers to a technology for converting image information into text information, primarily using optical character recognition (OCR) to generate text data from image data.

[0676] "Processing means" refers to devices or algorithms that perform the process of analyzing input image information and converting it into text information.

[0677] "Analysis means" refers to technologies and devices used to analyze generated textual information and identify patterns of incorrect answers made by users, and includes machine learning algorithms, etc.

[0678] "Problem generation means" refers to a device or algorithm that automatically generates review questions optimized to maximize educational effectiveness based on the user's error patterns.

[0679] "Display medium" refers to devices and systems used to provide and display generated review questions, explanations, and learning materials to users, and this particularly includes displays and mobile devices.

[0680] "Recording and reporting means" refers to devices or software that have the function of saving the user's learning progress and correct answer rate, and notifying the user themselves, or, if necessary, teachers or guardians, of this information.

[0681] To implement this invention, the user begins by using a device with a dedicated application installed to take a picture of an incorrectly answered test question or capture an image of the question via a screenshot. The device then converts this image information into text information using optical character recognition (OCR), a type of optical character conversion technology. Specific examples of such technologies include Tesseract and cloud-based OCR services.

[0682] The terminal then sends the generated text information to the server. The server uses a machine learning algorithm to analyze this text information and identify the user's error patterns. The server then uses a generative AI model to generate review questions tailored to the user's needs, referencing past training data and other users' error records. This process applies theories from educational technology and problem design, aiming to deepen understanding at an appropriate difficulty level.

[0683] In addition, the server generates explanations for the user's incorrect answers and related learning materials, and sends them to the terminal. The terminal displays the generated review questions and learning materials within the application, allowing the user to continue their learning through them.

[0684] For example, if a user makes a mistake on a quadratic function problem in a math test, the server generates review problems that focus on "graph interpretation," which is a particular area of ​​difficulty for the user, and provides them as learning material. As a result, users can effectively review based on their individual error patterns, supporting a deeper understanding in a short period of time.

[0685] An example of a prompt message for a generating AI model is: "I made a mistake in reading the graph of a quadratic function. Please generate review questions specifically for my weak areas. Please also refer to past incorrect answer data and add explanations to deepen my understanding."

[0686] Thus, this invention is a system that provides customized learning support based on each user's tendency to make mistakes, thereby improving learning efficiency.

[0687] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0688] Step 1:

[0689] Users take photos or screenshots of incorrectly answered exam questions using a smartphone, tablet, or other device. The question data is then entered as image information. Users must ensure the question is clearly visible in the image.

[0690] Step 2:

[0691] The terminal uses OCR software to generate text information from acquired image information. In this process, image data is input and text data is output. For example, Tesseract is used to perform calculations to identify data containing characters and mathematical formulas as text.

[0692] Step 3:

[0693] The terminal sends the generated character data to the server. The input here is character data, and the output is notification information indicating that communication with the server has been established and data has been sent. The terminal uses protocols such as HTTPS to ensure secure data communication.

[0694] Step 4:

[0695] The server analyzes the received text data using a machine learning algorithm to identify patterns in the user's incorrect responses. The input is the transmitted text data, and the output is information about the incorrect response patterns. The analysis calculations are performed by referring to past learning history and other user data.

[0696] Step 5:

[0697] The server uses a generative AI model to create review questions and explanations based on incorrect answer patterns. The input in this step is incorrect answer pattern information, and the output is the generated review questions and explanation materials. Optimal questions and answers are designed based on educational technology theory.

[0698] Step 6:

[0699] The server sends the generated review questions and explanatory materials to the terminal. The input is the review questions and explanatory materials, and the output is the state in which this data has been transferred to the terminal. The terminal displays the information through a user-friendly interface.

[0700] Step 7:

[0701] Users solve review problems provided through their devices and deepen their understanding by checking the explanations. Input consists of problems and materials displayed on the device, while output consists of the user's answers and progress data for review. The system records the user's learning progress and reports it to educators and parents as needed.

[0702] (Application Example 1)

[0703] 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".

[0704] Traditional learning support systems have faced challenges in efficiently reviewing incorrect answers and addressing individual learning needs. Furthermore, they lacked dynamic learning support utilizing audio and visual feedback, making it difficult to provide users with the optimal educational experience. Additionally, teachers and parents had limited information to track users' learning progress and provide appropriate support.

[0705] 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.

[0706] In this invention, the server includes a processing device that acquires visual data via an input device and generates character information from the visual data using optical character recognition; an analysis device that analyzes the generated character information and identifies the user's error patterns; a task generation device that generates review tasks suitable for the user based on the identified error patterns; a display device that provides the generated review tasks to the user and provides explanations and educational materials; and a support device that provides additional learning support to the user using audio or visual feedback. This enables users to review optimally according to their individual error tendencies and enjoy an intuitive learning experience through audio and visual feedback. Furthermore, it enables more effective educational support by providing educators with progress information for each user and creating individually optimized prompt sentences using a generation AI model.

[0707] An "input device" is a device used to acquire visual data, such as a camera or scanner.

[0708] "Visual data" refers to data that includes visual information, such as images and videos, and is acquired by an input device.

[0709] Optical character recognition (OCR) is a technology that extracts character information from image data and converts it into text data.

[0710] A "processing unit" is a computer unit that converts visual data into textual information and performs the optical character recognition process.

[0711] "Character information" refers to text data generated by optical character recognition.

[0712] An "analysis device" is a computer unit that analyzes the user's error patterns based on the generated character information.

[0713] "Incorrect answer patterns" refer to the tendencies and characteristics of how users answer questions incorrectly.

[0714] A "task generation device" is a computer unit that creates appropriate review tasks based on the user's error patterns.

[0715] "Assignments" refer to problems or exercises presented to users to support their learning.

[0716] A "display device" is a device that provides users with generated review assignments, explanations, and educational materials visually or audibly.

[0717] "Voice feedback" is a technology that provides supplementary information or guidance to users through audio.

[0718] "Visual feedback" is a technique that supplements or instructs users on learning content through visual information.

[0719] A "support device" is a device that provides additional learning support, such as audio or visual feedback.

[0720] To realize this invention, the system is configured as follows: First, the user takes a picture of a problem on paper using an input device, such as a tablet with a camera. The captured visual data is collected by the terminal and converted into text information by optical character recognition software, such as an OCR engine like Tesseract. Through this process, the visual data becomes digital text.

[0721] Next, the server receives the processed character information and analyzes the error patterns. The analysis device uses machine learning algorithms to analyze the user's past answer data and similar data from other users. In this phase, machine learning libraries such as scikit-learn are utilized to identify the user's learning needs based on the error patterns.

[0722] Based on identified error patterns, the server uses a task generator to create personalized review tasks for each user. These tasks include questions designed to reinforce areas where the user frequently makes mistakes, as well as exercises to deepen understanding. The generated tasks, explanations, and related educational materials are provided to the user via the terminal's display device.

[0723] Furthermore, the support device utilizes audio and visual feedback to provide additional learning support to the user. Users can systematically progress through learning while receiving feedback from support devices such as robots.

[0724] For example, if a child mispronounces a particular word while doing their English homework, this system can provide additional practice exercises to reinforce that word. Using a generative AI model, it's possible to provide prompts such as, "Please pronounce the following word correctly: 'develop'."

[0725] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0726] Step 1:

[0727] The user takes a picture of their homework or problem using an input device. The input is visual data, which is captured by the terminal. The captured visual data is then prepared for further processing.

[0728] Step 2:

[0729] The device uses optical character recognition (OCR) technology to generate character information from the captured visual data. In this step, the visual data is converted into text data, and the character information recognized by the OCR engine is output.

[0730] Step 3:

[0731] The terminal sends the generated character information to the server. The server receives this character information and begins analysis. The input is text data, and the output is the identification of incorrect answer patterns.

[0732] Step 4:

[0733] The server uses a machine learning model to analyze user error patterns. It compares past answers with data from other similar users to identify error trends. The input consists of text data and past learning history data, and the output is the user's error patterns.

[0734] Step 5:

[0735] Based on identified incorrect answer patterns, the server generates review tasks suitable for the user using a task generation device. The input is the incorrect answer patterns, and the output is the review tasks and explanations.

[0736] Step 6:

[0737] The generated review assignments and explanations are sent to the terminal and provided to the user via a display device. The input here is the review assignments and explanations, and the output is presented visually or audibly.

[0738] Step 7:

[0739] The terminal or assistive device provides the user with additional learning support using audio or visual feedback. Specifically, it provides audio guidance on how to solve problems or the correct pronunciation of incorrect words. The input for this step is audio instructions or visual data, and the output is direct educational support for the user.

[0740] Step 8:

[0741] Ultimately, a generative AI model is used to optimize prompts for the user. For example, it provides dynamic instructions such as, "Please pronounce the following word correctly: 'develop'." Based on the input, feedback tailored to the user's needs is output.

[0742] 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.

[0743] The learning support system of the present invention aims to analyze the user's tendency to make incorrect answers, recognize the user's emotional state, and provide an appropriate learning experience based on that.

[0744] First, the user takes a picture of the question they answered incorrectly with their smartphone or tablet and inputs it as image data into the device through the application. The device then uses optical character recognition (OCR) technology to convert this image into text data. This text data is sent to a server and used to analyze the user's answering patterns.

[0745] The server utilizes an emotion engine to recognize the user's emotional state when analyzing received text data. Emotion recognition uses cameras and voice input to analyze the user's facial expressions, reactions, and tone of voice to extract emotional data. By combining emotional data with information on error tendencies, a deep understanding of each user's learning needs can be obtained.

[0746] Based on the analysis results, the server generates review questions that take into account the user's emotional state. For example, if the user is feeling frustrated, it will present relatively easy questions to give them a sense of accomplishment and increase their motivation to learn. It can also customize and provide explanations and learning materials based on the user's interests and concerns.

[0747] The generated problems and materials are provided to the user via their device. The user then proceeds with their learning based on these materials and checks their answers and feedback within the application. Furthermore, learning progress and emotional states are reported to teachers and parents, helping to deepen their understanding.

[0748] As a concrete example, suppose a user incorrectly answers an English grammar question and uploads a photo of the answer to the app. If the server detects that the user is fatigued, it will generate a slightly easier, more engaging review question. This allows the user to continue learning without feeling excessively stressed. Through such a mechanism, it becomes possible to provide more personalized learning support.

[0749] The following describes the processing flow.

[0750] Step 1:

[0751] Users take photos of questions they answered incorrectly with their smartphones or tablets, and input the image data into the device via the application.

[0752] Step 2:

[0753] The device receives image data and uses Optical Character Recognition (OCR) to convert the text information within the image into text data. During this process, the accuracy of character recognition is improved by correcting the image resolution and brightness.

[0754] Step 3:

[0755] The device sends the converted text data, along with user facial expression and audio data obtained during the capture, to the server. This data is used to identify the user's emotional state.

[0756] Step 4:

[0757] The server analyzes the received text data and uses an AI algorithm to identify patterns in the user's incorrect responses. Simultaneously, an emotion engine analyzes facial expression and voice data to recognize the user's emotional state (e.g., concentration, fatigue, frustration).

[0758] Step 5:

[0759] The server combines data on incorrect answer patterns and emotional states to generate review questions tailored to the user. For example, if a user is feeling fatigued, the server will either lower the difficulty level of the questions or create questions with more engaging content. It will also select appropriate explanations and reference materials to stimulate the user's motivation to learn.

[0760] Step 6:

[0761] The server sends the generated review questions and explanatory materials to the terminal. The terminal displays these within the application, taking care to ensure that the user can understand them intuitively.

[0762] Step 7:

[0763] Users solve the provided problems, review the explanations, and progress through their learning. Throughout this process, the user's facial expressions and reactions are continuously collected on the device and sent to the server as feedback. Data on learning progress and emotional state is also accumulated and used to support future learning.

[0764] (Example 2)

[0765] 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".

[0766] Conventional learning support systems lack sufficient analysis and response capabilities for user errors, making it difficult to provide a learning experience tailored to individual learners. Furthermore, a learning environment that disregards the user's emotional state can lead to decreased motivation and increased stress. There is a need to solve these problems and provide more effective and personalized learning support.

[0767] 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.

[0768] In this invention, the server includes means for acquiring image information via an input device, means for generating character information from the image information using character recognition technology, means for analyzing the generated character information to identify the user's tendency to make incorrect answers, means for generating review tasks suitable for the user based on the identified tendency to make incorrect answers, means for recognizing the user's emotional state and providing an appropriate learning experience, and means for providing the generated review tasks to the user and providing explanations and learning materials. This makes it possible to provide a more appropriate and personalized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0769] An "input device" is a general term for hardware or software used to acquire image information from a user as digital data.

[0770] "Character recognition technology" is a technology that extracts character information from image information and converts it into digital text.

[0771] A "processing device" is a device that analyzes input information and performs processing according to its purpose.

[0772] An "analysis device" is a device that analyzes collected data and identifies patterns and trends.

[0773] A "task generation device" is a device that creates review tasks tailored to the user based on identified trends in incorrect answers.

[0774] An "emotion analysis device" is a device that recognizes the user's emotional state and provides the necessary information to offer an appropriate learning experience.

[0775] A "display device" is a device that provides users with generated assignments and explanatory materials visually.

[0776] The embodiments of the invention described herein provide a detailed configuration for realizing a system that provides an individually customized learning experience by recognizing the user's tendency to make incorrect answers and their emotional state.

[0777] Users take photos of incorrectly answered learning questions using a device such as a smartphone or tablet, and input the image data into the device via an application. The device then converts the acquired image data into text information using, for example, OCR (Optical Character Recognition) software, also known as character recognition technology. A concrete example of this would be the use of general-purpose OCR software.

[0778] The converted text information is sent from the terminal to the server. The server analyzes the received text information and records it in a database to identify the user's tendency to make incorrect answers. For example, analysis software is used for this analysis. The server also utilizes emotion recognition technologies such as an Emotion Engine to evaluate the user's emotional state. In this process, additional audio and video data from the terminal can be used to include the user's facial expressions and tone of voice in the analysis.

[0779] Based on the analysis results, the server generates review tasks that take into account the user's current state. If the emotional state indicates frustration, it generates relatively easy and engaging review tasks to encourage a sense of accomplishment. It can also select explanations and additional materials tailored to the user's interests, providing extra learning opportunities.

[0780] The generated assignments and materials are sent back from the server to the terminal and presented to the user through the terminal. The user can use these as a reference to progress with their learning and check their answers and feedback within the application. Furthermore, the system reports the user's learning progress and emotional state to educators and parents via the server, which is used to support learning.

[0781] As a concrete example, consider a scenario where a user incorrectly answers an English grammar question, takes a picture of the question, and uploads it. In this case, the server analyzes the image data to identify the pattern of incorrect answers, and if it determines that the user is showing signs of fatigue, it sets up a simple and engaging review question. An example of a prompt message for the generating AI model would be, "Generate a simple English grammar review question to present when the user looks tired."

[0782] This enables efficient and personalized learning support without causing excessive stress to the user.

[0783] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0784] Step 1:

[0785] Users take photos of incorrectly answered questions with their smartphones or tablets and input the image data into their devices via the application. Specifically, the user uses the camera function to capture an image of the question, and the image data is saved to a designated folder within the application. This allows the user to input the visual information of the incorrectly answered question into their device in digital format.

[0786] Step 2:

[0787] The device converts the input image data into text data using optical character recognition (OCR) technology. The input for this step is image data captured by the user, and the OCR software processes the data by detecting and identifying characters within the image. As output, text data is generated and stored in the device's memory as a readable string.

[0788] Step 3:

[0789] The terminal sends the converted text data to the server. This involves converting image data into text information, encrypting that text data, and then transferring it to the server. The transmission to the server is performed using a secure communication protocol, protecting the user's data.

[0790] Step 4:

[0791] The server analyzes the received text data to identify the user's tendency to make incorrect answers. The input for this step is the text data sent from the terminal. As part of the data calculation, the server uses statistical methods to perform pattern recognition while referring to a database of past incorrect answers, and the output is information that identifies the user's tendency to make incorrect answers.

[0792] Step 5:

[0793] The server uses emotion recognition technology to analyze additional user data (video and audio) and evaluate their emotional state. The input for this step is the video and audio data provided additionally via the terminal. Specifically, the server inputs this data into the emotion analysis engine and generates information indicating the user's emotional state as output.

[0794] Step 6:

[0795] The server generates review tasks tailored to the user based on their error tendencies and emotional state. Using error tendency information and emotional state information as input, a generative AI model is used to create prompts and perform data calculations to generate appropriate tasks. The output is a personalized review task.

[0796] Step 7:

[0797] The server sends the generated review assignments to the terminal, which then displays them to the user. At this stage, the review assignments are converted into a user-friendly format and delivered to the terminal via secure communication. The user can then receive them and proceed with their learning.

[0798] Step 8:

[0799] Users work on review assignments while checking their answers and feedback. Specifically, users answer assignments within the application on their device and receive feedback on their results through a confirmation screen.

[0800] (Application Example 2)

[0801] 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".

[0802] While conventional learning support systems could analyze users' error tendencies, they struggled to adjust learning content to take into account the user's emotional state. Furthermore, providing an optimal learning experience for each individual user requires real-time analysis of their emotional state and the provision of review questions based on those results, but achieving this has been a challenge.

[0803] 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.

[0804] In this invention, the server includes a conversion means that acquires visual data via an input device and generates character data from the visual data using optical character recognition; an analysis means that analyzes the generated character data and identifies the user's tendency to make incorrect answers; and an adaptation means that identifies the analyzed emotional state and generates problems adapted to the user's emotions. This makes it possible to provide a customized learning experience based on the user's tendency to make incorrect answers and their emotional state.

[0805] An "input device" refers to hardware or software used to acquire visual data from an external source and incorporate it into the system.

[0806] Optical character recognition (OCR) is a technology that identifies characters contained within an image and converts them into character data.

[0807] "Conversion means" refers to a device or program that performs the process of converting visual data into text data.

[0808] "Analysis means" refers to a device or program for analyzing the user's tendency to make incorrect answers based on the generated character data.

[0809] "User" refers to anyone who uses this system to learn.

[0810] "Incorrect answer tendency" refers to data that shows the types of questions that users repeatedly get wrong and the tendencies behind those mistakes.

[0811] "Emotional state" refers to the user's emotional response or mental state at that particular moment.

[0812] An "adaptive measure" is a device or program that generates problems adapted to the user's emotions based on analyzed data.

[0813] "Presentation means" refers to a device or program for providing generated review questions or educational materials to users visually or audibly.

[0814] The term "educator" refers to an individual or organization responsible for providing education and guidance to users.

[0815] "Learning progress" refers to data that shows the level of understanding and achievement a user has made as they progress through their learning.

[0816] This invention is a system for analyzing a user's error tendencies and emotional state to provide a personalized learning experience. In this system, the terminal uses an input device to acquire visual data of the problems the user has solved. The acquired data is converted into text data using optical character recognition (OCR) software. In this conversion, Pytesseract OCR software is often used.

[0817] The converted text data is then sent to a server for analysis. The server uses analysis tools to identify the user's tendency to make incorrect answers from the text data. It also analyzes real-time emotional data of the user acquired using a camera and microphone, and identifies the emotional state using an emotion recognition engine such as Emotion Recognizer. Based on the analysis results, an adaptation tool generates review questions that match the user's emotional state.

[0818] The generated problems are provided to the user through a presentation method. This presentation utilizes devices such as smartphones and tablets, providing educational materials and explanations visually or audibly. Furthermore, learning progress is reported to educators, enabling them to support the user's learning.

[0819] As a concrete example, suppose a user solves a math division problem and makes a mistake. The user takes a picture of the image with their device and uploads it to the system. If the camera detects that the user's facial expression indicates anxiety, the server, using its emotion recognition engine, generates and provides a simpler division problem to alleviate the anxiety. Then, it gradually moves the user to problems that improve their problem-solving skills. In this way, problems are provided that are tailored to the user's emotions and learning needs.

[0820] An example of a prompt message for a generative AI model might be: "The user's emotional state has been identified as anxious. Based on the incorrect answers and emotional state, please generate a math division problem that is easy but gradually increases in difficulty."

[0821] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0822] Step 1:

[0823] The terminal uses its camera, which is an input device, to capture images of questions that the user answered incorrectly. These images are incorporated into the system as visual data. The captured image of the question is obtained as input and is used for subsequent processing.

[0824] Step 2:

[0825] The device uses optical character recognition (OCR) software to convert acquired visual data into text data. Specifically, it uses OCR technology such as Pytesseract to recognize characters in an image and generate text data. The input is the image data obtained in step 1, and the output is text data.

[0826] Step 3:

[0827] The terminal sends the generated text data to the server. The server receives this text data as input and uses analysis tools to identify the user's tendency to make incorrect answers. Specifically, it refers to past incorrect answer data and other problem databases and performs data analysis to identify incorrect answer patterns. The output is data on the tendency to make incorrect answers.

[0828] Step 4:

[0829] The device acquires the user's emotional state using a camera and microphone and sends that data to a server. The server uses an emotion recognition engine (e.g., Emotion Recognizer) to identify the user's emotional state from the input audio and video data. The input is audio and facial expression data, and the output is the analyzed emotional state.

[0830] Step 5:

[0831] The server uses adaptive mechanisms to generate review questions tailored to the user, based on error tendency data and emotional state data. Here, a generative AI model is utilized to assemble an appropriate set of questions. Prompts may also be used to instruct the AI ​​to present questions in a way that suits it. The output consists of customized questions.

[0832] Step 6:

[0833] The server sends the generated questions and explanations back to the terminal. The terminal then presents this to the user, specifically displaying educational materials and explanations on the screen, and providing them in audio format as needed. The input is the questions and materials obtained in step 5, and the output is presentation via visual and auditory means.

[0834] Step 7:

[0835] The terminal sends the user's learning progress to the server. The progress data obtained here is reported to the educator, thereby promoting support for the user's learning. The server receives the progress information as input, generates a report for the educator, and outputs it.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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."

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] The following is further disclosed regarding the embodiments described above.

[0858] (Claim 1)

[0859] Image data is acquired via the input means.

[0860] A processing means for generating text data from image data using optical character recognition,

[0861] An analytical means for analyzing generated text data and identifying the user's tendency to make incorrect answers,

[0862] A question generation means that generates review questions suitable for the user based on identified error tendencies,

[0863] A display means that provides users with generated review questions, along with explanations and learning materials.

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, wherein the analysis means analyzes the cause of incorrect answers by referring to past user data and other similar problem databases.

[0867] (Claim 3)

[0868] The system according to claim 1, wherein the display means has a function to report the learning progress of each user to the teacher.

[0869] "Example 1"

[0870] (Claim 1)

[0871] Image information of test questions that users answered incorrectly is obtained via an input medium.

[0872] A processing means for generating character information from image information using optical character conversion,

[0873] An analytical means for analyzing generated text information and identifying user error patterns,

[0874] A question generation means that generates review questions optimized for the user based on identified incorrect answer patterns,

[0875] A display medium that provides users with generated review questions, explanations, and learning materials,

[0876] A means of recording and reporting that records the user's learning progress and correct answer rate, and notifies the user, teacher, or guardian of this information.

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, wherein the analysis means analyzes the root cause of incorrect answers by referring to past user data and other similar problem sources, and the generating AI model generates appropriate review questions using the results.

[0880] (Claim 3)

[0881] The system according to claim 1, wherein the display medium has a function to report the learning progress of each user to an educator, and the educator can adjust the difficulty level of the generated problems.

[0882] "Application Example 1"

[0883] (Claim 1)

[0884] Visual data is acquired via an input device.

[0885] A processing device that generates character information from visual data using optical character recognition,

[0886] An analysis device that analyzes generated character information and identifies the user's error patterns,

[0887] A task generation device that generates review tasks suitable for the user based on identified error patterns,

[0888] A display device that provides users with generated review assignments and offers explanations and educational materials,

[0889] A support device that provides additional learning support to users using audio or visual feedback,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, wherein the analysis device analyzes the cause of incorrect answers by referring to past user data and other similar task databases, and generates feedback according to the user's level of understanding.

[0893] (Claim 3)

[0894] The system according to claim 1, wherein the display device has a function to report the learning progress of each user to an educator, and further generates individually optimized prompt sentences using a generative AI model.

[0895] "Example 2 of combining an emotion engine"

[0896] (Claim 1)

[0897] Image information is acquired via the input device.

[0898] A processing device that generates character information from image information using character recognition technology,

[0899] An analysis device that analyzes generated text information and identifies the user's tendency to make incorrect answers,

[0900] A task generation device that generates review tasks suitable for the user based on identified trends in incorrect answers,

[0901] An emotion analysis device that recognizes the user's emotional state and provides an appropriate learning experience,

[0902] A display device that provides the user with generated review assignments, along with explanations and learning materials.

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, wherein the analysis device analyzes the cause of incorrect answers by referring to past user information and other similar task databases.

[0906] (Claim 3)

[0907] The system according to claim 1, wherein the display device has a function to report the learning progress of each user to an educator.

[0908] "Application example 2 when combining with an emotional engine"

[0909] (Claim 1)

[0910] Visual data is acquired via an input device.

[0911] A conversion means for generating character data from visual data using optical character recognition,

[0912] An analysis method that analyzes the generated character data and identifies the user's tendency to make incorrect answers,

[0913] An adaptive means that identifies the analyzed emotional state and generates a problem adapted to the user's emotions,

[0914] A presentation method that provides users with generated review questions, along with explanations and educational materials.

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, wherein the analysis means analyzes the cause of incorrect answers by referring to past user data and other similar problem information sources.

[0918] (Claim 3)

[0919] The system according to claim 1, wherein the presentation means has a function to report the learning progress of each user to an educator. [Explanation of Symbols]

[0920] 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. Visual data is acquired via an input device. A processing device that generates character information from visual data using optical character recognition, An analysis device that analyzes generated character information and identifies the user's error patterns, A task generation device that generates review tasks suitable for the user based on identified error patterns, A display device that provides users with generated review assignments and offers explanations and educational materials, A support device that provides additional learning support to users using audio or visual feedback, A system that includes this.

2. The system according to claim 1, wherein the analysis device analyzes the cause of incorrect answers by referring to past user data and other similar task databases, and generates feedback according to the user's level of understanding.

3. The system according to claim 1, wherein the display device has a function to report the learning progress of each user to an educator, and further generates individually optimized prompt sentences using a generative AI model.

Images