System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving learning contents uploaded by a learner; means for converting the received learning contents into text data; means for receiving information of a drawing style selected by the learner from a plurality of drawing styles; means for generating a comics format teaching material using a generative AI model based on the text data and the information of the drawing style; and means for providing the generated comics format teaching material to the learner.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] Traditional learning methods have the problem that the content of textbooks and specialized books is difficult to understand, which can easily cause students to lose motivation and fail to understand. Furthermore, reading text-based materials for long periods of time is tedious and it is difficult to maintain concentration. As a result, many learners lose interest in learning and their learning efficiency declines. To solve these issues, there is a need for visually appealing learning tools that are tailored to individual learning styles and interests. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means: A means for receiving learning content uploaded by a learner is provided; A means for converting the received learning content into text data is provided; A means for receiving information on a drawing style selected by a learner from multiple drawing styles is provided; A means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information is provided; and A system is constructed that includes a means for providing the generated manga-style teaching materials to learners, allowing learners to study efficiently while having fun. Furthermore, the generated manga-style teaching materials can include quizzes and problem-solving scenarios to deepen learners' understanding and maintain their interest in learning.

[0006] A "learner" is an individual who engages in learning activities to improve their knowledge and skills.

[0007] "Learning content" refers to information and data about a particular topic or theme that a learner wants to learn.

[0008] "Means for receiving" refers to the function or device for acquiring data or information from learners and incorporating it into the system.

[0009] "Text data" refers to data that represents sentences or character information in digital form.

[0010] "Art style" refers to the visual drawing and design characteristics of manga and illustrations.

[0011] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate new content based on specific input data.

[0012] "Manga-style teaching materials" refers to teaching materials written in manga format for educational or learning purposes.

[0013] "Means of provision" refers to the functions and processes that allow learners to view and download the generated manga-style teaching materials.

[0014] A "quiz" refers to questions or problems that are used to check the level of understanding of the learning content.

[0015] "Problem-solving scenarios" refer to parts of teaching materials that show specific situations or stories in which learners can apply what they have learned to solve problems.

[0016] "System" refers to a series of devices or programs that operate by combining the above-mentioned various means. [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] To specifically put the present invention into practice, a system that performs the following processes is constructed.

[0039] Upload and convert learning content

[0040] First, the user prepares the study material they want to study (for example, a chapter from a textbook or a section from a technical book) in a digital format such as a PDF file, and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0041] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[0042] Selecting and applying a drawing style

[0043] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0044] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[0045] Automatic manga generation

[0046] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[0047] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0048] Provision and use of manga

[0049] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0050] Specific examples

[0051] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. Then, they select a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download the manga and continue their learning in an enjoyable way.

[0052] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[0056] Step 2:

[0057] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[0058] Step 3:

[0059] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[0060] Step 4:

[0061] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[0062] Step 5:

[0063] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[0064] Step 6:

[0065] Terminal: Sends information about the selected drawing style to the server.

[0066] Step 7:

[0067] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[0068] Step 8:

[0069] Server: Inputs the formatted text data and the selected drawing style information into the generative AI model. The generative AI model is executed and generates each page of the manga based on the text data.

[0070] Step 9:

[0071] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[0072] Step 10:

[0073] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[0074] Step 11:

[0075] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[0076] Step 12:

[0077] Terminal: Displays the generated manga download link to the user through the user interface.

[0078] Step 13:

[0079] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[0080] In this way, at each step, the entire system works together to provide the user with the content they want to learn in manga format.

[0081] Example 1

[0082] 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."

[0083] Conventional learning materials are mainly text and static diagrams, and it often takes a long time for learners to understand the content. Furthermore, they lack visual aids to make learning fun for learners, making it difficult to maintain motivation. To address these issues, there is a need for a more efficient way to provide learning materials that are more visually appealing and easier to understand.

[0084] 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.

[0085] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a style selected by the learner from a plurality of visual styles, means for generating learning materials with illustrations using a generative AI model based on the text data and the style information, and means for providing the generated learning materials with illustrations to the learner, thereby enabling the learner to efficiently understand the learning content while having fun.

[0086] "Learner" refers to an individual or group who uses the system to carry out learning activities.

[0087] "Upload" refers to the act of a user sending a file from their own device to a server.

[0088] "Learning content" refers to the teaching materials and documents that learners upload to the system, including digital data such as text and PDF format.

[0089] "Means for receiving" refers to the function that allows the server to obtain uploaded files and information.

[0090] "Text Data" refers to textual information extracted from PDFs and other digital formats.

[0091] "Means for conversion" refers to the function for converting received learning content into text data.

[0092] "Visual styles" refers to various visual designs and formats for presenting learning content, such as manga and picture books.

[0093] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates visual teaching materials such as manga and illustrations based on learning content.

[0094] "Means of providing" refers to the function of making the generated illustrated teaching materials available to learners in the form of downloading or viewing.

[0095] "Illustrated teaching materials" are teaching materials that visually represent the learning content, and include materials in manga format and illustrations.

[0096] "Parameters" refer to settings or conditions that affect the behavior of a generative AI model.

[0097] In order to implement the present invention, the system must be configured as follows.

[0098] First, the user prepares the learning materials they want to study as digital data, such as PDF format. The user accesses the system's upload screen and uses the upload button to send the learning materials to the server. The terminal provides a file selection and upload button through the user interface, allowing the user to send the selected file to the server.

[0099] The server then checks the received PDF file, verifies that it is in the correct format, and converts it to text data using a PDF parsing library such as the PyMuPDF library. The parsed text data is then converted to JSON format for subsequent processing.

[0100] After the upload process is complete, the user has access to a list of options for selecting a drawing style. The system displays multiple visual style options through the terminal. The user selects the style that best suits their preferences and sends the selection to the server. The server applies the received style information as parameters for the generative AI model. This step ensures that the generated manga is drawn in the style selected by the user.

[0101] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate illustrated learning materials corresponding to the learning content. Specifically, it generates manga pages using generative AI models such as GPT-4 (registered trademark) and VQ-VAE-2. The generated manga pages include scenarios and illustrations related to the learning content, and automatically incorporate quizzes and problem-solving scenarios to support the user's learning.

[0102] Finally, the server stores the generated manga-style learning materials in a database and generates a download link. A NoSQL database such as MongoDB is used for this storage. The device displays the download link through a user interface, and users can click the link to download the manga and proceed with their learning at their own pace.

[0103] As a specific example of use, consider the case where a user wants to study the "Differential Calculus" chapter in mathematics. The user uploads the relevant page of a PDF textbook to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download it and continue learning while having fun.

[0104] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[0105] Prompt Sentence Examples

[0106] I want to learn the differential calculus chapter from my textbook in manga format. Upload the file and generate it in a "pop art style."

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] The user prepares a PDF file of the learning material they want to study and accesses the system's upload screen. The terminal displays a file selection button and an upload button on the user interface. The user clicks the file selection button to select the file to upload. They then click the upload button to send the file to the server. The input is a PDF file, and the output is a PDF file saved on the server. Specifically, the file is uploaded to the server via the browser.

[0110] Step 2:

[0111] The server receives the uploaded PDF file and verifies that the file format is appropriate. Then, it uses a PDF parsing library (e.g., PyMuPDF) to convert the PDF to text data. The input is the PDF file, and the output is text data (JSON format). Specifically, it extracts the text from the PDF and formats it in JSON format.

[0112] Step 3:

[0113] The device displays multiple visual style options through a user interface. The user selects their preferred drawing style from the displayed list of options. The user's input is the selected drawing style, and the output is the corresponding information. Specific operations include selecting a style through a UI component such as a drop-down menu, and sending the selection information to the server.

[0114] Step 4:

[0115] The server receives the selected drawing style information and applies it as a parameter for the generative AI model. The input is the style selection information, and the output is the updated parameters for the generative AI model. Specifically, the server updates the setting parameters of the AI ​​model based on the style information.

[0116] Step 5:

[0117] The server inputs the prepared text data and drawing style information into a generative AI model to generate illustrated teaching materials corresponding to the learning content. The input is text data and drawing style information, and the output is the generated illustrated teaching materials. Specifically, it uses a generative AI model (e.g., GPT-4, VQ-VAE-2) to generate manga pages, and then places the scenario and illustrations on those manga pages.

[0118] Step 6:

[0119] The server stores the generated illustrated teaching materials in a database and generates a download link. The input is the generated illustrated teaching materials, and the output is a download link. Specifically, the generated teaching materials are stored in a NoSQL database (e.g., MongoDB) and an access link is generated.

[0120] Step 7:

[0121] The device displays this download link on the user interface. The user clicks the link to download the generated manga. The input is the download link, and the output is a manga file saved on the user's local device. Specifically, the link is clicked via a browser, and the file is downloaded to the user's device.

[0122] (Application example 1)

[0123] 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."

[0124] Traditional learning content is visually unattractive, and the text content can be boring and difficult to understand, especially when learning about cooking and food delivery. Furthermore, it is difficult to understand the cooking process in detail and recreate it at home. Therefore, a method to efficiently progress learning while attracting learners' interest is needed.

[0125] 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.

[0126] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from a plurality of drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for providing the generated manga-style teaching materials to the learner, means for converting menus and recipes uploaded by the learner into text data, and means for generating a manga-style food guide using a generative AI model based on the text data and the selected drawing style, thereby enabling learners to learn, analyze, and reproduce cooking processes in an enjoyable and visual way.

[0127] "Learner" means a user who uses the system to upload learning content and advance their own learning.

[0128] "Learning content" refers to the learning materials and information that learners upload to the system, including textbook chapters, recipes, etc.

[0129] "Text data" refers to character information extracted by analyzing the received learning content.

[0130] "Art style" refers to the visual expression method used when generating teaching materials in manga format, and refers to the design and art style that learners can choose from.

[0131] A "generative AI model" is a machine learning model used to generate manga-style teaching materials based on text data and drawing style information.

[0132] "Manga-style teaching materials" refers to visual teaching materials in manga format generated by a generative AI model to make it easier for learners to understand the learning content.

[0133] A "menu" is a document or piece of information that lists dishes or foods, and is often provided with food delivery.

[0134] A "recipe" is information that lists the steps and ingredients for making a particular dish.

[0135] A "food guide" is a teaching material that provides information about cooking and food in manga format.

[0136] "Server" refers to the computer and its software that serves as the core of this system and performs various processes.

[0137] To specifically implement the present invention, it is necessary to build a system that performs the following processes. The specific system configuration and processing procedures are shown below.

[0138] System configuration

[0139] This system consists of the following elements:

[0140] 1. Server: The central processing unit that analyzes uploaded data, runs generative AI models, and stores and serves generated content.

[0141] 2. Terminal: A device that provides a user interface and allows users to upload learning content, select a drawing style, and download the generated manga content.

[0142] 3. Generative AI model: A machine learning model for generating manga-style teaching materials based on text data and drawing style.

[0143] 4. Database: A storage device for storing the generated manga-style teaching materials.

[0144] Processing Details

[0145] Uploading and analyzing learning content

[0146] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as a PDF and accesses the upload screen to the system. The device provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0147] The server receives the uploaded file and verifies that it is in the correct format. Once verified, the server parses the PDF file, converts it to text data, and extracts the learning content. This conversion process uses a library such as PyPDF2 to extract the text data.

[0148] Selecting and applying a drawing style

[0149] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0150] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[0151] Automatic manga generation

[0152] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model and generates manga pages corresponding to the learned content. Here, machine learning models such as the transformers library and VisionEncoderDecoderModel are used.

[0153] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0154] Provision and use of manga

[0155] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0156] Specific examples

[0157] As a specific use case, suppose a user wants to learn about "Italian dinner set menus." The user uploads a PDF menu to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually depicts the cooking process of an Italian dinner, and the user can download it to continue learning in a fun way.

[0158] Prompt Sentence Examples

[0159] Convert the following text into a cartoon in pop art style:

[0160] "How to make pizza: 1. Knead the dough. 2. Add the toppings. 3. Bake in the oven. How to cook pasta: 1. Boil the pasta. 2. Add the sauce. 3. Add the cheese."

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as PDF and uploads it to the system. At this time, the device provides file selection and upload buttons via a user interface, and the user selects the file and clicks the "Upload" button. The PDF file containing the learning content is received as input, and the file is sent to the server as output.

[0164] Step 2:

[0165] The server receives the uploaded PDF file and verifies that the file is in the proper format. Once verified, the server parses the PDF file and converts it into text data. This process uses the PyPDF2 library to extract text information from each page of the PDF. It takes the received PDF file as input and generates text data as output.

[0166] Step 3:

[0167] After the text data is generated, the server saves it and displays a list of multiple drawing style options to the user via the terminal, where the user can select the drawing style that best suits their preference. As input, the text data and drawing style options are displayed, and as output, the user's selected drawing style information is sent to the server.

[0168] Step 4:

[0169] The server receives the selected drawing style information and sets it as a parameter in the generative AI model. It then inputs the prepared text data into the model and generates manga pages corresponding to the learning content. In this step, the transformers library and VisionEncoderDecoderModel are used to create manga-style content containing the generated illustrations and dialogue. Text data and drawing style information are used as input, and manga-style image data is obtained as output.

[0170] Step 5:

[0171] The server stores the generated manga-style teaching materials in a database and generates a download link to provide them to users via their devices. Users can click the link to download the generated manga and proceed with their studies at their own pace. Manga-style teaching material data is saved as input, and a download link is generated as output.

[0172] This allows users to enjoy visually learning about uploaded menus and recipes using the drawing style of their choice.

[0173] 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.

[0174] To specifically implement this invention, a system is constructed that combines the following elements.

[0175] Upload and convert learning content

[0176] First, the user prepares the learning materials they want to study in a digital format such as a PDF file and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0177] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[0178] Selecting and applying a drawing style

[0179] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0180] The server receives the selected drawing style information and stores it in a database, where it is set as a parameter for the generative AI model.

[0181] Incorporating an emotion engine

[0182] Furthermore, the server includes an emotion engine for recognizing the user's emotions in real time. This emotion engine analyzes data acquired from the device's camera and microphone and recognizes the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[0183] Based on the recognized emotions, the server adjusts the difficulty and tone of the generated manga-style learning material, providing a learning experience optimized for the user's emotional state.

[0184] Automatic manga generation

[0185] Based on the prepared text data, selected drawing style information, and the output of the emotion engine, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[0186] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0187] Provision and use of manga

[0188] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0189] Specific examples

[0190] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. After that, the user selects a "pop art style." The system then recognizes the user's emotional state from their facial expressions to ensure that they are concentrating. The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download this and continue their learning in an enjoyable way.

[0191] In this way, by combining the emotion engine, a personalized learning experience is provided that corresponds to the user's emotional state. This invention is a system that solves the problems of conventional learning materials and enables learners to study efficiently while having fun.

[0192] The processing flow will be explained below.

[0193] Step 1:

[0194] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[0195] Step 2:

[0196] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[0197] Step 3:

[0198] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[0199] Step 4:

[0200] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[0201] Step 5:

[0202] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[0203] Step 6:

[0204] Terminal: Sends information about the selected drawing style to the server.

[0205] Step 7:

[0206] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[0207] Step 8:

[0208] Device: A camera and microphone are used to capture facial expressions and voice data in order to recognize the user's emotions in real time.

[0209] Step 9:

[0210] Server: Using an emotion engine, analyzes the acquired facial expressions and voice data to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[0211] Step 10:

[0212] Server: Adjusts the difficulty and tone of the generated manga-style educational material based on the perceived emotional state. For example, if the user is bored, it will add more engaging elements.

[0213] Step 11:

[0214] Server: Inputs the formatted text data, selected drawing style information, and emotional state data into the generative AI model. The generative AI model is executed to generate each page of the manga based on the text data.

[0215] Step 12:

[0216] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[0217] Step 13:

[0218] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[0219] Step 14:

[0220] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[0221] Step 15:

[0222] Terminal: Displays the generated manga download link to the user through the user interface.

[0223] Step 16:

[0224] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[0225] In this way, the entire system works together at each step to provide the user with the content they want to learn in manga format.The introduction of an emotion engine provides a personalized learning experience that matches the user's emotional state.

[0226] Example 2

[0227] 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."

[0228] Traditional learning systems have limited means of converting text data into a visually digestible format, making it difficult to maintain learner interest. They also lack the ability to dynamically adapt learning content to the learner's emotional state, resulting in a lack of personalized learning experiences. Furthermore, they struggle to provide consistent learning materials, including quizzes and problem-solving scenarios.

[0229] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from multiple drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for analyzing data acquired from the terminal to recognize the learner's emotions, means for adjusting the generated teaching materials based on the results of emotion recognition, and means for providing the generated manga-style teaching materials to the learner. This not only enables learners to study effectively while remaining interested, but also provides a personalized learning experience.

[0230] "Learner" refers to a person who accesses the system, uploads learning content, and uses the generated learning materials.

[0231] "Upload" refers to the process by which a learner sends learning content to the system.

[0232] "Learning content" refers to the teaching materials and resources prepared by learners to use the system.

[0233] "Means of receiving" refers to the function of the system to receive data uploaded by learners.

[0234] "Text data" refers to textual information extracted from PDFs and other formats.

[0235] "Means for conversion" refers to the function of analyzing the received learning content and converting it into text data.

[0236] "Artistic style" refers to the visual form of expression chosen by the learner.

[0237] "Drawing style information" refers to data about the drawing style selected by the learner.

[0238] A "generative AI model" refers to an artificial intelligence algorithm that takes text data and drawing style information as input and generates visual teaching materials.

[0239] "Manga-style teaching materials" refers to visual learning materials created by generative AI models.

[0240] "Means for providing" refers to the function for making the generated teaching materials available to learners.

[0241] "Means for recognizing emotions" refers to the function of analyzing data obtained from the device and determining the learner's emotions.

[0242] "Adjustment means" refers to the ability to change the content and format of the generated teaching materials based on the results of emotion recognition.

[0243] This invention is a system for providing learners with a personalized visual learning experience. Specifically, it receives learning content uploaded by users, converts it into text data, and automatically generates manga-style learning materials using a generative AI model based on the selected drawing style. It also recognizes learners' emotions in real time and adjusts the learning materials based on the results to maximize learning effectiveness.

[0244] Hardware and software used

[0245] server

[0246] Hardware: A server with a powerful processor, sufficient memory, and storage, such as an Intel Xeon or AMD Ryzen processor.

[0247] software:

[0248] OCR software: Tesseract

[0249] Generative AI models: GPT-4, Stable Diffusion

[0250] Sentiment analysis engine: Affectiva SDK

[0251] Terminal

[0252] Hardware: A PC or smart device with a camera and microphone, such as a desktop PC with a webcam, a laptop, or a tablet device.

[0253] software:

[0254] Browser: Major browsers such as Chrome, Firefox, and Safari

[0255] User interface: HTML, CSS, JavaScript (registered trademark) interface

[0256] User

[0257] Hardware: Devices listed above

[0258] Software: Uses specific applications and web browsers

[0259] Data processing and calculation

[0260] A user prepares learning materials in PDF file format and accesses the system's upload screen. For example, they use any browser to access a specific URL (e.g., https: / / manga-learning-system.com), click the "Choose File" button in the user interface, select the PDF file (e.g., mathematics_differentiation.pdf), and click the upload button.

[0261] The device sends files uploaded through the user interface to the server, which then verifies the received files and converts them into text using OCR software (Tesseract), which then formats the text for input into the generative AI model and stores it in a database.

[0262] The user then selects the manga drawing style. Multiple visual styles (e.g., simple, pop, realistic) are provided for selection, and the user chooses the style that best suits their preferences. The selected style information is sent to the server via the terminal. The server receives this information and stores it in a database.

[0263] The server uses the device's camera and microphone to recognize the user's emotions in real time. The acquired data is analyzed using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). Based on the recognized emotional state, the content and tone of the generated learning material are adjusted.

[0264] The server inputs the prepared text data, the selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, it sends a prompt to the generative AI model: "Text data: text explaining differentiation, drawing style: pop, emotional state: concentration." The generative AI model then automatically generates manga-style teaching materials based on this information and stores them in a database.

[0265] The server generates a download link for providing the created manga-style learning material and displays it through the user interface. The user can click the displayed link to download the learning material and proceed with the learning at their own pace.

[0266] Examples of specific examples and prompts

[0267] For example, if a user wants to learn "differential calculus," they upload the relevant page from a PDF textbook to the system. They then select a "pop art style." The system checks the user's facial expression to see if they are concentrating and extracts text data. Based on the selected style, a generative AI model (e.g., GPT-4) is used to generate a manga. The generated manga visually illustrates the basic concepts of differentiation and examples of calculations. Users can download it and continue their learning in an enjoyable way.

[0268] Example prompt sentence:

[0269] "Text Data: Basic Concepts of Differentiation and Examples"

[0270] "Drawing style: Pop"

[0271] "Emotional state: Focused"

[0272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0273] Step 1:

[0274] The user prepares the learning material they want to study in PDF file format and accesses the system's upload screen. The device displays a screen with a file selection and upload button. The user clicks the "Choose File" button, selects the PDF file (e.g., mathematics_differentiation.pdf), and clicks the "Upload" button. This starts the upload operation, with the PDF file serving as input.

[0275] Step 2:

[0276] The terminal sends the file uploaded through the user interface to the server. The server checks the received file and verifies whether the file is in PDF format. If the file is in PDF format, the server analyzes the PDF file and converts it into text data. The input here is the PDF file, and the output is text data. The server uses OCR software (Tesseract) to extract the text information from the PDF and stores this text data in a database.

[0277] Step 3:

[0278] The user accesses an option list to select a manga drawing style. The terminal displays multiple drawing style options (e.g., simple, pop, realistic) on the user interface. The user selects the drawing style that suits their preference and sends the information to the server. The input here is the selected drawing style information, and the output is the drawing style information saved on the server side.

[0279] Step 4:

[0280] The server uses the device's camera and microphone to recognize the user's emotions in real time. The device collects the user's facial expression and voice data and sends it to the server. The server then analyzes this data using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). The input here is the data obtained from the camera and microphone, and the output is the user's emotional state information.

[0281] Step 5:

[0282] The server inputs prepared text data, selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, by sending a prompt such as "Text data: text explaining differentiation, drawing style: pop, emotional state: focused" to the generative AI model, a manga-style teaching material is generated. The inputs are the text data, drawing style information, and emotional state information, which form the prompt sentence, and the output is the generated manga page.

[0283] Step 6:

[0284] The generated manga-style teaching materials are stored in a database by the server. The server then generates a download link to provide to the user. The device displays this download link on its user interface. The user can click the displayed link to download the teaching materials and proceed with their learning at their own pace. The input here is the generated manga teaching materials, and the output is the generation and display of a download link.

[0285] (Application example 2)

[0286] 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."

[0287] Traditional learning methods have the drawback of making it difficult to maintain learners' concentration and interest, making it difficult to achieve efficient learning. Furthermore, it has been difficult to provide learning materials that respond to the emotions and state of each individual learner, making it impossible to provide a personalized learning experience. This has led to problems such as reduced learning effectiveness, especially in online and remote learning.

[0288] 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.

[0289] In this invention, the server includes: means for receiving learning content uploaded by a learner; means for converting the received learning content into text data; means for receiving information on a drawing style selected by the learner from multiple drawing styles; means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information; means for providing the generated manga-style teaching materials to the learner; emotion analysis means for analyzing the learner's emotions in real time; means for adjusting the difficulty and tone of the generated manga-style teaching materials based on the emotional state analyzed by the emotion analysis means; and means for displaying the generated manga-style teaching materials on a visual device. This enables a personalized learning experience tailored to the learner's emotional state. Furthermore, by maintaining the learner's interest and concentration, efficient learning can be achieved.

[0290] A "learner" is a person who is learning specific knowledge or skills.

[0291] "Uploading" is the act of sending or transferring data to an external device or server.

[0292] "Learning content" refers to the information and materials that a learner is trying to acquire.

[0293] "Receiving" is the act of taking in information or data sent from another source.

[0294] "Text data" refers to information expressed as characters or sentences.

[0295] "Art style" refers to the drawing method and design characteristics of visual content.

[0296] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate a specific result.

[0297] "Manga-style teaching materials" refers to educational content drawn in manga format.

[0298] "Emotion analysis" is the process of analyzing a user's emotions and sensory state through data.

[0299] "Visual device" refers to equipment or devices that allow a user to receive information visually.

[0300] "Adjustment" is the act of changing to an optimal state depending on specific conditions or situations.

[0301] This invention provides a system that visualizes the learning materials uploaded by learners, enabling more effective and interesting learning.

[0302] System configuration

[0303] Hardware

[0304] The system uses the following hardware:

[0305] Smart glasses (used as a visual device)

[0306] Smartphone (used for uploading teaching materials and as a user interface)

[0307] Servers (used for data processing and running AI models)

[0308] software

[0309] The system uses the following software:

[0310] cv2 (OpenCV toolkit): Used to analyze the user's face image

[0311] pytesseract: Used to extract text from PDF

[0312] pdf2image: Convert PDF files to images

[0313] TENSORFLOW®: Used to run generative AI models

[0314] transformers (Hugging Face Transformers): used for sentiment analysis and text generation

[0315] Processing flow

[0316] 1. Uploading study materials

[0317] Users upload PDF-format learning materials to the system using their smartphones. The server receives the uploaded files and proceeds to the next step.

[0318] 2. Text data conversion

[0319] The server converts PDF files to images using pdf2image, then extracts text data from these images using pytesseract.

[0320] 3. Choose your drawing style

[0321] Users can select their preferred drawing style from multiple options, and the selected style information is sent to the server and used as parameters for the generative AI model.

[0322] 4. Emotion analysis

[0323] Using the camera and microphone of the smart glasses, the system analyzes the user's emotions in real time using the CV2 and Transformers libraries. The analyzed emotional information is used to adjust the generated manga teaching materials.

[0324] 5. Manga Generation

[0325] The server automatically generates manga-style teaching materials using a generative AI model based on the extracted text data and the results of user sentiment analysis.

[0326] 6. Display of Manga

[0327] The generated manga-style learning materials are displayed on smart glasses, allowing users to study the visualized learning materials in real time.

[0328] Specific examples

[0329] Consider a case where a user who wants to learn differential calculus uploads the relevant page from a PDF textbook. The user selects the "pop art style" and begins learning through smart glasses. The system then analyzes the user's facial expression to determine their level of concentration, and uses a generative AI model to generate visually easy-to-understand manga content.

[0330] Specific examples of prompts are as follows:

[0331] Generate a fun manga based on the following text: The derivative of a function measures how the function value changes as its input changes. For example, the derivative of y = x^2 is 2x.

[0332] This system provides learners with a personalized learning experience that is tailored to their emotional state, making learning more effective and engaging.

[0333] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0334] Step 1:

[0335] Uploading teaching materials

[0336] Input: Learning materials in PDF format uploaded by users from their smartphones.

[0337] Process: Select a PDF file through the terminal's user interface and send it to the server.

[0338] Data processing / calculation: Upload the PDF file to the server using an HTTP request.

[0339] Output: The server receives the PDF file and prepares it for the next step.

[0340] Step 2:

[0341] Text data conversion

[0342] Input: A PDF file uploaded to the server.

[0343] Processing: The server converts the PDF file to an image file using the pdf2image library, then extracts the text data from the image using pytesseract.

[0344] Data processing / calculation: By performing OCR (optical character recognition), text information is obtained from the images of each page.

[0345] Output: The retrieved text data.

[0346] Step 3:

[0347] Selecting a drawing style

[0348] Input: User selected drawing style information.

[0349] Processing: The user selects the preferred drawing style from multiple drawing style options and sends that information to the server.

[0350] Data processing / calculation: Sends style information selected through the user interface to the server.

[0351] Output: The server receives the drawing style information and stores it as parameters to be applied to the generative AI model.

[0352] Step 4:

[0353] Emotion analysis

[0354] Input: User's facial image and voice data captured by the smart glasses' camera and microphone.

[0355] Processing: The server uses cv2 and transformers libraries to analyze the user's emotional state in real time.

[0356] Data processing / calculation: Recognize emotions from facial expressions using image analysis algorithms and generate emotional data based on that.

[0357] Output: User's emotional state data (e.g., happy, sad, excited, bored, etc.).

[0358] Step 5:

[0359] Manga Generation

[0360] Input: Text data, drawing style information, and user emotional state data.

[0361] Processing: The server inputs these input data into a generative AI model to automatically generate manga-style teaching materials.

[0362] Data processing / computation: Generate stories using text generation algorithms and synthesize appropriate visuals based on drawing style and emotional state.

[0363] Output: Generated manga-style teaching materials.

[0364] Step 6:

[0365] Manga display

[0366] Input: Generated manga-style teaching materials.

[0367] Processing: The server sends the generated manga to the smart glasses and displays it for the user to learn visually in real time.

[0368] Data processing / calculation: Manga data is sent to the smart glasses using a data transfer protocol.

[0369] Output: Manga-style educational material displayed on smart glasses.

[0370] 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.

[0371] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0372] 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.

[0373] [Second embodiment]

[0374] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] In the smart glasses 214, 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.

[0385] 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."

[0386] To specifically put the present invention into practice, a system that performs the following processes is constructed.

[0387] Upload and convert learning content

[0388] First, the user prepares the study material they want to study (for example, a chapter from a textbook or a section from a technical book) in a digital format such as a PDF file, and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0389] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[0390] Selecting and applying a drawing style

[0391] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0392] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[0393] Automatic manga generation

[0394] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[0395] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0396] Provision and use of manga

[0397] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0398] Specific examples

[0399] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. Then, they select a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download the manga and continue their learning in an enjoyable way.

[0400] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[0401] The processing flow will be explained below.

[0402] Step 1:

[0403] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[0404] Step 2:

[0405] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[0406] Step 3:

[0407] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[0408] Step 4:

[0409] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[0410] Step 5:

[0411] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[0412] Step 6:

[0413] Terminal: Sends information about the selected drawing style to the server.

[0414] Step 7:

[0415] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[0416] Step 8:

[0417] Server: Inputs the formatted text data and the selected drawing style information into the generative AI model. The generative AI model is executed and generates each page of the manga based on the text data.

[0418] Step 9:

[0419] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[0420] Step 10:

[0421] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[0422] Step 11:

[0423] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[0424] Step 12:

[0425] Terminal: Displays the generated manga download link to the user through the user interface.

[0426] Step 13:

[0427] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[0428] In this way, at each step, the entire system works together to provide the user with the content they want to learn in manga format.

[0429] Example 1

[0430] 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."

[0431] Conventional learning materials are mainly text and static diagrams, and it often takes a long time for learners to understand the content. Furthermore, they lack visual aids to make learning fun for learners, making it difficult to maintain motivation. To address these issues, there is a need for a more efficient way to provide learning materials that are more visually appealing and easier to understand.

[0432] 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.

[0433] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a style selected by the learner from a plurality of visual styles, means for generating learning materials with illustrations using a generative AI model based on the text data and the style information, and means for providing the generated learning materials with illustrations to the learner, thereby enabling the learner to efficiently understand the learning content while having fun.

[0434] "Learner" refers to an individual or group who uses the system to carry out learning activities.

[0435] "Upload" refers to the act of a user sending a file from their own device to a server.

[0436] "Learning content" refers to the teaching materials and documents that learners upload to the system, including digital data such as text and PDF format.

[0437] "Means for receiving" refers to the function that allows the server to obtain uploaded files and information.

[0438] "Text Data" refers to textual information extracted from PDFs and other digital formats.

[0439] "Means for conversion" refers to the function for converting received learning content into text data.

[0440] "Visual styles" refers to various visual designs and formats for presenting learning content, such as manga and picture books.

[0441] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates visual teaching materials such as manga and illustrations based on learning content.

[0442] "Means of providing" refers to the function of making the generated illustrated teaching materials available to learners in the form of downloading or viewing.

[0443] "Illustrated teaching materials" are teaching materials that visually represent the learning content, and include materials in manga format and illustrations.

[0444] "Parameters" refer to settings or conditions that affect the behavior of a generative AI model.

[0445] In order to implement the present invention, the system must be configured as follows.

[0446] First, the user prepares the learning materials they want to study as digital data, such as PDF format. The user accesses the system's upload screen and uses the upload button to send the learning materials to the server. The terminal provides a file selection and upload button through the user interface, allowing the user to send the selected file to the server.

[0447] The server then checks the received PDF file, verifies that it is in the correct format, and converts it to text data using a PDF parsing library such as the PyMuPDF library. The parsed text data is then converted to JSON format for subsequent processing.

[0448] After the upload process is complete, the user has access to a list of options for selecting a drawing style. The system displays multiple visual style options through the terminal. The user selects the style that best suits their preferences and sends the selection to the server. The server applies the received style information as parameters for the generative AI model. This step ensures that the generated manga is drawn in the style selected by the user.

[0449] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate illustrated learning materials corresponding to the learning content. Specifically, it generates manga pages using generative AI models such as GPT-4 and VQ-VAE-2. The generated manga pages include scenarios and illustrations related to the learning content, and automatically incorporate quizzes and problem-solving scenarios to support the user's learning.

[0450] Finally, the server stores the generated manga-style learning materials in a database and generates a download link. A NoSQL database such as MongoDB is used for this storage. The device displays the download link through a user interface, and users can click the link to download the manga and proceed with their learning at their own pace.

[0451] As a specific example of use, consider the case where a user wants to study the "Differential Calculus" chapter in mathematics. The user uploads the relevant page of a PDF textbook to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download it and continue learning while having fun.

[0452] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[0453] Prompt Sentence Examples

[0454] I want to learn the differential calculus chapter from my textbook in manga format. Upload the file and generate it in a "pop art style."

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1:

[0457] The user prepares a PDF file of the learning material they want to study and accesses the system's upload screen. The terminal displays a file selection button and an upload button on the user interface. The user clicks the file selection button to select the file to upload. They then click the upload button to send the file to the server. The input is a PDF file, and the output is a PDF file saved on the server. Specifically, the file is uploaded to the server via the browser.

[0458] Step 2:

[0459] The server receives the uploaded PDF file and verifies that the file format is appropriate. Then, it uses a PDF parsing library (e.g., PyMuPDF) to convert the PDF to text data. The input is the PDF file, and the output is text data (JSON format). Specifically, it extracts the text from the PDF and formats it in JSON format.

[0460] Step 3:

[0461] The device displays multiple visual style options through a user interface. The user selects their preferred drawing style from the displayed list of options. The user's input is the selected drawing style, and the output is the corresponding information. Specific operations include selecting a style through a UI component such as a drop-down menu, and sending the selection information to the server.

[0462] Step 4:

[0463] The server receives the selected drawing style information and applies it as a parameter for the generative AI model. The input is the style selection information, and the output is the updated parameters for the generative AI model. Specifically, the server updates the setting parameters of the AI ​​model based on the style information.

[0464] Step 5:

[0465] The server inputs the prepared text data and drawing style information into a generative AI model to generate illustrated teaching materials corresponding to the learning content. The input is text data and drawing style information, and the output is the generated illustrated teaching materials. Specifically, it uses a generative AI model (e.g., GPT-4, VQ-VAE-2) to generate manga pages, and then places the scenario and illustrations on those manga pages.

[0466] Step 6:

[0467] The server stores the generated illustrated teaching materials in a database and generates a download link. The input is the generated illustrated teaching materials, and the output is a download link. Specifically, the generated teaching materials are stored in a NoSQL database (e.g., MongoDB) and an access link is generated.

[0468] Step 7:

[0469] The device displays this download link on the user interface. The user clicks the link to download the generated manga. The input is the download link, and the output is a manga file saved on the user's local device. Specifically, the link is clicked via a browser, and the file is downloaded to the user's device.

[0470] (Application example 1)

[0471] 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."

[0472] Traditional learning content is visually unattractive, and the text content can be boring and difficult to understand, especially when learning about cooking and food delivery. Furthermore, it is difficult to understand the cooking process in detail and recreate it at home. Therefore, a method to efficiently progress learning while attracting learners' interest is needed.

[0473] 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.

[0474] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from a plurality of drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for providing the generated manga-style teaching materials to the learner, means for converting menus and recipes uploaded by the learner into text data, and means for generating a manga-style food guide using a generative AI model based on the text data and the selected drawing style, thereby enabling learners to learn, analyze, and reproduce cooking processes in an enjoyable and visual way.

[0475] "Learner" means a user who uses the system to upload learning content and advance their own learning.

[0476] "Learning content" refers to the learning materials and information that learners upload to the system, including textbook chapters, recipes, etc.

[0477] "Text data" refers to character information extracted by analyzing the received learning content.

[0478] "Art style" refers to the visual expression method used when generating teaching materials in manga format, and refers to the design and art style that learners can choose from.

[0479] A "generative AI model" is a machine learning model used to generate manga-style teaching materials based on text data and drawing style information.

[0480] "Manga-style teaching materials" refers to visual teaching materials in manga format generated by a generative AI model to make it easier for learners to understand the learning content.

[0481] A "menu" is a document or piece of information that lists dishes or foods, and is often provided with food delivery.

[0482] A "recipe" is information that lists the steps and ingredients for making a particular dish.

[0483] A "food guide" is a teaching material that provides information about cooking and food in manga format.

[0484] "Server" refers to the computer and its software that serves as the core of this system and performs various processes.

[0485] To specifically implement the present invention, it is necessary to build a system that performs the following processes. The specific system configuration and processing procedures are shown below.

[0486] System configuration

[0487] This system consists of the following elements:

[0488] 1. Server: The central processing unit that analyzes uploaded data, runs generative AI models, and stores and serves generated content.

[0489] 2. Terminal: A device that provides a user interface and allows users to upload learning content, select a drawing style, and download the generated manga content.

[0490] 3. Generative AI model: A machine learning model for generating manga-style teaching materials based on text data and drawing style.

[0491] 4. Database: A storage device for storing the generated manga-style teaching materials.

[0492] Processing Details

[0493] Uploading and analyzing learning content

[0494] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as a PDF and accesses the upload screen to the system. The device provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0495] The server receives the uploaded file and verifies that it is in the correct format. Once verified, the server parses the PDF file, converts it to text data, and extracts the learning content. This conversion process uses a library such as PyPDF2 to extract the text data.

[0496] Selecting and applying a drawing style

[0497] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0498] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[0499] Automatic manga generation

[0500] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model and generates manga pages corresponding to the learned content. Here, machine learning models such as the transformers library and VisionEncoderDecoderModel are used.

[0501] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0502] Provision and use of manga

[0503] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0504] Specific examples

[0505] As a specific use case, suppose a user wants to learn about "Italian dinner set menus." The user uploads a PDF menu to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually depicts the cooking process of an Italian dinner, and the user can download it to continue learning in a fun way.

[0506] Prompt Sentence Examples

[0507] Convert the following text into a cartoon in pop art style:

[0508] "How to make pizza: 1. Knead the dough. 2. Add the toppings. 3. Bake in the oven. How to cook pasta: 1. Boil the pasta. 2. Add the sauce. 3. Add the cheese."

[0509] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0510] Step 1:

[0511] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as PDF and uploads it to the system. At this time, the device provides file selection and upload buttons via a user interface, and the user selects the file and clicks the "Upload" button. The PDF file containing the learning content is received as input, and the file is sent to the server as output.

[0512] Step 2:

[0513] The server receives the uploaded PDF file and verifies that the file is in the proper format. Once verified, the server parses the PDF file and converts it into text data. This process uses the PyPDF2 library to extract text information from each page of the PDF. It takes the received PDF file as input and generates text data as output.

[0514] Step 3:

[0515] After the text data is generated, the server saves it and displays a list of multiple drawing style options to the user via the terminal, where the user can select the drawing style that best suits their preference. As input, the text data and drawing style options are displayed, and as output, the user's selected drawing style information is sent to the server.

[0516] Step 4:

[0517] The server receives the selected drawing style information and sets it as a parameter in the generative AI model. It then inputs the prepared text data into the model and generates manga pages corresponding to the learning content. In this step, the transformers library and VisionEncoderDecoderModel are used to create manga-style content containing the generated illustrations and dialogue. Text data and drawing style information are used as input, and manga-style image data is obtained as output.

[0518] Step 5:

[0519] The server stores the generated manga-style teaching materials in a database and generates a download link to provide them to users via their devices. Users can click the link to download the generated manga and proceed with their studies at their own pace. Manga-style teaching material data is saved as input, and a download link is generated as output.

[0520] This allows users to enjoy visually learning about uploaded menus and recipes using the drawing style of their choice.

[0521] 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.

[0522] To specifically implement this invention, a system is constructed that combines the following elements.

[0523] Upload and convert learning content

[0524] First, the user prepares the learning materials they want to study in a digital format such as a PDF file and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0525] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[0526] Selecting and applying a drawing style

[0527] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0528] The server receives the selected drawing style information and stores it in a database, where it is set as a parameter for the generative AI model.

[0529] Incorporating an emotion engine

[0530] Furthermore, the server includes an emotion engine for recognizing the user's emotions in real time. This emotion engine analyzes data acquired from the device's camera and microphone and recognizes the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[0531] Based on the recognized emotions, the server adjusts the difficulty and tone of the generated manga-style learning material, providing a learning experience optimized for the user's emotional state.

[0532] Automatic manga generation

[0533] Based on the prepared text data, selected drawing style information, and the output of the emotion engine, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[0534] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0535] Provision and use of manga

[0536] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0537] Specific examples

[0538] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. After that, the user selects a "pop art style." The system then recognizes the user's emotional state from their facial expressions to ensure that they are concentrating. The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download this and continue their learning in an enjoyable way.

[0539] In this way, by combining the emotion engine, a personalized learning experience is provided that corresponds to the user's emotional state. This invention is a system that solves the problems of conventional learning materials and enables learners to study efficiently while having fun.

[0540] The processing flow will be explained below.

[0541] Step 1:

[0542] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[0543] Step 2:

[0544] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[0545] Step 3:

[0546] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[0547] Step 4:

[0548] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[0549] Step 5:

[0550] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[0551] Step 6:

[0552] Terminal: Sends information about the selected drawing style to the server.

[0553] Step 7:

[0554] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[0555] Step 8:

[0556] Device: A camera and microphone are used to capture facial expressions and voice data in order to recognize the user's emotions in real time.

[0557] Step 9:

[0558] Server: Using an emotion engine, analyzes the acquired facial expressions and voice data to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[0559] Step 10:

[0560] Server: Adjusts the difficulty and tone of the generated manga-style educational material based on the perceived emotional state. For example, if the user is bored, it will add more engaging elements.

[0561] Step 11:

[0562] Server: Inputs the formatted text data, selected drawing style information, and emotional state data into the generative AI model. The generative AI model is executed to generate each page of the manga based on the text data.

[0563] Step 12:

[0564] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[0565] Step 13:

[0566] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[0567] Step 14:

[0568] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[0569] Step 15:

[0570] Terminal: Displays the generated manga download link to the user through the user interface.

[0571] Step 16:

[0572] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[0573] In this way, the entire system works together at each step to provide the user with the content they want to learn in manga format.The introduction of an emotion engine provides a personalized learning experience that matches the user's emotional state.

[0574] Example 2

[0575] 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."

[0576] Traditional learning systems have limited means of converting text data into a visually digestible format, making it difficult to maintain learner interest. They also lack the ability to dynamically adapt learning content to the learner's emotional state, resulting in a lack of personalized learning experiences. Furthermore, they struggle to provide consistent learning materials, including quizzes and problem-solving scenarios.

[0577] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from multiple drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for analyzing data acquired from the terminal to recognize the learner's emotions, means for adjusting the generated teaching materials based on the results of emotion recognition, and means for providing the generated manga-style teaching materials to the learner. This not only enables learners to study effectively while remaining interested, but also provides a personalized learning experience.

[0578] "Learner" refers to a person who accesses the system, uploads learning content, and uses the generated learning materials.

[0579] "Upload" refers to the process by which a learner sends learning content to the system.

[0580] "Learning content" refers to the teaching materials and resources prepared by learners to use the system.

[0581] "Means of receiving" refers to the function of the system to receive data uploaded by learners.

[0582] "Text data" refers to textual information extracted from PDFs and other formats.

[0583] "Means for conversion" refers to the function of analyzing the received learning content and converting it into text data.

[0584] "Artistic style" refers to the visual form of expression chosen by the learner.

[0585] "Drawing style information" refers to data about the drawing style selected by the learner.

[0586] A "generative AI model" refers to an artificial intelligence algorithm that takes text data and drawing style information as input and generates visual teaching materials.

[0587] "Manga-style teaching materials" refers to visual learning materials created by generative AI models.

[0588] "Means for providing" refers to the function for making the generated teaching materials available to learners.

[0589] "Means for recognizing emotions" refers to the function of analyzing data obtained from the device and determining the learner's emotions.

[0590] "Adjustment means" refers to the ability to change the content and format of the generated teaching materials based on the results of emotion recognition.

[0591] This invention is a system for providing learners with a personalized visual learning experience. Specifically, it receives learning content uploaded by users, converts it into text data, and automatically generates manga-style learning materials using a generative AI model based on the selected drawing style. It also recognizes learners' emotions in real time and adjusts the learning materials based on the results to maximize learning effectiveness.

[0592] Hardware and software used

[0593] server

[0594] Hardware: A server with a powerful processor, sufficient memory, and storage, such as an Intel Xeon or AMD Ryzen processor.

[0595] software:

[0596] OCR software: Tesseract

[0597] Generative AI models: GPT-4, Stable Diffusion

[0598] Sentiment analysis engine: Affectiva SDK

[0599] Terminal

[0600] Hardware: A PC or smart device with a camera and microphone, such as a desktop PC with a webcam, a laptop, or a tablet device.

[0601] software:

[0602] Browser: Major browsers such as Chrome, Firefox, and Safari

[0603] User Interface: HTML, CSS, and JavaScript interface

[0604] User

[0605] Hardware: Devices listed above

[0606] Software: Uses specific applications and web browsers

[0607] Data processing and calculation

[0608] A user prepares learning materials in PDF file format and accesses the system's upload screen. For example, they use any browser to access a specific URL (e.g., https: / / manga-learning-system.com), click the "Choose File" button in the user interface, select the PDF file (e.g., mathematics_differentiation.pdf), and click the upload button.

[0609] The device sends files uploaded through the user interface to the server, which then verifies the received files and converts them into text using OCR software (Tesseract), which then formats the text for input into the generative AI model and stores it in a database.

[0610] The user then selects the manga drawing style. Multiple visual styles (e.g., simple, pop, realistic) are provided for selection, and the user chooses the style that best suits their preferences. The selected style information is sent to the server via the terminal. The server receives this information and stores it in a database.

[0611] The server uses the device's camera and microphone to recognize the user's emotions in real time. The acquired data is analyzed using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). Based on the recognized emotional state, the content and tone of the generated learning material are adjusted.

[0612] The server inputs the prepared text data, the selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, it sends a prompt to the generative AI model: "Text data: text explaining differentiation, drawing style: pop, emotional state: concentration." The generative AI model then automatically generates manga-style teaching materials based on this information and stores them in a database.

[0613] The server generates a download link for providing the created manga-style learning material and displays it through the user interface. The user can click the displayed link to download the learning material and proceed with the learning at their own pace.

[0614] Examples of specific examples and prompts

[0615] For example, if a user wants to learn "differential calculus," they upload the relevant page from a PDF textbook to the system. They then select a "pop art style." The system checks the user's facial expression to see if they are concentrating and extracts text data. Based on the selected style, a generative AI model (e.g., GPT-4) is used to generate a manga. The generated manga visually illustrates the basic concepts of differentiation and examples of calculations. Users can download it and continue their learning in an enjoyable way.

[0616] Example prompt sentence:

[0617] "Text Data: Basic Concepts of Differentiation and Examples"

[0618] "Drawing style: Pop"

[0619] "Emotional state: Focused"

[0620] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0621] Step 1:

[0622] The user prepares the learning material they want to study in PDF file format and accesses the system's upload screen. The device displays a screen with a file selection and upload button. The user clicks the "Choose File" button, selects the PDF file (e.g., mathematics_differentiation.pdf), and clicks the "Upload" button. This starts the upload operation, with the PDF file serving as input.

[0623] Step 2:

[0624] The terminal sends the file uploaded through the user interface to the server. The server checks the received file and verifies whether the file is in PDF format. If the file is in PDF format, the server analyzes the PDF file and converts it into text data. The input here is the PDF file, and the output is text data. The server uses OCR software (Tesseract) to extract the text information from the PDF and stores this text data in a database.

[0625] Step 3:

[0626] The user accesses an option list to select a manga drawing style. The terminal displays multiple drawing style options (e.g., simple, pop, realistic) on the user interface. The user selects the drawing style that suits their preference and sends the information to the server. The input here is the selected drawing style information, and the output is the drawing style information saved on the server side.

[0627] Step 4:

[0628] The server uses the device's camera and microphone to recognize the user's emotions in real time. The device collects the user's facial expression and voice data and sends it to the server. The server then analyzes this data using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). The input here is the data obtained from the camera and microphone, and the output is the user's emotional state information.

[0629] Step 5:

[0630] The server inputs prepared text data, selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, by sending a prompt such as "Text data: text explaining differentiation, drawing style: pop, emotional state: focused" to the generative AI model, a manga-style teaching material is generated. The inputs are the text data, drawing style information, and emotional state information, which form the prompt sentence, and the output is the generated manga page.

[0631] Step 6:

[0632] The generated manga-style teaching materials are stored in a database by the server. The server then generates a download link to provide to the user. The device displays this download link on its user interface. The user can click the displayed link to download the teaching materials and proceed with their learning at their own pace. The input here is the generated manga teaching materials, and the output is the generation and display of a download link.

[0633] (Application example 2)

[0634] 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."

[0635] Traditional learning methods have the drawback of making it difficult to maintain learners' concentration and interest, making it difficult to achieve efficient learning. Furthermore, it has been difficult to provide learning materials that respond to the emotions and state of each individual learner, making it impossible to provide a personalized learning experience. This has led to problems such as reduced learning effectiveness, especially in online and remote learning.

[0636] 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.

[0637] In this invention, the server includes: means for receiving learning content uploaded by a learner; means for converting the received learning content into text data; means for receiving information on a drawing style selected by the learner from multiple drawing styles; means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information; means for providing the generated manga-style teaching materials to the learner; emotion analysis means for analyzing the learner's emotions in real time; means for adjusting the difficulty and tone of the generated manga-style teaching materials based on the emotional state analyzed by the emotion analysis means; and means for displaying the generated manga-style teaching materials on a visual device. This enables a personalized learning experience tailored to the learner's emotional state. Furthermore, by maintaining the learner's interest and concentration, efficient learning can be achieved.

[0638] A "learner" is a person who is learning specific knowledge or skills.

[0639] "Uploading" is the act of sending or transferring data to an external device or server.

[0640] "Learning content" refers to the information and materials that a learner is trying to acquire.

[0641] "Receiving" is the act of taking in information or data sent from another source.

[0642] "Text data" refers to information expressed as characters or sentences.

[0643] "Art style" refers to the drawing method and design characteristics of visual content.

[0644] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate a specific result.

[0645] "Manga-style teaching materials" refers to educational content drawn in manga format.

[0646] "Emotion analysis" is the process of analyzing a user's emotions and sensory state through data.

[0647] "Visual device" refers to equipment or devices that allow a user to receive information visually.

[0648] "Adjustment" is the act of changing to an optimal state depending on specific conditions or situations.

[0649] This invention provides a system that visualizes the learning materials uploaded by learners, enabling more effective and interesting learning.

[0650] System configuration

[0651] Hardware

[0652] The system uses the following hardware:

[0653] Smart glasses (used as a visual device)

[0654] Smartphone (used for uploading teaching materials and as a user interface)

[0655] Servers (used for data processing and running AI models)

[0656] software

[0657] The system uses the following software:

[0658] cv2 (OpenCV toolkit): Used to analyze the user's face image

[0659] pytesseract: Used to extract text from PDF

[0660] pdf2image: Convert PDF files to images

[0661] tensorflow: Used to run generative AI models

[0662] transformers (Hugging Face Transformers): used for sentiment analysis and text generation

[0663] Processing flow

[0664] 1. Uploading study materials

[0665] Users upload PDF-format learning materials to the system using their smartphones. The server receives the uploaded files and proceeds to the next step.

[0666] 2. Text data conversion

[0667] The server converts PDF files to images using pdf2image, then extracts text data from these images using pytesseract.

[0668] 3. Choose your drawing style

[0669] Users can select their preferred drawing style from multiple options, and the selected style information is sent to the server and used as parameters for the generative AI model.

[0670] 4. Emotion analysis

[0671] Using the camera and microphone of the smart glasses, the system analyzes the user's emotions in real time using the CV2 and Transformers libraries. The analyzed emotional information is used to adjust the generated manga teaching materials.

[0672] 5. Manga Generation

[0673] The server automatically generates manga-style teaching materials using a generative AI model based on the extracted text data and the results of user sentiment analysis.

[0674] 6. Display of Manga

[0675] The generated manga-style learning materials are displayed on smart glasses, allowing users to study the visualized learning materials in real time.

[0676] Specific examples

[0677] Consider a case where a user who wants to learn differential calculus uploads the relevant page from a PDF textbook. The user selects the "pop art style" and begins learning through smart glasses. The system then analyzes the user's facial expression to determine their level of concentration, and uses a generative AI model to generate visually easy-to-understand manga content.

[0678] Specific examples of prompts are as follows:

[0679] Generate a fun manga based on the following text: The derivative of a function measures how the function value changes as its input changes. For example, the derivative of y = x^2 is 2x.

[0680] This system provides learners with a personalized learning experience that is tailored to their emotional state, making learning more effective and engaging.

[0681] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0682] Step 1:

[0683] Uploading teaching materials

[0684] Input: Learning materials in PDF format uploaded by users from their smartphones.

[0685] Process: Select a PDF file through the terminal's user interface and send it to the server.

[0686] Data processing / calculation: Upload the PDF file to the server using an HTTP request.

[0687] Output: The server receives the PDF file and prepares it for the next step.

[0688] Step 2:

[0689] Text data conversion

[0690] Input: A PDF file uploaded to the server.

[0691] Processing: The server converts the PDF file to an image file using the pdf2image library, then extracts the text data from the image using pytesseract.

[0692] Data processing / calculation: By performing OCR (optical character recognition), text information is obtained from the images of each page.

[0693] Output: The retrieved text data.

[0694] Step 3:

[0695] Selecting a drawing style

[0696] Input: User selected drawing style information.

[0697] Processing: The user selects the preferred drawing style from multiple drawing style options and sends that information to the server.

[0698] Data processing / calculation: Sends style information selected through the user interface to the server.

[0699] Output: The server receives the drawing style information and stores it as parameters to be applied to the generative AI model.

[0700] Step 4:

[0701] Emotion analysis

[0702] Input: User's facial image and voice data captured by the smart glasses' camera and microphone.

[0703] Processing: The server uses cv2 and transformers libraries to analyze the user's emotional state in real time.

[0704] Data processing / calculation: Recognize emotions from facial expressions using image analysis algorithms and generate emotional data based on that.

[0705] Output: User's emotional state data (e.g., happy, sad, excited, bored, etc.).

[0706] Step 5:

[0707] Manga Generation

[0708] Input: Text data, drawing style information, and user emotional state data.

[0709] Processing: The server inputs these input data into a generative AI model to automatically generate manga-style teaching materials.

[0710] Data processing / computation: Generate stories using text generation algorithms and synthesize appropriate visuals based on drawing style and emotional state.

[0711] Output: Generated manga-style teaching materials.

[0712] Step 6:

[0713] Manga display

[0714] Input: Generated manga-style teaching materials.

[0715] Processing: The server sends the generated manga to the smart glasses and displays it for the user to learn visually in real time.

[0716] Data processing / calculation: Manga data is sent to the smart glasses using a data transfer protocol.

[0717] Output: Manga-style educational material displayed on smart glasses.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] [Third embodiment]

[0722] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0723] 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.

[0724] 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).

[0725] 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.

[0726] 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.

[0727] 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).

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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."

[0734] To specifically put the present invention into practice, a system that performs the following processes is constructed.

[0735] Upload and convert learning content

[0736] First, the user prepares the study material they want to study (for example, a chapter from a textbook or a section from a technical book) in a digital format such as a PDF file, and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0737] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[0738] Selecting and applying a drawing style

[0739] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0740] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[0741] Automatic manga generation

[0742] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[0743] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0744] Provision and use of manga

[0745] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0746] Specific examples

[0747] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. Then, they select a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download the manga and continue their learning in an enjoyable way.

[0748] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[0752] Step 2:

[0753] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[0754] Step 3:

[0755] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[0756] Step 4:

[0757] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[0758] Step 5:

[0759] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[0760] Step 6:

[0761] Terminal: Sends information about the selected drawing style to the server.

[0762] Step 7:

[0763] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[0764] Step 8:

[0765] Server: Inputs the formatted text data and the selected drawing style information into the generative AI model. The generative AI model is executed and generates each page of the manga based on the text data.

[0766] Step 9:

[0767] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[0768] Step 10:

[0769] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[0770] Step 11:

[0771] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[0772] Step 12:

[0773] Terminal: Displays the generated manga download link to the user through the user interface.

[0774] Step 13:

[0775] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[0776] In this way, at each step, the entire system works together to provide the user with the content they want to learn in manga format.

[0777] Example 1

[0778] 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."

[0779] Conventional learning materials are mainly text and static diagrams, and it often takes a long time for learners to understand the content. Furthermore, they lack visual aids to make learning fun for learners, making it difficult to maintain motivation. To address these issues, there is a need for a more efficient way to provide learning materials that are more visually appealing and easier to understand.

[0780] 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.

[0781] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a style selected by the learner from a plurality of visual styles, means for generating learning materials with illustrations using a generative AI model based on the text data and the style information, and means for providing the generated learning materials with illustrations to the learner, thereby enabling the learner to efficiently understand the learning content while having fun.

[0782] "Learner" refers to an individual or group who uses the system to carry out learning activities.

[0783] "Upload" refers to the act of a user sending a file from their own device to a server.

[0784] "Learning content" refers to the teaching materials and documents that learners upload to the system, including digital data such as text and PDF format.

[0785] "Means for receiving" refers to the function that allows the server to obtain uploaded files and information.

[0786] "Text Data" refers to textual information extracted from PDFs and other digital formats.

[0787] "Means for conversion" refers to the function for converting received learning content into text data.

[0788] "Visual styles" refers to various visual designs and formats for presenting learning content, such as manga and picture books.

[0789] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates visual teaching materials such as manga and illustrations based on learning content.

[0790] "Means of providing" refers to the function of making the generated illustrated teaching materials available to learners in the form of downloading or viewing.

[0791] "Illustrated teaching materials" are teaching materials that visually represent the learning content, and include materials in manga format and illustrations.

[0792] "Parameters" refer to settings or conditions that affect the behavior of a generative AI model.

[0793] In order to implement the present invention, the system must be configured as follows.

[0794] First, the user prepares the learning materials they want to study as digital data, such as PDF format. The user accesses the system's upload screen and uses the upload button to send the learning materials to the server. The terminal provides a file selection and upload button through the user interface, allowing the user to send the selected file to the server.

[0795] The server then checks the received PDF file, verifies that it is in the correct format, and converts it to text data using a PDF parsing library such as the PyMuPDF library. The parsed text data is then converted to JSON format for subsequent processing.

[0796] After the upload process is complete, the user has access to a list of options for selecting a drawing style. The system displays multiple visual style options through the terminal. The user selects the style that best suits their preferences and sends the selection to the server. The server applies the received style information as parameters for the generative AI model. This step ensures that the generated manga is drawn in the style selected by the user.

[0797] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate illustrated learning materials corresponding to the learning content. Specifically, it generates manga pages using generative AI models such as GPT-4 and VQ-VAE-2. The generated manga pages include scenarios and illustrations related to the learning content, and automatically incorporate quizzes and problem-solving scenarios to support the user's learning.

[0798] Finally, the server stores the generated manga-style learning materials in a database and generates a download link. A NoSQL database such as MongoDB is used for this storage. The device displays the download link through a user interface, and users can click the link to download the manga and proceed with their learning at their own pace.

[0799] As a specific example of use, consider the case where a user wants to study the "Differential Calculus" chapter in mathematics. The user uploads the relevant page of a PDF textbook to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download it and continue learning while having fun.

[0800] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[0801] Prompt Sentence Examples

[0802] I want to learn the differential calculus chapter from my textbook in manga format. Upload the file and generate it in a "pop art style."

[0803] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0804] Step 1:

[0805] The user prepares a PDF file of the learning material they want to study and accesses the system's upload screen. The terminal displays a file selection button and an upload button on the user interface. The user clicks the file selection button to select the file to upload. They then click the upload button to send the file to the server. The input is a PDF file, and the output is a PDF file saved on the server. Specifically, the file is uploaded to the server via the browser.

[0806] Step 2:

[0807] The server receives the uploaded PDF file and verifies that the file format is appropriate. Then, it uses a PDF parsing library (e.g., PyMuPDF) to convert the PDF to text data. The input is the PDF file, and the output is text data (JSON format). Specifically, it extracts the text from the PDF and formats it in JSON format.

[0808] Step 3:

[0809] The device displays multiple visual style options through a user interface. The user selects their preferred drawing style from the displayed list of options. The user's input is the selected drawing style, and the output is the corresponding information. Specific operations include selecting a style through a UI component such as a drop-down menu, and sending the selection information to the server.

[0810] Step 4:

[0811] The server receives the selected drawing style information and applies it as a parameter for the generative AI model. The input is the style selection information, and the output is the updated parameters for the generative AI model. Specifically, the server updates the setting parameters of the AI ​​model based on the style information.

[0812] Step 5:

[0813] The server inputs the prepared text data and drawing style information into a generative AI model to generate illustrated teaching materials corresponding to the learning content. The input is text data and drawing style information, and the output is the generated illustrated teaching materials. Specifically, it uses a generative AI model (e.g., GPT-4, VQ-VAE-2) to generate manga pages, and then places the scenario and illustrations on those manga pages.

[0814] Step 6:

[0815] The server stores the generated illustrated teaching materials in a database and generates a download link. The input is the generated illustrated teaching materials, and the output is a download link. Specifically, the generated teaching materials are stored in a NoSQL database (e.g., MongoDB) and an access link is generated.

[0816] Step 7:

[0817] The device displays this download link on the user interface. The user clicks the link to download the generated manga. The input is the download link, and the output is a manga file saved on the user's local device. Specifically, the link is clicked via a browser, and the file is downloaded to the user's device.

[0818] (Application example 1)

[0819] 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."

[0820] Traditional learning content is visually unattractive, and the text content can be boring and difficult to understand, especially when learning about cooking and food delivery. Furthermore, it is difficult to understand the cooking process in detail and recreate it at home. Therefore, a method to efficiently progress learning while attracting learners' interest is needed.

[0821] 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.

[0822] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from a plurality of drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for providing the generated manga-style teaching materials to the learner, means for converting menus and recipes uploaded by the learner into text data, and means for generating a manga-style food guide using a generative AI model based on the text data and the selected drawing style, thereby enabling learners to learn, analyze, and reproduce cooking processes in an enjoyable and visual way.

[0823] "Learner" means a user who uses the system to upload learning content and advance their own learning.

[0824] "Learning content" refers to the learning materials and information that learners upload to the system, including textbook chapters, recipes, etc.

[0825] "Text data" refers to character information extracted by analyzing the received learning content.

[0826] "Art style" refers to the visual expression method used when generating teaching materials in manga format, and refers to the design and art style that learners can choose from.

[0827] A "generative AI model" is a machine learning model used to generate manga-style teaching materials based on text data and drawing style information.

[0828] "Manga-style teaching materials" refers to visual teaching materials in manga format generated by a generative AI model to make it easier for learners to understand the learning content.

[0829] A "menu" is a document or piece of information that lists dishes or foods, and is often provided with food delivery.

[0830] A "recipe" is information that lists the steps and ingredients for making a particular dish.

[0831] A "food guide" is a teaching material that provides information about cooking and food in manga format.

[0832] "Server" refers to the computer and its software that serves as the core of this system and performs various processes.

[0833] To specifically implement the present invention, it is necessary to build a system that performs the following processes. The specific system configuration and processing procedures are shown below.

[0834] System configuration

[0835] This system consists of the following elements:

[0836] 1. Server: The central processing unit that analyzes uploaded data, runs generative AI models, and stores and serves generated content.

[0837] 2. Terminal: A device that provides a user interface and allows users to upload learning content, select a drawing style, and download the generated manga content.

[0838] 3. Generative AI model: A machine learning model for generating manga-style teaching materials based on text data and drawing style.

[0839] 4. Database: A storage device for storing the generated manga-style teaching materials.

[0840] Processing Details

[0841] Uploading and analyzing learning content

[0842] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as a PDF and accesses the upload screen to the system. The device provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0843] The server receives the uploaded file and verifies that it is in the correct format. Once verified, the server parses the PDF file, converts it to text data, and extracts the learning content. This conversion process uses a library such as PyPDF2 to extract the text data.

[0844] Selecting and applying a drawing style

[0845] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0846] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[0847] Automatic manga generation

[0848] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model and generates manga pages corresponding to the learned content. Here, machine learning models such as the transformers library and VisionEncoderDecoderModel are used.

[0849] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0850] Provision and use of manga

[0851] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0852] Specific examples

[0853] As a specific use case, suppose a user wants to learn about "Italian dinner set menus." The user uploads a PDF menu to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually depicts the cooking process of an Italian dinner, and the user can download it to continue learning in a fun way.

[0854] Prompt Sentence Examples

[0855] Convert the following text into a cartoon in pop art style:

[0856] "How to make pizza: 1. Knead the dough. 2. Add the toppings. 3. Bake in the oven. How to cook pasta: 1. Boil the pasta. 2. Add the sauce. 3. Add the cheese."

[0857] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0858] Step 1:

[0859] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as PDF and uploads it to the system. At this time, the device provides file selection and upload buttons via a user interface, and the user selects the file and clicks the "Upload" button. The PDF file containing the learning content is received as input, and the file is sent to the server as output.

[0860] Step 2:

[0861] The server receives the uploaded PDF file and verifies that the file is in the proper format. Once verified, the server parses the PDF file and converts it into text data. This process uses the PyPDF2 library to extract text information from each page of the PDF. It takes the received PDF file as input and generates text data as output.

[0862] Step 3:

[0863] After the text data is generated, the server saves it and displays a list of multiple drawing style options to the user via the terminal, where the user can select the drawing style that best suits their preference. As input, the text data and drawing style options are displayed, and as output, the user's selected drawing style information is sent to the server.

[0864] Step 4:

[0865] The server receives the selected drawing style information and sets it as a parameter in the generative AI model. It then inputs the prepared text data into the model and generates manga pages corresponding to the learning content. In this step, the transformers library and VisionEncoderDecoderModel are used to create manga-style content containing the generated illustrations and dialogue. Text data and drawing style information are used as input, and manga-style image data is obtained as output.

[0866] Step 5:

[0867] The server stores the generated manga-style teaching materials in a database and generates a download link to provide them to users via their devices. Users can click the link to download the generated manga and proceed with their studies at their own pace. Manga-style teaching material data is saved as input, and a download link is generated as output.

[0868] This allows users to enjoy visually learning about uploaded menus and recipes using the drawing style of their choice.

[0869] 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.

[0870] To specifically implement this invention, a system is constructed that combines the following elements.

[0871] Upload and convert learning content

[0872] First, the user prepares the learning materials they want to study in a digital format such as a PDF file and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[0873] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[0874] Selecting and applying a drawing style

[0875] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[0876] The server receives the selected drawing style information and stores it in a database, where it is set as a parameter for the generative AI model.

[0877] Incorporating an emotion engine

[0878] Furthermore, the server includes an emotion engine for recognizing the user's emotions in real time. This emotion engine analyzes data acquired from the device's camera and microphone and recognizes the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[0879] Based on the recognized emotions, the server adjusts the difficulty and tone of the generated manga-style learning material, providing a learning experience optimized for the user's emotional state.

[0880] Automatic manga generation

[0881] Based on the prepared text data, selected drawing style information, and the output of the emotion engine, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[0882] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[0883] Provision and use of manga

[0884] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[0885] Specific examples

[0886] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. After that, the user selects a "pop art style." The system then recognizes the user's emotional state from their facial expressions to ensure that they are concentrating. The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download this and continue their learning in an enjoyable way.

[0887] In this way, by combining the emotion engine, a personalized learning experience is provided that corresponds to the user's emotional state. This invention is a system that solves the problems of conventional learning materials and enables learners to study efficiently while having fun.

[0888] The processing flow will be explained below.

[0889] Step 1:

[0890] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[0891] Step 2:

[0892] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[0893] Step 3:

[0894] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[0895] Step 4:

[0896] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[0897] Step 5:

[0898] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[0899] Step 6:

[0900] Terminal: Sends information about the selected drawing style to the server.

[0901] Step 7:

[0902] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[0903] Step 8:

[0904] Device: A camera and microphone are used to capture facial expressions and voice data in order to recognize the user's emotions in real time.

[0905] Step 9:

[0906] Server: Using an emotion engine, analyzes the acquired facial expressions and voice data to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[0907] Step 10:

[0908] Server: Adjusts the difficulty and tone of the generated manga-style educational material based on the perceived emotional state. For example, if the user is bored, it will add more engaging elements.

[0909] Step 11:

[0910] Server: Inputs the formatted text data, selected drawing style information, and emotional state data into the generative AI model. The generative AI model is executed to generate each page of the manga based on the text data.

[0911] Step 12:

[0912] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[0913] Step 13:

[0914] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[0915] Step 14:

[0916] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[0917] Step 15:

[0918] Terminal: Displays the generated manga download link to the user through the user interface.

[0919] Step 16:

[0920] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[0921] In this way, the entire system works together at each step to provide the user with the content they want to learn in manga format.The introduction of an emotion engine provides a personalized learning experience that matches the user's emotional state.

[0922] Example 2

[0923] 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."

[0924] Traditional learning systems have limited means of converting text data into a visually digestible format, making it difficult to maintain learner interest. They also lack the ability to dynamically adapt learning content to the learner's emotional state, resulting in a lack of personalized learning experiences. Furthermore, they struggle to provide consistent learning materials, including quizzes and problem-solving scenarios.

[0925] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from multiple drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for analyzing data acquired from the terminal to recognize the learner's emotions, means for adjusting the generated teaching materials based on the results of emotion recognition, and means for providing the generated manga-style teaching materials to the learner. This not only enables learners to study effectively while remaining interested, but also provides a personalized learning experience.

[0926] "Learner" refers to a person who accesses the system, uploads learning content, and uses the generated learning materials.

[0927] "Upload" refers to the process by which a learner sends learning content to the system.

[0928] "Learning content" refers to the teaching materials and resources prepared by learners to use the system.

[0929] "Means of receiving" refers to the function of the system to receive data uploaded by learners.

[0930] "Text data" refers to textual information extracted from PDFs and other formats.

[0931] "Means for conversion" refers to the function of analyzing the received learning content and converting it into text data.

[0932] "Artistic style" refers to the visual form of expression chosen by the learner.

[0933] "Drawing style information" refers to data about the drawing style selected by the learner.

[0934] A "generative AI model" refers to an artificial intelligence algorithm that takes text data and drawing style information as input and generates visual teaching materials.

[0935] "Manga-style teaching materials" refers to visual learning materials created by generative AI models.

[0936] "Means for providing" refers to the function for making the generated teaching materials available to learners.

[0937] "Means for recognizing emotions" refers to the function of analyzing data obtained from the device and determining the learner's emotions.

[0938] "Adjustment means" refers to the ability to change the content and format of the generated teaching materials based on the results of emotion recognition.

[0939] This invention is a system for providing learners with a personalized visual learning experience. Specifically, it receives learning content uploaded by users, converts it into text data, and automatically generates manga-style learning materials using a generative AI model based on the selected drawing style. It also recognizes learners' emotions in real time and adjusts the learning materials based on the results to maximize learning effectiveness.

[0940] Hardware and software used

[0941] server

[0942] Hardware: A server with a powerful processor, sufficient memory, and storage, such as an Intel Xeon or AMD Ryzen processor.

[0943] software:

[0944] OCR software: Tesseract

[0945] Generative AI models: GPT-4, Stable Diffusion

[0946] Sentiment analysis engine: Affectiva SDK

[0947] Terminal

[0948] Hardware: A PC or smart device with a camera and microphone, such as a desktop PC with a webcam, a laptop, or a tablet device.

[0949] software:

[0950] Browser: Major browsers such as Chrome, Firefox, and Safari

[0951] User Interface: HTML, CSS, and JavaScript interface

[0952] User

[0953] Hardware: Devices listed above

[0954] Software: Uses specific applications and web browsers

[0955] Data processing and calculation

[0956] A user prepares learning materials in PDF file format and accesses the system's upload screen. For example, they use any browser to access a specific URL (e.g., https: / / manga-learning-system.com), click the "Choose File" button in the user interface, select the PDF file (e.g., mathematics_differentiation.pdf), and click the upload button.

[0957] The device sends files uploaded through the user interface to the server, which then verifies the received files and converts them into text using OCR software (Tesseract), which then formats the text for input into the generative AI model and stores it in a database.

[0958] The user then selects the manga drawing style. Multiple visual styles (e.g., simple, pop, realistic) are provided for selection, and the user chooses the style that best suits their preferences. The selected style information is sent to the server via the terminal. The server receives this information and stores it in a database.

[0959] The server uses the device's camera and microphone to recognize the user's emotions in real time. The acquired data is analyzed using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). Based on the recognized emotional state, the content and tone of the generated learning material are adjusted.

[0960] The server inputs the prepared text data, the selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, it sends a prompt to the generative AI model: "Text data: text explaining differentiation, drawing style: pop, emotional state: concentration." The generative AI model then automatically generates manga-style teaching materials based on this information and stores them in a database.

[0961] The server generates a download link for providing the created manga-style learning material and displays it through the user interface. The user can click the displayed link to download the learning material and proceed with the learning at their own pace.

[0962] Examples of specific examples and prompts

[0963] For example, if a user wants to learn "differential calculus," they upload the relevant page from a PDF textbook to the system. They then select a "pop art style." The system checks the user's facial expression to see if they are concentrating and extracts text data. Based on the selected style, a generative AI model (e.g., GPT-4) is used to generate a manga. The generated manga visually illustrates the basic concepts of differentiation and examples of calculations. Users can download it and continue their learning in an enjoyable way.

[0964] Example prompt sentence:

[0965] "Text Data: Basic Concepts of Differentiation and Examples"

[0966] "Drawing style: Pop"

[0967] "Emotional state: Focused"

[0968] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0969] Step 1:

[0970] The user prepares the learning material they want to study in PDF file format and accesses the system's upload screen. The device displays a screen with a file selection and upload button. The user clicks the "Choose File" button, selects the PDF file (e.g., mathematics_differentiation.pdf), and clicks the "Upload" button. This starts the upload operation, with the PDF file serving as input.

[0971] Step 2:

[0972] The terminal sends the file uploaded through the user interface to the server. The server checks the received file and verifies whether the file is in PDF format. If the file is in PDF format, the server analyzes the PDF file and converts it into text data. The input here is the PDF file, and the output is text data. The server uses OCR software (Tesseract) to extract the text information from the PDF and stores this text data in a database.

[0973] Step 3:

[0974] The user accesses an option list to select a manga drawing style. The terminal displays multiple drawing style options (e.g., simple, pop, realistic) on the user interface. The user selects the drawing style that suits their preference and sends the information to the server. The input here is the selected drawing style information, and the output is the drawing style information saved on the server side.

[0975] Step 4:

[0976] The server uses the device's camera and microphone to recognize the user's emotions in real time. The device collects the user's facial expression and voice data and sends it to the server. The server then analyzes this data using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). The input here is the data obtained from the camera and microphone, and the output is the user's emotional state information.

[0977] Step 5:

[0978] The server inputs prepared text data, selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, by sending a prompt such as "Text data: text explaining differentiation, drawing style: pop, emotional state: focused" to the generative AI model, a manga-style teaching material is generated. The inputs are the text data, drawing style information, and emotional state information, which form the prompt sentence, and the output is the generated manga page.

[0979] Step 6:

[0980] The generated manga-style teaching materials are stored in a database by the server. The server then generates a download link to provide to the user. The device displays this download link on its user interface. The user can click the displayed link to download the teaching materials and proceed with their learning at their own pace. The input here is the generated manga teaching materials, and the output is the generation and display of a download link.

[0981] (Application example 2)

[0982] 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."

[0983] Traditional learning methods have the drawback of making it difficult to maintain learners' concentration and interest, making it difficult to achieve efficient learning. Furthermore, it has been difficult to provide learning materials that respond to the emotions and state of each individual learner, making it impossible to provide a personalized learning experience. This has led to problems such as reduced learning effectiveness, especially in online and remote learning.

[0984] 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.

[0985] In this invention, the server includes: means for receiving learning content uploaded by a learner; means for converting the received learning content into text data; means for receiving information on a drawing style selected by the learner from multiple drawing styles; means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information; means for providing the generated manga-style teaching materials to the learner; emotion analysis means for analyzing the learner's emotions in real time; means for adjusting the difficulty and tone of the generated manga-style teaching materials based on the emotional state analyzed by the emotion analysis means; and means for displaying the generated manga-style teaching materials on a visual device. This enables a personalized learning experience tailored to the learner's emotional state. Furthermore, by maintaining the learner's interest and concentration, efficient learning can be achieved.

[0986] A "learner" is a person who is learning specific knowledge or skills.

[0987] "Uploading" is the act of sending or transferring data to an external device or server.

[0988] "Learning content" refers to the information and materials that a learner is trying to acquire.

[0989] "Receiving" is the act of taking in information or data sent from another source.

[0990] "Text data" refers to information expressed as characters or sentences.

[0991] "Art style" refers to the drawing method and design characteristics of visual content.

[0992] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate a specific result.

[0993] "Manga-style teaching materials" refers to educational content drawn in manga format.

[0994] "Emotion analysis" is the process of analyzing a user's emotions and sensory state through data.

[0995] "Visual device" refers to equipment or devices that allow a user to receive information visually.

[0996] "Adjustment" is the act of changing to an optimal state depending on specific conditions or situations.

[0997] This invention provides a system that visualizes the learning materials uploaded by learners, enabling more effective and interesting learning.

[0998] System configuration

[0999] Hardware

[1000] The system uses the following hardware:

[1001] Smart glasses (used as a visual device)

[1002] Smartphone (used for uploading teaching materials and as a user interface)

[1003] Servers (used for data processing and running AI models)

[1004] software

[1005] The system uses the following software:

[1006] cv2 (OpenCV toolkit): Used to analyze the user's face image

[1007] pytesseract: Used to extract text from PDF

[1008] pdf2image: Convert PDF files to images

[1009] tensorflow: Used to run generative AI models

[1010] transformers (Hugging Face Transformers): used for sentiment analysis and text generation

[1011] Processing flow

[1012] 1. Uploading study materials

[1013] Users upload PDF-format learning materials to the system using their smartphones. The server receives the uploaded files and proceeds to the next step.

[1014] 2. Text data conversion

[1015] The server converts PDF files to images using pdf2image, then extracts text data from these images using pytesseract.

[1016] 3. Choose your drawing style

[1017] Users can select their preferred drawing style from multiple options, and the selected style information is sent to the server and used as parameters for the generative AI model.

[1018] 4. Emotion analysis

[1019] Using the camera and microphone of the smart glasses, the system analyzes the user's emotions in real time using the CV2 and Transformers libraries. The analyzed emotional information is used to adjust the generated manga teaching materials.

[1020] 5. Manga Generation

[1021] The server automatically generates manga-style teaching materials using a generative AI model based on the extracted text data and the results of user sentiment analysis.

[1022] 6. Display of Manga

[1023] The generated manga-style learning materials are displayed on smart glasses, allowing users to study the visualized learning materials in real time.

[1024] Specific examples

[1025] Consider a case where a user who wants to learn differential calculus uploads the relevant page from a PDF textbook. The user selects the "pop art style" and begins learning through smart glasses. The system then analyzes the user's facial expression to determine their level of concentration, and uses a generative AI model to generate visually easy-to-understand manga content.

[1026] Specific examples of prompts are as follows:

[1027] Generate a fun manga based on the following text: The derivative of a function measures how the function value changes as its input changes. For example, the derivative of y = x^2 is 2x.

[1028] This system provides learners with a personalized learning experience that is tailored to their emotional state, making learning more effective and engaging.

[1029] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1030] Step 1:

[1031] Uploading teaching materials

[1032] Input: Learning materials in PDF format uploaded by users from their smartphones.

[1033] Process: Select a PDF file through the terminal's user interface and send it to the server.

[1034] Data processing / calculation: Upload the PDF file to the server using an HTTP request.

[1035] Output: The server receives the PDF file and prepares it for the next step.

[1036] Step 2:

[1037] Text data conversion

[1038] Input: A PDF file uploaded to the server.

[1039] Processing: The server converts the PDF file to an image file using the pdf2image library, then extracts the text data from the image using pytesseract.

[1040] Data processing / calculation: By performing OCR (optical character recognition), text information is obtained from the images of each page.

[1041] Output: The retrieved text data.

[1042] Step 3:

[1043] Selecting a drawing style

[1044] Input: User selected drawing style information.

[1045] Processing: The user selects the preferred drawing style from multiple drawing style options and sends that information to the server.

[1046] Data processing / calculation: Sends style information selected through the user interface to the server.

[1047] Output: The server receives the drawing style information and stores it as parameters to be applied to the generative AI model.

[1048] Step 4:

[1049] Emotion analysis

[1050] Input: User's facial image and voice data captured by the smart glasses' camera and microphone.

[1051] Processing: The server uses cv2 and transformers libraries to analyze the user's emotional state in real time.

[1052] Data processing / calculation: Recognize emotions from facial expressions using image analysis algorithms and generate emotional data based on that.

[1053] Output: User's emotional state data (e.g., happy, sad, excited, bored, etc.).

[1054] Step 5:

[1055] Manga Generation

[1056] Input: Text data, drawing style information, and user emotional state data.

[1057] Processing: The server inputs these input data into a generative AI model to automatically generate manga-style teaching materials.

[1058] Data processing / computation: Generate stories using text generation algorithms and synthesize appropriate visuals based on drawing style and emotional state.

[1059] Output: Generated manga-style teaching materials.

[1060] Step 6:

[1061] Manga display

[1062] Input: Generated manga-style teaching materials.

[1063] Processing: The server sends the generated manga to the smart glasses and displays it for the user to learn visually in real time.

[1064] Data processing / calculation: Manga data is sent to the smart glasses using a data transfer protocol.

[1065] Output: Manga-style educational material displayed on smart glasses.

[1066] 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.

[1067] 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.

[1068] 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.

[1069] [Fourth embodiment]

[1070] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1071] 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.

[1072] 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).

[1073] 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.

[1074] 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.

[1075] 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).

[1076] 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.

[1077] 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.

[1078] 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.

[1079] 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.

[1080] 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.

[1081] 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.

[1082] 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."

[1083] To specifically put the present invention into practice, a system that performs the following processes is constructed.

[1084] Upload and convert learning content

[1085] First, the user prepares the study material they want to study (for example, a chapter from a textbook or a section from a technical book) in a digital format such as a PDF file, and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[1086] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[1087] Selecting and applying a drawing style

[1088] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[1089] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[1090] Automatic manga generation

[1091] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[1092] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[1093] Provision and use of manga

[1094] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[1095] Specific examples

[1096] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. Then, they select a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download the manga and continue their learning in an enjoyable way.

[1097] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[1098] The processing flow will be explained below.

[1099] Step 1:

[1100] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[1101] Step 2:

[1102] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[1103] Step 3:

[1104] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[1105] Step 4:

[1106] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[1107] Step 5:

[1108] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[1109] Step 6:

[1110] Terminal: Sends information about the selected drawing style to the server.

[1111] Step 7:

[1112] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[1113] Step 8:

[1114] Server: Inputs the formatted text data and the selected drawing style information into the generative AI model. The generative AI model is executed and generates each page of the manga based on the text data.

[1115] Step 9:

[1116] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[1117] Step 10:

[1118] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[1119] Step 11:

[1120] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[1121] Step 12:

[1122] Terminal: Displays the generated manga download link to the user through the user interface.

[1123] Step 13:

[1124] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[1125] In this way, at each step, the entire system works together to provide the user with the content they want to learn in manga format.

[1126] Example 1

[1127] 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."

[1128] Conventional learning materials are mainly text and static diagrams, and it often takes a long time for learners to understand the content. Furthermore, they lack visual aids to make learning fun for learners, making it difficult to maintain motivation. To address these issues, there is a need for a more efficient way to provide learning materials that are more visually appealing and easier to understand.

[1129] 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.

[1130] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a style selected by the learner from a plurality of visual styles, means for generating learning materials with illustrations using a generative AI model based on the text data and the style information, and means for providing the generated learning materials with illustrations to the learner, thereby enabling the learner to efficiently understand the learning content while having fun.

[1131] "Learner" refers to an individual or group who uses the system to carry out learning activities.

[1132] "Upload" refers to the act of a user sending a file from their own device to a server.

[1133] "Learning content" refers to the teaching materials and documents that learners upload to the system, including digital data such as text and PDF format.

[1134] "Means for receiving" refers to the function that allows the server to obtain uploaded files and information.

[1135] "Text Data" refers to textual information extracted from PDFs and other digital formats.

[1136] "Means for conversion" refers to the function for converting received learning content into text data.

[1137] "Visual styles" refers to various visual designs and formats for presenting learning content, such as manga and picture books.

[1138] A "generative AI model" refers to an artificial intelligence algorithm that automatically generates visual teaching materials such as manga and illustrations based on learning content.

[1139] "Means of providing" refers to the function of making the generated illustrated teaching materials available to learners in the form of downloading or viewing.

[1140] "Illustrated teaching materials" are teaching materials that visually represent the learning content, and include materials in manga format and illustrations.

[1141] "Parameters" refer to settings or conditions that affect the behavior of a generative AI model.

[1142] In order to implement the present invention, the system must be configured as follows.

[1143] First, the user prepares the learning materials they want to study as digital data, such as PDF format. The user accesses the system's upload screen and uses the upload button to send the learning materials to the server. The terminal provides a file selection and upload button through the user interface, allowing the user to send the selected file to the server.

[1144] The server then checks the received PDF file, verifies that it is in the correct format, and converts it to text data using a PDF parsing library such as the PyMuPDF library. The parsed text data is then converted to JSON format for subsequent processing.

[1145] After the upload process is complete, the user has access to a list of options for selecting a drawing style. The system displays multiple visual style options through the terminal. The user selects the style that best suits their preferences and sends the selection to the server. The server applies the received style information as parameters for the generative AI model. This step ensures that the generated manga is drawn in the style selected by the user.

[1146] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model to generate illustrated learning materials corresponding to the learning content. Specifically, it generates manga pages using generative AI models such as GPT-4 and VQ-VAE-2. The generated manga pages include scenarios and illustrations related to the learning content, and automatically incorporate quizzes and problem-solving scenarios to support the user's learning.

[1147] Finally, the server stores the generated manga-style learning materials in a database and generates a download link. A NoSQL database such as MongoDB is used for this storage. The device displays the download link through a user interface, and users can click the link to download the manga and proceed with their learning at their own pace.

[1148] As a specific example of use, consider the case where a user wants to study the "Differential Calculus" chapter in mathematics. The user uploads the relevant page of a PDF textbook to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download it and continue learning while having fun.

[1149] In this way, this invention is a system that solves the problems of conventional teaching materials and enables learners to study efficiently while having fun.

[1150] Prompt Sentence Examples

[1151] I want to learn the differential calculus chapter from my textbook in manga format. Upload the file and generate it in a "pop art style."

[1152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1153] Step 1:

[1154] The user prepares a PDF file of the learning material they want to study and accesses the system's upload screen. The terminal displays a file selection button and an upload button on the user interface. The user clicks the file selection button to select the file to upload. They then click the upload button to send the file to the server. The input is a PDF file, and the output is a PDF file saved on the server. Specifically, the file is uploaded to the server via the browser.

[1155] Step 2:

[1156] The server receives the uploaded PDF file and verifies that the file format is appropriate. Then, it uses a PDF parsing library (e.g., PyMuPDF) to convert the PDF to text data. The input is the PDF file, and the output is text data (JSON format). Specifically, it extracts the text from the PDF and formats it in JSON format.

[1157] Step 3:

[1158] The device displays multiple visual style options through a user interface. The user selects their preferred drawing style from the displayed list of options. The user's input is the selected drawing style, and the output is the corresponding information. Specific operations include selecting a style through a UI component such as a drop-down menu, and sending the selection information to the server.

[1159] Step 4:

[1160] The server receives the selected drawing style information and applies it as a parameter for the generative AI model. The input is the style selection information, and the output is the updated parameters for the generative AI model. Specifically, the server updates the setting parameters of the AI ​​model based on the style information.

[1161] Step 5:

[1162] The server inputs the prepared text data and drawing style information into a generative AI model to generate illustrated teaching materials corresponding to the learning content. The input is text data and drawing style information, and the output is the generated illustrated teaching materials. Specifically, it uses a generative AI model (e.g., GPT-4, VQ-VAE-2) to generate manga pages, and then places the scenario and illustrations on those manga pages.

[1163] Step 6:

[1164] The server stores the generated illustrated teaching materials in a database and generates a download link. The input is the generated illustrated teaching materials, and the output is a download link. Specifically, the generated teaching materials are stored in a NoSQL database (e.g., MongoDB) and an access link is generated.

[1165] Step 7:

[1166] The device displays this download link on the user interface. The user clicks the link to download the generated manga. The input is the download link, and the output is a manga file saved on the user's local device. Specifically, the link is clicked via a browser, and the file is downloaded to the user's device.

[1167] (Application example 1)

[1168] 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."

[1169] Traditional learning content is visually unattractive, and the text content can be boring and difficult to understand, especially when learning about cooking and food delivery. Furthermore, it is difficult to understand the cooking process in detail and recreate it at home. Therefore, a method to efficiently progress learning while attracting learners' interest is needed.

[1170] 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.

[1171] In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from a plurality of drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for providing the generated manga-style teaching materials to the learner, means for converting menus and recipes uploaded by the learner into text data, and means for generating a manga-style food guide using a generative AI model based on the text data and the selected drawing style, thereby enabling learners to learn, analyze, and reproduce cooking processes in an enjoyable and visual way.

[1172] "Learner" means a user who uses the system to upload learning content and advance their own learning.

[1173] "Learning content" refers to the learning materials and information that learners upload to the system, including textbook chapters, recipes, etc.

[1174] "Text data" refers to character information extracted by analyzing the received learning content.

[1175] "Art style" refers to the visual expression method used when generating teaching materials in manga format, and refers to the design and art style that learners can choose from.

[1176] A "generative AI model" is a machine learning model used to generate manga-style teaching materials based on text data and drawing style information.

[1177] "Manga-style teaching materials" refers to visual teaching materials in manga format generated by a generative AI model to make it easier for learners to understand the learning content.

[1178] A "menu" is a document or piece of information that lists dishes or foods, and is often provided with food delivery.

[1179] A "recipe" is information that lists the steps and ingredients for making a particular dish.

[1180] A "food guide" is a teaching material that provides information about cooking and food in manga format.

[1181] "Server" refers to the computer and its software that serves as the core of this system and performs various processes.

[1182] To specifically implement the present invention, it is necessary to build a system that performs the following processes. The specific system configuration and processing procedures are shown below.

[1183] System configuration

[1184] This system consists of the following elements:

[1185] 1. Server: The central processing unit that analyzes uploaded data, runs generative AI models, and stores and serves generated content.

[1186] 2. Terminal: A device that provides a user interface and allows users to upload learning content, select a drawing style, and download the generated manga content.

[1187] 3. Generative AI model: A machine learning model for generating manga-style teaching materials based on text data and drawing style.

[1188] 4. Database: A storage device for storing the generated manga-style teaching materials.

[1189] Processing Details

[1190] Uploading and analyzing learning content

[1191] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as a PDF and accesses the upload screen to the system. The device provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[1192] The server receives the uploaded file and verifies that it is in the correct format. Once verified, the server parses the PDF file, converts it to text data, and extracts the learning content. This conversion process uses a library such as PyPDF2 to extract the text data.

[1193] Selecting and applying a drawing style

[1194] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[1195] The server receives the selected drawing style information and applies it as a parameter to the generative AI model. This step is important to ensure that the generated manga is drawn in accordance with the user's chosen style.

[1196] Automatic manga generation

[1197] Based on the prepared text data and drawing style information, the server inputs these into a generative AI model and generates manga pages corresponding to the learned content. Here, machine learning models such as the transformers library and VisionEncoderDecoderModel are used.

[1198] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[1199] Provision and use of manga

[1200] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[1201] Specific examples

[1202] As a specific use case, suppose a user wants to learn about "Italian dinner set menus." The user uploads a PDF menu to the system. Then, the user selects a "pop art style." The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually depicts the cooking process of an Italian dinner, and the user can download it to continue learning in a fun way.

[1203] Prompt Sentence Examples

[1204] Convert the following text into a cartoon in pop art style:

[1205] "How to make pizza: 1. Knead the dough. 2. Add the toppings. 3. Bake in the oven. How to cook pasta: 1. Boil the pasta. 2. Add the sauce. 3. Add the cheese."

[1206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1207] Step 1:

[1208] The user prepares the content they want to learn (e.g., food menus or recipes) in a digital format such as PDF and uploads it to the system. At this time, the device provides file selection and upload buttons via a user interface, and the user selects the file and clicks the "Upload" button. The PDF file containing the learning content is received as input, and the file is sent to the server as output.

[1209] Step 2:

[1210] The server receives the uploaded PDF file and verifies that the file is in the proper format. Once verified, the server parses the PDF file and converts it into text data. This process uses the PyPDF2 library to extract text information from each page of the PDF. It takes the received PDF file as input and generates text data as output.

[1211] Step 3:

[1212] After the text data is generated, the server saves it and displays a list of multiple drawing style options to the user via the terminal, where the user can select the drawing style that best suits their preference. As input, the text data and drawing style options are displayed, and as output, the user's selected drawing style information is sent to the server.

[1213] Step 4:

[1214] The server receives the selected drawing style information and sets it as a parameter in the generative AI model. It then inputs the prepared text data into the model and generates manga pages corresponding to the learning content. In this step, the transformers library and VisionEncoderDecoderModel are used to create manga-style content containing the generated illustrations and dialogue. Text data and drawing style information are used as input, and manga-style image data is obtained as output.

[1215] Step 5:

[1216] The server stores the generated manga-style teaching materials in a database and generates a download link to provide them to users via their devices. Users can click the link to download the generated manga and proceed with their studies at their own pace. Manga-style teaching material data is saved as input, and a download link is generated as output.

[1217] This allows users to enjoy visually learning about uploaded menus and recipes using the drawing style of their choice.

[1218] 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.

[1219] To specifically implement this invention, a system is constructed that combines the following elements.

[1220] Upload and convert learning content

[1221] First, the user prepares the learning materials they want to study in a digital format such as a PDF file and accesses the system's upload screen. The terminal provides a file selection and upload button through the user interface. The user uses this to select the file and click the "Upload" button.

[1222] The server then receives the uploaded file and verifies that it is in the proper format. Once verified, the server parses the PDF file, converts it into text data, and extracts learnings. The resulting text data is then ready to be fed into a generative AI model.

[1223] Selecting and applying a drawing style

[1224] After the upload process is complete, the user accesses a list of options provided to select a manga drawing style. The list includes multiple visual drawing styles, allowing the user to choose the style that best suits their preferences. The terminal displays the drawing style options through a user interface and transmits the user's selection to the server.

[1225] The server receives the selected drawing style information and stores it in a database, where it is set as a parameter for the generative AI model.

[1226] Incorporating an emotion engine

[1227] Furthermore, the server includes an emotion engine for recognizing the user's emotions in real time. This emotion engine analyzes data acquired from the device's camera and microphone and recognizes the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[1228] Based on the recognized emotions, the server adjusts the difficulty and tone of the generated manga-style learning material, providing a learning experience optimized for the user's emotional state.

[1229] Automatic manga generation

[1230] Based on the prepared text data, selected drawing style information, and the output of the emotion engine, the server inputs these into a generative AI model to generate manga pages corresponding to the learning content. The generative AI model automatically draws scenarios related to the text data in manga format, creating visually easy-to-learn teaching materials.

[1231] The generated manga pages contain illustrations and dialogue that correspond to the learning content, and quizzes and problem-solving scenarios are incorporated as needed, making it easier for users to understand the learning content and keeping them interested in learning.

[1232] Provision and use of manga

[1233] Finally, the server stores the generated manga-style teaching materials in a database and generates a download link for providing them to users. The device displays this download link through a user interface. Users can click the link to download the generated manga and proceed with their learning at their own pace.

[1234] Specific examples

[1235] As a specific example of use, imagine a user who wants to study the mathematics chapter on "differential calculus." The user uploads the relevant page from a PDF textbook to the system. After that, the user selects a "pop art style." The system then recognizes the user's emotional state from their facial expressions to ensure that they are concentrating. The server extracts the text data and generates a manga using a generative AI model based on the selected style. The generated manga visually illustrates the basic concepts of differentiation and calculation examples. The user can download this and continue their learning in an enjoyable way.

[1236] In this way, by combining the emotion engine, a personalized learning experience is provided that corresponds to the user's emotional state. This invention is a system that solves the problems of conventional learning materials and enables learners to study efficiently while having fun.

[1237] The processing flow will be explained below.

[1238] Step 1:

[1239] User: Prepare the learning materials they want to study as a PDF file and access the system's upload screen.

[1240] Step 2:

[1241] Terminal: Through the user interface, a file selection dialog is displayed, and the user selects a file. When the user clicks the "Upload" button, the selected PDF file is sent to the server.

[1242] Step 3:

[1243] Server: Receives the uploaded PDF file and checks that the file is in the correct format. It performs a format error check and, if there are no problems, proceeds to the next step.

[1244] Step 4:

[1245] Server: Analyze and extract text data from PDF files. Using a PDF parsing library, extract text data for each page and convert it into the appropriate data format.

[1246] Step 5:

[1247] User: Select the preferred drawing style from a list of multiple drawing styles provided on the system.

[1248] Step 6:

[1249] Terminal: Sends information about the selected drawing style to the server.

[1250] Step 7:

[1251] Server: Receives the selected drawing style information and stores it in a database. It sets it as a parameter to be applied to the generative AI model.

[1252] Step 8:

[1253] Device: A camera and microphone are used to capture facial expressions and voice data in order to recognize the user's emotions in real time.

[1254] Step 9:

[1255] Server: Using an emotion engine, analyzes the acquired facial expressions and voice data to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom, etc.).

[1256] Step 10:

[1257] Server: Adjusts the difficulty and tone of the generated manga-style educational material based on the perceived emotional state. For example, if the user is bored, it will add more engaging elements.

[1258] Step 11:

[1259] Server: Inputs the formatted text data, selected drawing style information, and emotional state data into the generative AI model. The generative AI model is executed to generate each page of the manga based on the text data.

[1260] Step 12:

[1261] Generative AI model: Analyzes input data, creates a manga-style scenario based on the text content, and generates illustrations and dialogue in a specified drawing style.

[1262] Step 13:

[1263] Server: Checks the generated manga pages, checks for errors and makes any necessary corrections. After all pages are generated correctly, the manga data is saved in the database.

[1264] Step 14:

[1265] Server: Generates a download link for the saved manga data. Generates a URL for the download link and returns it to the user interface.

[1266] Step 15:

[1267] Terminal: Displays the generated manga download link to the user through the user interface.

[1268] Step 16:

[1269] Users: Click the download link provided to download and view the generated manga. This allows users to enjoy learning using visually easy-to-understand teaching materials.

[1270] In this way, the entire system works together at each step to provide the user with the content they want to learn in manga format.The introduction of an emotion engine provides a personalized learning experience that matches the user's emotional state.

[1271] Example 2

[1272] 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."

[1273] Traditional learning systems have limited means of converting text data into a visually digestible format, making it difficult to maintain learner interest. They also lack the ability to dynamically adapt learning content to the learner's emotional state, resulting in a lack of personalized learning experiences. Furthermore, they struggle to provide consistent learning materials, including quizzes and problem-solving scenarios.

[1274] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving learning content uploaded by a learner, means for converting the received learning content into text data, means for receiving information on a drawing style selected by the learner from multiple drawing styles, means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information, means for analyzing data acquired from the terminal to recognize the learner's emotions, means for adjusting the generated teaching materials based on the results of emotion recognition, and means for providing the generated manga-style teaching materials to the learner. This not only enables learners to study effectively while remaining interested, but also provides a personalized learning experience.

[1275] "Learner" refers to a person who accesses the system, uploads learning content, and uses the generated learning materials.

[1276] "Upload" refers to the process by which a learner sends learning content to the system.

[1277] "Learning content" refers to the teaching materials and resources prepared by learners to use the system.

[1278] "Means of receiving" refers to the function of the system to receive data uploaded by learners.

[1279] "Text data" refers to textual information extracted from PDFs and other formats.

[1280] "Means for conversion" refers to the function of analyzing the received learning content and converting it into text data.

[1281] "Artistic style" refers to the visual form of expression chosen by the learner.

[1282] "Drawing style information" refers to data about the drawing style selected by the learner.

[1283] A "generative AI model" refers to an artificial intelligence algorithm that takes text data and drawing style information as input and generates visual teaching materials.

[1284] "Manga-style teaching materials" refers to visual learning materials created by generative AI models.

[1285] "Means for providing" refers to the function for making the generated teaching materials available to learners.

[1286] "Means for recognizing emotions" refers to the function of analyzing data obtained from the device and determining the learner's emotions.

[1287] "Adjustment means" refers to the ability to change the content and format of the generated teaching materials based on the results of emotion recognition.

[1288] This invention is a system for providing learners with a personalized visual learning experience. Specifically, it receives learning content uploaded by users, converts it into text data, and automatically generates manga-style learning materials using a generative AI model based on the selected drawing style. It also recognizes learners' emotions in real time and adjusts the learning materials based on the results to maximize learning effectiveness.

[1289] Hardware and software used

[1290] server

[1291] Hardware: A server with a powerful processor, sufficient memory, and storage, such as an Intel Xeon or AMD Ryzen processor.

[1292] software:

[1293] OCR software: Tesseract

[1294] Generative AI models: GPT-4, Stable Diffusion

[1295] Sentiment analysis engine: Affectiva SDK

[1296] Terminal

[1297] Hardware: A PC or smart device with a camera and microphone, such as a desktop PC with a webcam, a laptop, or a tablet device.

[1298] software:

[1299] Browser: Major browsers such as Chrome, Firefox, and Safari

[1300] User Interface: HTML, CSS, and JavaScript interface

[1301] User

[1302] Hardware: Devices listed above

[1303] Software: Uses specific applications and web browsers

[1304] Data processing and calculation

[1305] A user prepares learning materials in PDF file format and accesses the system's upload screen. For example, they use any browser to access a specific URL (e.g., https: / / manga-learning-system.com), click the "Choose File" button in the user interface, select the PDF file (e.g., mathematics_differentiation.pdf), and click the upload button.

[1306] The device sends files uploaded through the user interface to the server, which then verifies the received files and converts them into text using OCR software (Tesseract), which then formats the text for input into the generative AI model and stores it in a database.

[1307] The user then selects the manga drawing style. Multiple visual styles (e.g., simple, pop, realistic) are provided for selection, and the user chooses the style that best suits their preferences. The selected style information is sent to the server via the terminal. The server receives this information and stores it in a database.

[1308] The server uses the device's camera and microphone to recognize the user's emotions in real time. The acquired data is analyzed using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). Based on the recognized emotional state, the content and tone of the generated learning material are adjusted.

[1309] The server inputs the prepared text data, the selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, it sends a prompt to the generative AI model: "Text data: text explaining differentiation, drawing style: pop, emotional state: concentration." The generative AI model then automatically generates manga-style teaching materials based on this information and stores them in a database.

[1310] The server generates a download link for providing the created manga-style learning material and displays it through the user interface. The user can click the displayed link to download the learning material and proceed with the learning at their own pace.

[1311] Examples of specific examples and prompts

[1312] For example, if a user wants to learn "differential calculus," they upload the relevant page from a PDF textbook to the system. They then select a "pop art style." The system checks the user's facial expression to see if they are concentrating and extracts text data. Based on the selected style, a generative AI model (e.g., GPT-4) is used to generate a manga. The generated manga visually illustrates the basic concepts of differentiation and examples of calculations. Users can download it and continue their learning in an enjoyable way.

[1313] Example prompt sentence:

[1314] "Text Data: Basic Concepts of Differentiation and Examples"

[1315] "Drawing style: Pop"

[1316] "Emotional state: Focused"

[1317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] The user prepares the learning material they want to study in PDF file format and accesses the system's upload screen. The device displays a screen with a file selection and upload button. The user clicks the "Choose File" button, selects the PDF file (e.g., mathematics_differentiation.pdf), and clicks the "Upload" button. This starts the upload operation, with the PDF file serving as input.

[1320] Step 2:

[1321] The terminal sends the file uploaded through the user interface to the server. The server checks the received file and verifies whether the file is in PDF format. If the file is in PDF format, the server analyzes the PDF file and converts it into text data. The input here is the PDF file, and the output is text data. The server uses OCR software (Tesseract) to extract the text information from the PDF and stores this text data in a database.

[1322] Step 3:

[1323] The user accesses an option list to select a manga drawing style. The terminal displays multiple drawing style options (e.g., simple, pop, realistic) on the user interface. The user selects the drawing style that suits their preference and sends the information to the server. The input here is the selected drawing style information, and the output is the drawing style information saved on the server side.

[1324] Step 4:

[1325] The server uses the device's camera and microphone to recognize the user's emotions in real time. The device collects the user's facial expression and voice data and sends it to the server. The server then analyzes this data using an emotion analysis engine (Affectiva SDK) to recognize the user's emotional state (e.g., joy, sadness, excitement, boredom). The input here is the data obtained from the camera and microphone, and the output is the user's emotional state information.

[1326] Step 5:

[1327] The server inputs prepared text data, selected drawing style information, and the output of the emotion engine into a generative AI model (e.g., GPT-4, Stable Diffusion). For example, by sending a prompt such as "Text data: text explaining differentiation, drawing style: pop, emotional state: focused" to the generative AI model, a manga-style teaching material is generated. The inputs are the text data, drawing style information, and emotional state information, which form the prompt sentence, and the output is the generated manga page.

[1328] Step 6:

[1329] The generated manga-style teaching materials are stored in a database by the server. The server then generates a download link to provide to the user. The device displays this download link on its user interface. The user can click the displayed link to download the teaching materials and proceed with their learning at their own pace. The input here is the generated manga teaching materials, and the output is the generation and display of a download link.

[1330] (Application example 2)

[1331] 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."

[1332] Traditional learning methods have the drawback of making it difficult to maintain learners' concentration and interest, making it difficult to achieve efficient learning. Furthermore, it has been difficult to provide learning materials that respond to the emotions and state of each individual learner, making it impossible to provide a personalized learning experience. This has led to problems such as reduced learning effectiveness, especially in online and remote learning.

[1333] 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.

[1334] In this invention, the server includes: means for receiving learning content uploaded by a learner; means for converting the received learning content into text data; means for receiving information on a drawing style selected by the learner from multiple drawing styles; means for generating manga-style teaching materials using a generative AI model based on the text data and the drawing style information; means for providing the generated manga-style teaching materials to the learner; emotion analysis means for analyzing the learner's emotions in real time; means for adjusting the difficulty and tone of the generated manga-style teaching materials based on the emotional state analyzed by the emotion analysis means; and means for displaying the generated manga-style teaching materials on a visual device. This enables a personalized learning experience tailored to the learner's emotional state. Furthermore, by maintaining the learner's interest and concentration, efficient learning can be achieved.

[1335] A "learner" is a person who is learning specific knowledge or skills.

[1336] "Uploading" is the act of sending or transferring data to an external device or server.

[1337] "Learning content" refers to the information and materials that a learner is trying to acquire.

[1338] "Receiving" is the act of taking in information or data sent from another source.

[1339] "Text data" refers to information expressed as characters or sentences.

[1340] "Art style" refers to the drawing method and design characteristics of visual content.

[1341] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to generate a specific result.

[1342] "Manga-style teaching materials" refers to educational content drawn in manga format.

[1343] "Emotion analysis" is the process of analyzing a user's emotions and sensory state through data.

[1344] "Visual device" refers to equipment or devices that allow a user to receive information visually.

[1345] "Adjustment" is the act of changing to an optimal state depending on specific conditions or situations.

[1346] This invention provides a system that visualizes the learning materials uploaded by learners, enabling more effective and interesting learning.

[1347] System configuration

[1348] Hardware

[1349] The system uses the following hardware:

[1350] Smart glasses (used as a visual device)

[1351] Smartphone (used for uploading teaching materials and as a user interface)

[1352] Servers (used for data processing and running AI models)

[1353] software

[1354] The system uses the following software:

[1355] cv2 (OpenCV toolkit): Used to analyze the user's face image

[1356] pytesseract: Used to extract text from PDF

[1357] pdf2image: Convert PDF files to images

[1358] tensorflow: Used to run generative AI models

[1359] transformers (Hugging Face Transformers): used for sentiment analysis and text generation

[1360] Processing flow

[1361] 1. Uploading study materials

[1362] Users upload PDF-format learning materials to the system using their smartphones. The server receives the uploaded files and proceeds to the next step.

[1363] 2. Text data conversion

[1364] The server converts PDF files to images using pdf2image, then extracts text data from these images using pytesseract.

[1365] 3. Choose your drawing style

[1366] Users can select their preferred drawing style from multiple options, and the selected style information is sent to the server and used as parameters for the generative AI model.

[1367] 4. Emotion analysis

[1368] Using the camera and microphone of the smart glasses, the system analyzes the user's emotions in real time using the CV2 and Transformers libraries. The analyzed emotional information is used to adjust the generated manga teaching materials.

[1369] 5. Manga Generation

[1370] The server automatically generates manga-style teaching materials using a generative AI model based on the extracted text data and the results of user sentiment analysis.

[1371] 6. Display of Manga

[1372] The generated manga-style learning materials are displayed on smart glasses, allowing users to study the visualized learning materials in real time.

[1373] Specific examples

[1374] Consider a case where a user who wants to learn differential calculus uploads the relevant page from a PDF textbook. The user selects the "pop art style" and begins learning through smart glasses. The system then analyzes the user's facial expression to determine their level of concentration, and uses a generative AI model to generate visually easy-to-understand manga content.

[1375] Specific examples of prompts are as follows:

[1376] Generate a fun manga based on the following text: The derivative of a function measures how the function value changes as its input changes. For example, the derivative of y = x^2 is 2x.

[1377] This system provides learners with a personalized learning experience that is tailored to their emotional state, making learning more effective and engaging.

[1378] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1379] Step 1:

[1380] Uploading teaching materials

[1381] Input: Learning materials in PDF format uploaded by users from their smartphones.

[1382] Process: Select a PDF file through the terminal's user interface and send it to the server.

[1383] Data processing / calculation: Upload the PDF file to the server using an HTTP request.

[1384] Output: The server receives the PDF file and prepares it for the next step.

[1385] Step 2:

[1386] Text data conversion

[1387] Input: A PDF file uploaded to the server.

[1388] Processing: The server converts the PDF file to an image file using the pdf2image library, then extracts the text data from the image using pytesseract.

[1389] Data processing / calculation: By performing OCR (optical character recognition), text information is obtained from the images of each page.

[1390] Output: The retrieved text data.

[1391] Step 3:

[1392] Selecting a drawing style

[1393] Input: User selected drawing style information.

[1394] Processing: The user selects the preferred drawing style from multiple drawing style options and sends that information to the server.

[1395] Data processing / calculation: Sends style information selected through the user interface to the server.

[1396] Output: The server receives the drawing style information and stores it as parameters to be applied to the generative AI model.

[1397] Step 4:

[1398] Emotion analysis

[1399] Input: User's facial image and voice data captured by the smart glasses' camera and microphone.

[1400] Processing: The server uses cv2 and transformers libraries to analyze the user's emotional state in real time.

[1401] Data processing / calculation: Recognize emotions from facial expressions using image analysis algorithms and generate emotional data based on that.

[1402] Output: User's emotional state data (e.g., happy, sad, excited, bored, etc.).

[1403] Step 5:

[1404] Manga Generation

[1405] Input: Text data, drawing style information, and user emotional state data.

[1406] Processing: The server inputs these input data into a generative AI model to automatically generate manga-style teaching materials.

[1407] Data processing / computation: Generate stories using text generation algorithms and synthesize appropriate visuals based on drawing style and emotional state.

[1408] Output: Generated manga-style teaching materials.

[1409] Step 6:

[1410] Manga display

[1411] Input: Generated manga-style teaching materials.

[1412] Processing: The server sends the generated manga to the smart glasses and displays it for the user to learn visually in real time.

[1413] Data processing / calculation: Manga data is sent to the smart glasses using a data transfer protocol.

[1414] Output: Manga-style educational material displayed on smart glasses.

[1415] 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.

[1416] 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.

[1417] 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 robot 414.

[1418] 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.

[1419] FIG. 9 is a diagram illustrating 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 actions 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.

[1420] 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.

[1421] 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).

[1422] 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.

[1423] 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."

[1424] 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.

[1425] 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).

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] The following is further disclosed regarding the above embodiment.

[1437] (Claim 1)

[1438] a means for receiving learning content uploaded by learners;

[1439] A means for converting the received learning content into text data;

[1440] means for receiving information on a drawing style selected by a learner from a plurality of drawing styles;

[1441] means for generating manga-style teaching materials using a generative AI model based on the text data and drawing style information;

[1442] A means for providing the generated manga-style teaching materials to learners;

[1443] A system including:

[1444] (Claim 2)

[1445] The system according to claim 1, wherein the generated manga-style teaching materials include quizzes and problem-solving scenarios.

[1446] (Claim 3)

[1447] 10. The system of claim 1, further comprising means for applying style parameters selected based on the drawing style information to the generative AI model.

[1448] "Example 1"

[1449] (Claim 1)

[1450] a means for receiving learning content uploaded by learners;

[1451] A means for converting the received learning content into text data;

[1452] a means for receiving information in a style selected by the learner from a plurality of visual styles;

[1453] means for generating teaching materials with illustrations using a generative AI model based on the text data and style information;

[1454] A means for providing the generated illustrated teaching materials to learners;

[1455] A system including:

[1456] (Claim 2)

[1457] 10. The system of claim 1, wherein the generated illustrated teaching materials include quizzes and problem-solving scenarios.

[1458] (Claim 3)

[1459] 10. The system of claim 1, further comprising means for applying stylistic parameters selected based on the stylistic information to the generative AI model.

[1460] "Application Example 1"

[1461] (Claim 1)

[1462] a means for receiving learning content uploaded by learners;

[1463] A means for converting the received learning content into text data;

[1464] means for receiving information on a drawing style selected by a learner from a plurality of drawing styles;

[1465] means for generating manga-style teaching materials using a generative AI model based on the text data and drawing style information;

[1466] A means for providing the generated manga-style teaching materials to learners;

[1467] A means to convert menus and recipes uploaded by learners into text data,

[1468] means for generating a manga-style food guide using a generative AI model based on the text data and a selected drawing style;

[1469] A system including:

[1470] (Claim 2)

[1471] The system according to claim 1, wherein the generated manga-style teaching materials include quizzes and problem-solving scenarios.

[1472] (Claim 3)

[1473] 10. The system of claim 1, further comprising means for applying style parameters selected based on the drawing style information to the generative AI model.

[1474] "Example 2: Combining Emotion Engines"

[1475] (Claim 1)

[1476] a means for receiving learning content uploaded by learners;

[1477] A means for converting the received learning content into text data;

[1478] means for receiving information on a drawing style selected by a learner from a plurality of drawing styles;

[1479] means for generating manga-style teaching materials using a generative AI model based on the text data and drawing style information;

[1480] means for analyzing data obtained from the device to recognize the learner's emotions;

[1481] a means for adjusting the generated educational material based on the result of the emotion recognition;

[1482] A means for providing the generated manga-style teaching materials to learners;

[1483] A system including:

[1484] (Claim 2)

[1485] The system according to claim 1, wherein the generated manga-style teaching materials include quizzes and problem-solving scenarios.

[1486] (Claim 3)

[1487] 10. The system of claim 1, further comprising means for applying style parameters selected based on the drawing style information to the generative AI model.

[1488] "Application example 2 when combining emotion engines"

[1489] (Claim 1)

[1490] a means for receiving learning content uploaded by learners;

[1491] A means for converting the received learning content into text data;

[1492] means for receiving information on a drawing style selected by a learner from a plurality of drawing styles;

[1493] means for generating manga-style teaching materials using a generative AI model based on the text data and drawing style information;

[1494] A means for providing the generated manga-style teaching materials to learners;

[1495] An emotion analysis means for analyzing learners' emotions in real time;

[1496] a means for adjusting the difficulty level and tone of the manga-style teaching material to be generated based on the emotional state analyzed by the emotional analysis means;

[1497] a means for displaying the generated manga-style teaching material on a visual device;

[1498] A system including:

[1499] (Claim 2)

[1500] The system according to claim 1, wherein the generated manga-style teaching materials include quizzes and problem-solving scenarios.

[1501] (Claim 3)

[1502] 10. The system of claim 1, further comprising means for applying style parameters selected based on the drawing style information to the generative AI model. [Explanation of symbols]

[1503] 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 receiving learning content uploaded by learners; A means for converting the received learning content into text data; means for receiving information on a drawing style selected by a learner from a plurality of drawing styles; means for generating manga-style teaching materials using a generative AI model based on the text data and drawing style information; A means for providing the generated manga-style teaching materials to learners; A system including:

2. The system according to claim 1, wherein the generated cartoon-style teaching materials include quizzes and problem-solving scenarios.

3. 10. The system of claim 1, further comprising means for applying style parameters selected based on the drawing style information to the generative AI model.

Images