System

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to photograph a handwritten note; means for a terminal to transmit photographed image data to a server; means for the server to analyze the image data and extract text data; means for the server to generate a wordbook, a workbook, and a reference based on the extracted text data; means for the server to transmit generated content to the terminal; and means for the user to view the generated content through the terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Many learners who use handwritten notes face the hassle of organizing their notes and the risk of losing important information. Furthermore, there is a lack of suitable methods for easily generating useful learning materials from handwritten notes. Given these circumstances, there is a need to automate the organization of handwritten notes and the generation of learning materials, thereby providing easy and effective learning support for users. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. Specifically, a means is provided for a user to photograph handwritten notes and send the image data from the terminal to a server. The server analyzes the received image data, extracts text data, and uses the extracted text data to generate a vocabulary book, workbook, and reference materials. The generated content is sent from the server to the terminal, allowing the user to view the content via the terminal. Furthermore, the terminal includes a means for compressing image data and the server includes a means for classifying the extracted text data by category and generating content using appropriate templates, thereby achieving efficient and accurate generation of learning materials.

[0006] "User" refers to an individual or entity who uses handwritten notes and creates and views learning content.

[0007] "Device" refers to a smartphone, tablet, or other electronic device used by a user to capture and communicate handwritten notes.

[0008] A "server" is a computer system that receives image data sent from a terminal, analyzes it, and generates study content.

[0009] "Image data" refers to a digital image file that is saved on a device when a user takes a photo of a handwritten note.

[0010] "Analysis" is the process in which the server identifies handwritten characters and graphics from image data and extracts them as text data.

[0011] "Text data" refers to character information extracted from image data through analysis, and is stored on a server as a digital text file.

[0012] A "vocabulary book" is a type of learning content generated based on extracted text data, and is a list containing keywords and their explanations.

[0013] A "question set" is a type of learning content generated based on extracted text data, and is a list of related questions and their answers.

[0014] A "reference" is a type of learning content generated based on extracted text data, and is a list containing related book titles and website links.

[0015] A "template" is a format or form that the server uses to generate decks, exercises, and references.

[0016] "Compression" is the process of reducing the size of image data, thereby improving the efficiency of data transfer. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a 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.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0031] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system involves a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[0039] 1. The user takes a photo of their handwritten notes

[0040] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[0041] As a concrete example, consider the case where a user takes a photo of a biology notebook. The user uses the device's camera to capture the entire notebook so that it is saved as a single image.

[0042] 2. The device sends the image data to the server

[0043] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[0044] 3. The server performs image analysis

[0045] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[0046] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[0047] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[0048] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[0049] For example, the server might generate the following vocabulary list from the analysis of "cell division":

[0050] "Mitosis: the process by which cells divide, resulting in the accurate duplication of genetic material."

[0051] "Meiosis: A specialized division that occurs during the production of germ cells"

[0052] It also generates a set of questions:

[0053] "Question: Explain the difference between mitosis and meiosis. Answer: In mitosis..."

[0054] 5. Sending server-generated content to the device

[0055] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0056] 6. Use user-generated learning materials

[0057] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study.

[0058] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[0062] Step 2:

[0063] The device sends the captured image data to the server. The device first compresses the image data and sends it to the server's upload URL using the HTTPS protocol. After sending is complete, the device waits for a confirmation response from the server.

[0064] Step 3:

[0065] The server receives the image data. The server verifies the received image data and checks the data format and completeness. If there are no problems, the server returns a receipt confirmation message to the terminal.

[0066] Step 4:

[0067] The server performs image analysis. The server launches an image analysis module and uses OCR technology to identify handwritten characters and figures in the image. This process also involves preprocessing such as noise removal and binarization. Text data is extracted as a result of the analysis.

[0068] Step 5:

[0069] The server classifies the extracted text data and applies a keyword extraction algorithm to detect important words and phrases, which are then used to categorize the learning content.

[0070] Step 6:

[0071] The server generates a vocabulary list, a question bank, and a reference book. The server selects an appropriate template based on each category and generates content by inserting the extracted text data. The generated content includes keywords and their explanations (vocabulary list), related questions and answers (questions), and links to reference books and websites (reference book).

[0072] Step 7:

[0073] The server sends the generated content to the terminal. The server packages the content data and sends it to the terminal using the HTTPS protocol. After the transmission is complete, a confirmation message is sent back to the terminal.

[0074] Step 8:

[0075] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that reception is complete.

[0076] Step 9:

[0077] The user accesses the generated learning materials. They launch a dedicated application and view the generated vocabulary book, practice questions, and reference materials. They can sort the content and mark important points.

[0078] These are the specific processing steps of the program. This series of steps allows users to effectively organize the contents of their handwritten notes and use them as learning materials.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Learning using handwritten notes has the problem that it is difficult to manage and search for information, and creating learning materials manually requires time and effort. Furthermore, there is a need for a method to efficiently analyze the data from photographed notes and extract information that can be used as effective learning materials. Current technology does not provide sufficient efficiency for extracting data from handwritten notes and generating learning materials, making it difficult to improve learning efficiency.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes means for analyzing received image data using optical character recognition technology and extracting text data, means for preprocessing the extracted text data, such as noise removal and binarization, and means for generating vocabulary lists, workbooks, and reference materials using natural language processing technology based on the classified text data. This makes it possible to efficiently extract data from handwritten notes and automatically generate effective and systematic study materials.

[0084] A "user" is someone who uses this system to take pictures of handwritten notes and view the generated content.

[0085] "Electronic devices" refer to portable devices such as smartphones and tablets that capture images of handwritten notes and send the image data to a server.

[0086] A "server" is a computer system that analyzes received image data, extracts and processes text data, and generates learning materials based on that data.

[0087] "Means" refers to the method or apparatus used by the system to perform a particular function or operation.

[0088] "Optical character recognition technology" is a technology that recognizes characters from image data and converts them into text data.

[0089] "Preprocessing" refers to processing of image data, such as noise removal and binarization, in order to improve the accuracy of analysis.

[0090] "Text data" is character information extracted using optical character recognition technology.

[0091] "Natural language processing technology" is a set of technologies that enable computers to understand and generate human language.

[0092] "Content" refers to server-generated learning materials such as vocabulary books, workbooks, and reference materials.

[0093] A "template" is a format that pre-designs the form and framework of the content to be generated.

[0094] "Network" refers to a communications infrastructure such as the Internet, and is a means for connecting electronic devices and servers.

[0095] A "dedicated application" is specific software that a user uses to view generated content.

[0096] This system allows users to take photos of their handwritten notes, and a server analyzes the content to automatically generate learning materials. This system provides a series of processes, from taking photos of the user's handwritten notes to analyzing the images, generating learning materials, and providing them to the user.

[0097] Hardware and Software Use

[0098] User side

[0099] A user uses an electronic device such as a smartphone or tablet. The device launches a camera application and takes a photo of the handwritten note. After the photo is taken, the image data is temporarily stored in the device's internal storage. Specific camera applications include the standard camera app found on most smartphones.

[0100] Terminal side

[0101] The device compresses the captured image data and sends the compressed data to the server using the HTTPS protocol. The software used in this step includes an image compression library and a secure communication protocol (e.g., OpenSSL).

[0102] Server side

[0103] The server uses OCR (Optical Character Recognition) technology to analyze the received image data. Image analysis libraries such as OpenCV and Tesseract are used for this analysis. The server performs preprocessing such as noise removal and binarization to improve the accuracy of the analysis.

[0104] The parsed text data is then processed using natural language processing techniques to classify the resulting text data and generate vocabulary lists, exercise books, reference books, etc. using appropriate templates. This is done using Python scripts and NLP (Natural Language Processing) libraries (e.g., NLTK and spaCy).

[0105] Content Creation and Delivery

[0106] The generated learning materials (vocabulary book, workbook, references) are compressed again and sent to the device using the HTTPS protocol. Users can view these materials through a dedicated application, which provides an intuitive interface and is developed using React Native.

[0107] Examples and Prompts

[0108] As a concrete example, let's imagine a user takes a picture of a page about "cell division" in a high school biology notebook. The user launches the camera app and takes a picture so that the entire notebook is clearly visible. The image data is then sent by the device to a server, where it is analyzed.

[0109] The server uses OCR and NLP techniques to extract text such as "cell division," "mitosis," and "meiosis," and generates learning materials like the following:

[0110] Vocabulary: "Mitosis: The process by which cells divide, resulting in the precise duplication of genetic material."

[0111] Question: Explain the difference between mitosis and meiosis. Answer: In mitosis...

[0112] Example prompt sentence:

[0113] "I have taken a photo of a handwritten high school biology notebook. The notebook contains a description of cell division. Please generate a vocabulary book and question set based on the content."

[0114] In this way, this system efficiently analyzes the contents of handwritten notes and automatically generates and provides optimal learning materials to users, thereby improving learning efficiency.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1:

[0117] The user takes a photo of their handwritten notes with an electronic device. The user launches the camera app on their smartphone or tablet and takes a photo of the handwritten notes. The input is the handwritten notes, and the output is an image file (e.g., JPEG format). This image file is temporarily stored in the device's internal storage.

[0118] Step 2:

[0119] The image data captured by the device is compressed and sent to the server via the network. The input is an image file (JPEG format) and the output is compressed image data. This data is sent securely using the HTTPS protocol. Specifically, the device compresses the image and executes the sending script to send it to the server.

[0120] Step 3:

[0121] The server analyzes the image data it receives using optical character recognition (OCR) technology and extracts text data. The input is compressed image data, and the output is analyzed text data. After receiving the image data, the server uses an OCR library to recognize handwritten characters and convert them into text. Specifically, the server uses OpenCV and Tesseract to perform preprocessing such as noise removal and binarization, and then performs character recognition.

[0122] Step 4:

[0123] The server preprocesses the extracted text data, removing noise and converting it to binary data. The input is raw text data, and the output is preprocessed text data. Specifically, the server performs text formatting, removing unnecessary whitespace, checking grammar, and other operations to improve analysis accuracy.

[0124] Step 5:

[0125] The server uses natural language processing technology to generate vocabulary lists, workbooks, and reference materials based on the classified text data. The input is preprocessed text data, and the output is the generated learning materials (vocabulary lists, workbooks, and reference materials). Specifically, the server uses Python scripts and NLP libraries (such as NLTK or spaCy) to insert data into appropriate templates to generate the learning materials.

[0126] Step 6:

[0127] The server compresses the generated content and transmits it to the electronic device again via the network. The input is the generated learning material, and the output is the compressed learning material data. Specifically, the server compresses the content and transmits it to the terminal via the HTTPS protocol.

[0128] Step 7:

[0129] The user views the generated content through a dedicated application. The input is the compressed data sent to the terminal, and the output is the learning materials that the user can view. Specifically, the user launches the application, views the decompressed learning materials, and uses them for learning.

[0130] In this way, each processing step of the system works together to efficiently extract data from handwritten notes and provide users with optimal learning materials.

[0131] (Application example 1)

[0132] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0133] Conventional learning systems have the problem that it takes a great deal of time and effort for users to digitize their handwritten notes and generate effective learning materials based on those contents. It is also difficult to properly manage the quality of the generated materials and the user's learning progress. Furthermore, there are many cases where the generated materials do not meet the individual learning needs of the user. There is a need to solve these problems and provide effective and efficient learning support.

[0134] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0135] In this invention, the server includes means for analyzing the contents of a user's handwritten notes and generating appropriate learning materials using a generative AI model, means for linking the generated learning materials with feedback and progress management functions, and means for classifying the extracted text data and generating content using different templates based on each category. This allows a user to automatically generate high-quality learning materials tailored to their individual learning needs simply by taking a photo of their handwritten notes, enabling effective and efficient learning.

[0136] "User" refers to an individual or organization that uses the system of the present invention to capture handwritten notes and generate study materials.

[0137] "Handwritten notes" are learning and memo notes that users write by hand on paper or a digital device.

[0138] "Terminal" refers to a smartphone, tablet, or other computing device used by a user that captures images of handwritten notes and transmits them to a server for analysis.

[0139] "Image data" refers to digital image data generated after photographing a handwritten note.

[0140] A "server" is a remote computer system that receives image data sent from a terminal and performs analysis and processing to generate teaching materials.

[0141] "Image analysis" is the process by which the server recognizes characters and figures from the image data it receives and extracts them as text data.

[0142] "Text data" refers to text information extracted through image analysis, and is the data that forms the basis for generating learning materials.

[0143] A "vocabulary book" is a learning material that includes a list of vocabulary or terms and their definitions or explanations, generated to assist users in their learning.

[0144] A "question bank" is a learning material that includes a set of questions and answers that are generated to facilitate understanding of the learning content.

[0145] A "bibliography" is a list of references or sources created to provide additional information or materials related to the learning content.

[0146] A "generative AI model" is an artificial intelligence model used within a server, and is a technology that automatically generates appropriate learning materials based on input text data.

[0147] "Feedback" refers to evaluations and advice provided based on a user's learning progress and performance.

[0148] The "progress management function" is a function that tracks the user's learning status and supports effective learning plans.

[0149] A "template" is a model for generating content set for each different category, and is a format for inserting extracted text data.

[0150] "Compression" is the process of reducing the size of image data for more efficient transmission to a server.

[0151] "Categories" are divisions for classifying extracted text data and help structure learning materials.

[0152] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system includes a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[0153] 1. The user takes a photo of their handwritten notes

[0154] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[0155] Examples:

[0156] When a user takes a photo of a "biology notebook," the device's camera is used to capture the entire notebook so that it is saved as a single image.

[0157] 2. The device sends the image data to the server

[0158] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[0159] 3. The server performs image analysis

[0160] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[0161] Software used:

[0162] OCR: Tesseract

[0163] Image processing: OpenCV

[0164] Examples:

[0165] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[0166] 4. The server generates learning materials based on the analysis results.

[0167] The server first categorizes the learning content based on the extracted text data, then generates vocabulary lists, practice questions, and reference materials for each category. This process uses a generative AI model to generate content using appropriate templates based on prompts.

[0168] Software used:

[0169] Language model: GPT-4 (OpenAI)

[0170] Programming languages: Python, Node.js

[0171] Example prompt sentence:

[0172] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[0173] --- Note contents ---

[0174] Title: Cell division

[0175] Contents: Mitosis, meiosis

[0176] --- Notes content ends here ---

[0177] Request details:

[0178] 1. Vocabulary

[0179] 2. Problem set

[0180] Output format:

[0181] 1. Vocabulary

[0182] Mitosis: (Explanation)

[0183] Meiosis: (Explanation)

[0184] 2. Problem set

[0185] 3 questions in question and answer format

[0186] 5. Sending server-generated content to the device

[0187] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0188] 6. Use user-generated learning materials

[0189] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study. It also works with feedback and progress management functions, allowing users to study efficiently while checking their progress.

[0190] Software used:

[0191] Application framework: Flutter, React Native

[0192] Database: SQLite

[0193] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] The user takes a photo of their handwritten notes using a smartphone or tablet (device). The user launches the device's camera app, frames the shot, and presses the shutter to capture image data. The input is the handwritten notes, and the output is image data. This image data is temporarily stored inside the device.

[0197] Step 2:

[0198] Compresses image data acquired by the device. A compression algorithm is used to reduce the size of the image and convert it into a format suitable for transmission. The input is raw image data, and the output is compressed image data.

[0199] Step 3:

[0200] Sends compressed image data to the server. The terminal transfers data to the server via the Internet using the HTTPS protocol. The input is the compressed image data and the output is the transmitted data. When the server receives the data, it sends an acknowledgment back to the terminal.

[0201] Step 4:

[0202] The server analyzes the received image data. The server applies OCR technology to extract handwritten characters in the image as text data. The software used is Tesseract and OpenCV. The input is image data, and the output is text data. Noise removal and binarization are performed to improve analysis accuracy.

[0203] Step 5:

[0204] The server classifies the extracted text data. Based on the text data, it organizes the learning content into categories and selects the appropriate template. The input is text data, and the output is classified text data.

[0205] Step 6:

[0206] The server generates learning materials using a generative AI model. It creates vocabulary books and question sets based on prompts using GPT-4 (OpenAI). The prompts include the content of handwritten notes and the format of the learning materials to be generated. The input is classified text data and prompts, and the output is the generated learning materials.

[0207] Example prompt sentence:

[0208] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[0209] --- Note contents ---

[0210] Title: Cell division

[0211] Contents: Mitosis, meiosis

[0212] --- Notes content ends here ---

[0213] Request details:

[0214] 1. Vocabulary

[0215] 2. Problem set

[0216] Output format:

[0217] 1. Vocabulary

[0218] Mitosis: (Explanation)

[0219] Meiosis: (Explanation)

[0220] 2. Problem set

[0221] 3 questions in question and answer format

[0222] Step 7:

[0223] The server compresses the generated content and sends it to the device. The data is transferred securely using the HTTPS protocol. The input is the generated learning material and the output is the transmitted data. The device decompresses the received data and saves it in its internal storage.

[0224] Step 8:

[0225] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application provides an intuitive user interface and is also integrated with feedback and progress management functions. The input is the generated learning material data, and the output is the user's learning progress and viewing of the materials.

[0226] The above processing flow provides a system that allows users to digitize their handwritten notes, automatically generate efficient learning materials, and manage their learning progress.

[0227] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0228] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[0229] 1. The user takes a photo of their handwritten notes

[0230] Users take a photo of their handwritten notes using a smartphone or tablet device, and the captured image data is temporarily saved in the device's internal storage.

[0231] As a concrete example, consider the case where a user takes a picture of their "math notebook." The user uses the device's camera app to take a picture so that the entire notebook is saved as a single image.

[0232] 2. The device sends the image data to the server

[0233] The device compresses the stored image data and sends it to the server over the Internet, using the HTTPS protocol to ensure data security, and waits for a confirmation response from the server after the transmission is complete.

[0234] 3. The server performs image analysis

[0235] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[0236] As a concrete example of the server analyzing an image of a "math notebook," the following shows how the title "Quadratic Equation" and the content "Solution Formula, Factorization" are extracted as text data.

[0237] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[0238] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[0239] For example, the server generates the following vocabulary list from the analysis of "quadratic equations":

[0240] "Formula for finding the solution of ax^2 + bx + c = 0"

[0241] "Factorization: A method of decomposing one polynomial into two or more polynomials"

[0242] It also generates a set of questions:

[0243] "Question: Solve the quadratic equation using the formula. Answer: x = (-b±√(b^2-4ac)) / 2a"

[0244] 5. Sending server-generated content to the device

[0245] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0246] 6. Emotion engine recognizes user emotions

[0247] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to the server.

[0248] 7. Emotional Content Presentation

[0249] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[0250] 8. Use user-generated learning materials

[0251] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by the emotion engine.

[0252] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials according to the user's emotional state, thereby significantly improving the efficiency and effectiveness of learning.

[0253] The processing flow will be explained below.

[0254] Step 1:

[0255] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[0256] Step 2:

[0257] The device compresses the image data it captures. The device uses a compression algorithm to reduce the size of the image file and improve transfer efficiency. The compressed image data is temporarily stored in internal storage.

[0258] Step 3:

[0259] The device sends the compressed image data to the server. The device sends the image data to the server's upload URL using an HTTP request. The HTTPS protocol is used to ensure security. When the server receives the data, it returns a confirmation message to the device that reception has been completed.

[0260] Step 4:

[0261] The server analyzes the image data. It then launches an image analysis module and uses OCR technology to identify handwritten characters and graphics. It first performs preprocessing such as noise removal and binarization, then performs character analysis. It extracts text data as the analysis result and stores it in an internal database.

[0262] Step 5:

[0263] The server classifies the extracted text data. The server extracts keywords from the text data and classifies each keyword into categories, such as mathematics, science, history, etc. Based on the classification results, the server prepares to generate content using appropriate templates.

[0264] Step 6:

[0265] The server generates a vocabulary list, a workbook, and a bibliography. The server selects a template for each category and inserts the extracted text data into the template. For example, the server inserts keywords and their explanations into the vocabulary list, related questions and answers into the workbook, and links to related books and websites into the bibliography.

[0266] Step 7:

[0267] The server sends the generated content to the terminal. The server packages the generated content data and sends it to the terminal using an HTTP response. The HTTPS protocol is used to keep the data secure. After transmission is complete, a confirmation message is sent back to the terminal.

[0268] Step 8:

[0269] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that data reception is complete.

[0270] Step 9:

[0271] The user launches the dedicated application, and the emotion recognition engine captures the user's facial expressions. The device's camera periodically acquires images of the user's face and analyzes them to recognize their emotional state. The recognized emotion data is then sent to the server.

[0272] Step 10:

[0273] The server adjusts the way content is presented based on emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or prioritize relaxation content.

[0274] Step 11:

[0275] Users can access the generated learning materials. They can browse the generated vocabulary books, workbooks, and reference materials through a dedicated application. Personalized content is displayed according to the user's emotional state, improving the efficiency and effectiveness of learning.

[0276] Example 2

[0277] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0278] Traditional learning systems that use handwritten notes lack the ability to efficiently organize note content and improve learning efficiency through automatically generated learning materials. Furthermore, there is no system that provides appropriate learning support according to the user's emotional state, making it difficult to improve learning efficiency and provide a personalized learning experience.

[0279] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0280] In this invention, the server includes: means for a user to photograph handwritten notes; means for a terminal to transmit the photographed image data to the server; means for the server to analyze the image data and extract text data; means for the server to generate a vocabulary book, a workbook, and reference materials based on the extracted text data; means for the server to transmit the generated content to the terminal; means for a user to view the generated content through the terminal; emotion engine means for capturing the user's facial expressions using a camera in the terminal and recognizing their emotional state; and means for the server to adjust the presentation method of the study content based on the recognized emotion data. This makes it possible to effectively organize the contents of handwritten notes and automatically generate and provide study materials that correspond to the user's emotional state.

[0281] "User" refers to an individual user who uses handwritten notes and utilizes functions such as photography, learning, and emotion recognition through the system.

[0282] "Device" refers to a portable electronic device, such as a smartphone or tablet, that a user uses to capture handwritten notes and store, compress, and transmit the image data.

[0283] "Server" refers to a central processing unit that receives image data sent from a terminal, analyzes the image, extracts text data, generates content, receives user emotional data, and delivers optimal learning content.

[0284] "Image data" refers to the digital image file that a user takes of their handwritten notes and stores on their device.

[0285] "Image analysis" refers to the technical means of processing received image data, identifying handwritten characters and graphics in the image, and converting them into text data.

[0286] "Text data" refers to data in text format that expresses the contents of handwritten notes extracted by image analysis.

[0287] "Extracted text data" refers to information that the server identifies through image analysis and extracts in text form.

[0288] A "vocabulary book" refers to a learning material that organizes technical terms and words necessary for the learning content and lists them, including their meanings and usage.

[0289] A "problem book" refers to a learning material that provides organized practice questions and explanations based on extracted text data.

[0290] "References" refers to materials or literature that provide additional information or in-depth content related to the learning content.

[0291] "Content" refers to the entire information package that users use when studying, such as vocabulary lists, workbooks, and reference materials.

[0292] "Emotion engine" refers to a technical means of analyzing a user's facial expressions and recognizing their emotional state (e.g., joy, sadness, stress, etc.).

[0293] "Emotional data" refers to data that quantifies or categorizes the user's emotional state obtained through analysis by the emotion engine.

[0294] "Learning content presentation method" refers to the means by which learning content is presented to a user in a manner that is responsive to the user's emotional state.

[0295] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[0296] The user takes a picture of the handwritten notes using a smartphone or tablet (hereinafter referred to as the "device"). The captured image data is temporarily stored in the device's internal storage. The specific hardware used is the camera function of the smartphone or tablet.

[0297] Next, the device sends the image data to the server. The image data is compressed and then sent to the server via the Internet. At this time, the HTTPS protocol is used to ensure data security. After the transmission is complete, a confirmation response from the server is awaited. Specific software used is an image compression library (e.g., Picasso, Glide) or an HTTP request library (e.g., Retrofit).

[0298] The server launches an image analysis module to analyze the received image data. Specifically, it uses OCR (Optical Character Recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization. The specific software used is the OpenCV library and Tesseract OCR.

[0299] The server categorizes the learning content based on the extracted text data and generates vocabulary books, exercise books, and reference materials for each category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, it uses a generative AI model (e.g., GPT-3) to optimize the generated learning content.

[0300] The server sends the generated content to the device, where it is compressed again and securely transferred using the HTTPS protocol. The device then decompresses the received data and stores it in its internal storage.

[0301] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to a server. The specific software used is an emotion analysis engine (e.g., Microsoft Azure Face API).

[0302] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize displaying information on relaxation techniques and easy questions to reduce the learning load.

[0303] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application has an intuitive user interface and is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by an emotion engine.

[0304] Specific examples

[0305] Example prompt sentence:

[0306] "Please provide a detailed description of the system that automatically analyzes the contents of handwritten notes and generates effective learning materials that match the user's emotional state. Please include the entire process, from the user taking a photo of the notes with their smartphone to the provision of learning content based on the emotional data."

[0307] In this way, the present invention provides a system that effectively organizes the contents of handwritten notes and automatically generates and provides learning materials that correspond to the user's emotional state, thereby improving the efficiency and effectiveness of learning.

[0308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0309] Step 1:

[0310] The user takes a photo of their handwritten notes

[0311] The user uses a device (smartphone or tablet) to take an image of their handwritten notes. The input data is the physical handwritten notes, and the output is a digital image file. This digital image file is temporarily stored in the device's internal storage.

[0312] Specific operation: The user opens the camera app, adjusts the camera so that the entire handwritten note is in view, and presses the shutter button to take a picture. After taking the picture, the image is saved in the "Photos" app or similar.

[0313] Step 2:

[0314] The device sends the image data to the server.

[0315] The device selects the stored image data, compresses it, and then sends it to the server via the Internet. The input data is the captured image data, and the output is the compressed image data. The HTTPS protocol is used to ensure data security, and a confirmation response from the server is waited for after transmission is complete.

[0316] Specific operation: After the device selects an image, it compresses the data using an image compression library (e.g., Picasso or Glide), then sends the image data to the server using an HTTP request library (e.g., Retrofit), and receives a "data reception completed" confirmation message as a response.

[0317] Step 3:

[0318] The server performs image analysis

[0319] The server launches an image analysis module to analyze the received image data. The input data is compressed image data, and the output is extracted text data. OCR (Optical Character Recognition) technology is used to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[0320] Specific operation: The server preprocesses the received image using the OpenCV library, then calls Tesseract OCR to analyze the handwritten characters and extract keywords such as "quadratic equation," "solution formula," and "factorization" as text.

[0321] Step 4:

[0322] The server generates learning materials based on the analysis results.

[0323] The server categorizes the learning content based on the extracted text data and generates vocabulary books, workbooks, and reference materials for each category. The input data is the extracted text data, and the output is learning materials generated by category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, a generative AI model (e.g., GPT-3) is used to optimize the generated learning content.

[0324] How it works: The server stores the text data in a database and runs a category classification algorithm. After classification, it invokes a generative AI model, inserts the text into templates, and automatically generates a vocabulary book and exercises that explain "solution formulas" and "factorization."

[0325] Step 5:

[0326] Sending server-generated content to the device

[0327] The server sends the generated vocabulary book, question book, and reference materials to the device. The input data is the generated learning materials, and the output is the transmission of compressed data. The transmitted data is compressed again and securely transferred. The device decompresses the received data and saves it in its internal storage.

[0328] Specific operation: The server compresses the generated content in Zip format and sends it to the device via an HTTP request. The device unzips the received Zip file and saves it in the app's internal storage.

[0329] Step 6:

[0330] Emotion engine recognizes user emotions

[0331] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input data is image data of the captured facial expressions, and the output is recognized emotion data. The emotion engine analyzes the captured image data, recognizes the user's emotional state, and sends the data to the server.

[0332] How it works: When a user opens the app, the camera automatically activates and detects their face. The emotion engine analyzes the user's facial expressions, identifies emotions such as "joy" or "stress," and sends the data to the server.

[0333] Step 7:

[0334] Emotion-based content presentation

[0335] The server adjusts the presentation of the generated learning content based on the received emotional data. The input data is the emotional data, and the output is the adjusted learning content. If the user is feeling stressed, it will prioritize displaying easy problems or information on relaxation techniques.

[0336] How it works: The server receives the emotion data and uses an AI model to select appropriate content. If the user is in a stressful state, it generates a page containing short questions and relaxation guides and sends it to a dedicated app.

[0337] Step 8:

[0338] Use user-generated learning materials

[0339] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The input data is the learning materials stored on the device, and the output is the user's learning results. The application has an intuitive user interface and is designed to allow users to easily access the learning content. In addition, the content is personalized based on the emotional state recognized by the emotion engine.

[0340] What it does: If a user is browsing a vocabulary book within the app and is feeling stressed, the app will provide a personalized learning experience based on the user's emotions, such as playing relaxing music while displaying the learning content.

[0341] (Application example 2)

[0342] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0343] Conventional industrial robots operate according to pre-programmed work procedures, but their lack of flexibility makes it difficult to quickly incorporate handwritten work instructions on-site. Furthermore, they are unable to take into account the emotional state of the worker, raising concerns that work efficiency may decline in environments prone to stress or strain. The lack of a system that can immediately respond to handwritten instructions or reflect the emotional state of the worker poses challenges in ensuring sufficient work efficiency and safety.

[0344] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0345] In this invention, the server includes a means for recognizing the emotional state of the user, a means for adjusting the content presentation method according to the emotional state of the user, a means for generating a work procedure to be performed by the industrial robot based on the analyzed text data, and a means for the industrial robot to execute the generated work procedure, thereby enabling immediate response to handwritten instructions and optimizing the work environment based on the emotional state of the worker.

[0346] A "handwritten notebook" is a notebook containing information that is handwritten by the user using a writing instrument.

[0347] "Image data" refers to data representing visual digital information generated by a user photographing a handwritten note.

[0348] A "server" is a computer system that receives, analyzes, stores, and transmits data over a network.

[0349] "Text data" refers to data that indicates character information extracted from image data using OCR technology.

[0350] A "vocabulary book" is a book containing words, their meanings, and definitions to aid in learning and memorization.

[0351] A "workbook" is a teaching material that includes a set of questions and their answers related to a specific learning content.

[0352] "References" are related materials and documents that deepen understanding of specific learning content.

[0353] "Emotional state" refers to the user's psychological state, such as happiness, sadness, or stress.

[0354] "Content presentation" refers to how the generated learning materials and information are displayed and provided to the user.

[0355] An "industrial robot" is an automated mechanical device used in an industrial setting that has the ability to perform specific tasks.

[0356] A "work procedure" is a series of operations or operational procedures that an industrial robot must execute.

[0357] Overall system picture

[0358] The system of the present invention allows users to take photos of their handwritten notes, analyzes the content, and provides learning content and work procedures. It also includes a function to adjust the way content is presented based on the user's emotional state, and automatically execute work procedures using an industrial robot.

[0359] Hardware and software used

[0360] Hardware:

[0361] Smartphone or tablet (with camera)

[0362] Server (high-performance CPU, GPU, storage)

[0363] industrial robots

[0364] software:

[0365] Python

[0366] OCR tool (Pytesseract)

[0367] Image processing library (OpenCV)

[0368] Emotion recognition API (Microsoft Azure Face API)

[0369] Web frameworks (Flask / Django)

[0370] Communication protocol (HTTPS)

[0371] Specific operation of the system

[0372] 1. Photographing handwritten notes

[0373] Users take a photo of their handwritten notes using a smartphone or tablet, and the image data is temporarily stored in the device's internal storage.

[0374] 2. Sending image data

[0375] The device compresses the stored image data and sends it to the server using the HTTPS protocol, which encrypts the data to ensure its security and returns a confirmation response after the transmission is complete.

[0376] 3. Analysis of image data

[0377] The server analyzes the image data using OCR technology and extracts handwritten characters and graphics as text data. This process includes preprocessing such as noise removal and binarization.

[0378] 4. Content Generation

[0379] The server generates vocabulary books, exercise books, and reference books based on the extracted text data by inserting the text data using appropriate templates.

[0380] 5. Submission of Content

[0381] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is again securely transferred via HTTPS. The device unpacks the received data and saves it in its internal storage.

[0382] 6. Emotional Recognition

[0383] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state. The recognized emotion data is then sent to the server.

[0384] 7. Emotional Content Presentation

[0385] The server adjusts the presentation of the generated learning content based on the received emotional data: if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[0386] 8. Workflow generation and execution

[0387] The server generates work procedures for the industrial robot based on the analyzed text data, and the robot then executes the work procedures. This allows the contents of handwritten instructions to be efficiently incorporated, enabling flexible work.

[0388] Examples of concrete examples and prompts

[0389] Examples:

[0390] A factory worker writes down the work procedures for a new product line in a handwritten notebook and takes a photo of the notes with a smartphone. The photo data is sent to a server and analyzed using OCR. Based on the analysis results, an industrial robot executes the work procedures and responds quickly.

[0391] Example prompt sentence:

[0392] "Generate work procedures for an industrial robot from photographed data of handwritten notes. The data will include the following information: work procedures, precautions, and tools to be used. Please tell me how to implement a system that generates an appropriate work plan based on the analysis results and sends it to the robot."

[0393] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0394] Step 1:

[0395] The user takes an image of their handwritten notes using a smartphone or tablet. The input is the handwritten notes, and the output is the captured image data. Specifically, the user launches the camera app to take a picture of the notes, and the image data is saved in the device's internal storage.

[0396] Step 2:

[0397] The device compresses the captured image data and sends it to the server using the HTTPS protocol. The input is the image data stored in the internal storage, and the output is the transmission of the compressed image data to the server. Specifically, the device runs the compression algorithm, encrypts the compressed data using HTTPS, and sends it to the server.

[0398] Step 3:

[0399] The server uses OCR technology to analyze the received image data. The input is compressed image data, and the output is analyzed text data. Specifically, the server first decompresses the data and then uses Pytesseract or OpenCV to extract handwritten characters and shapes from the image as text data.

[0400] Step 4:

[0401] The server generates vocabulary books, exercise books, and reference materials based on the extracted text data. The input is the analyzed text data, and the output is the generated learning content. Specifically, the server inserts the text data into appropriate templates, classifies them into categories, and generates content.

[0402] Step 5:

[0403] The server sends the generated learning content to the terminal. The input is the generated learning content, and the output is the data that has been sent to the terminal. Specifically, the server compresses the data again and sends it securely to the terminal using the HTTPS protocol.

[0404] Step 6:

[0405] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input is the user's facial expressions, and the output is the captured image data. Specifically, the device starts up the camera, captures the user's facial expressions, and saves the image data in its internal storage.

[0406] Step 7:

[0407] The server receives the captured image data and uses an emotion engine to recognize the user's emotional state. The input is the captured image data, and the output is the recognized emotion data. Specifically, the server uses the Microsoft Azure Face API to analyze the image data and evaluate the emotional state.

[0408] Step 8:

[0409] The server adjusts the presentation method of the generated learning content based on the received emotional data. The input is the emotional data and learning content, and the output is the adjusted presentation method. Specifically, the server evaluates the emotional data and determines how to prioritize the presentation of relaxation information and easy questions.

[0410] Step 9:

[0411] The server generates work procedures to be executed by the industrial robot based on the analyzed text data. The input is text data and the output is work procedures. Specifically, the server analyzes the text data, generates appropriate work procedures, and transmits them to the robot.

[0412] Step 10:

[0413] Industrial robots perform tasks according to the procedures provided by the server. The input is the procedure, and the output is the executed task. In terms of specific operations, the robot acts as instructed and completes the specified task.

[0414] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0415] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0416] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0420] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0421] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0422] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0423] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0424] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0425] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0426] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0427] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0428] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0429] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0430] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system involves a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[0431] 1. The user takes a photo of their handwritten notes

[0432] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[0433] As a concrete example, consider the case where a user takes a photo of a biology notebook. The user uses the device's camera to capture the entire notebook so that it is saved as a single image.

[0434] 2. The device sends the image data to the server

[0435] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[0436] 3. The server performs image analysis

[0437] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[0438] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[0439] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[0440] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[0441] For example, the server might generate the following vocabulary list from the analysis of "cell division":

[0442] "Mitosis: the process by which cells divide, resulting in the accurate duplication of genetic material."

[0443] "Meiosis: A specialized division that occurs during the production of germ cells"

[0444] It also generates a set of questions:

[0445] "Question: Explain the difference between mitosis and meiosis. Answer: In mitosis..."

[0446] 5. Sending server-generated content to the device

[0447] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0448] 6. Use user-generated learning materials

[0449] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study.

[0450] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[0451] The processing flow will be explained below.

[0452] Step 1:

[0453] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[0454] Step 2:

[0455] The device sends the captured image data to the server. The device first compresses the image data and sends it to the server's upload URL using the HTTPS protocol. After sending is complete, the device waits for a confirmation response from the server.

[0456] Step 3:

[0457] The server receives the image data. The server verifies the received image data and checks the data format and completeness. If there are no problems, the server returns a receipt confirmation message to the terminal.

[0458] Step 4:

[0459] The server performs image analysis. The server launches an image analysis module and uses OCR technology to identify handwritten characters and figures in the image. This process also involves preprocessing such as noise removal and binarization. Text data is extracted as a result of the analysis.

[0460] Step 5:

[0461] The server classifies the extracted text data and applies a keyword extraction algorithm to detect important words and phrases, which are then used to categorize the learning content.

[0462] Step 6:

[0463] The server generates a vocabulary list, a question bank, and a reference book. The server selects an appropriate template based on each category and generates content by inserting the extracted text data. The generated content includes keywords and their explanations (vocabulary list), related questions and answers (questions), and links to reference books and websites (reference book).

[0464] Step 7:

[0465] The server sends the generated content to the terminal. The server packages the content data and sends it to the terminal using the HTTPS protocol. After the transmission is complete, a confirmation message is sent back to the terminal.

[0466] Step 8:

[0467] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that reception is complete.

[0468] Step 9:

[0469] The user accesses the generated learning materials. They launch a dedicated application and view the generated vocabulary book, practice questions, and reference materials. They can sort the content and mark important points.

[0470] These are the specific processing steps of the program. This series of steps allows users to effectively organize the contents of their handwritten notes and use them as learning materials.

[0471] Example 1

[0472] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] Learning using handwritten notes has the problem that it is difficult to manage and search for information, and creating learning materials manually requires time and effort. Furthermore, there is a need for a method to efficiently analyze the data from photographed notes and extract information that can be used as effective learning materials. Current technology does not provide sufficient efficiency for extracting data from handwritten notes and generating learning materials, making it difficult to improve learning efficiency.

[0474] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0475] In this invention, the server includes means for analyzing received image data using optical character recognition technology and extracting text data, means for preprocessing the extracted text data, such as noise removal and binarization, and means for generating vocabulary lists, workbooks, and reference materials using natural language processing technology based on the classified text data. This makes it possible to efficiently extract data from handwritten notes and automatically generate effective and systematic study materials.

[0476] A "user" is someone who uses this system to take pictures of handwritten notes and view the generated content.

[0477] "Electronic devices" refer to portable devices such as smartphones and tablets that capture images of handwritten notes and send the image data to a server.

[0478] A "server" is a computer system that analyzes received image data, extracts and processes text data, and generates learning materials based on that data.

[0479] "Means" refers to the method or apparatus used by the system to perform a particular function or operation.

[0480] "Optical character recognition technology" is a technology that recognizes characters from image data and converts them into text data.

[0481] "Preprocessing" refers to processing of image data, such as noise removal and binarization, in order to improve the accuracy of analysis.

[0482] "Text data" is character information extracted using optical character recognition technology.

[0483] "Natural language processing technology" is a set of technologies that enable computers to understand and generate human language.

[0484] "Content" refers to server-generated learning materials such as vocabulary books, workbooks, and reference materials.

[0485] A "template" is a format that pre-designs the form and framework of the content to be generated.

[0486] "Network" refers to a communications infrastructure such as the Internet, and is a means for connecting electronic devices and servers.

[0487] A "dedicated application" is specific software that a user uses to view generated content.

[0488] This system allows users to take photos of their handwritten notes, and a server analyzes the content to automatically generate learning materials. This system provides a series of processes, from taking photos of the user's handwritten notes to analyzing the images, generating learning materials, and providing them to the user.

[0489] Hardware and Software Use

[0490] User side

[0491] A user uses an electronic device such as a smartphone or tablet. The device launches a camera application and takes a photo of the handwritten note. After the photo is taken, the image data is temporarily stored in the device's internal storage. Specific camera applications include the standard camera app found on most smartphones.

[0492] Terminal side

[0493] The device compresses the captured image data and sends the compressed data to the server using the HTTPS protocol. The software used in this step includes an image compression library and a secure communication protocol (e.g., OpenSSL).

[0494] Server side

[0495] The server uses OCR (Optical Character Recognition) technology to analyze the received image data. Image analysis libraries such as OpenCV and Tesseract are used for this analysis. The server performs preprocessing such as noise removal and binarization to improve the accuracy of the analysis.

[0496] The parsed text data is then processed using natural language processing techniques to classify the resulting text data and generate vocabulary lists, exercise books, reference books, etc. using appropriate templates. This is done using Python scripts and NLP (Natural Language Processing) libraries (e.g., NLTK and spaCy).

[0497] Content Creation and Delivery

[0498] The generated learning materials (vocabulary book, workbook, references) are compressed again and sent to the device using the HTTPS protocol. Users can view these materials through a dedicated application, which provides an intuitive interface and is developed using React Native.

[0499] Examples and Prompts

[0500] As a concrete example, let's imagine a user takes a picture of a page about "cell division" in a high school biology notebook. The user launches the camera app and takes a picture so that the entire notebook is clearly visible. The image data is then sent by the device to a server, where it is analyzed.

[0501] The server uses OCR and NLP techniques to extract text such as "cell division," "mitosis," and "meiosis," and generates learning materials like the following:

[0502] Vocabulary: "Mitosis: The process by which cells divide, resulting in the precise duplication of genetic material."

[0503] Question: Explain the difference between mitosis and meiosis. Answer: In mitosis...

[0504] Example prompt sentence:

[0505] "I have taken a photo of a handwritten high school biology notebook. The notebook contains a description of cell division. Please generate a vocabulary book and question set based on the content."

[0506] In this way, this system efficiently analyzes the contents of handwritten notes and automatically generates and provides optimal learning materials to users, thereby improving learning efficiency.

[0507] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0508] Step 1:

[0509] The user takes a photo of their handwritten notes with an electronic device. The user launches the camera app on their smartphone or tablet and takes a photo of the handwritten notes. The input is the handwritten notes, and the output is an image file (e.g., JPEG format). This image file is temporarily stored in the device's internal storage.

[0510] Step 2:

[0511] The image data captured by the device is compressed and sent to the server via the network. The input is an image file (JPEG format) and the output is compressed image data. This data is sent securely using the HTTPS protocol. Specifically, the device compresses the image and executes the sending script to send it to the server.

[0512] Step 3:

[0513] The server analyzes the image data it receives using optical character recognition (OCR) technology and extracts text data. The input is compressed image data, and the output is analyzed text data. After receiving the image data, the server uses an OCR library to recognize handwritten characters and convert them into text. Specifically, the server uses OpenCV and Tesseract to perform preprocessing such as noise removal and binarization, and then performs character recognition.

[0514] Step 4:

[0515] The server preprocesses the extracted text data, removing noise and converting it to binary data. The input is raw text data, and the output is preprocessed text data. Specifically, the server performs text formatting, removing unnecessary whitespace, checking grammar, and other operations to improve analysis accuracy.

[0516] Step 5:

[0517] The server uses natural language processing technology to generate vocabulary lists, workbooks, and reference materials based on the classified text data. The input is preprocessed text data, and the output is the generated learning materials (vocabulary lists, workbooks, and reference materials). Specifically, the server uses Python scripts and NLP libraries (such as NLTK or spaCy) to insert data into appropriate templates to generate the learning materials.

[0518] Step 6:

[0519] The server compresses the generated content and transmits it to the electronic device again via the network. The input is the generated learning material, and the output is the compressed learning material data. Specifically, the server compresses the content and transmits it to the terminal via the HTTPS protocol.

[0520] Step 7:

[0521] The user views the generated content through a dedicated application. The input is the compressed data sent to the terminal, and the output is the learning materials that the user can view. Specifically, the user launches the application, views the decompressed learning materials, and uses them for learning.

[0522] In this way, each processing step of the system works together to efficiently extract data from handwritten notes and provide users with optimal learning materials.

[0523] (Application example 1)

[0524] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0525] Conventional learning systems have the problem that it takes a great deal of time and effort for users to digitize their handwritten notes and generate effective learning materials based on those contents. It is also difficult to properly manage the quality of the generated materials and the user's learning progress. Furthermore, there are many cases where the generated materials do not meet the individual learning needs of the user. There is a need to solve these problems and provide effective and efficient learning support.

[0526] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0527] In this invention, the server includes means for analyzing the contents of a user's handwritten notes and generating appropriate learning materials using a generative AI model, means for linking the generated learning materials with feedback and progress management functions, and means for classifying the extracted text data and generating content using different templates based on each category. This allows a user to automatically generate high-quality learning materials tailored to their individual learning needs simply by taking a photo of their handwritten notes, enabling effective and efficient learning.

[0528] "User" refers to an individual or organization that uses the system of the present invention to capture handwritten notes and generate study materials.

[0529] "Handwritten notes" are learning and memo notes that users write by hand on paper or a digital device.

[0530] "Terminal" refers to a smartphone, tablet, or other computing device used by a user that captures images of handwritten notes and transmits them to a server for analysis.

[0531] "Image data" refers to digital image data generated after photographing a handwritten note.

[0532] A "server" is a remote computer system that receives image data sent from a terminal and performs analysis and processing to generate teaching materials.

[0533] "Image analysis" is the process by which the server recognizes characters and figures from the image data it receives and extracts them as text data.

[0534] "Text data" refers to text information extracted through image analysis, and is the data that forms the basis for generating learning materials.

[0535] A "vocabulary book" is a learning material that includes a list of vocabulary or terms and their definitions or explanations, generated to assist users in their learning.

[0536] A "question bank" is a learning material that includes a set of questions and answers that are generated to facilitate understanding of the learning content.

[0537] A "bibliography" is a list of references or sources created to provide additional information or materials related to the learning content.

[0538] A "generative AI model" is an artificial intelligence model used within a server, and is a technology that automatically generates appropriate learning materials based on input text data.

[0539] "Feedback" refers to evaluations and advice provided based on a user's learning progress and performance.

[0540] The "progress management function" is a function that tracks the user's learning status and supports effective learning plans.

[0541] A "template" is a model for generating content set for each different category, and is a format for inserting extracted text data.

[0542] "Compression" is the process of reducing the size of image data for more efficient transmission to a server.

[0543] "Categories" are divisions for classifying extracted text data and help structure learning materials.

[0544] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system includes a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[0545] 1. The user takes a photo of their handwritten notes

[0546] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[0547] Examples:

[0548] When a user takes a photo of a "biology notebook," the device's camera is used to capture the entire notebook so that it is saved as a single image.

[0549] 2. The device sends the image data to the server

[0550] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[0551] 3. The server performs image analysis

[0552] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[0553] Software used:

[0554] OCR: Tesseract

[0555] Image processing: OpenCV

[0556] Examples:

[0557] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[0558] 4. The server generates learning materials based on the analysis results.

[0559] The server first categorizes the learning content based on the extracted text data, then generates vocabulary lists, practice questions, and reference materials for each category. This process uses a generative AI model to generate content using appropriate templates based on prompts.

[0560] Software used:

[0561] Language model: GPT-4 (OpenAI)

[0562] Programming languages: Python, Node.js

[0563] Example prompt sentence:

[0564] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[0565] --- Note contents ---

[0566] Title: Cell division

[0567] Contents: Mitosis, meiosis

[0568] --- Notes content ends here ---

[0569] Request details:

[0570] 1. Vocabulary

[0571] 2. Problem set

[0572] Output format:

[0573] 1. Vocabulary

[0574] Mitosis: (Explanation)

[0575] Meiosis: (Explanation)

[0576] 2. Problem set

[0577] 3 questions in question and answer format

[0578] 5. Sending server-generated content to the device

[0579] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0580] 6. Use user-generated learning materials

[0581] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study. It also works with feedback and progress management functions, allowing users to study efficiently while checking their progress.

[0582] Software used:

[0583] Application framework: Flutter, React Native

[0584] Database: SQLite

[0585] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[0586] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0587] Step 1:

[0588] The user takes a photo of their handwritten notes using a smartphone or tablet (device). The user launches the device's camera app, frames the shot, and presses the shutter to capture image data. The input is the handwritten notes, and the output is image data. This image data is temporarily stored inside the device.

[0589] Step 2:

[0590] Compresses image data acquired by the device. A compression algorithm is used to reduce the size of the image and convert it into a format suitable for transmission. The input is raw image data, and the output is compressed image data.

[0591] Step 3:

[0592] Sends compressed image data to the server. The terminal transfers data to the server via the Internet using the HTTPS protocol. The input is the compressed image data and the output is the transmitted data. When the server receives the data, it sends an acknowledgment back to the terminal.

[0593] Step 4:

[0594] The server analyzes the received image data. The server applies OCR technology to extract handwritten characters in the image as text data. The software used is Tesseract and OpenCV. The input is image data, and the output is text data. Noise removal and binarization are performed to improve analysis accuracy.

[0595] Step 5:

[0596] The server classifies the extracted text data. Based on the text data, it organizes the learning content into categories and selects the appropriate template. The input is text data, and the output is classified text data.

[0597] Step 6:

[0598] The server generates learning materials using a generative AI model. It creates vocabulary books and question sets based on prompts using GPT-4 (OpenAI). The prompts include the content of handwritten notes and the format of the learning materials to be generated. The input is classified text data and prompts, and the output is the generated learning materials.

[0599] Example prompt sentence:

[0600] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[0601] --- Note contents ---

[0602] Title: Cell division

[0603] Contents: Mitosis, meiosis

[0604] --- Notes content ends here ---

[0605] Request details:

[0606] 1. Vocabulary

[0607] 2. Problem set

[0608] Output format:

[0609] 1. Vocabulary

[0610] Mitosis: (Explanation)

[0611] Meiosis: (Explanation)

[0612] 2. Problem set

[0613] 3 questions in question and answer format

[0614] Step 7:

[0615] The server compresses the generated content and sends it to the device. The data is transferred securely using the HTTPS protocol. The input is the generated learning material and the output is the transmitted data. The device decompresses the received data and saves it in its internal storage.

[0616] Step 8:

[0617] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application provides an intuitive user interface and is also integrated with feedback and progress management functions. The input is the generated learning material data, and the output is the user's learning progress and viewing of the materials.

[0618] The above processing flow provides a system that allows users to digitize their handwritten notes, automatically generate efficient learning materials, and manage their learning progress.

[0619] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0620] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[0621] 1. The user takes a photo of their handwritten notes

[0622] Users take a photo of their handwritten notes using a smartphone or tablet device, and the captured image data is temporarily saved in the device's internal storage.

[0623] As a concrete example, consider the case where a user takes a picture of their "math notebook." The user uses the device's camera app to take a picture so that the entire notebook is saved as a single image.

[0624] 2. The device sends the image data to the server

[0625] The device compresses the stored image data and sends it to the server over the Internet, using the HTTPS protocol to ensure data security, and waits for a confirmation response from the server after the transmission is complete.

[0626] 3. The server performs image analysis

[0627] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[0628] As a concrete example of the server analyzing an image of a "math notebook," the following shows how the title "Quadratic Equation" and the content "Solution Formula, Factorization" are extracted as text data.

[0629] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[0630] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[0631] For example, the server generates the following vocabulary list from the analysis of "quadratic equations":

[0632] "Formula for finding the solution of ax^2 + bx + c = 0"

[0633] "Factorization: A method of decomposing one polynomial into two or more polynomials"

[0634] It also generates a set of questions:

[0635] "Question: Solve the quadratic equation using the formula. Answer: x = (-b±√(b^2-4ac)) / 2a"

[0636] 5. Sending server-generated content to the device

[0637] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0638] 6. Emotion engine recognizes user emotions

[0639] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to the server.

[0640] 7. Emotional Content Presentation

[0641] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[0642] 8. Use user-generated learning materials

[0643] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by the emotion engine.

[0644] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials according to the user's emotional state, thereby significantly improving the efficiency and effectiveness of learning.

[0645] The processing flow will be explained below.

[0646] Step 1:

[0647] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[0648] Step 2:

[0649] The device compresses the image data it captures. The device uses a compression algorithm to reduce the size of the image file and improve transfer efficiency. The compressed image data is temporarily stored in internal storage.

[0650] Step 3:

[0651] The device sends the compressed image data to the server. The device sends the image data to the server's upload URL using an HTTP request. The HTTPS protocol is used to ensure security. When the server receives the data, it returns a confirmation message to the device that reception has been completed.

[0652] Step 4:

[0653] The server analyzes the image data. It then launches an image analysis module and uses OCR technology to identify handwritten characters and graphics. It first performs preprocessing such as noise removal and binarization, then performs character analysis. It extracts text data as the analysis result and stores it in an internal database.

[0654] Step 5:

[0655] The server classifies the extracted text data. The server extracts keywords from the text data and classifies each keyword into categories, such as mathematics, science, history, etc. Based on the classification results, the server prepares to generate content using appropriate templates.

[0656] Step 6:

[0657] The server generates a vocabulary list, a workbook, and a bibliography. The server selects a template for each category and inserts the extracted text data into the template. For example, the server inserts keywords and their explanations into the vocabulary list, related questions and answers into the workbook, and links to related books and websites into the bibliography.

[0658] Step 7:

[0659] The server sends the generated content to the terminal. The server packages the generated content data and sends it to the terminal using an HTTP response. The HTTPS protocol is used to keep the data secure. After transmission is complete, a confirmation message is sent back to the terminal.

[0660] Step 8:

[0661] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that data reception is complete.

[0662] Step 9:

[0663] The user launches the dedicated application, and the emotion recognition engine captures the user's facial expressions. The device's camera periodically acquires images of the user's face and analyzes them to recognize their emotional state. The recognized emotion data is then sent to the server.

[0664] Step 10:

[0665] The server adjusts the way content is presented based on emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or prioritize relaxation content.

[0666] Step 11:

[0667] Users can access the generated learning materials. They can browse the generated vocabulary books, workbooks, and reference materials through a dedicated application. Personalized content is displayed according to the user's emotional state, improving the efficiency and effectiveness of learning.

[0668] Example 2

[0669] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0670] Traditional learning systems that use handwritten notes lack the ability to efficiently organize note content and improve learning efficiency through automatically generated learning materials. Furthermore, there is no system that provides appropriate learning support according to the user's emotional state, making it difficult to improve learning efficiency and provide a personalized learning experience.

[0671] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0672] In this invention, the server includes: means for a user to photograph handwritten notes; means for a terminal to transmit the photographed image data to the server; means for the server to analyze the image data and extract text data; means for the server to generate a vocabulary book, a workbook, and reference materials based on the extracted text data; means for the server to transmit the generated content to the terminal; means for a user to view the generated content through the terminal; emotion engine means for capturing the user's facial expressions using a camera in the terminal and recognizing their emotional state; and means for the server to adjust the presentation method of the study content based on the recognized emotion data. This makes it possible to effectively organize the contents of handwritten notes and automatically generate and provide study materials that correspond to the user's emotional state.

[0673] "User" refers to an individual user who uses handwritten notes and utilizes functions such as photography, learning, and emotion recognition through the system.

[0674] "Device" refers to a portable electronic device, such as a smartphone or tablet, that a user uses to capture handwritten notes and store, compress, and transmit the image data.

[0675] "Server" refers to a central processing unit that receives image data sent from a terminal, analyzes the image, extracts text data, generates content, receives user emotional data, and delivers optimal learning content.

[0676] "Image data" refers to the digital image file that a user takes of their handwritten notes and stores on their device.

[0677] "Image analysis" refers to the technical means of processing received image data, identifying handwritten characters and graphics in the image, and converting them into text data.

[0678] "Text data" refers to data in text format that expresses the contents of handwritten notes extracted by image analysis.

[0679] "Extracted text data" refers to information that the server identifies through image analysis and extracts in text form.

[0680] A "vocabulary book" refers to a learning material that organizes technical terms and words necessary for the learning content and lists them, including their meanings and usage.

[0681] A "problem book" refers to a learning material that provides organized practice questions and explanations based on extracted text data.

[0682] "References" refers to materials or literature that provide additional information or in-depth content related to the learning content.

[0683] "Content" refers to the entire information package that users use when studying, such as vocabulary lists, workbooks, and reference materials.

[0684] "Emotion engine" refers to a technical means of analyzing a user's facial expressions and recognizing their emotional state (e.g., joy, sadness, stress, etc.).

[0685] "Emotional data" refers to data that quantifies or categorizes the user's emotional state obtained through analysis by the emotion engine.

[0686] "Learning content presentation method" refers to the means by which learning content is presented to a user in a manner that is responsive to the user's emotional state.

[0687] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[0688] The user takes a picture of the handwritten notes using a smartphone or tablet (hereinafter referred to as the "device"). The captured image data is temporarily stored in the device's internal storage. The specific hardware used is the camera function of the smartphone or tablet.

[0689] Next, the device sends the image data to the server. The image data is compressed and then sent to the server via the Internet. At this time, the HTTPS protocol is used to ensure data security. After the transmission is complete, a confirmation response from the server is awaited. Specific software used is an image compression library (e.g., Picasso, Glide) or an HTTP request library (e.g., Retrofit).

[0690] The server launches an image analysis module to analyze the received image data. Specifically, it uses OCR (Optical Character Recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization. The specific software used is the OpenCV library and Tesseract OCR.

[0691] The server categorizes the learning content based on the extracted text data and generates vocabulary books, exercise books, and reference materials for each category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, it uses a generative AI model (e.g., GPT-3) to optimize the generated learning content.

[0692] The server sends the generated content to the device, where it is compressed again and securely transferred using the HTTPS protocol. The device then decompresses the received data and stores it in its internal storage.

[0693] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to a server. The specific software used is an emotion analysis engine (e.g., Microsoft Azure Face API).

[0694] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize displaying information on relaxation techniques and easy questions to reduce the learning load.

[0695] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application has an intuitive user interface and is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by an emotion engine.

[0696] Specific examples

[0697] Example prompt sentence:

[0698] "Please provide a detailed description of the system that automatically analyzes the contents of handwritten notes and generates effective learning materials that match the user's emotional state. Please include the entire process, from the user taking a photo of the notes with their smartphone to the provision of learning content based on the emotional data."

[0699] In this way, the present invention provides a system that effectively organizes the contents of handwritten notes and automatically generates and provides learning materials that correspond to the user's emotional state, thereby improving the efficiency and effectiveness of learning.

[0700] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0701] Step 1:

[0702] The user takes a photo of their handwritten notes

[0703] The user uses a device (smartphone or tablet) to take an image of their handwritten notes. The input data is the physical handwritten notes, and the output is a digital image file. This digital image file is temporarily stored in the device's internal storage.

[0704] Specific operation: The user opens the camera app, adjusts the camera so that the entire handwritten note is in view, and presses the shutter button to take a picture. After taking the picture, the image is saved in the "Photos" app or similar.

[0705] Step 2:

[0706] The device sends the image data to the server.

[0707] The device selects the stored image data, compresses it, and then sends it to the server via the Internet. The input data is the captured image data, and the output is the compressed image data. The HTTPS protocol is used to ensure data security, and a confirmation response from the server is waited for after transmission is complete.

[0708] Specific operation: After the device selects an image, it compresses the data using an image compression library (e.g., Picasso or Glide), then sends the image data to the server using an HTTP request library (e.g., Retrofit), and receives a "data reception completed" confirmation message as a response.

[0709] Step 3:

[0710] The server performs image analysis

[0711] The server launches an image analysis module to analyze the received image data. The input data is compressed image data, and the output is extracted text data. OCR (Optical Character Recognition) technology is used to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[0712] Specific operation: The server preprocesses the received image using the OpenCV library, then calls Tesseract OCR to analyze the handwritten characters and extract keywords such as "quadratic equation," "solution formula," and "factorization" as text.

[0713] Step 4:

[0714] The server generates learning materials based on the analysis results.

[0715] The server categorizes the learning content based on the extracted text data and generates vocabulary books, workbooks, and reference materials for each category. The input data is the extracted text data, and the output is learning materials generated by category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, a generative AI model (e.g., GPT-3) is used to optimize the generated learning content.

[0716] How it works: The server stores the text data in a database and runs a category classification algorithm. After classification, it invokes a generative AI model, inserts the text into templates, and automatically generates a vocabulary book and exercises that explain "solution formulas" and "factorization."

[0717] Step 5:

[0718] Sending server-generated content to the device

[0719] The server sends the generated vocabulary book, question book, and reference materials to the device. The input data is the generated learning materials, and the output is the transmission of compressed data. The transmitted data is compressed again and securely transferred. The device decompresses the received data and saves it in its internal storage.

[0720] Specific operation: The server compresses the generated content in Zip format and sends it to the device via an HTTP request. The device unzips the received Zip file and saves it in the app's internal storage.

[0721] Step 6:

[0722] Emotion engine recognizes user emotions

[0723] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input data is image data of the captured facial expressions, and the output is recognized emotion data. The emotion engine analyzes the captured image data, recognizes the user's emotional state, and sends the data to the server.

[0724] How it works: When a user opens the app, the camera automatically activates and detects their face. The emotion engine analyzes the user's facial expressions, identifies emotions such as "joy" or "stress," and sends the data to the server.

[0725] Step 7:

[0726] Emotion-based content presentation

[0727] The server adjusts the presentation of the generated learning content based on the received emotional data. The input data is the emotional data, and the output is the adjusted learning content. If the user is feeling stressed, it will prioritize displaying easy problems or information on relaxation techniques.

[0728] How it works: The server receives the emotion data and uses an AI model to select appropriate content. If the user is in a stressful state, it generates a page containing short questions and relaxation guides and sends it to a dedicated app.

[0729] Step 8:

[0730] Use user-generated learning materials

[0731] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The input data is the learning materials stored on the device, and the output is the user's learning results. The application has an intuitive user interface and is designed to allow users to easily access the learning content. In addition, the content is personalized based on the emotional state recognized by the emotion engine.

[0732] What it does: If a user is browsing a vocabulary book within the app and is feeling stressed, the app will provide a personalized learning experience based on the user's emotions, such as playing relaxing music while displaying the learning content.

[0733] (Application example 2)

[0734] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0735] Conventional industrial robots operate according to pre-programmed work procedures, but their lack of flexibility makes it difficult to quickly incorporate handwritten work instructions on-site. Furthermore, they are unable to take into account the emotional state of the worker, raising concerns that work efficiency may decline in environments prone to stress or strain. The lack of a system that can immediately respond to handwritten instructions or reflect the emotional state of the worker poses challenges in ensuring sufficient work efficiency and safety.

[0736] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0737] In this invention, the server includes a means for recognizing the emotional state of the user, a means for adjusting the content presentation method according to the emotional state of the user, a means for generating a work procedure to be performed by the industrial robot based on the analyzed text data, and a means for the industrial robot to execute the generated work procedure, thereby enabling immediate response to handwritten instructions and optimizing the work environment based on the emotional state of the worker.

[0738] A "handwritten notebook" is a notebook containing information that is handwritten by the user using a writing instrument.

[0739] "Image data" refers to data representing visual digital information generated by a user photographing a handwritten note.

[0740] A "server" is a computer system that receives, analyzes, stores, and transmits data over a network.

[0741] "Text data" refers to data that indicates character information extracted from image data using OCR technology.

[0742] A "vocabulary book" is a book containing words, their meanings, and definitions to aid in learning and memorization.

[0743] A "workbook" is a teaching material that includes a set of questions and their answers related to a specific learning content.

[0744] "References" are related materials and documents that deepen understanding of specific learning content.

[0745] "Emotional state" refers to the user's psychological state, such as happiness, sadness, or stress.

[0746] "Content presentation" refers to how the generated learning materials and information are displayed and provided to the user.

[0747] An "industrial robot" is an automated mechanical device used in an industrial setting that has the ability to perform specific tasks.

[0748] A "work procedure" is a series of operations or operational procedures that an industrial robot must execute.

[0749] Overall system picture

[0750] The system of the present invention allows users to take photos of their handwritten notes, analyzes the content, and provides learning content and work procedures. It also includes a function to adjust the way content is presented based on the user's emotional state, and automatically execute work procedures using an industrial robot.

[0751] Hardware and software used

[0752] Hardware:

[0753] Smartphone or tablet (with camera)

[0754] Server (high-performance CPU, GPU, storage)

[0755] industrial robots

[0756] software:

[0757] Python

[0758] OCR tool (Pytesseract)

[0759] Image processing library (OpenCV)

[0760] Emotion recognition API (Microsoft Azure Face API)

[0761] Web frameworks (Flask / Django)

[0762] Communication protocol (HTTPS)

[0763] Specific operation of the system

[0764] 1. Photographing handwritten notes

[0765] Users take a photo of their handwritten notes using a smartphone or tablet, and the image data is temporarily stored in the device's internal storage.

[0766] 2. Sending image data

[0767] The device compresses the stored image data and sends it to the server using the HTTPS protocol, which encrypts the data to ensure its security and returns a confirmation response after the transmission is complete.

[0768] 3. Analysis of image data

[0769] The server analyzes the image data using OCR technology and extracts handwritten characters and graphics as text data. This process includes preprocessing such as noise removal and binarization.

[0770] 4. Content Generation

[0771] The server generates vocabulary books, exercise books, and reference books based on the extracted text data by inserting the text data using appropriate templates.

[0772] 5. Submission of Content

[0773] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is again securely transferred via HTTPS. The device unpacks the received data and saves it in its internal storage.

[0774] 6. Emotional Recognition

[0775] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state. The recognized emotion data is then sent to the server.

[0776] 7. Emotional Content Presentation

[0777] The server adjusts the presentation of the generated learning content based on the received emotional data: if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[0778] 8. Workflow generation and execution

[0779] The server generates work procedures for the industrial robot based on the analyzed text data, and the robot then executes the work procedures. This allows the contents of handwritten instructions to be efficiently incorporated, enabling flexible work.

[0780] Examples of concrete examples and prompts

[0781] Examples:

[0782] A factory worker writes down the work procedures for a new product line in a handwritten notebook and takes a photo of the notes with a smartphone. The photo data is sent to a server and analyzed using OCR. Based on the analysis results, an industrial robot executes the work procedures and responds quickly.

[0783] Example prompt sentence:

[0784] "Generate work procedures for an industrial robot from photographed data of handwritten notes. The data will include the following information: work procedures, precautions, and tools to be used. Please tell me how to implement a system that generates an appropriate work plan based on the analysis results and sends it to the robot."

[0785] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0786] Step 1:

[0787] The user takes an image of their handwritten notes using a smartphone or tablet. The input is the handwritten notes, and the output is the captured image data. Specifically, the user launches the camera app to take a picture of the notes, and the image data is saved in the device's internal storage.

[0788] Step 2:

[0789] The device compresses the captured image data and sends it to the server using the HTTPS protocol. The input is the image data stored in the internal storage, and the output is the transmission of the compressed image data to the server. Specifically, the device runs the compression algorithm, encrypts the compressed data using HTTPS, and sends it to the server.

[0790] Step 3:

[0791] The server uses OCR technology to analyze the received image data. The input is compressed image data, and the output is analyzed text data. Specifically, the server first decompresses the data and then uses Pytesseract or OpenCV to extract handwritten characters and shapes from the image as text data.

[0792] Step 4:

[0793] The server generates vocabulary books, exercise books, and reference materials based on the extracted text data. The input is the analyzed text data, and the output is the generated learning content. Specifically, the server inserts the text data into appropriate templates, classifies them into categories, and generates content.

[0794] Step 5:

[0795] The server sends the generated learning content to the terminal. The input is the generated learning content, and the output is the data that has been sent to the terminal. Specifically, the server compresses the data again and sends it securely to the terminal using the HTTPS protocol.

[0796] Step 6:

[0797] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input is the user's facial expressions, and the output is the captured image data. Specifically, the device starts up the camera, captures the user's facial expressions, and saves the image data in its internal storage.

[0798] Step 7:

[0799] The server receives the captured image data and uses an emotion engine to recognize the user's emotional state. The input is the captured image data, and the output is the recognized emotion data. Specifically, the server uses the Microsoft Azure Face API to analyze the image data and evaluate the emotional state.

[0800] Step 8:

[0801] The server adjusts the presentation method of the generated learning content based on the received emotional data. The input is the emotional data and learning content, and the output is the adjusted presentation method. Specifically, the server evaluates the emotional data and determines how to prioritize the presentation of relaxation information and easy questions.

[0802] Step 9:

[0803] The server generates work procedures to be executed by the industrial robot based on the analyzed text data. The input is text data and the output is work procedures. Specifically, the server analyzes the text data, generates appropriate work procedures, and transmits them to the robot.

[0804] Step 10:

[0805] Industrial robots perform tasks according to the procedures provided by the server. The input is the procedure, and the output is the executed task. In terms of specific operations, the robot acts as instructed and completes the specified task.

[0806] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0807] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0808] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0809] [Third embodiment]

[0810] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0811] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0812] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0813] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0814] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0815] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0816] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0817] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0818] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0819] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0820] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0821] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0822] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system involves a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[0823] 1. The user takes a photo of their handwritten notes

[0824] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[0825] As a concrete example, consider the case where a user takes a photo of a biology notebook. The user uses the device's camera to capture the entire notebook so that it is saved as a single image.

[0826] 2. The device sends the image data to the server

[0827] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[0828] 3. The server performs image analysis

[0829] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[0830] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[0831] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[0832] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[0833] For example, the server might generate the following vocabulary list from the analysis of "cell division":

[0834] "Mitosis: the process by which cells divide, resulting in the accurate duplication of genetic material."

[0835] "Meiosis: A specialized division that occurs during the production of germ cells"

[0836] It also generates a set of questions:

[0837] "Question: Explain the difference between mitosis and meiosis. Answer: In mitosis..."

[0838] 5. Sending server-generated content to the device

[0839] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0840] 6. Use user-generated learning materials

[0841] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study.

[0842] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[0843] The processing flow will be explained below.

[0844] Step 1:

[0845] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[0846] Step 2:

[0847] The device sends the captured image data to the server. The device first compresses the image data and sends it to the server's upload URL using the HTTPS protocol. After sending is complete, the device waits for a confirmation response from the server.

[0848] Step 3:

[0849] The server receives the image data. The server verifies the received image data and checks the data format and completeness. If there are no problems, the server returns a receipt confirmation message to the terminal.

[0850] Step 4:

[0851] The server performs image analysis. The server launches an image analysis module and uses OCR technology to identify handwritten characters and figures in the image. This process also involves preprocessing such as noise removal and binarization. Text data is extracted as a result of the analysis.

[0852] Step 5:

[0853] The server classifies the extracted text data and applies a keyword extraction algorithm to detect important words and phrases, which are then used to categorize the learning content.

[0854] Step 6:

[0855] The server generates a vocabulary list, a question bank, and a reference book. The server selects an appropriate template based on each category and generates content by inserting the extracted text data. The generated content includes keywords and their explanations (vocabulary list), related questions and answers (questions), and links to reference books and websites (reference book).

[0856] Step 7:

[0857] The server sends the generated content to the terminal. The server packages the content data and sends it to the terminal using the HTTPS protocol. After the transmission is complete, a confirmation message is sent back to the terminal.

[0858] Step 8:

[0859] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that reception is complete.

[0860] Step 9:

[0861] The user accesses the generated learning materials. They launch a dedicated application and view the generated vocabulary book, practice questions, and reference materials. They can sort the content and mark important points.

[0862] These are the specific processing steps of the program. This series of steps allows users to effectively organize the contents of their handwritten notes and use them as learning materials.

[0863] Example 1

[0864] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0865] Learning using handwritten notes has the problem that it is difficult to manage and search for information, and creating learning materials manually requires time and effort. Furthermore, there is a need for a method to efficiently analyze the data from photographed notes and extract information that can be used as effective learning materials. Current technology does not provide sufficient efficiency for extracting data from handwritten notes and generating learning materials, making it difficult to improve learning efficiency.

[0866] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0867] In this invention, the server includes means for analyzing received image data using optical character recognition technology and extracting text data, means for preprocessing the extracted text data, such as noise removal and binarization, and means for generating vocabulary lists, workbooks, and reference materials using natural language processing technology based on the classified text data. This makes it possible to efficiently extract data from handwritten notes and automatically generate effective and systematic study materials.

[0868] A "user" is someone who uses this system to take pictures of handwritten notes and view the generated content.

[0869] "Electronic devices" refer to portable devices such as smartphones and tablets that capture images of handwritten notes and send the image data to a server.

[0870] A "server" is a computer system that analyzes received image data, extracts and processes text data, and generates learning materials based on that data.

[0871] "Means" refers to the method or apparatus used by the system to perform a particular function or operation.

[0872] "Optical character recognition technology" is a technology that recognizes characters from image data and converts them into text data.

[0873] "Preprocessing" refers to processing of image data, such as noise removal and binarization, in order to improve the accuracy of analysis.

[0874] "Text data" is character information extracted using optical character recognition technology.

[0875] "Natural language processing technology" is a set of technologies that enable computers to understand and generate human language.

[0876] "Content" refers to server-generated learning materials such as vocabulary books, workbooks, and reference materials.

[0877] A "template" is a format that pre-designs the form and framework of the content to be generated.

[0878] "Network" refers to a communications infrastructure such as the Internet, and is a means for connecting electronic devices and servers.

[0879] A "dedicated application" is specific software that a user uses to view generated content.

[0880] This system allows users to take photos of their handwritten notes, and a server analyzes the content to automatically generate learning materials. This system provides a series of processes, from taking photos of the user's handwritten notes to analyzing the images, generating learning materials, and providing them to the user.

[0881] Hardware and Software Use

[0882] User side

[0883] A user uses an electronic device such as a smartphone or tablet. The device launches a camera application and takes a photo of the handwritten note. After the photo is taken, the image data is temporarily stored in the device's internal storage. Specific camera applications include the standard camera app found on most smartphones.

[0884] Terminal side

[0885] The device compresses the captured image data and sends the compressed data to the server using the HTTPS protocol. The software used in this step includes an image compression library and a secure communication protocol (e.g., OpenSSL).

[0886] Server side

[0887] The server uses OCR (Optical Character Recognition) technology to analyze the received image data. Image analysis libraries such as OpenCV and Tesseract are used for this analysis. The server performs preprocessing such as noise removal and binarization to improve the accuracy of the analysis.

[0888] The parsed text data is then processed using natural language processing techniques to classify the resulting text data and generate vocabulary lists, exercise books, reference books, etc. using appropriate templates. This is done using Python scripts and NLP (Natural Language Processing) libraries (e.g., NLTK and spaCy).

[0889] Content Creation and Delivery

[0890] The generated learning materials (vocabulary book, workbook, references) are compressed again and sent to the device using the HTTPS protocol. Users can view these materials through a dedicated application, which provides an intuitive interface and is developed using React Native.

[0891] Examples and Prompts

[0892] As a concrete example, let's imagine a user takes a picture of a page about "cell division" in a high school biology notebook. The user launches the camera app and takes a picture so that the entire notebook is clearly visible. The image data is then sent by the device to a server, where it is analyzed.

[0893] The server uses OCR and NLP techniques to extract text such as "cell division," "mitosis," and "meiosis," and generates learning materials like the following:

[0894] Vocabulary: "Mitosis: The process by which cells divide, resulting in the precise duplication of genetic material."

[0895] Question: Explain the difference between mitosis and meiosis. Answer: In mitosis...

[0896] Example prompt sentence:

[0897] "I have taken a photo of a handwritten high school biology notebook. The notebook contains a description of cell division. Please generate a vocabulary book and question set based on the content."

[0898] In this way, this system efficiently analyzes the contents of handwritten notes and automatically generates and provides optimal learning materials to users, thereby improving learning efficiency.

[0899] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0900] Step 1:

[0901] The user takes a photo of their handwritten notes with an electronic device. The user launches the camera app on their smartphone or tablet and takes a photo of the handwritten notes. The input is the handwritten notes, and the output is an image file (e.g., JPEG format). This image file is temporarily stored in the device's internal storage.

[0902] Step 2:

[0903] The image data captured by the device is compressed and sent to the server via the network. The input is an image file (JPEG format) and the output is compressed image data. This data is sent securely using the HTTPS protocol. Specifically, the device compresses the image and executes the sending script to send it to the server.

[0904] Step 3:

[0905] The server analyzes the image data it receives using optical character recognition (OCR) technology and extracts text data. The input is compressed image data, and the output is analyzed text data. After receiving the image data, the server uses an OCR library to recognize handwritten characters and convert them into text. Specifically, the server uses OpenCV and Tesseract to perform preprocessing such as noise removal and binarization, and then performs character recognition.

[0906] Step 4:

[0907] The server preprocesses the extracted text data, removing noise and converting it to binary data. The input is raw text data, and the output is preprocessed text data. Specifically, the server performs text formatting, removing unnecessary whitespace, checking grammar, and other operations to improve analysis accuracy.

[0908] Step 5:

[0909] The server uses natural language processing technology to generate vocabulary lists, workbooks, and reference materials based on the classified text data. The input is preprocessed text data, and the output is the generated learning materials (vocabulary lists, workbooks, and reference materials). Specifically, the server uses Python scripts and NLP libraries (such as NLTK or spaCy) to insert data into appropriate templates to generate the learning materials.

[0910] Step 6:

[0911] The server compresses the generated content and transmits it to the electronic device again via the network. The input is the generated learning material, and the output is the compressed learning material data. Specifically, the server compresses the content and transmits it to the terminal via the HTTPS protocol.

[0912] Step 7:

[0913] The user views the generated content through a dedicated application. The input is the compressed data sent to the terminal, and the output is the learning materials that the user can view. Specifically, the user launches the application, views the decompressed learning materials, and uses them for learning.

[0914] In this way, each processing step of the system works together to efficiently extract data from handwritten notes and provide users with optimal learning materials.

[0915] (Application example 1)

[0916] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0917] Conventional learning systems have the problem that it takes a great deal of time and effort for users to digitize their handwritten notes and generate effective learning materials based on those contents. It is also difficult to properly manage the quality of the generated materials and the user's learning progress. Furthermore, there are many cases where the generated materials do not meet the individual learning needs of the user. There is a need to solve these problems and provide effective and efficient learning support.

[0918] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0919] In this invention, the server includes means for analyzing the contents of a user's handwritten notes and generating appropriate learning materials using a generative AI model, means for linking the generated learning materials with feedback and progress management functions, and means for classifying the extracted text data and generating content using different templates based on each category. This allows a user to automatically generate high-quality learning materials tailored to their individual learning needs simply by taking a photo of their handwritten notes, enabling effective and efficient learning.

[0920] "User" refers to an individual or organization that uses the system of the present invention to capture handwritten notes and generate study materials.

[0921] "Handwritten notes" are learning and memo notes that users write by hand on paper or a digital device.

[0922] "Terminal" refers to a smartphone, tablet, or other computing device used by a user that captures images of handwritten notes and transmits them to a server for analysis.

[0923] "Image data" refers to digital image data generated after photographing a handwritten note.

[0924] A "server" is a remote computer system that receives image data sent from a terminal and performs analysis and processing to generate teaching materials.

[0925] "Image analysis" is the process by which the server recognizes characters and figures from the image data it receives and extracts them as text data.

[0926] "Text data" refers to text information extracted through image analysis, and is the data that forms the basis for generating learning materials.

[0927] A "vocabulary book" is a learning material that includes a list of vocabulary or terms and their definitions or explanations, generated to assist users in their learning.

[0928] A "question bank" is a learning material that includes a set of questions and answers that are generated to facilitate understanding of the learning content.

[0929] A "bibliography" is a list of references or sources created to provide additional information or materials related to the learning content.

[0930] A "generative AI model" is an artificial intelligence model used within a server, and is a technology that automatically generates appropriate learning materials based on input text data.

[0931] "Feedback" refers to evaluations and advice provided based on a user's learning progress and performance.

[0932] The "progress management function" is a function that tracks the user's learning status and supports effective learning plans.

[0933] A "template" is a model for generating content set for each different category, and is a format for inserting extracted text data.

[0934] "Compression" is the process of reducing the size of image data for more efficient transmission to a server.

[0935] "Categories" are divisions for classifying extracted text data and help structure learning materials.

[0936] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system includes a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[0937] 1. The user takes a photo of their handwritten notes

[0938] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[0939] Examples:

[0940] When a user takes a photo of a "biology notebook," the device's camera is used to capture the entire notebook so that it is saved as a single image.

[0941] 2. The device sends the image data to the server

[0942] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[0943] 3. The server performs image analysis

[0944] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[0945] Software used:

[0946] OCR: Tesseract

[0947] Image processing: OpenCV

[0948] Examples:

[0949] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[0950] 4. The server generates learning materials based on the analysis results.

[0951] The server first categorizes the learning content based on the extracted text data, then generates vocabulary lists, practice questions, and reference materials for each category. This process uses a generative AI model to generate content using appropriate templates based on prompts.

[0952] Software used:

[0953] Language model: GPT-4 (OpenAI)

[0954] Programming languages: Python, Node.js

[0955] Example prompt sentence:

[0956] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[0957] --- Note contents ---

[0958] Title: Cell division

[0959] Contents: Mitosis, meiosis

[0960] --- Notes content ends here ---

[0961] Request details:

[0962] 1. Vocabulary

[0963] 2. Problem set

[0964] Output format:

[0965] 1. Vocabulary

[0966] Mitosis: (Explanation)

[0967] Meiosis: (Explanation)

[0968] 2. Problem set

[0969] 3 questions in question and answer format

[0970] 5. Sending server-generated content to the device

[0971] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[0972] 6. Use user-generated learning materials

[0973] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study. It also works with feedback and progress management functions, allowing users to study efficiently while checking their progress.

[0974] Software used:

[0975] Application framework: Flutter, React Native

[0976] Database: SQLite

[0977] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[0978] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0979] Step 1:

[0980] The user takes a photo of their handwritten notes using a smartphone or tablet (device). The user launches the device's camera app, frames the shot, and presses the shutter to capture image data. The input is the handwritten notes, and the output is image data. This image data is temporarily stored inside the device.

[0981] Step 2:

[0982] Compresses image data acquired by the device. A compression algorithm is used to reduce the size of the image and convert it into a format suitable for transmission. The input is raw image data, and the output is compressed image data.

[0983] Step 3:

[0984] Sends compressed image data to the server. The terminal transfers data to the server via the Internet using the HTTPS protocol. The input is the compressed image data and the output is the transmitted data. When the server receives the data, it sends an acknowledgment back to the terminal.

[0985] Step 4:

[0986] The server analyzes the received image data. The server applies OCR technology to extract handwritten characters in the image as text data. The software used is Tesseract and OpenCV. The input is image data, and the output is text data. Noise removal and binarization are performed to improve analysis accuracy.

[0987] Step 5:

[0988] The server classifies the extracted text data. Based on the text data, it organizes the learning content into categories and selects the appropriate template. The input is text data, and the output is classified text data.

[0989] Step 6:

[0990] The server generates learning materials using a generative AI model. It creates vocabulary books and question sets based on prompts using GPT-4 (OpenAI). The prompts include the content of handwritten notes and the format of the learning materials to be generated. The input is classified text data and prompts, and the output is the generated learning materials.

[0991] Example prompt sentence:

[0992] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[0993] --- Note contents ---

[0994] Title: Cell division

[0995] Contents: Mitosis, meiosis

[0996] --- Notes content ends here ---

[0997] Request details:

[0998] 1. Vocabulary

[0999] 2. Problem set

[1000] Output format:

[1001] 1. Vocabulary

[1002] Mitosis: (Explanation)

[1003] Meiosis: (Explanation)

[1004] 2. Problem set

[1005] 3 questions in question and answer format

[1006] Step 7:

[1007] The server compresses the generated content and sends it to the device. The data is transferred securely using the HTTPS protocol. The input is the generated learning material and the output is the transmitted data. The device decompresses the received data and saves it in its internal storage.

[1008] Step 8:

[1009] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application provides an intuitive user interface and is also integrated with feedback and progress management functions. The input is the generated learning material data, and the output is the user's learning progress and viewing of the materials.

[1010] The above processing flow provides a system that allows users to digitize their handwritten notes, automatically generate efficient learning materials, and manage their learning progress.

[1011] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1012] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[1013] 1. The user takes a photo of their handwritten notes

[1014] Users take a photo of their handwritten notes using a smartphone or tablet device, and the captured image data is temporarily saved in the device's internal storage.

[1015] As a concrete example, consider the case where a user takes a picture of their "math notebook." The user uses the device's camera app to take a picture so that the entire notebook is saved as a single image.

[1016] 2. The device sends the image data to the server

[1017] The device compresses the stored image data and sends it to the server over the Internet, using the HTTPS protocol to ensure data security, and waits for a confirmation response from the server after the transmission is complete.

[1018] 3. The server performs image analysis

[1019] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[1020] As a concrete example of the server analyzing an image of a "math notebook," the following shows how the title "Quadratic Equation" and the content "Solution Formula, Factorization" are extracted as text data.

[1021] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[1022] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[1023] For example, the server generates the following vocabulary list from the analysis of "quadratic equations":

[1024] "Formula for finding the solution of ax^2 + bx + c = 0"

[1025] "Factorization: A method of decomposing one polynomial into two or more polynomials"

[1026] It also generates a set of questions:

[1027] "Question: Solve the quadratic equation using the formula. Answer: x = (-b±√(b^2-4ac)) / 2a"

[1028] 5. Sending server-generated content to the device

[1029] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[1030] 6. Emotion engine recognizes user emotions

[1031] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to the server.

[1032] 7. Emotional Content Presentation

[1033] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[1034] 8. Use user-generated learning materials

[1035] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by the emotion engine.

[1036] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials according to the user's emotional state, thereby significantly improving the efficiency and effectiveness of learning.

[1037] The processing flow will be explained below.

[1038] Step 1:

[1039] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[1040] Step 2:

[1041] The device compresses the image data it captures. The device uses a compression algorithm to reduce the size of the image file and improve transfer efficiency. The compressed image data is temporarily stored in internal storage.

[1042] Step 3:

[1043] The device sends the compressed image data to the server. The device sends the image data to the server's upload URL using an HTTP request. The HTTPS protocol is used to ensure security. When the server receives the data, it returns a confirmation message to the device that reception has been completed.

[1044] Step 4:

[1045] The server analyzes the image data. It then launches an image analysis module and uses OCR technology to identify handwritten characters and graphics. It first performs preprocessing such as noise removal and binarization, then performs character analysis. It extracts text data as the analysis result and stores it in an internal database.

[1046] Step 5:

[1047] The server classifies the extracted text data. The server extracts keywords from the text data and classifies each keyword into categories, such as mathematics, science, history, etc. Based on the classification results, the server prepares to generate content using appropriate templates.

[1048] Step 6:

[1049] The server generates a vocabulary list, a workbook, and a bibliography. The server selects a template for each category and inserts the extracted text data into the template. For example, the server inserts keywords and their explanations into the vocabulary list, related questions and answers into the workbook, and links to related books and websites into the bibliography.

[1050] Step 7:

[1051] The server sends the generated content to the terminal. The server packages the generated content data and sends it to the terminal using an HTTP response. The HTTPS protocol is used to keep the data secure. After transmission is complete, a confirmation message is sent back to the terminal.

[1052] Step 8:

[1053] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that data reception is complete.

[1054] Step 9:

[1055] The user launches the dedicated application, and the emotion recognition engine captures the user's facial expressions. The device's camera periodically acquires images of the user's face and analyzes them to recognize their emotional state. The recognized emotion data is then sent to the server.

[1056] Step 10:

[1057] The server adjusts the way content is presented based on emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or prioritize relaxation content.

[1058] Step 11:

[1059] Users can access the generated learning materials. They can browse the generated vocabulary books, workbooks, and reference materials through a dedicated application. Personalized content is displayed according to the user's emotional state, improving the efficiency and effectiveness of learning.

[1060] Example 2

[1061] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1062] Traditional learning systems that use handwritten notes lack the ability to efficiently organize note content and improve learning efficiency through automatically generated learning materials. Furthermore, there is no system that provides appropriate learning support according to the user's emotional state, making it difficult to improve learning efficiency and provide a personalized learning experience.

[1063] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1064] In this invention, the server includes: means for a user to photograph handwritten notes; means for a terminal to transmit the photographed image data to the server; means for the server to analyze the image data and extract text data; means for the server to generate a vocabulary book, a workbook, and reference materials based on the extracted text data; means for the server to transmit the generated content to the terminal; means for a user to view the generated content through the terminal; emotion engine means for capturing the user's facial expressions using a camera in the terminal and recognizing their emotional state; and means for the server to adjust the presentation method of the study content based on the recognized emotion data. This makes it possible to effectively organize the contents of handwritten notes and automatically generate and provide study materials that correspond to the user's emotional state.

[1065] "User" refers to an individual user who uses handwritten notes and utilizes functions such as photography, learning, and emotion recognition through the system.

[1066] "Device" refers to a portable electronic device, such as a smartphone or tablet, that a user uses to capture handwritten notes and store, compress, and transmit the image data.

[1067] "Server" refers to a central processing unit that receives image data sent from a terminal, analyzes the image, extracts text data, generates content, receives user emotional data, and delivers optimal learning content.

[1068] "Image data" refers to the digital image file that a user takes of their handwritten notes and stores on their device.

[1069] "Image analysis" refers to the technical means of processing received image data, identifying handwritten characters and graphics in the image, and converting them into text data.

[1070] "Text data" refers to data in text format that expresses the contents of handwritten notes extracted by image analysis.

[1071] "Extracted text data" refers to information that the server identifies through image analysis and extracts in text form.

[1072] A "vocabulary book" refers to a learning material that organizes technical terms and words necessary for the learning content and lists them, including their meanings and usage.

[1073] A "problem book" refers to a learning material that provides organized practice questions and explanations based on extracted text data.

[1074] "References" refers to materials or literature that provide additional information or in-depth content related to the learning content.

[1075] "Content" refers to the entire information package that users use when studying, such as vocabulary lists, workbooks, and reference materials.

[1076] "Emotion engine" refers to a technical means of analyzing a user's facial expressions and recognizing their emotional state (e.g., joy, sadness, stress, etc.).

[1077] "Emotional data" refers to data that quantifies or categorizes the user's emotional state obtained through analysis by the emotion engine.

[1078] "Learning content presentation method" refers to the means by which learning content is presented to a user in a manner that is responsive to the user's emotional state.

[1079] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[1080] The user takes a picture of the handwritten notes using a smartphone or tablet (hereinafter referred to as the "device"). The captured image data is temporarily stored in the device's internal storage. The specific hardware used is the camera function of the smartphone or tablet.

[1081] Next, the device sends the image data to the server. The image data is compressed and then sent to the server via the Internet. At this time, the HTTPS protocol is used to ensure data security. After the transmission is complete, a confirmation response from the server is awaited. Specific software used is an image compression library (e.g., Picasso, Glide) or an HTTP request library (e.g., Retrofit).

[1082] The server launches an image analysis module to analyze the received image data. Specifically, it uses OCR (Optical Character Recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization. The specific software used is the OpenCV library and Tesseract OCR.

[1083] The server categorizes the learning content based on the extracted text data and generates vocabulary books, exercise books, and reference materials for each category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, it uses a generative AI model (e.g., GPT-3) to optimize the generated learning content.

[1084] The server sends the generated content to the device, where it is compressed again and securely transferred using the HTTPS protocol. The device then decompresses the received data and stores it in its internal storage.

[1085] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to a server. The specific software used is an emotion analysis engine (e.g., Microsoft Azure Face API).

[1086] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize displaying information on relaxation techniques and easy questions to reduce the learning load.

[1087] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application has an intuitive user interface and is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by an emotion engine.

[1088] Specific examples

[1089] Example prompt sentence:

[1090] "Please provide a detailed description of the system that automatically analyzes the contents of handwritten notes and generates effective learning materials that match the user's emotional state. Please include the entire process, from the user taking a photo of the notes with their smartphone to the provision of learning content based on the emotional data."

[1091] In this way, the present invention provides a system that effectively organizes the contents of handwritten notes and automatically generates and provides learning materials that correspond to the user's emotional state, thereby improving the efficiency and effectiveness of learning.

[1092] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1093] Step 1:

[1094] The user takes a photo of their handwritten notes

[1095] The user uses a device (smartphone or tablet) to take an image of their handwritten notes. The input data is the physical handwritten notes, and the output is a digital image file. This digital image file is temporarily stored in the device's internal storage.

[1096] Specific operation: The user opens the camera app, adjusts the camera so that the entire handwritten note is in view, and presses the shutter button to take a picture. After taking the picture, the image is saved in the "Photos" app or similar.

[1097] Step 2:

[1098] The device sends the image data to the server.

[1099] The device selects the stored image data, compresses it, and then sends it to the server via the Internet. The input data is the captured image data, and the output is the compressed image data. The HTTPS protocol is used to ensure data security, and a confirmation response from the server is waited for after transmission is complete.

[1100] Specific operation: After the device selects an image, it compresses the data using an image compression library (e.g., Picasso or Glide), then sends the image data to the server using an HTTP request library (e.g., Retrofit), and receives a "data reception completed" confirmation message as a response.

[1101] Step 3:

[1102] The server performs image analysis

[1103] The server launches an image analysis module to analyze the received image data. The input data is compressed image data, and the output is extracted text data. OCR (Optical Character Recognition) technology is used to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[1104] Specific operation: The server preprocesses the received image using the OpenCV library, then calls Tesseract OCR to analyze the handwritten characters and extract keywords such as "quadratic equation," "solution formula," and "factorization" as text.

[1105] Step 4:

[1106] The server generates learning materials based on the analysis results.

[1107] The server categorizes the learning content based on the extracted text data and generates vocabulary books, workbooks, and reference materials for each category. The input data is the extracted text data, and the output is learning materials generated by category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, a generative AI model (e.g., GPT-3) is used to optimize the generated learning content.

[1108] How it works: The server stores the text data in a database and runs a category classification algorithm. After classification, it invokes a generative AI model, inserts the text into templates, and automatically generates a vocabulary book and exercises that explain "solution formulas" and "factorization."

[1109] Step 5:

[1110] Sending server-generated content to the device

[1111] The server sends the generated vocabulary book, question book, and reference materials to the device. The input data is the generated learning materials, and the output is the transmission of compressed data. The transmitted data is compressed again and securely transferred. The device decompresses the received data and saves it in its internal storage.

[1112] Specific operation: The server compresses the generated content in Zip format and sends it to the device via an HTTP request. The device unzips the received Zip file and saves it in the app's internal storage.

[1113] Step 6:

[1114] Emotion engine recognizes user emotions

[1115] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input data is image data of the captured facial expressions, and the output is recognized emotion data. The emotion engine analyzes the captured image data, recognizes the user's emotional state, and sends the data to the server.

[1116] How it works: When a user opens the app, the camera automatically activates and detects their face. The emotion engine analyzes the user's facial expressions, identifies emotions such as "joy" or "stress," and sends the data to the server.

[1117] Step 7:

[1118] Emotion-based content presentation

[1119] The server adjusts the presentation of the generated learning content based on the received emotional data. The input data is the emotional data, and the output is the adjusted learning content. If the user is feeling stressed, it will prioritize displaying easy problems or information on relaxation techniques.

[1120] How it works: The server receives the emotion data and uses an AI model to select appropriate content. If the user is in a stressful state, it generates a page containing short questions and relaxation guides and sends it to a dedicated app.

[1121] Step 8:

[1122] Use user-generated learning materials

[1123] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The input data is the learning materials stored on the device, and the output is the user's learning results. The application has an intuitive user interface and is designed to allow users to easily access the learning content. In addition, the content is personalized based on the emotional state recognized by the emotion engine.

[1124] What it does: If a user is browsing a vocabulary book within the app and is feeling stressed, the app will provide a personalized learning experience based on the user's emotions, such as playing relaxing music while displaying the learning content.

[1125] (Application example 2)

[1126] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1127] Conventional industrial robots operate according to pre-programmed work procedures, but their lack of flexibility makes it difficult to quickly incorporate handwritten work instructions on-site. Furthermore, they are unable to take into account the emotional state of the worker, raising concerns that work efficiency may decline in environments prone to stress or strain. The lack of a system that can immediately respond to handwritten instructions or reflect the emotional state of the worker poses challenges in ensuring sufficient work efficiency and safety.

[1128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1129] In this invention, the server includes a means for recognizing the emotional state of the user, a means for adjusting the content presentation method according to the emotional state of the user, a means for generating a work procedure to be performed by the industrial robot based on the analyzed text data, and a means for the industrial robot to execute the generated work procedure, thereby enabling immediate response to handwritten instructions and optimizing the work environment based on the emotional state of the worker.

[1130] A "handwritten notebook" is a notebook containing information that is handwritten by the user using a writing instrument.

[1131] "Image data" refers to data representing visual digital information generated by a user photographing a handwritten note.

[1132] A "server" is a computer system that receives, analyzes, stores, and transmits data over a network.

[1133] "Text data" refers to data that indicates character information extracted from image data using OCR technology.

[1134] A "vocabulary book" is a book containing words, their meanings, and definitions to aid in learning and memorization.

[1135] A "workbook" is a teaching material that includes a set of questions and their answers related to a specific learning content.

[1136] "References" are related materials and documents that deepen understanding of specific learning content.

[1137] "Emotional state" refers to the user's psychological state, such as happiness, sadness, or stress.

[1138] "Content presentation" refers to how the generated learning materials and information are displayed and provided to the user.

[1139] An "industrial robot" is an automated mechanical device used in an industrial setting that has the ability to perform specific tasks.

[1140] A "work procedure" is a series of operations or operational procedures that an industrial robot must execute.

[1141] Overall system picture

[1142] The system of the present invention allows users to take photos of their handwritten notes, analyzes the content, and provides learning content and work procedures. It also includes a function to adjust the way content is presented based on the user's emotional state, and automatically execute work procedures using an industrial robot.

[1143] Hardware and software used

[1144] Hardware:

[1145] Smartphone or tablet (with camera)

[1146] Server (high-performance CPU, GPU, storage)

[1147] industrial robots

[1148] software:

[1149] Python

[1150] OCR tool (Pytesseract)

[1151] Image processing library (OpenCV)

[1152] Emotion recognition API (Microsoft Azure Face API)

[1153] Web frameworks (Flask / Django)

[1154] Communication protocol (HTTPS)

[1155] Specific operation of the system

[1156] 1. Photographing handwritten notes

[1157] Users take a photo of their handwritten notes using a smartphone or tablet, and the image data is temporarily stored in the device's internal storage.

[1158] 2. Sending image data

[1159] The device compresses the stored image data and sends it to the server using the HTTPS protocol, which encrypts the data to ensure its security and returns a confirmation response after the transmission is complete.

[1160] 3. Analysis of image data

[1161] The server analyzes the image data using OCR technology and extracts handwritten characters and graphics as text data. This process includes preprocessing such as noise removal and binarization.

[1162] 4. Content Generation

[1163] The server generates vocabulary books, exercise books, and reference books based on the extracted text data by inserting the text data using appropriate templates.

[1164] 5. Submission of Content

[1165] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is again securely transferred via HTTPS. The device unpacks the received data and saves it in its internal storage.

[1166] 6. Emotional Recognition

[1167] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state. The recognized emotion data is then sent to the server.

[1168] 7. Emotional Content Presentation

[1169] The server adjusts the presentation of the generated learning content based on the received emotional data: if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[1170] 8. Workflow generation and execution

[1171] The server generates work procedures for the industrial robot based on the analyzed text data, and the robot then executes the work procedures. This allows the contents of handwritten instructions to be efficiently incorporated, enabling flexible work.

[1172] Examples of concrete examples and prompts

[1173] Examples:

[1174] A factory worker writes down the work procedures for a new product line in a handwritten notebook and takes a photo of the notes with a smartphone. The photo data is sent to a server and analyzed using OCR. Based on the analysis results, an industrial robot executes the work procedures and responds quickly.

[1175] Example prompt sentence:

[1176] "Generate work procedures for an industrial robot from photographed data of handwritten notes. The data will include the following information: work procedures, precautions, and tools to be used. Please tell me how to implement a system that generates an appropriate work plan based on the analysis results and sends it to the robot."

[1177] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1178] Step 1:

[1179] The user takes an image of their handwritten notes using a smartphone or tablet. The input is the handwritten notes, and the output is the captured image data. Specifically, the user launches the camera app to take a picture of the notes, and the image data is saved in the device's internal storage.

[1180] Step 2:

[1181] The device compresses the captured image data and sends it to the server using the HTTPS protocol. The input is the image data stored in the internal storage, and the output is the transmission of the compressed image data to the server. Specifically, the device runs the compression algorithm, encrypts the compressed data using HTTPS, and sends it to the server.

[1182] Step 3:

[1183] The server uses OCR technology to analyze the received image data. The input is compressed image data, and the output is analyzed text data. Specifically, the server first decompresses the data and then uses Pytesseract or OpenCV to extract handwritten characters and shapes from the image as text data.

[1184] Step 4:

[1185] The server generates vocabulary books, exercise books, and reference materials based on the extracted text data. The input is the analyzed text data, and the output is the generated learning content. Specifically, the server inserts the text data into appropriate templates, classifies them into categories, and generates content.

[1186] Step 5:

[1187] The server sends the generated learning content to the terminal. The input is the generated learning content, and the output is the data that has been sent to the terminal. Specifically, the server compresses the data again and sends it securely to the terminal using the HTTPS protocol.

[1188] Step 6:

[1189] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input is the user's facial expressions, and the output is the captured image data. Specifically, the device starts up the camera, captures the user's facial expressions, and saves the image data in its internal storage.

[1190] Step 7:

[1191] The server receives the captured image data and uses an emotion engine to recognize the user's emotional state. The input is the captured image data, and the output is the recognized emotion data. Specifically, the server uses the Microsoft Azure Face API to analyze the image data and evaluate the emotional state.

[1192] Step 8:

[1193] The server adjusts the presentation method of the generated learning content based on the received emotional data. The input is the emotional data and learning content, and the output is the adjusted presentation method. Specifically, the server evaluates the emotional data and determines how to prioritize the presentation of relaxation information and easy questions.

[1194] Step 9:

[1195] The server generates work procedures to be executed by the industrial robot based on the analyzed text data. The input is text data and the output is work procedures. Specifically, the server analyzes the text data, generates appropriate work procedures, and transmits them to the robot.

[1196] Step 10:

[1197] Industrial robots perform tasks according to the procedures provided by the server. The input is the procedure, and the output is the executed task. In terms of specific operations, the robot acts as instructed and completes the specified task.

[1198] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1199] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1200] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1201] [Fourth embodiment]

[1202] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1203] 7, a 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.

[1204] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1205] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1206] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1207] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1208] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1209] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1210] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1211] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1212] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1213] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1214] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1215] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system involves a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[1216] 1. The user takes a photo of their handwritten notes

[1217] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[1218] As a concrete example, consider the case where a user takes a photo of a biology notebook. The user uses the device's camera to capture the entire notebook so that it is saved as a single image.

[1219] 2. The device sends the image data to the server

[1220] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[1221] 3. The server performs image analysis

[1222] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[1223] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[1224] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[1225] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[1226] For example, the server might generate the following vocabulary list from the analysis of "cell division":

[1227] "Mitosis: the process by which cells divide, resulting in the accurate duplication of genetic material."

[1228] "Meiosis: A specialized division that occurs during the production of germ cells"

[1229] It also generates a set of questions:

[1230] "Question: Explain the difference between mitosis and meiosis. Answer: In mitosis..."

[1231] 5. Sending server-generated content to the device

[1232] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[1233] 6. Use user-generated learning materials

[1234] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study.

[1235] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[1236] The processing flow will be explained below.

[1237] Step 1:

[1238] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[1239] Step 2:

[1240] The device sends the captured image data to the server. The device first compresses the image data and sends it to the server's upload URL using the HTTPS protocol. After sending is complete, the device waits for a confirmation response from the server.

[1241] Step 3:

[1242] The server receives the image data. The server verifies the received image data and checks the data format and completeness. If there are no problems, the server returns a receipt confirmation message to the terminal.

[1243] Step 4:

[1244] The server performs image analysis. The server launches an image analysis module and uses OCR technology to identify handwritten characters and figures in the image. This process also involves preprocessing such as noise removal and binarization. Text data is extracted as a result of the analysis.

[1245] Step 5:

[1246] The server classifies the extracted text data and applies a keyword extraction algorithm to detect important words and phrases, which are then used to categorize the learning content.

[1247] Step 6:

[1248] The server generates a vocabulary list, a question bank, and a reference book. The server selects an appropriate template based on each category and generates content by inserting the extracted text data. The generated content includes keywords and their explanations (vocabulary list), related questions and answers (questions), and links to reference books and websites (reference book).

[1249] Step 7:

[1250] The server sends the generated content to the terminal. The server packages the content data and sends it to the terminal using the HTTPS protocol. After the transmission is complete, a confirmation message is sent back to the terminal.

[1251] Step 8:

[1252] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that reception is complete.

[1253] Step 9:

[1254] The user accesses the generated learning materials. They launch a dedicated application and view the generated vocabulary book, practice questions, and reference materials. They can sort the content and mark important points.

[1255] These are the specific processing steps of the program. This series of steps allows users to effectively organize the contents of their handwritten notes and use them as learning materials.

[1256] Example 1

[1257] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1258] Learning using handwritten notes has the problem that it is difficult to manage and search for information, and creating learning materials manually requires time and effort. Furthermore, there is a need for a method to efficiently analyze the data from photographed notes and extract information that can be used as effective learning materials. Current technology does not provide sufficient efficiency for extracting data from handwritten notes and generating learning materials, making it difficult to improve learning efficiency.

[1259] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1260] In this invention, the server includes means for analyzing received image data using optical character recognition technology and extracting text data, means for preprocessing the extracted text data, such as noise removal and binarization, and means for generating vocabulary lists, workbooks, and reference materials using natural language processing technology based on the classified text data. This makes it possible to efficiently extract data from handwritten notes and automatically generate effective and systematic study materials.

[1261] A "user" is someone who uses this system to take pictures of handwritten notes and view the generated content.

[1262] "Electronic devices" refer to portable devices such as smartphones and tablets that capture images of handwritten notes and send the image data to a server.

[1263] A "server" is a computer system that analyzes received image data, extracts and processes text data, and generates learning materials based on that data.

[1264] "Means" refers to the method or apparatus used by the system to perform a particular function or operation.

[1265] "Optical character recognition technology" is a technology that recognizes characters from image data and converts them into text data.

[1266] "Preprocessing" refers to processing of image data, such as noise removal and binarization, in order to improve the accuracy of analysis.

[1267] "Text data" is character information extracted using optical character recognition technology.

[1268] "Natural language processing technology" is a set of technologies that enable computers to understand and generate human language.

[1269] "Content" refers to server-generated learning materials such as vocabulary books, workbooks, and reference materials.

[1270] A "template" is a format that pre-designs the form and framework of the content to be generated.

[1271] "Network" refers to a communications infrastructure such as the Internet, and is a means for connecting electronic devices and servers.

[1272] A "dedicated application" is specific software that a user uses to view generated content.

[1273] This system allows users to take photos of their handwritten notes, and a server analyzes the content to automatically generate learning materials. This system provides a series of processes, from taking photos of the user's handwritten notes to analyzing the images, generating learning materials, and providing them to the user.

[1274] Hardware and Software Use

[1275] User side

[1276] A user uses an electronic device such as a smartphone or tablet. The device launches a camera application and takes a photo of the handwritten note. After the photo is taken, the image data is temporarily stored in the device's internal storage. Specific camera applications include the standard camera app found on most smartphones.

[1277] Terminal side

[1278] The device compresses the captured image data and sends the compressed data to the server using the HTTPS protocol. The software used in this step includes an image compression library and a secure communication protocol (e.g., OpenSSL).

[1279] Server side

[1280] The server uses OCR (Optical Character Recognition) technology to analyze the received image data. Image analysis libraries such as OpenCV and Tesseract are used for this analysis. The server performs preprocessing such as noise removal and binarization to improve the accuracy of the analysis.

[1281] The parsed text data is then processed using natural language processing techniques to classify the resulting text data and generate vocabulary lists, exercise books, reference books, etc. using appropriate templates. This is done using Python scripts and NLP (Natural Language Processing) libraries (e.g., NLTK and spaCy).

[1282] Content Creation and Delivery

[1283] The generated learning materials (vocabulary book, workbook, references) are compressed again and sent to the device using the HTTPS protocol. Users can view these materials through a dedicated application, which provides an intuitive interface and is developed using React Native.

[1284] Examples and Prompts

[1285] As a concrete example, let's imagine a user takes a picture of a page about "cell division" in a high school biology notebook. The user launches the camera app and takes a picture so that the entire notebook is clearly visible. The image data is then sent by the device to a server, where it is analyzed.

[1286] The server uses OCR and NLP techniques to extract text such as "cell division," "mitosis," and "meiosis," and generates learning materials like the following:

[1287] Vocabulary: "Mitosis: The process by which cells divide, resulting in the precise duplication of genetic material."

[1288] Question: Explain the difference between mitosis and meiosis. Answer: In mitosis...

[1289] Example prompt sentence:

[1290] "I have taken a photo of a handwritten high school biology notebook. The notebook contains a description of cell division. Please generate a vocabulary book and question set based on the content."

[1291] In this way, this system efficiently analyzes the contents of handwritten notes and automatically generates and provides optimal learning materials to users, thereby improving learning efficiency.

[1292] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1293] Step 1:

[1294] The user takes a photo of their handwritten notes with an electronic device. The user launches the camera app on their smartphone or tablet and takes a photo of the handwritten notes. The input is the handwritten notes, and the output is an image file (e.g., JPEG format). This image file is temporarily stored in the device's internal storage.

[1295] Step 2:

[1296] The image data captured by the device is compressed and sent to the server via the network. The input is an image file (JPEG format) and the output is compressed image data. This data is sent securely using the HTTPS protocol. Specifically, the device compresses the image and executes the sending script to send it to the server.

[1297] Step 3:

[1298] The server analyzes the image data it receives using optical character recognition (OCR) technology and extracts text data. The input is compressed image data, and the output is analyzed text data. After receiving the image data, the server uses an OCR library to recognize handwritten characters and convert them into text. Specifically, the server uses OpenCV and Tesseract to perform preprocessing such as noise removal and binarization, and then performs character recognition.

[1299] Step 4:

[1300] The server preprocesses the extracted text data, removing noise and converting it to binary data. The input is raw text data, and the output is preprocessed text data. Specifically, the server performs text formatting, removing unnecessary whitespace, checking grammar, and other operations to improve analysis accuracy.

[1301] Step 5:

[1302] The server uses natural language processing technology to generate vocabulary lists, workbooks, and reference materials based on the classified text data. The input is preprocessed text data, and the output is the generated learning materials (vocabulary lists, workbooks, and reference materials). Specifically, the server uses Python scripts and NLP libraries (such as NLTK or spaCy) to insert data into appropriate templates to generate the learning materials.

[1303] Step 6:

[1304] The server compresses the generated content and transmits it to the electronic device again via the network. The input is the generated learning material, and the output is the compressed learning material data. Specifically, the server compresses the content and transmits it to the terminal via the HTTPS protocol.

[1305] Step 7:

[1306] The user views the generated content through a dedicated application. The input is the compressed data sent to the terminal, and the output is the learning materials that the user can view. Specifically, the user launches the application, views the decompressed learning materials, and uses them for learning.

[1307] In this way, each processing step of the system works together to efficiently extract data from handwritten notes and provide users with optimal learning materials.

[1308] (Application example 1)

[1309] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1310] Conventional learning systems have the problem that it takes a great deal of time and effort for users to digitize their handwritten notes and generate effective learning materials based on those contents. It is also difficult to properly manage the quality of the generated materials and the user's learning progress. Furthermore, there are many cases where the generated materials do not meet the individual learning needs of the user. There is a need to solve these problems and provide effective and efficient learning support.

[1311] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1312] In this invention, the server includes means for analyzing the contents of a user's handwritten notes and generating appropriate learning materials using a generative AI model, means for linking the generated learning materials with feedback and progress management functions, and means for classifying the extracted text data and generating content using different templates based on each category. This allows a user to automatically generate high-quality learning materials tailored to their individual learning needs simply by taking a photo of their handwritten notes, enabling effective and efficient learning.

[1313] "User" refers to an individual or organization that uses the system of the present invention to capture handwritten notes and generate study materials.

[1314] "Handwritten notes" are learning and memo notes that users write by hand on paper or a digital device.

[1315] "Terminal" refers to a smartphone, tablet, or other computing device used by a user that captures images of handwritten notes and transmits them to a server for analysis.

[1316] "Image data" refers to digital image data generated after photographing a handwritten note.

[1317] A "server" is a remote computer system that receives image data sent from a terminal and performs analysis and processing to generate teaching materials.

[1318] "Image analysis" is the process by which the server recognizes characters and figures from the image data it receives and extracts them as text data.

[1319] "Text data" refers to text information extracted through image analysis, and is the data that forms the basis for generating learning materials.

[1320] A "vocabulary book" is a learning material that includes a list of vocabulary or terms and their definitions or explanations, generated to assist users in their learning.

[1321] A "question bank" is a learning material that includes a set of questions and answers that are generated to facilitate understanding of the learning content.

[1322] A "bibliography" is a list of references or sources created to provide additional information or materials related to the learning content.

[1323] A "generative AI model" is an artificial intelligence model used within a server, and is a technology that automatically generates appropriate learning materials based on input text data.

[1324] "Feedback" refers to evaluations and advice provided based on a user's learning progress and performance.

[1325] The "progress management function" is a function that tracks the user's learning status and supports effective learning plans.

[1326] A "template" is a model for generating content set for each different category, and is a format for inserting extracted text data.

[1327] "Compression" is the process of reducing the size of image data for more efficient transmission to a server.

[1328] "Categories" are divisions for classifying extracted text data and help structure learning materials.

[1329] The system of the present invention allows users to photograph their handwritten notes, analyze the contents of those notes, and automatically generate effective learning materials. This system includes a series of processes, starting with the user photographing their handwritten notes, followed by image analysis, content generation, and provision to the user.

[1330] 1. The user takes a photo of their handwritten notes

[1331] The user takes a photo of their handwritten notes using a smartphone or tablet. The device launches the camera app, sets the appropriate resolution and framing, and then presses the shutter to capture the image data. The captured image data is temporarily stored in the device.

[1332] Examples:

[1333] When a user takes a photo of a "biology notebook," the device's camera is used to capture the entire notebook so that it is saved as a single image.

[1334] 2. The device sends the image data to the server

[1335] The device compresses the stored image data and sends it to the server via the Internet. The HTTPS protocol is used to ensure data security during transmission, and after transmission is complete, the device waits for a response from the server. Once the server receives the data, it sends a confirmation response back to the device.

[1336] 3. The server performs image analysis

[1337] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. Preprocessing such as noise removal and binarization is performed to improve the accuracy of the analysis.

[1338] Software used:

[1339] OCR: Tesseract

[1340] Image processing: OpenCV

[1341] Examples:

[1342] As a concrete example of the server analyzing an image of a "biology notebook," the title "Cell division" and the content "Mitosis, meiosis" are extracted as text data.

[1343] 4. The server generates learning materials based on the analysis results.

[1344] The server first categorizes the learning content based on the extracted text data, then generates vocabulary lists, practice questions, and reference materials for each category. This process uses a generative AI model to generate content using appropriate templates based on prompts.

[1345] Software used:

[1346] Language model: GPT-4 (OpenAI)

[1347] Programming languages: Python, Node.js

[1348] Example prompt sentence:

[1349] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[1350] --- Note contents ---

[1351] Title: Cell division

[1352] Contents: Mitosis, meiosis

[1353] --- Notes content ends here ---

[1354] Request details:

[1355] 1. Vocabulary

[1356] 2. Problem set

[1357] Output format:

[1358] 1. Vocabulary

[1359] Mitosis: (Explanation)

[1360] Meiosis: (Explanation)

[1361] 2. Problem set

[1362] 3 questions in question and answer format

[1363] 5. Sending server-generated content to the device

[1364] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[1365] 6. Use user-generated learning materials

[1366] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application's user interface is intuitive and designed to provide easy access to the information needed for study. It also works with feedback and progress management functions, allowing users to study efficiently while checking their progress.

[1367] Software used:

[1368] Application framework: Flutter, React Native

[1369] Database: SQLite

[1370] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials for users, thereby significantly improving learning efficiency.

[1371] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1372] Step 1:

[1373] The user takes a photo of their handwritten notes using a smartphone or tablet (device). The user launches the device's camera app, frames the shot, and presses the shutter to capture image data. The input is the handwritten notes, and the output is image data. This image data is temporarily stored inside the device.

[1374] Step 2:

[1375] Compresses image data acquired by the device. A compression algorithm is used to reduce the size of the image and convert it into a format suitable for transmission. The input is raw image data, and the output is compressed image data.

[1376] Step 3:

[1377] Sends compressed image data to the server. The terminal transfers data to the server via the Internet using the HTTPS protocol. The input is the compressed image data and the output is the transmitted data. When the server receives the data, it sends an acknowledgment back to the terminal.

[1378] Step 4:

[1379] The server analyzes the received image data. The server applies OCR technology to extract handwritten characters in the image as text data. The software used is Tesseract and OpenCV. The input is image data, and the output is text data. Noise removal and binarization are performed to improve analysis accuracy.

[1380] Step 5:

[1381] The server classifies the extracted text data. Based on the text data, it organizes the learning content into categories and selects the appropriate template. The input is text data, and the output is classified text data.

[1382] Step 6:

[1383] The server generates learning materials using a generative AI model. It creates vocabulary books and question sets based on prompts using GPT-4 (OpenAI). The prompts include the content of handwritten notes and the format of the learning materials to be generated. The input is classified text data and prompts, and the output is the generated learning materials.

[1384] Example prompt sentence:

[1385] Prompt: Analyze the contents of the handwritten notes below and generate a vocabulary book and question set for study.

[1386] --- Note contents ---

[1387] Title: Cell division

[1388] Contents: Mitosis, meiosis

[1389] --- Notes content ends here ---

[1390] Request details:

[1391] 1. Vocabulary

[1392] 2. Problem set

[1393] Output format:

[1394] 1. Vocabulary

[1395] Mitosis: (Explanation)

[1396] Meiosis: (Explanation)

[1397] 2. Problem set

[1398] 3 questions in question and answer format

[1399] Step 7:

[1400] The server compresses the generated content and sends it to the device. The data is transferred securely using the HTTPS protocol. The input is the generated learning material and the output is the transmitted data. The device decompresses the received data and saves it in its internal storage.

[1401] Step 8:

[1402] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The application provides an intuitive user interface and is also integrated with feedback and progress management functions. The input is the generated learning material data, and the output is the user's learning progress and viewing of the materials.

[1403] The above processing flow provides a system that allows users to digitize their handwritten notes, automatically generate efficient learning materials, and manage their learning progress.

[1404] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1405] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[1406] 1. The user takes a photo of their handwritten notes

[1407] Users take a photo of their handwritten notes using a smartphone or tablet device, and the captured image data is temporarily saved in the device's internal storage.

[1408] As a concrete example, consider the case where a user takes a picture of their "math notebook." The user uses the device's camera app to take a picture so that the entire notebook is saved as a single image.

[1409] 2. The device sends the image data to the server

[1410] The device compresses the stored image data and sends it to the server over the Internet, using the HTTPS protocol to ensure data security, and waits for a confirmation response from the server after the transmission is complete.

[1411] 3. The server performs image analysis

[1412] To analyze the received image data, the server first launches the image analysis module. The server uses OCR (optical character recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[1413] As a concrete example of the server analyzing an image of a "math notebook," the following shows how the title "Quadratic Equation" and the content "Solution Formula, Factorization" are extracted as text data.

[1414] 4. The server generates a vocabulary list, exercise book, and reference materials based on the analysis results.

[1415] The server first categorizes the learning content based on the extracted text data, then generates a vocabulary book, exercise book, and reference materials for each category. This process uses appropriate templates and inserts the text data to generate the content.

[1416] For example, the server generates the following vocabulary list from the analysis of "quadratic equations":

[1417] "Formula for finding the solution of ax^2 + bx + c = 0"

[1418] "Factorization: A method of decomposing one polynomial into two or more polynomials"

[1419] It also generates a set of questions:

[1420] "Question: Solve the quadratic equation using the formula. Answer: x = (-b±√(b^2-4ac)) / 2a"

[1421] 5. Sending server-generated content to the device

[1422] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is compressed and securely transferred using the HTTPS protocol. The device decompresses the received data and saves it in its internal storage.

[1423] 6. Emotion engine recognizes user emotions

[1424] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to the server.

[1425] 7. Emotional Content Presentation

[1426] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[1427] 8. Use user-generated learning materials

[1428] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application's user interface is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by the emotion engine.

[1429] In this way, the present invention provides a system that automatically analyzes the contents of handwritten notes and generates and provides effective learning materials according to the user's emotional state, thereby significantly improving the efficiency and effectiveness of learning.

[1430] The processing flow will be explained below.

[1431] Step 1:

[1432] The user takes a photo of their handwritten notes. The user launches the device's camera app, adjusts the framing and resolution appropriately, and then presses the shutter button to capture an image of the notes. The captured image data is temporarily stored in the device's internal storage.

[1433] Step 2:

[1434] The device compresses the image data it captures. The device uses a compression algorithm to reduce the size of the image file and improve transfer efficiency. The compressed image data is temporarily stored in internal storage.

[1435] Step 3:

[1436] The device sends the compressed image data to the server. The device sends the image data to the server's upload URL using an HTTP request. The HTTPS protocol is used to ensure security. When the server receives the data, it returns a confirmation message to the device that reception has been completed.

[1437] Step 4:

[1438] The server analyzes the image data. It then launches an image analysis module and uses OCR technology to identify handwritten characters and graphics. It first performs preprocessing such as noise removal and binarization, then performs character analysis. It extracts text data as the analysis result and stores it in an internal database.

[1439] Step 5:

[1440] The server classifies the extracted text data. The server extracts keywords from the text data and classifies each keyword into categories, such as mathematics, science, history, etc. Based on the classification results, the server prepares to generate content using appropriate templates.

[1441] Step 6:

[1442] The server generates a vocabulary list, a workbook, and a bibliography. The server selects a template for each category and inserts the extracted text data into the template. For example, the server inserts keywords and their explanations into the vocabulary list, related questions and answers into the workbook, and links to related books and websites into the bibliography.

[1443] Step 7:

[1444] The server sends the generated content to the terminal. The server packages the generated content data and sends it to the terminal using an HTTP response. The HTTPS protocol is used to keep the data secure. After transmission is complete, a confirmation message is sent back to the terminal.

[1445] Step 8:

[1446] The device receives the content data sent from the server. The device decompresses the received data and saves it to internal storage. The device notifies the user that data reception is complete.

[1447] Step 9:

[1448] The user launches the dedicated application, and the emotion recognition engine captures the user's facial expressions. The device's camera periodically acquires images of the user's face and analyzes them to recognize their emotional state. The recognized emotion data is then sent to the server.

[1449] Step 10:

[1450] The server adjusts the way content is presented based on emotional data. For example, if the user is feeling stressed, it may lower the difficulty of the questions or prioritize relaxation content.

[1451] Step 11:

[1452] Users can access the generated learning materials. They can browse the generated vocabulary books, workbooks, and reference materials through a dedicated application. Personalized content is displayed according to the user's emotional state, improving the efficiency and effectiveness of learning.

[1453] Example 2

[1454] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1455] Traditional learning systems that use handwritten notes lack the ability to efficiently organize note content and improve learning efficiency through automatically generated learning materials. Furthermore, there is no system that provides appropriate learning support according to the user's emotional state, making it difficult to improve learning efficiency and provide a personalized learning experience.

[1456] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1457] In this invention, the server includes: means for a user to photograph handwritten notes; means for a terminal to transmit the photographed image data to the server; means for the server to analyze the image data and extract text data; means for the server to generate a vocabulary book, a workbook, and reference materials based on the extracted text data; means for the server to transmit the generated content to the terminal; means for a user to view the generated content through the terminal; emotion engine means for capturing the user's facial expressions using a camera in the terminal and recognizing their emotional state; and means for the server to adjust the presentation method of the study content based on the recognized emotion data. This makes it possible to effectively organize the contents of handwritten notes and automatically generate and provide study materials that correspond to the user's emotional state.

[1458] "User" refers to an individual user who uses handwritten notes and utilizes functions such as photography, learning, and emotion recognition through the system.

[1459] "Device" refers to a portable electronic device, such as a smartphone or tablet, that a user uses to capture handwritten notes and store, compress, and transmit the image data.

[1460] "Server" refers to a central processing unit that receives image data sent from a terminal, analyzes the image, extracts text data, generates content, receives user emotional data, and delivers optimal learning content.

[1461] "Image data" refers to the digital image file that a user takes of their handwritten notes and stores on their device.

[1462] "Image analysis" refers to the technical means of processing received image data, identifying handwritten characters and graphics in the image, and converting them into text data.

[1463] "Text data" refers to data in text format that expresses the contents of handwritten notes extracted by image analysis.

[1464] "Extracted text data" refers to information that the server identifies through image analysis and extracts in text form.

[1465] A "vocabulary book" refers to a learning material that organizes technical terms and words necessary for the learning content and lists them, including their meanings and usage.

[1466] A "problem book" refers to a learning material that provides organized practice questions and explanations based on extracted text data.

[1467] "References" refers to materials or literature that provide additional information or in-depth content related to the learning content.

[1468] "Content" refers to the entire information package that users use when studying, such as vocabulary lists, workbooks, and reference materials.

[1469] "Emotion engine" refers to a technical means of analyzing a user's facial expressions and recognizing their emotional state (e.g., joy, sadness, stress, etc.).

[1470] "Emotional data" refers to data that quantifies or categorizes the user's emotional state obtained through analysis by the emotion engine.

[1471] "Learning content presentation method" refers to the means by which learning content is presented to a user in a manner that is responsive to the user's emotional state.

[1472] The system of the present invention aims to help users who use handwritten notes to effectively organize the contents of their notes and improve their learning efficiency through automatically generated learning materials. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides appropriate learning support according to the user's emotional state.

[1473] The user takes a picture of the handwritten notes using a smartphone or tablet (hereinafter referred to as the "device"). The captured image data is temporarily stored in the device's internal storage. The specific hardware used is the camera function of the smartphone or tablet.

[1474] Next, the device sends the image data to the server. The image data is compressed and then sent to the server via the Internet. At this time, the HTTPS protocol is used to ensure data security. After the transmission is complete, a confirmation response from the server is awaited. Specific software used is an image compression library (e.g., Picasso, Glide) or an HTTP request library (e.g., Retrofit).

[1475] The server launches an image analysis module to analyze the received image data. Specifically, it uses OCR (Optical Character Recognition) technology to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization. The specific software used is the OpenCV library and Tesseract OCR.

[1476] The server categorizes the learning content based on the extracted text data and generates vocabulary books, exercise books, and reference materials for each category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, it uses a generative AI model (e.g., GPT-3) to optimize the generated learning content.

[1477] The server sends the generated content to the device, where it is compressed again and securely transferred using the HTTPS protocol. The device then decompresses the received data and stores it in its internal storage.

[1478] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state (e.g., joy, sadness, stress, etc.). The recognized emotion data is sent to a server. The specific software used is an emotion analysis engine (e.g., Microsoft Azure Face API).

[1479] The server then adjusts the presentation of the generated learning content based on the received emotional data. For example, if the user is feeling stressed, it will prioritize displaying information on relaxation techniques and easy questions to reduce the learning load.

[1480] Users can view the generated vocabulary books, practice questions, and reference materials through a dedicated application. The application has an intuitive user interface and is designed to allow users to easily access the learning content. The content is also personalized based on the user's emotional state as recognized by an emotion engine.

[1481] Specific examples

[1482] Example prompt sentence:

[1483] "Please provide a detailed description of the system that automatically analyzes the contents of handwritten notes and generates effective learning materials that match the user's emotional state. Please include the entire process, from the user taking a photo of the notes with their smartphone to the provision of learning content based on the emotional data."

[1484] In this way, the present invention provides a system that effectively organizes the contents of handwritten notes and automatically generates and provides learning materials that correspond to the user's emotional state, thereby improving the efficiency and effectiveness of learning.

[1485] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1486] Step 1:

[1487] The user takes a photo of their handwritten notes

[1488] The user uses a device (smartphone or tablet) to take an image of their handwritten notes. The input data is the physical handwritten notes, and the output is a digital image file. This digital image file is temporarily stored in the device's internal storage.

[1489] Specific operation: The user opens the camera app, adjusts the camera so that the entire handwritten note is in view, and presses the shutter button to take a picture. After taking the picture, the image is saved in the "Photos" app or similar.

[1490] Step 2:

[1491] The device sends the image data to the server.

[1492] The device selects the stored image data, compresses it, and then sends it to the server via the Internet. The input data is the captured image data, and the output is the compressed image data. The HTTPS protocol is used to ensure data security, and a confirmation response from the server is waited for after transmission is complete.

[1493] Specific operation: After the device selects an image, it compresses the data using an image compression library (e.g., Picasso or Glide), then sends the image data to the server using an HTTP request library (e.g., Retrofit), and receives a "data reception completed" confirmation message as a response.

[1494] Step 3:

[1495] The server performs image analysis

[1496] The server launches an image analysis module to analyze the received image data. The input data is compressed image data, and the output is extracted text data. OCR (Optical Character Recognition) technology is used to identify handwritten characters and figures in the image and extract them as text data. This process also includes preprocessing such as noise removal and binarization.

[1497] Specific operation: The server preprocesses the received image using the OpenCV library, then calls Tesseract OCR to analyze the handwritten characters and extract keywords such as "quadratic equation," "solution formula," and "factorization" as text.

[1498] Step 4:

[1499] The server generates learning materials based on the analysis results.

[1500] The server categorizes the learning content based on the extracted text data and generates vocabulary books, workbooks, and reference materials for each category. The input data is the extracted text data, and the output is learning materials generated by category. This process uses a template engine (e.g., Handlebars.js) to insert the text data into appropriate templates to generate content. Furthermore, a generative AI model (e.g., GPT-3) is used to optimize the generated learning content.

[1501] How it works: The server stores the text data in a database and runs a category classification algorithm. After classification, it invokes a generative AI model, inserts the text into templates, and automatically generates a vocabulary book and exercises that explain "solution formulas" and "factorization."

[1502] Step 5:

[1503] Sending server-generated content to the device

[1504] The server sends the generated vocabulary book, question book, and reference materials to the device. The input data is the generated learning materials, and the output is the transmission of compressed data. The transmitted data is compressed again and securely transferred. The device decompresses the received data and saves it in its internal storage.

[1505] Specific operation: The server compresses the generated content in Zip format and sends it to the device via an HTTP request. The device unzips the received Zip file and saves it in the app's internal storage.

[1506] Step 6:

[1507] Emotion engine recognizes user emotions

[1508] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input data is image data of the captured facial expressions, and the output is recognized emotion data. The emotion engine analyzes the captured image data, recognizes the user's emotional state, and sends the data to the server.

[1509] How it works: When a user opens the app, the camera automatically activates and detects their face. The emotion engine analyzes the user's facial expressions, identifies emotions such as "joy" or "stress," and sends the data to the server.

[1510] Step 7:

[1511] Emotion-based content presentation

[1512] The server adjusts the presentation of the generated learning content based on the received emotional data. The input data is the emotional data, and the output is the adjusted learning content. If the user is feeling stressed, it will prioritize displaying easy problems or information on relaxation techniques.

[1513] How it works: The server receives the emotion data and uses an AI model to select appropriate content. If the user is in a stressful state, it generates a page containing short questions and relaxation guides and sends it to a dedicated app.

[1514] Step 8:

[1515] Use user-generated learning materials

[1516] Users can view the generated vocabulary books, workbooks, and reference materials through a dedicated application. The input data is the learning materials stored on the device, and the output is the user's learning results. The application has an intuitive user interface and is designed to allow users to easily access the learning content. In addition, the content is personalized based on the emotional state recognized by the emotion engine.

[1517] What it does: If a user is browsing a vocabulary book within the app and is feeling stressed, the app will provide a personalized learning experience based on the user's emotions, such as playing relaxing music while displaying the learning content.

[1518] (Application example 2)

[1519] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1520] Conventional industrial robots operate according to pre-programmed work procedures, but their lack of flexibility makes it difficult to quickly incorporate handwritten work instructions on-site. Furthermore, they are unable to take into account the emotional state of the worker, raising concerns that work efficiency may decline in environments prone to stress or strain. The lack of a system that can immediately respond to handwritten instructions or reflect the emotional state of the worker poses challenges in ensuring sufficient work efficiency and safety.

[1521] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1522] In this invention, the server includes a means for recognizing the emotional state of the user, a means for adjusting the content presentation method according to the emotional state of the user, a means for generating a work procedure to be performed by the industrial robot based on the analyzed text data, and a means for the industrial robot to execute the generated work procedure, thereby enabling immediate response to handwritten instructions and optimizing the work environment based on the emotional state of the worker.

[1523] A "handwritten notebook" is a notebook containing information that is handwritten by the user using a writing instrument.

[1524] "Image data" refers to data representing visual digital information generated by a user photographing a handwritten note.

[1525] A "server" is a computer system that receives, analyzes, stores, and transmits data over a network.

[1526] "Text data" refers to data that indicates character information extracted from image data using OCR technology.

[1527] A "vocabulary book" is a book containing words, their meanings, and definitions to aid in learning and memorization.

[1528] A "workbook" is a teaching material that includes a set of questions and their answers related to a specific learning content.

[1529] "References" are related materials and documents that deepen understanding of specific learning content.

[1530] "Emotional state" refers to the user's psychological state, such as happiness, sadness, or stress.

[1531] "Content presentation" refers to how the generated learning materials and information are displayed and provided to the user.

[1532] An "industrial robot" is an automated mechanical device used in an industrial setting that has the ability to perform specific tasks.

[1533] A "work procedure" is a series of operations or operational procedures that an industrial robot must execute.

[1534] Overall system picture

[1535] The system of the present invention allows users to take photos of their handwritten notes, analyzes the content, and provides learning content and work procedures. It also includes a function to adjust the way content is presented based on the user's emotional state, and automatically execute work procedures using an industrial robot.

[1536] Hardware and software used

[1537] Hardware:

[1538] Smartphone or tablet (with camera)

[1539] Server (high-performance CPU, GPU, storage)

[1540] industrial robots

[1541] software:

[1542] Python

[1543] OCR tool (Pytesseract)

[1544] Image processing library (OpenCV)

[1545] Emotion recognition API (Microsoft Azure Face API)

[1546] Web frameworks (Flask / Django)

[1547] Communication protocol (HTTPS)

[1548] Specific operation of the system

[1549] 1. Photographing handwritten notes

[1550] Users take a photo of their handwritten notes using a smartphone or tablet, and the image data is temporarily stored in the device's internal storage.

[1551] 2. Sending image data

[1552] The device compresses the stored image data and sends it to the server using the HTTPS protocol, which encrypts the data to ensure its security and returns a confirmation response after the transmission is complete.

[1553] 3. Analysis of image data

[1554] The server analyzes the image data using OCR technology and extracts handwritten characters and graphics as text data. This process includes preprocessing such as noise removal and binarization.

[1555] 4. Content Generation

[1556] The server generates vocabulary books, exercise books, and reference books based on the extracted text data by inserting the text data using appropriate templates.

[1557] 5. Submission of Content

[1558] The server sends the generated vocabulary book, exercise book, and reference materials to the device. The data is again securely transferred via HTTPS. The device unpacks the received data and saves it in its internal storage.

[1559] 6. Emotional Recognition

[1560] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The emotion engine analyzes the captured image data and recognizes the user's emotional state. The recognized emotion data is then sent to the server.

[1561] 7. Emotional Content Presentation

[1562] The server adjusts the presentation of the generated learning content based on the received emotional data: if the user is feeling stressed, it will prioritize presenting information on relaxation techniques and easy questions to reduce the learning load.

[1563] 8. Workflow generation and execution

[1564] The server generates work procedures for the industrial robot based on the analyzed text data, and the robot then executes the work procedures. This allows the contents of handwritten instructions to be efficiently incorporated, enabling flexible work.

[1565] Examples of concrete examples and prompts

[1566] Examples:

[1567] A factory worker writes down the work procedures for a new product line in a handwritten notebook and takes a photo of the notes with a smartphone. The photo data is sent to a server and analyzed using OCR. Based on the analysis results, an industrial robot executes the work procedures and responds quickly.

[1568] Example prompt sentence:

[1569] "Generate work procedures for an industrial robot from photographed data of handwritten notes. The data will include the following information: work procedures, precautions, and tools to be used. Please tell me how to implement a system that generates an appropriate work plan based on the analysis results and sends it to the robot."

[1570] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1571] Step 1:

[1572] The user takes an image of their handwritten notes using a smartphone or tablet. The input is the handwritten notes, and the output is the captured image data. Specifically, the user launches the camera app to take a picture of the notes, and the image data is saved in the device's internal storage.

[1573] Step 2:

[1574] The device compresses the captured image data and sends it to the server using the HTTPS protocol. The input is the image data stored in the internal storage, and the output is the transmission of the compressed image data to the server. Specifically, the device runs the compression algorithm, encrypts the compressed data using HTTPS, and sends it to the server.

[1575] Step 3:

[1576] The server uses OCR technology to analyze the received image data. The input is compressed image data, and the output is analyzed text data. Specifically, the server first decompresses the data and then uses Pytesseract or OpenCV to extract handwritten characters and shapes from the image as text data.

[1577] Step 4:

[1578] The server generates vocabulary books, exercise books, and reference materials based on the extracted text data. The input is the analyzed text data, and the output is the generated learning content. Specifically, the server inserts the text data into appropriate templates, classifies them into categories, and generates content.

[1579] Step 5:

[1580] The server sends the generated learning content to the terminal. The input is the generated learning content, and the output is the data that has been sent to the terminal. Specifically, the server compresses the data again and sends it securely to the terminal using the HTTPS protocol.

[1581] Step 6:

[1582] When a user launches the dedicated application, the device's camera captures the user's facial expressions. The input is the user's facial expressions, and the output is the captured image data. Specifically, the device starts up the camera, captures the user's facial expressions, and saves the image data in its internal storage.

[1583] Step 7:

[1584] The server receives the captured image data and uses an emotion engine to recognize the user's emotional state. The input is the captured image data, and the output is the recognized emotion data. Specifically, the server uses the Microsoft Azure Face API to analyze the image data and evaluate the emotional state.

[1585] Step 8:

[1586] The server adjusts the presentation method of the generated learning content based on the received emotional data. The input is the emotional data and learning content, and the output is the adjusted presentation method. Specifically, the server evaluates the emotional data and determines how to prioritize the presentation of relaxation information and easy questions.

[1587] Step 9:

[1588] The server generates work procedures to be executed by the industrial robot based on the analyzed text data. The input is text data and the output is work procedures. Specifically, the server analyzes the text data, generates appropriate work procedures, and transmits them to the robot.

[1589] Step 10:

[1590] Industrial robots perform tasks according to the procedures provided by the server. The input is the procedure, and the output is the executed task. In terms of specific operations, the robot acts as instructed and completes the specified task.

[1591] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1592] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1593] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1594] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1595] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1596] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1597] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1598] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1599] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1600] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1601] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1602] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1603] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1604] 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.

[1605] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1606] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1607] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1608] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1609] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1610] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1611] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1612] The following is further disclosed regarding the above embodiment.

[1613] (Claim 1)

[1614] A means for users to take photos of their handwritten notes;

[1615] means for transmitting image data captured by the terminal to a server;

[1616] A means for the server to analyze the image data and extract text data;

[1617] means for the server to generate a vocabulary book, a workbook, and a reference book based on the extracted text data;

[1618] A means for the server to transmit the generated content to the terminal;

[1619] a means for a user to view the generated content through the device;

[1620] A system including:

[1621] (Claim 2)

[1622] 10. The system of claim 1, wherein the terminal further comprises means for compressing the image data.

[1623] (Claim 3)

[1624] 10. The system of claim 1, wherein the server further comprises means for categorizing the extracted text data and generating content using different templates based on each category.

[1625] "Example 1"

[1626] (Claim 1)

[1627] A means for users to take pictures of their handwritten notes with an electronic device;

[1628] a means for compressing image data captured by the electronic device and transmitting the compressed image data to a server via a network;

[1629] A means for analyzing the image data received by the server using optical character recognition technology and extracting text data;

[1630] The server preprocesses the extracted text data, removing noise and converting it to binary data.

[1631] A means for the server to generate a vocabulary book, a workbook, and reference materials based on the classified text data using natural language processing technology;

[1632] A means for the server to compress the generated content and transmit it again to the electronic device through the network;

[1633] A means for users to view the generated content through a dedicated application;

[1634] A system including:

[1635] (Claim 2)

[1636] 10. The system of claim 1, wherein the electronic device further comprises means for compressing the image data.

[1637] (Claim 3)

[1638] 10. The system of claim 1, wherein the server further comprises means for classifying the extracted text data based on categories and generating content using different templates.

[1639] "Application Example 1"

[1640] (Claim 1)

[1641] A means for users to take photos of their handwritten notes;

[1642] means for transmitting image data captured by the terminal to a server;

[1643] A means for the server to analyze the image data and extract text data;

[1644] means for the server to generate a vocabulary book, a workbook, and a reference book based on the extracted text data;

[1645] A means for the server to transmit the generated content to the terminal;

[1646] a means for a user to view the generated content through the device;

[1647] A means for analyzing the contents of handwritten notes by users and generating appropriate learning materials using a generative AI model;

[1648] A means to link the generated learning materials with feedback and progress management functions,

[1649] A system including:

[1650] (Claim 2)

[1651] 10. The system of claim 1, wherein the terminal further comprises means for compressing the image data.

[1652] (Claim 3)

[1653] 10. The system of claim 1, wherein the server further comprises means for categorizing the extracted text data and generating content using different templates based on each category.

[1654] "Example 2: Combining Emotion Engines"

[1655] (Claim 1)

[1656] A means for users to take photos of their handwritten notes;

[1657] means for transmitting image data captured by the terminal to a server;

[1658] A means for the server to analyze the image data and extract text data;

[1659] means for the server to generate a vocabulary book, a workbook, and a reference book based on the extracted text data;

[1660] A means for the server to transmit the generated content to the terminal;

[1661] a means for a user to view the generated content through the device;

[1662] An emotion engine means for capturing a user's facial expression using a camera in the device and recognizing the user's emotional state;

[1663] a means for the server to adjust the presentation of the learning content based on the recognized emotion data;

[1664] A system including:

[1665] (Claim 2)

[1666] 10. The system of claim 1, wherein the terminal further comprises means for compressing the image data.

[1667] (Claim 3)

[1668] 10. The system of claim 1, wherein the server further comprises means for categorizing the extracted text data and generating content using different templates based on each category.

[1669] "Application example 2 when combining emotion engines"

[1670] (Claim 1)

[1671] A means for users to take photos of their handwritten notes;

[1672] means for transmitting image data captured by the terminal to a server;

[1673] A means for the server to analyze the image data and extract text data;

[1674] means for the server to generate a vocabulary book, a workbook, and a reference book based on the extracted text data;

[1675] A means for the server to transmit the generated content to the terminal;

[1676] a means for a user to view the generated content through the device;

[1677] a means for recognizing the emotional state of a user;

[1678] a means for adjusting the presentation of content according to the user's emotional state;

[1679] Furthermore, a means for generating a work procedure to be executed by the industrial robot based on the analyzed text data;

[1680] A means for an industrial robot to execute the generated work procedure;

[1681] A system including:

[1682] (Claim 2)

[1683] 10. The system of claim 1, wherein the terminal further comprises means for compressing the image data.

[1684] (Claim 3)

[1685] 10. The system of claim 1, wherein the server further comprises means for categorizing the extracted text data and generating content using different templates based on each category. [Explanation of symbols]

[1686] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to take photos of their handwritten notes; means for transmitting image data captured by the terminal to a server; A means for the server to analyze the image data and extract text data; means for the server to generate a vocabulary book, a workbook, and a reference book based on the extracted text data; A means for the server to transmit the generated content to the terminal; a means for a user to view the generated content through the device; A system including:

2. 10. The system of claim 1, wherein the terminal further comprises means for compressing the image data.

3. 10. The system of claim 1, wherein the server further comprises means for categorizing the extracted text data and generating content using different templates based on each category.

Images