system

Abstract

We provide the system. [Solution] A means for uploading test results from educational devices, A method for analyzing test results and extracting text data, A method for analyzing learners' strengths and weaknesses based on extracted text data, A means of generating individual homework assignments based on analysis results, A means of providing the generated homework to learning-related devices, A means of recording the progress of homework and saving it to data storage, A method for recommending the next learning content based on progress and analytical data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional educational system, it is difficult to optimize the learning content and progress of each individual child. Specifically, it takes a great deal of time and effort for teachers to manually analyze the test content of children and create individually optimized teaching materials and homework. In addition, there is a lack of means to quickly and accurately identify which parts a child has difficulty with, making it difficult to improve learning efficiency. Furthermore, it is impossible to grasp the progress of each individual child in real time and provide the next learning step accordingly. There is a need for a system that solves such problems and effectively supports individual learning of children.

Means for Solving the Problems

[0005] The present invention is a system that includes means for uploading test results from an educational device, means for analyzing the test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to a learning device, means for recording the progress of the homework and saving it to data storage, and means for recommending the next learning content based on the progress and analysis data. This system makes it possible to automatically analyze the learning situation of each child and provide individually optimized learning content, thereby significantly improving learning efficiency. Furthermore, by grasping learning progress in real time and appropriately suggesting the next necessary learning content, it can support children's independent learning.

[0006] "Educational devices" is a general term for electronic devices and software used by learners to perform learning activities such as referencing learning content, answering questions, and uploading them.

[0007] "Test results" refer to data showing the results of tests taken by learners, and are usually provided in paper or electronic format.

[0008] "Uploading" refers to the operation of sending data from a local device to remote storage such as a server.

[0009] "Text data" refers to character information extracted from test results using OCR technology or other methods.

[0010] A "learner" refers to an individual who engages in learning activities using educational devices.

[0011] "Analysis" refers to the act of applying specific rules or algorithms to text data to identify learners' tendencies and patterns.

[0012] "Areas of difficulty" refers to problems or subjects that learners repeatedly get wrong or do not fully understand.

[0013] "Areas of expertise" refers to questions or subjects that a learner can answer accurately and consistently.

[0014] "Homework" refers to assignments or sets of problems given to learners, intended to check their learning progress.

[0015] "Progress" refers to data that records the learner's progress in completing homework and other learning content.

[0016] "Data storage" refers to physical or cloud-based storage devices used to store collected data for the long term.

[0017] "Learning content" is a general term for educational materials such as textbooks, workbooks, videos, and other materials used by learners to study. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0020] First, the language used in the following description will be described.

[0021] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This invention relates to a system that uses educational devices to analyze learners' test results and provides individually optimized homework. This system can be specifically implemented as follows:

[0040] Upload test results

[0041] User:

[0042] Learners open a dedicated app on their educational device (e.g., a tablet or smartphone) and upload their test results.

[0043] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[0044] Terminal:

[0045] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[0046] The file is sent to the server.

[0047] server:

[0048] Check the received file and double-check that it is not in an invalid format.

[0049] OCR technology is used to extract text data from a file and save it to temporary storage.

[0050] Analysis of test results and homework generation

[0051] server:

[0052] Move the text data from temporary storage to the database and save it.

[0053] Text data stored in a database is input into a machine learning model, and the learner's response patterns are analyzed.

[0054] An algorithm is executed that identifies the learner's strengths and weaknesses and generates customized homework assignments.

[0055] The generated homework is provided to learning-related devices.

[0056] User:

[0057] Learners review the generated homework on the app and send correction instructions to the server as needed.

[0058] Download and print the corrected homework, or start answering it directly within the app.

[0059] Learning at your own pace

[0060] User:

[0061] Students complete their homework and answer questions at their own pace.

[0062] Once you have finished answering, press the submit button to send your answer to the server.

[0063] Terminal:

[0064] The answer data is temporarily stored and prepared for transmission to the server.

[0065] Send the answer data to the server.

[0066] server:

[0067] The received answer data is analyzed and stored in a database.

[0068] Update learning progress information and recommend the next learning content the learner needs.

[0069] Specific example

[0070] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue. This system allows learners to always receive optimal learning content tailored to their level of understanding, enabling effective learning.

[0071] The following describes the processing flow.

[0072] Step 1: Upload test results

[0073] User:

[0074] Open the dedicated app and proceed to the screen where you upload your test results.

[0075] Click the "Select File" button and choose the test result file (PDF or image) from your device.

[0076] Press the "Upload" button.

[0077] Step 2: Upload Process

[0078] Terminal:

[0079] Check the format of the selected file and verify that it is a supported format (PDF or image).

[0080] The file is temporarily saved to storage and prepared for transmission to the server.

[0081] Send the file to the server.

[0082] server:

[0083] Check the received file and double-check that it is not in an invalid format.

[0084] The system sends a file to an OCR (Optical Character Recognition) system and extracts text data from the file.

[0085] The extracted text data is saved to temporary storage.

[0086] Step 3: Save text data

[0087] server:

[0088] Move text data stored in temporary storage to the database and save it permanently.

[0089] Step 4: Data Analysis

[0090] server:

[0091] Text data is retrieved from a database and input into a machine learning model.

[0092] Machine learning models are used to analyze test results and identify learners' strengths and weaknesses.

[0093] Based on the analysis results, the system generates homework assignments optimized for each learner.

[0094] Step 5: Homework Generation

[0095] server:

[0096] Automatically generates homework assignments that take into account the student's strengths and weaknesses.

[0097] The generated homework assignment sets are saved in a database and reflected in the learner's progress.

[0098] Step 6: Homework Distribution

[0099] User:

[0100] View a preview of the homework generated through the app.

[0101] If necessary, send correction instructions to the server.

[0102] After confirmation, download and print the homework, or start answering directly within the app.

[0103] Step 7: Answers to homework

[0104] User:

[0105] Students complete their homework at their own pace.

[0106] Once you have finished answering, press the "Submit" button to send your answer to the server.

[0107] Terminal:

[0108] The answer data is temporarily stored and prepared for transmission to the server.

[0109] Send the answer data to the server.

[0110] Step 8: Analyze and save the solution

[0111] server:

[0112] Review and analyze the received answer data.

[0113] The answer data is saved to the database, and the learner's progress information is updated.

[0114] Based on the learner's progress and answer results, the system recommends the next learning content they should proceed to.

[0115] This process ensures that learners always receive optimal learning content based on their learning progress and understanding, allowing them to continue learning effectively.

[0116] (Example 1)

[0117] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0118] Traditional education systems have struggled to provide appropriate learning content based on each learner's individual abilities and level of understanding. This made it difficult for learners to effectively overcome their weaknesses and prevented them from receiving appropriate learning content tailored to their progress. Furthermore, there was a lack of efficient methods for analyzing which areas of weakness existed.

[0119] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0120] In this invention, the server includes means for inspecting learning evaluation results and extracting textual information, means for analyzing the learner's weaknesses and strengths based on the extracted textual information, and means for providing individualized learning tasks based on the analysis results. This makes it possible to provide learning content optimized for each learner and to support them in efficiently overcoming their areas of weakness.

[0121] "Educational devices" refer to devices used by learners for educational purposes, including, for example, tablets, smartphones, and PCs.

[0122] "Learning assessment results" refer to data showing the results of tests and assignments completed by learners, and are uploaded as PDF or image files.

[0123] "Textual information" refers to text data extracted using OCR technology, obtained from uploaded learning evaluation results.

[0124] "Areas of weakness" refers to information that indicates the subjects or types of problems that learners find difficult, and this is determined through analysis of test results.

[0125] "Strengths" refer to information that indicates the areas and types of problems a learner excels at, and this is determined through analysis of test results.

[0126] "Individualized learning assignments" refer to homework or practice problems optimized for specific learners based on analysis results.

[0127] "Information storage device" refers to hardware or software that functions as data storage, including servers and cloud storage.

[0128] "Optical character recognition technology" is a technology that extracts text information from images and PDFs, and uses software such as Tesseract OCR.

[0129] A "machine learning model" is an algorithm that uses AI technology to perform data analysis and prediction, and refers to models that use frameworks such as TENSORFLOW®.

[0130] "Educational content" is a term that describes the content of learning materials and assignments provided to learners, including, for example, textbooks, videos, and practice problems.

[0131] Modes for carrying out the invention

[0132] This invention relates to a system that uses educational equipment to analyze learners' test results and provides individually optimized learning tasks. In this system, the user, terminal, and server each play important roles.

[0133] Hardware and software usage

[0134] This system utilizes tablets, smartphones, or PCs as educational devices. This allows learners to easily upload test results. The server-side uses a high-performance database (e.g., MySQL®) and machine learning models (e.g., TensorFlow) to analyze learner data and generate individualized learning assignments. OCR technology (e.g., Tesseract OCR) is used for text data extraction.

[0135] Data processing and data calculation

[0136] 1. User Operation: Learners upload their learning assessment results from educational devices using a dedicated app. The uploaded files are often in PDF or image format.

[0137] 2. Terminal operation: The system checks the format of the uploaded file and temporarily saves it to storage. Next, it calculates a checksum to verify data integrity and prepares to send the file to the server.

[0138] 3. Server operation: Check the received files and recheck for any invalid formats. Use OCR technology to extract character information from the files. This converts the learning evaluation results into text data.

[0139] 4. Database Use: The extracted text data is stored in a database. The stored data will later be used to analyze it using a machine learning model.

[0140] 5. Data Analysis: The server inputs the stored text data into a machine learning model. This identifies the learner's strengths and weaknesses. Based on the analysis results, individual learning tasks are generated.

[0141] 6. Assignment Provision: The generated learning assignments are provided again to the educational device. Learners can check their homework through a dedicated app and make corrections as needed.

[0142] 7. Recording progress: The server records the learner's progress on assignments and saves it in a database. Based on this information, it recommends the next necessary learning content.

[0143] Specific examples and prompt statements

[0144] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates a task specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the task and sends the answer back to the server. The server analyzes the answer and, upon confirming that A's understanding of multiplication problems has deepened, suggests long division as the next learning topic. In this way, learner A can progress through their learning with appropriate content and timing.

[0145] Example of a prompt:

[0146] "Please describe the specific processing steps of a system that allows learners to upload their math test results, analyzes that data, and provides them with the most suitable homework."

[0147] This prompt prompts the generative AI model to explain how the system will process the learner's test results and provide the most appropriate learning content.

[0148] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0149] Step 1:

[0150] User: Learners use educational devices (e.g., tablets, smartphones) to launch a dedicated app and upload their test results. Input is a test result file in PDF or image format. Output is the transmission of these files to the device.

[0151] Step 2:

[0152] Terminal: Verify that the uploaded file format is correct. Specifically, analyze the file header information to verify that it is a PDF or image file. The input is the file uploaded by the user in step 1. The output is the file stored in temporary storage.

[0153] Step 3:

[0154] Terminal: Saves the verified file to temporary storage and calculates its checksum. After calculation, it verifies data integrity and prepares it for transmission to the server. Input is a verified file. Output is a file ready for transmission to the server.

[0155] Step 4:

[0156] Server: The server re-examines the received file and checks for any formatting errors. Then, it uses OCR technology (e.g., Tesseract OCR) to extract text information from the file. The input is the file sent from the terminal. The output is the extracted text data.

[0157] Step 5:

[0158] Server: Stores the text data extracted by OCR in temporary storage. Then, saves the text data to a database (e.g., MySQL). Input is the text data extracted by OCR. Output is the text data stored in the database.

[0159] Step 6:

[0160] Server: Inputs text data stored in a database into a machine learning model (e.g., TensorFlow) to analyze the learner's strengths and weaknesses. The input is text data stored in a database. The output is the analysis results regarding the learner's strengths and weaknesses.

[0161] Step 7:

[0162] Server: Generates individual learning tasks based on analysis results. For example, for a learner who struggles with "carrying over in multiplication," it generates homework specifically tailored to that problem. The input is the learner's analysis results. The output is the generated learning task.

[0163] Step 8:

[0164] Server: Sends the generated learning tasks to educational devices. Input is the generated learning tasks. Output is the tasks sent to the educational devices.

[0165] Step 9:

[0166] User: Learners use a dedicated app to review generated homework and provide correction instructions as needed. Input is the assignment sent from the server. Output is correction instructions (if any).

[0167] Step 10:

[0168] User: Learners solve generated learning tasks and submit their answers to the server via a dedicated app. The input is the completed task. The output is the answer data submitted to the server.

[0169] Step 11:

[0170] Server: Analyzes received answer data and stores it in a database. Based on the analysis results, it recommends the next learning content. Input is the learner's answer data. Output is the next recommended learning content.

[0171] (Application Example 1)

[0172] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0173] Conventional learning support systems using educational devices struggle to provide optimal homework tailored to each learner's individual weaknesses. Furthermore, the process of learners uploading test results and receiving automatically customized homework requires efficient and accurate information analysis and delivery. Additionally, flexibility is needed to allow learners to monitor their progress and learning outcomes and move on to the next learning step. This system aims to solve these challenges and provide a system that enables learners to progress effectively and efficiently.

[0174] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0175] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, and means for automatically generating homework corresponding to a specific theme from the learner's test results and providing it through a content distribution application. This makes it possible to provide optimal homework that meets the individual needs of the learner.

[0176] "Educational devices" is a general term for electronic devices used to run learning-related applications, such as tablets, smartphones, and computers.

[0177] "Means for uploading test results" refers to a function that allows learners to send test results to a server using educational devices.

[0178] "Methods for analyzing test results and extracting text data" refers to a function that analyzes test results received on a server and extracts them as text data using OCR technology or similar methods.

[0179] "Methods for analyzing learners' strengths and weaknesses" refers to a function that analyzes learners' answer patterns based on text data from test results to identify areas of strength and weakness.

[0180] "Means for generating individualized homework" refers to a function that automatically creates homework optimized for a particular learner based on the results of an analysis of that learner.

[0181] "Means of providing to learning-related devices" refers to a function that sends homework generated on the server to learners' educational devices, making it accessible to the learners.

[0182] "Means for recording progress and saving it to data storage" refers to a function that records the process by which learners complete their homework and saves that data to storage on a server.

[0183] The "means for recommending the next learning content" refer to a function that recommends what the learner should study next, based on their saved progress and analytical data.

[0184] "A means of automatically generating homework corresponding to a specific theme and providing it through a content distribution application" refers to a function that creates homework based on theme-specific analytical information obtained from test results and provides it to learners using a content distribution service.

[0185] This invention is a system that uses educational devices to analyze learners' test results and provide individually optimized homework. This system functions through the cooperation of a server, terminals, and users.

[0186] The server provides a means for users to upload test results from educational devices (e.g., tablets and smartphones). Users can take photos or scan test results and send them to the server via their device in image or PDF format. This allows users to easily provide test results in digital format.

[0187] Next, the server analyzes the test results. Specifically, it uses OCR technology (e.g., Tesseract OCR) to extract text data from images and PDF files. This text data is temporarily stored and then transferred to a database. The server inputs this data into a machine learning model to automatically analyze the learner's strengths and weaknesses. For example, if the analysis reveals that the learner struggles with "carrying over in multiplication," the server uses this information to generate personalized homework.

[0188] The generated homework is provided to educational devices. Users can review the homework on their devices and make corrections as needed. While the user works on the provided homework, the device records their progress and sends it to the server. The server stores this information in a database and recommends the learning content the learner needs next.

[0189] Specifically, the server is built using the Flask framework, and Tesseract OCR is used for OCR technology. PIL (Pillow) is used for image processing. These technologies enable the efficient and accurate conversion of test results into digital data for analysis and storage.

[0190] Specific example

[0191] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server uses OCR technology to convert the received image into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue.

[0192] Example of a prompt

[0193] "Analyze the test results and generate homework specifically tailored to your weaknesses (e.g., carrying over in multiplication)."

[0194] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0195] Step 1:

[0196] Users upload test results using educational devices.

[0197] Specifically, learners take a picture of their test results with their smartphone camera, select an image or PDF file format through the application, and press the upload button.

[0198] Input: Image or PDF file of test results

[0199] Output: Sending files to the server

[0200] Step 2:

[0201] The terminal prepares to send the test result file to the server.

[0202] The device checks the uploaded file format, and if it is a supported format, it saves the file to temporary storage and prepares it for transfer to the server.

[0203] Input: Uploaded test result file

[0204] Output: Files saved to temporary storage

[0205] Step 3:

[0206] The server receives the test results file and extracts the text data.

[0207] The server checks the received file and uses OCR technology (e.g., Tesseract OCR) to extract text data from the image or PDF. The extracted text data is temporarily stored.

[0208] Input: Image or PDF file of test results

[0209] Output: Extracted text data

[0210] Step 4:

[0211] The server analyzes the text data.

[0212] The extracted text data is stored in a database and then input into a machine learning model. The server analyzes the learner's response patterns to identify their weak and strong areas.

[0213] Input: Extracted text data

[0214] Output: Analysis results (weaknesses and strengths)

[0215] Step 5:

[0216] The server generates individual homework assignments.

[0217] Based on the analysis results, the server automatically generates homework tailored to the learner's areas of difficulty. For example, if a learner struggles with "carrying over in multiplication," the server will create problems specifically focused on that topic.

[0218] Input: Analysis results (weaknesses and strengths)

[0219] Output: Generated homework

[0220] Step 6:

[0221] The server provides the generated homework to learning-related devices.

[0222] The server sends the generated homework to the user's educational device. The user can receive the provided homework and view it within the application.

[0223] Input: Generated homework

[0224] Output: Providing homework to educational devices

[0225] Step 7:

[0226] The user works on the homework assigned to them.

[0227] The user begins solving homework within the application. Progress and answer results are recorded on the device.

[0228] Input: Provided homework

[0229] Output: Progress and answer results

[0230] Step 8:

[0231] The device sends the progress and answer results to the server.

[0232] The device temporarily stores the user's answers and prepares to send them to the server. When the send button is pressed, the device sends the answer data to the server.

[0233] Input: Progress and answer results

[0234] Output: Sending data to the server

[0235] Step 9:

[0236] The server analyzes the received data and recommends the next learning step.

[0237] The server analyzes the received progress and answers, updates the learner's understanding, and recommends the next necessary learning content.

[0238] Input: Progress and answer results

[0239] Output: Recommendations for the following learning content

[0240] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0241] This invention is a system that combines an emotion engine with educational devices, analyzes learners' test results, provides individually optimized homework, and recognizes learners' emotions to improve learning efficiency. This system can be implemented as follows.

[0242] Upload test results

[0243] User:

[0244] Learners open a dedicated app on their educational device (such as a tablet or smartphone) and upload their test results.

[0245] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[0246] Terminal:

[0247] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[0248] The file is sent to the server.

[0249] Extracting and saving text data

[0250] server:

[0251] Check the received file and double-check that it is not in an invalid format.

[0252] OCR technology is used to extract text data from a file and save it to temporary storage.

[0253] Move text data stored in temporary storage to the database and save it permanently.

[0254] Data analysis and homework generation

[0255] server:

[0256] Text data is retrieved from a database and input into a machine learning model.

[0257] A machine learning model analyzes the test results to identify the learner's strengths and weaknesses.

[0258] Based on the analysis results, the system generates homework assignments optimized for each learner.

[0259] The system automatically generates homework assignments that take into account each student's strengths and weaknesses, and saves them in a database.

[0260] Using an Emotion Engine

[0261] server:

[0262] An emotion engine is used to collect emotional data in real time while learners are using educational devices.

[0263] Emotional data is obtained by analyzing the learner's facial expressions, voice tone, and behavioral patterns.

[0264] Based on the acquired emotional data, the difficulty and content of homework assignments will be appropriately adjusted.

[0265] Homework distribution and feedback

[0266] User:

[0267] Learners review the generated homework on the app and send correction instructions to the server as needed.

[0268] After confirmation, download and print the homework, or start answering directly within the app.

[0269] Terminal:

[0270] The learner's progress and answer data are temporarily saved and prepared to be sent to the server.

[0271] After completing your answer, press the submit button to send your answer to the server.

[0272] server:

[0273] The received answer data is analyzed and stored in a database.

[0274] Update learning progress information and recommend the next learning content to proceed with.

[0275] Based on user emotional data recognized by the emotion engine, feedback is provided to improve learner motivation. Specifically, this includes sending encouraging messages when learners are feeling stressed, and recommending breaks when concentration is low.

[0276] Specific example

[0277] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that B tends to struggle with division problems. Based on this, the server generates homework specifically focused on division and provides it to B's device. Furthermore, while B is working on the homework, the emotion engine recognizes B's facial expressions, and if it determines that B is experiencing stress, it displays advice and encouraging messages to reduce stress. B can receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[0278] The following describes the processing flow.

[0279] Step 1: Upload test results

[0280] User:

[0281] The learner opens the dedicated app on an education-related device (e.g., tablet or smartphone) and moves to the screen for uploading test results.

[0282] Click the "File Selection" button and select the test result file (PDF or image) from the terminal.

[0283] Press the "Upload" button.

[0284] Step 2: Upload Process

[0285] Terminal:

[0286] Check the selected file format (PDF or image) and verify that it is a supported format.

[0287] Temporarily save the file to storage and prepare for transfer to the server.

[0288] Send the file to the server.

[0289] Server:

[0290] Check the received file again to ensure it is not in an invalid format.

[0291] Send the file to the OCR (Optical Character Recognition) system to extract text data from the file.

[0292] Save the extracted text data to temporary storage.

[0293] Step 3: Saving Text Data

[0294] Server:

[0295] Move the text data saved in temporary storage to the database for permanent storage.

[0296] Step 4: Data Analysis

[0297] Server:

[0298] Retrieve text data from the database and input it into the machine learning model.

[0299] The machine learning model analyzes the test results to identify the learner's weak and strong areas.

[0300] Based on the analysis results, generate the optimal homework content for the learner.

[0301] Step 5: Homework Generation

[0302] Server:

[0303] Automatically generate a set of homework problems considering the learner's weak and strong areas and save them in the database.

[0304] Step 6: Analysis by Emotion Engine

[0305] Server:

[0306] Use the emotion engine to collect the learner's real-time emotion data from educational-related devices.

[0307] The emotion data is obtained by analyzing the learner's facial expressions, voice tones, behavior patterns, etc.

[0308] Based on the obtained emotion data, adjust the difficulty level and feedback of the homework.

[0309] Step 7: Delivery of Homework

[0310] User:

[0311] The learner checks the preview of the homework generated through the app.

[0312] Send correction instructions to the server as needed.

[0313] After confirmation, download and print the homework, or start answering directly within the app.

[0314] Step 8: Answers to homework

[0315] User:

[0316] Students complete their homework at their own pace.

[0317] Once you have finished answering, press the "Submit" button to send your answer to the server.

[0318] Terminal:

[0319] The learner's answer data is temporarily stored and prepared for transmission to the server.

[0320] Send the answer data to the server.

[0321] Step 9: Analyze and save the solution

[0322] server:

[0323] Review and analyze the received answer data.

[0324] The answer data is saved to the database, and the learner's progress information is updated.

[0325] Based on user emotion data recognized by the emotion engine, feedback is provided to improve learner motivation.

[0326] Specific example

[0327] Learner C takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that C has difficulty with "division of fractions." Based on this, the server generates homework specifically focused on division of fractions and provides it to C's device.

[0328] Furthermore, while C is working on homework, the emotion engine recognizes C's facial expressions and, if it determines that C is experiencing stress, displays advice and encouraging messages to help reduce stress. C can then receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[0329] (Example 2)

[0330] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0331] Traditional education systems have struggled to efficiently identify specific areas of difficulty for learners and provide individually optimized homework based on those areas. Furthermore, because learning progresses without considering the learner's emotional state, learners may experience stress or lack concentration. This raises concerns about decreased learning effectiveness and reduced motivation. Additionally, the cumbersome process of uploading test results and the lack of real-time monitoring of learners' progress made efficient feedback difficult. Moreover, homework was not adjusted based on the learner's emotional state, resulting in ineffective learning support.

[0332] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0333] In this invention, the server includes means for uploading test results from educational equipment, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational equipment, means for recording the progress of the homework and storing it in a data storage device, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing emotional data in real time, and means for adjusting the difficulty and content of the homework based on the emotional data. This makes it possible to efficiently identify the learner's weaknesses and provide individually optimized homework. Furthermore, by understanding the learner's emotional state in real time and adjusting the difficulty and content of the homework based on it, it is possible to reduce the learner's stress and maintain their concentration. With this system, learners can receive effective learning support, and improvements in learning effectiveness and motivation can be expected.

[0334] "Educational equipment" refers to devices used by learners to conduct learning activities, and specifically includes tablets, smartphones, and laptop computers.

[0335] "Test results" refer to data showing the answers and scores of students when they take a test, and are recorded in formats such as PDF or image.

[0336] A "server" is a computer system used to process data operations over a network, including data storage, analysis, and distribution.

[0337] "OCR technology" is an abbreviation for Optical Character Recognition technology, which is a technology that reads character data from image files and other sources and converts it into text data.

[0338] "Text data" refers to data in a string format that can be electronically recognized using OCR technology or other conversion methods.

[0339] A "machine learning model" is a model that builds algorithms based on large amounts of data and automatically performs specific tasks by learning patterns and rules from that data.

[0340] "Individualized homework" refers to learning tasks optimized for each learner's learning situation and abilities, and is specifically designed to improve areas of weakness.

[0341] A "data storage device" is a device that includes hardware and software used to store and manage data for long periods of time.

[0342] "Emotional data" refers to data that indicates a learner's emotional state, obtained by analyzing their facial expressions, voice tone, behavioral patterns, and other factors.

[0343] "Real-time" refers to the immediate processing and reflection of events currently in progress, meaning that specific data or interactions are processed instantly without delay.

[0344] "Analyzing" means processing and evaluating data using various techniques in order to find specific patterns or trends.

[0345] This invention is a system that combines an emotion engine with educational equipment, analyzes learners' test results, and provides individually optimized homework. Furthermore, it is characterized by its ability to recognize the learner's emotional state in real time and make adjustments to improve learning efficiency. This system can be implemented specifically as follows.

[0346] Hardware and software configuration

[0347] Educational devices include tablets, smartphones, and laptops. These devices have dedicated apps installed, which learners can use to upload test results and download homework.

[0348] The server is a central management system that receives and analyzes data transmitted from these educational devices, and further collects and analyzes emotional data using an emotion engine. Specifically, the following software and technologies are used.

[0349] 1. OCR technology (e.g., Tesseract OCR): Used to extract text data from image data of test results.

[0350] 2. Machine learning models (e.g., TensorFlow, PyTorch): These are used to identify the learner's strengths and weaknesses based on the acquired text data.

[0351] 3. Emotion engine (e.g., Microsoft® Azure® Face API): Used to collect and analyze emotion data in real time from the learner's facial expressions and voice tone.

[0352] 4. Data storage devices (e.g., MySQL, PostgreSQL): Used to permanently store analytical data, homework data, sentiment data, etc.

[0353] Specific example

[0354] The following shows specific examples of how the system according to the present invention can be used.

[0355] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads them through a dedicated app. The device checks the test results, saves them to temporary storage, and then sends them to the server. The server checks the received image data and uses Tesseract OCR to convert the answers into text data.

[0356] Next, the server inputs the converted text data into a machine learning model and analyzes the test results. The analysis identifies that B tends to struggle with division problems. Based on this, the server uses a generative AI model to generate homework specifically focused on division. The following prompts are used during the generation process.

[0357] Example of a prompt:

[0358] "Please generate five homework problems related to division, a topic that learners often struggle with. Set the difficulty level of each problem to medium."

[0359] The generated homework assignments are stored in a database and provided to B's smartphone. While B is working on the assignments, an emotion engine recognizes B's facial expressions and collects emotional data in real time. For example, if the system determines that B is stressed, it displays advice and encouraging messages to help reduce stress.

[0360] B can accept this advice and proceed with learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in effective learning.

[0361] Thus, by combining educational equipment and an emotion engine, the present invention can simultaneously provide individually optimized homework and learning support tailored to the learner's emotional state. This system is expected to improve learning effectiveness and enhance learner motivation.

[0362] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0363] Step 1: Upload test results

[0364] User: The learner launches the dedicated app for the educational device and selects the "Upload Test Results" function. They either take a picture of the test results with the device's camera or select an existing PDF / image file and press the upload button.

[0365] Input: Image data or PDF file of the captured test results

[0366] Output: Upload of recorded image data or PDF file

[0367] Specific operation: The user takes a test result with the camera or selects an existing file and presses the upload button.

[0368] Terminal: The terminal verifies the file format selected by the user and saves it to temporary storage. It then prepares the saved file to send to the server and sends the file to the server.

[0369] Input: Uploaded image data or PDF file

[0370] Output: Image data or PDF file transferred to the server

[0371] Specific actions: Check file format, temporarily save file, send file to server

[0372] Step 2: Extract and save text data

[0373] Server: The server checks the received file and re-verifies that it is not in an invalid format. Then, it uses Tesseract OCR to extract text data from the file. After saving it to temporary storage, it moves it to the database for permanent storage.

[0374] Input: Image data or PDF file transferred to the server

[0375] Output: Permanently saved text data

[0376] Specific actions: Reconfirm file format, extract text data using OCR technology, save to temporary storage, move text data to database.

[0377] Step 3: Data Analysis and Homework Generation

[0378] Server: The server retrieves text data from the database and inputs it into a machine learning model. The machine learning model analyzes the test results and identifies areas of weakness and strength. Based on the analysis results, it generates homework using a generative AI model. It inputs prompts into the generative AI model, generates a set of homework problems, and saves them to the database.

[0379] Input: Text data stored in the database

[0380] Output: Homework assignment set saved in the database

[0381] Specific operations: Input text data into a machine learning model, obtain analysis results, input prompt sentences into an AI model, generate homework assignments, and save the assignments to a database.

[0382] Example prompt: "Generate 5 homework problems related to division, which is a difficult topic for learners. Set the difficulty level of each problem to medium."

[0383] Step 4: Utilizing the Emotional Engine

[0384] Server: The server uses an emotion engine to collect emotional data in real time while learners are using educational equipment. It analyzes facial expressions and voice tone to obtain emotional data and adjusts the difficulty and content of homework based on that data. The collected emotional data is stored in a database.

[0385] Input: Sentimental data collected in real time from educational equipment.

[0386] Output: Homework adjusted according to emotions, and emotional data stored in the database.

[0387] Specific actions: Analysis of facial expressions and voice tone, collection and storage of emotional data, adjustment of homework content.

[0388] Step 5: Homework distribution and feedback

[0389] User: Learners can view the generated homework in a dedicated app and begin working on it. Correction instructions can be sent to the server as needed, and homework can be downloaded and printed, or completed directly within the app.

[0390] Input: Homework confirmation and answer data from the dedicated app.

[0391] Output: Answer data and correction instructions sent to the server

[0392] Specific actions: Checking homework, sending correction instructions, entering answers.

[0393] Terminal: The terminal temporarily stores the learner's progress and answer data in storage and prepares to send it to the server. After completing the answer, it sends the answer data to the server.

[0394] Input: Learner progress and answer data

[0395] Output: Answer data sent to the server

[0396] Specific actions: Temporarily save progress and answer data, prepare to send to the server, send answer data.

[0397] Server: The server analyzes the received answer data and stores it in a database. It updates learning progress information and recommends the next learning content to proceed with. It provides feedback based on sentiment data recognized by the sentiment engine.

[0398] Input: Answer data sent to the server

[0399] Output: Analysis data and feedback stored in the database

[0400] Specific actions: Analysis and storage of answer data, updating of learning progress information, generation and provision of feedback.

[0401] The above outlines the specific processing steps for implementing the present invention. Through this process, learners can receive effective and personalized learning support.

[0402] (Application Example 2)

[0403] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0404] In factory production operations, worker fatigue and stress are major factors leading to decreased work efficiency and errors. While conventional automation systems monitor work content and progress, they lack the ability to respond in real time to consider the emotional state and stress levels of workers. Therefore, a system is needed that simultaneously optimizes worker health and work efficiency.

[0405] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0406] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing the worker's emotional data using an emotion engine, and means for providing the worker with individually optimized work instructions and break advice based on the analysis results. This makes it possible to monitor the worker's fatigue and stress in real time and maintain their health while improving work efficiency.

[0407] "Educational devices" refer to electronic devices and tools used in educational activities, and specifically include tablets, smartphones, and personal computers.

[0408] "Test results" refers to the performance data and answers of tests taken by learners, including those saved in PDF or image formats.

[0409] "Text data" refers to character information extracted from test results, which is processed using OCR technology, etc.

[0410] "Learner" refers to an individual who uses educational devices to learn, including those who are studying a specific curriculum or course.

[0411] "Individualized homework" refers to homework assignments that are generated individually based on each student's learning progress and level of understanding.

[0412] "Learning content" refers to educational materials and assignments that learners access through educational devices, and includes text, videos, and interactive questions.

[0413] An "emotion engine" refers to technologies for recognizing and analyzing the emotional state of learners and workers in real time, and includes facial recognition, voice analysis, and behavioral pattern analysis.

[0414] "Emotional data" refers to information related to the emotions of learners and workers acquired by the emotion engine, and includes data such as facial expressions, tone of voice, and movements.

[0415] "Worker" refers to an individual performing tasks in a factory or manufacturing site, including those assigned to specific production lines or tasks.

[0416] "Work instructions" refer to instructions that communicate specific work content and procedures to workers, and include information to ensure work efficiency and safety.

[0417] "Break advice" refers to instructions that recommend taking breaks at appropriate times based on the worker's fatigue and stress levels, with the aim of maintaining health and improving work efficiency.

[0418] This invention is a system that uses an emotional engine to support factory workers. A specific embodiment is described below.

[0419] Hardware and software to be used

[0420] This system uses the following hardware and software:

[0421] Hardware:

[0422] Smart glasses and smart device cameras

[0423] Factory robot (equipped with an emotional engine)

[0424] High-performance camera (for frame capture)

[0425] software:

[0426] OpenCV (image processing)

[0427] Dlib (face detection)

[0428] EmotionRecognitionModel

[0429] Server software (data management and analysis)

[0430] Program Processing Overview

[0431] The server provides a system for recognizing and analyzing workers' emotions in real time. This system includes the following key steps:

[0432] 1. Collection and analysis of sentiment data:

[0433] Camera footage of the worker is acquired, and the worker's face is detected using facial recognition technology (Dlib). Next, emotions are analyzed using an EmotionRecognitionModel. This model is pre-trained and identifies the emotions the worker is experiencing (e.g., stress, fatigue, etc.).

[0434] 2. Providing individually optimized work instructions:

[0435] Based on the analyzed emotional data, the server generates appropriate advice and work instructions according to the worker's state. For example, if a worker is feeling stressed, it can provide a message recommending that the worker take a break.

[0436] 3. Uploading test results from educational devices:

[0437] Workers use smart devices to input and upload their daily work plans and progress to an app. The server stores the data in storage and prepares it for later analysis.

[0438] Specific example

[0439] As a concrete example, consider a scenario where factory line workers wear smart glasses, and camera footage is transmitted to a server. The server's emotion engine analyzes the worker's facial expressions in real time, and if signs of stress are detected, it automatically provides advice on taking a break. Data on work status is also collected and used to optimize the next work instructions.

[0440] Example of a prompt

[0441] The following are examples of prompts to input into the generating AI model.

[0442] "Develop a system to analyze the emotions of factory line workers. It should recognize workers' facial expressions in real time and provide advice, such as recommending a break, if the worker is experiencing stress. Worker emotion data should be collected using cameras and analyzed using an emotion recognition model. This should include specific break advice and stress reduction methods."

[0443] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0444] Step 1:

[0445] The user wears smart glasses or a smart device and uses its camera to capture video of the work scene in real time. The camera footage is captured by a local device and transferred to the next step. The input is camera footage, and the output is real-time video data. Specifically, the device's camera is activated and continuously captures video data.

[0446] Step 2:

[0447] The terminal transfers the captured camera footage to the server. The device compresses the captured video data and sends it to the server over the network. The input is real-time video data, and the output is the data transferred to the server. Specifically, the process involves compressing the video data and transferring it over the network.

[0448] Step 3:

[0449] The server stores the received video data in storage for analysis and uses image processing techniques to detect the worker's face. Specifically, it extracts face regions from video frames using OpenCV or Dlib. The input is the transmitted video data, and the output is the result of the worker's face detection. The specific operations include reading video frames and applying face recognition algorithms.

[0450] Step 4:

[0451] The server uses an emotion recognition model (EmotionRecognitionModel) based on face detection results to identify the worker's emotions. The emotion recognition model is pre-trained, accepts face images as input data, and outputs an estimated emotion. The input is the face detection result, and the output is the emotion analysis result. Specifically, the operation involves inputting face images into the model and executing an estimation algorithm to classify emotions.

[0452] Step 5:

[0453] The server generates appropriate advice and work instructions for the worker based on the emotion analysis results. If stress is detected, it generates a message recommending that the worker take a break. The input is the emotion analysis results, and the output is an advice message. Specifically, it selects the appropriate advice based on the emotion analysis results and generates a message.

[0454] Step 6:

[0455] The server forwards the generated advice message to the terminal and displays it to the worker. The terminal receives the message and presents it to the user visually or audibly. The input is the advice message, and the output is the display to the user. Specific operations include receiving, decoding, and outputting the message to a display device.

[0456] Step 7:

[0457] The user acts according to the advice displayed on the device. For example, they might take a break or change their work procedure. The input is the advice message, and the output is the user's action. Specific actions include the user's decisions and actions based on the displayed information.

[0458] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0459] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0460] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0461] [Second Embodiment]

[0462] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0463] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0464] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0465] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0466] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0467] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0468] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0469] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0470] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0471] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0472] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0473] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0474] This invention relates to a system that uses educational devices to analyze learners' test results and provides individually optimized homework. This system can be specifically implemented as follows:

[0475] Upload test results

[0476] User:

[0477] Learners open a dedicated app on their educational device (e.g., a tablet or smartphone) and upload their test results.

[0478] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[0479] Terminal:

[0480] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[0481] The file is sent to the server.

[0482] server:

[0483] Check the received file and double-check that it is not in an invalid format.

[0484] OCR technology is used to extract text data from a file and save it to temporary storage.

[0485] Analysis of test results and homework generation

[0486] server:

[0487] Move the text data from temporary storage to the database and save it.

[0488] Text data stored in a database is input into a machine learning model, and the learner's response patterns are analyzed.

[0489] An algorithm is executed that identifies the learner's strengths and weaknesses and generates customized homework assignments.

[0490] The generated homework is provided to learning-related devices.

[0491] User:

[0492] Learners review the generated homework on the app and send correction instructions to the server as needed.

[0493] Download and print the corrected homework, or start answering it directly within the app.

[0494] Learning at your own pace

[0495] User:

[0496] Students complete their homework and answer questions at their own pace.

[0497] Once you have finished answering, press the submit button to send your answer to the server.

[0498] Terminal:

[0499] The answer data is temporarily stored and prepared for transmission to the server.

[0500] Send the answer data to the server.

[0501] server:

[0502] The received answer data is analyzed and stored in a database.

[0503] Update learning progress information and recommend the next learning content the learner needs.

[0504] Specific example

[0505] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue. This system allows learners to always receive optimal learning content tailored to their level of understanding, enabling effective learning.

[0506] The following describes the processing flow.

[0507] Step 1: Upload test results

[0508] User:

[0509] Open the dedicated app and proceed to the screen where you upload your test results.

[0510] Click the "Select File" button and choose the test result file (PDF or image) from your device.

[0511] Press the "Upload" button.

[0512] Step 2: Upload Process

[0513] Terminal:

[0514] Check the format of the selected file and verify that it is a supported format (PDF or image).

[0515] The file is temporarily saved to storage and prepared for transmission to the server.

[0516] Send the file to the server.

[0517] server:

[0518] Check the received file and double-check that it is not in an invalid format.

[0519] The system sends a file to an OCR (Optical Character Recognition) system and extracts text data from the file.

[0520] The extracted text data is saved to temporary storage.

[0521] Step 3: Save text data

[0522] server:

[0523] Move text data stored in temporary storage to the database and save it permanently.

[0524] Step 4: Data Analysis

[0525] server:

[0526] Text data is retrieved from a database and input into a machine learning model.

[0527] Machine learning models are used to analyze test results and identify learners' strengths and weaknesses.

[0528] Based on the analysis results, the system generates homework assignments optimized for each learner.

[0529] Step 5: Homework Generation

[0530] server:

[0531] Automatically generates homework assignments that take into account the student's strengths and weaknesses.

[0532] The generated homework assignment sets are saved in a database and reflected in the learner's progress.

[0533] Step 6: Homework Distribution

[0534] User:

[0535] View a preview of the homework generated through the app.

[0536] If necessary, send correction instructions to the server.

[0537] After confirmation, download and print the homework, or start answering directly within the app.

[0538] Step 7: Answers to homework

[0539] User:

[0540] Students complete their homework at their own pace.

[0541] Once you have finished answering, press the "Submit" button to send your answer to the server.

[0542] Terminal:

[0543] The answer data is temporarily stored and prepared for transmission to the server.

[0544] Send the answer data to the server.

[0545] Step 8: Analyze and save the solution

[0546] server:

[0547] Review and analyze the received answer data.

[0548] The answer data is saved to the database, and the learner's progress information is updated.

[0549] Based on the learner's progress and answer results, the system recommends the next learning content they should proceed to.

[0550] This process ensures that learners always receive optimal learning content based on their learning progress and understanding, allowing them to continue learning effectively.

[0551] (Example 1)

[0552] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0553] Traditional education systems have struggled to provide appropriate learning content based on each learner's individual abilities and level of understanding. This made it difficult for learners to effectively overcome their weaknesses and prevented them from receiving appropriate learning content tailored to their progress. Furthermore, there was a lack of efficient methods for analyzing which areas of weakness existed.

[0554] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0555] In this invention, the server includes means for inspecting learning evaluation results and extracting textual information, means for analyzing the learner's weaknesses and strengths based on the extracted textual information, and means for providing individualized learning tasks based on the analysis results. This makes it possible to provide learning content optimized for each learner and to support them in efficiently overcoming their areas of weakness.

[0556] "Educational devices" refer to devices used by learners for educational purposes, including, for example, tablets, smartphones, and PCs.

[0557] "Learning assessment results" refer to data showing the results of tests and assignments completed by learners, and are uploaded as PDF or image files.

[0558] "Textual information" refers to text data extracted using OCR technology, obtained from uploaded learning evaluation results.

[0559] "Areas of weakness" refers to information that indicates the subjects or types of problems that learners find difficult, and this is determined through analysis of test results.

[0560] "Strengths" refer to information that indicates the areas and types of problems a learner excels at, and this is determined through analysis of test results.

[0561] "Individualized learning assignments" refer to homework or practice problems optimized for specific learners based on analysis results.

[0562] "Information storage device" refers to hardware or software that functions as data storage, including servers and cloud storage.

[0563] "Optical character recognition technology" is a technology that extracts text information from images and PDFs, and uses software such as Tesseract OCR.

[0564] A "machine learning model" is an algorithm that uses AI technology to perform data analysis and prediction, and refers to models that use frameworks such as TensorFlow.

[0565] "Educational content" is a term that describes the content of learning materials and assignments provided to learners, including, for example, textbooks, videos, and practice problems.

[0566] Modes for carrying out the invention

[0567] This invention relates to a system that uses educational equipment to analyze learners' test results and provides individually optimized learning tasks. In this system, the user, terminal, and server each play important roles.

[0568] Hardware and software usage

[0569] This system utilizes tablets, smartphones, or PCs as educational devices. This allows learners to easily upload test results. The server-side uses a high-performance database (e.g., MySQL) and machine learning models (e.g., TensorFlow) to analyze learner data and generate individualized learning assignments. OCR technology (e.g., Tesseract OCR) is used for text data extraction.

[0570] Data processing and data calculation

[0571] 1. User Operation: Learners upload their learning assessment results from educational devices using a dedicated app. The uploaded files are often in PDF or image format.

[0572] 2. Terminal operation: The system checks the format of the uploaded file and temporarily saves it to storage. Next, it calculates a checksum to verify data integrity and prepares to send the file to the server.

[0573] 3. Server operation: Check the received files and recheck for any invalid formats. Use OCR technology to extract character information from the files. This converts the learning evaluation results into text data.

[0574] 4. Database Use: The extracted text data is stored in a database. The stored data will later be used to analyze it using a machine learning model.

[0575] 5. Data Analysis: The server inputs the stored text data into a machine learning model. This identifies the learner's strengths and weaknesses. Based on the analysis results, individual learning tasks are generated.

[0576] 6. Assignment Provision: The generated learning assignments are provided again to the educational device. Learners can check their homework through a dedicated app and make corrections as needed.

[0577] 7. Recording progress: The server records the learner's progress on assignments and saves it in a database. Based on this information, it recommends the next necessary learning content.

[0578] Specific examples and prompt statements

[0579] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates a task specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the task and sends the answer back to the server. The server analyzes the answer and, upon confirming that A's understanding of multiplication problems has deepened, suggests long division as the next learning topic. In this way, learner A can progress through their learning with appropriate content and timing.

[0580] Example of a prompt:

[0581] "Please describe the specific processing steps of a system that allows learners to upload their math test results, analyzes that data, and provides them with the most suitable homework."

[0582] This prompt prompts the generative AI model to explain how the system will process the learner's test results and provide the most appropriate learning content.

[0583] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0584] Step 1:

[0585] User: Learners use educational devices (e.g., tablets, smartphones) to launch a dedicated app and upload their test results. Input is a test result file in PDF or image format. Output is the transmission of these files to the device.

[0586] Step 2:

[0587] Terminal: Verify that the uploaded file format is correct. Specifically, analyze the file header information to verify that it is a PDF or image file. The input is the file uploaded by the user in step 1. The output is the file stored in temporary storage.

[0588] Step 3:

[0589] Terminal: Saves the verified file to temporary storage and calculates its checksum. After calculation, it verifies data integrity and prepares it for transmission to the server. Input is a verified file. Output is a file ready for transmission to the server.

[0590] Step 4:

[0591] Server: The server re-examines the received file and checks for any formatting errors. Then, it uses OCR technology (e.g., Tesseract OCR) to extract text information from the file. The input is the file sent from the terminal. The output is the extracted text data.

[0592] Step 5:

[0593] Server: Stores the text data extracted by OCR in temporary storage. Then, saves the text data to a database (e.g., MySQL). Input is the text data extracted by OCR. Output is the text data stored in the database.

[0594] Step 6:

[0595] Server: Inputs text data stored in a database into a machine learning model (e.g., TensorFlow) to analyze the learner's strengths and weaknesses. The input is text data stored in a database. The output is the analysis results regarding the learner's strengths and weaknesses.

[0596] Step 7:

[0597] Server: Generates individual learning tasks based on analysis results. For example, for a learner who struggles with "carrying over in multiplication," it generates homework specifically tailored to that problem. The input is the learner's analysis results. The output is the generated learning task.

[0598] Step 8:

[0599] Server: Sends the generated learning tasks to educational devices. Input is the generated learning tasks. Output is the tasks sent to the educational devices.

[0600] Step 9:

[0601] User: Learners use a dedicated app to review generated homework and provide correction instructions as needed. Input is the assignment sent from the server. Output is correction instructions (if any).

[0602] Step 10:

[0603] User: Learners solve generated learning tasks and submit their answers to the server via a dedicated app. The input is the completed task. The output is the answer data submitted to the server.

[0604] Step 11:

[0605] Server: Analyzes received answer data and stores it in a database. Based on the analysis results, it recommends the next learning content. Input is the learner's answer data. Output is the next recommended learning content.

[0606] (Application Example 1)

[0607] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0608] Conventional learning support systems using educational devices struggle to provide optimal homework tailored to each learner's individual weaknesses. Furthermore, the process of learners uploading test results and receiving automatically customized homework requires efficient and accurate information analysis and delivery. Additionally, flexibility is needed to allow learners to monitor their progress and learning outcomes and move on to the next learning step. This system aims to solve these challenges and provide a system that enables learners to progress effectively and efficiently.

[0609] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0610] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, and means for automatically generating homework corresponding to a specific theme from the learner's test results and providing it through a content distribution application. This makes it possible to provide optimal homework that meets the individual needs of the learner.

[0611] "Educational devices" is a general term for electronic devices used to run learning-related applications, such as tablets, smartphones, and computers.

[0612] "Means for uploading test results" refers to a function that allows learners to send test results to a server using educational devices.

[0613] "Methods for analyzing test results and extracting text data" refers to a function that analyzes test results received on a server and extracts them as text data using OCR technology or similar methods.

[0614] "Methods for analyzing learners' strengths and weaknesses" refers to a function that analyzes learners' answer patterns based on text data from test results to identify areas of strength and weakness.

[0615] "Means for generating individualized homework" refers to a function that automatically creates homework optimized for a particular learner based on the results of an analysis of that learner.

[0616] "Means of providing to learning-related devices" refers to a function that sends homework generated on the server to learners' educational devices, making it accessible to the learners.

[0617] "Means for recording progress and saving it to data storage" refers to a function that records the process by which learners complete their homework and saves that data to storage on a server.

[0618] The "means for recommending the next learning content" refer to a function that recommends what the learner should study next, based on their saved progress and analytical data.

[0619] "A means of automatically generating homework corresponding to a specific theme and providing it through a content distribution application" refers to a function that creates homework based on theme-specific analytical information obtained from test results and provides it to learners using a content distribution service.

[0620] This invention is a system that uses educational devices to analyze learners' test results and provide individually optimized homework. This system functions through the cooperation of a server, terminals, and users.

[0621] The server provides a means for users to upload test results from educational devices (e.g., tablets and smartphones). Users can take photos or scan test results and send them to the server via their device in image or PDF format. This allows users to easily provide test results in digital format.

[0622] Next, the server analyzes the test results. Specifically, it uses OCR technology (e.g., Tesseract OCR) to extract text data from images and PDF files. This text data is temporarily stored and then transferred to a database. The server inputs this data into a machine learning model to automatically analyze the learner's strengths and weaknesses. For example, if the analysis reveals that the learner struggles with "carrying over in multiplication," the server uses this information to generate personalized homework.

[0623] The generated homework is provided to educational devices. Users can review the homework on their devices and make corrections as needed. While the user works on the provided homework, the device records their progress and sends it to the server. The server stores this information in a database and recommends the learning content the learner needs next.

[0624] Specifically, the server is built using the Flask framework, and Tesseract OCR is used for OCR technology. PIL (Pillow) is used for image processing. These technologies enable the efficient and accurate conversion of test results into digital data for analysis and storage.

[0625] Specific example

[0626] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server uses OCR technology to convert the received image into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue.

[0627] Example of a prompt

[0628] "Analyze the test results and generate homework specifically tailored to your weaknesses (e.g., carrying over in multiplication)."

[0629] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0630] Step 1:

[0631] Users upload test results using educational devices.

[0632] Specifically, learners take a picture of their test results with their smartphone camera, select an image or PDF file format through the application, and press the upload button.

[0633] Input: Image or PDF file of test results

[0634] Output: Sending files to the server

[0635] Step 2:

[0636] The terminal prepares to send the test result file to the server.

[0637] The device checks the uploaded file format, and if it is a supported format, it saves the file to temporary storage and prepares it for transfer to the server.

[0638] Input: Uploaded test result file

[0639] Output: Files saved to temporary storage

[0640] Step 3:

[0641] The server receives the test results file and extracts the text data.

[0642] The server checks the received file and uses OCR technology (e.g., Tesseract OCR) to extract text data from the image or PDF. The extracted text data is temporarily stored.

[0643] Input: Image or PDF file of test results

[0644] Output: Extracted text data

[0645] Step 4:

[0646] The server analyzes the text data.

[0647] The extracted text data is stored in a database and then input into a machine learning model. The server analyzes the learner's response patterns to identify their weak and strong areas.

[0648] Input: Extracted text data

[0649] Output: Analysis results (weaknesses and strengths)

[0650] Step 5:

[0651] The server generates individual homework assignments.

[0652] Based on the analysis results, the server automatically generates homework tailored to the learner's areas of difficulty. For example, if a learner struggles with "carrying over in multiplication," the server will create problems specifically focused on that topic.

[0653] Input: Analysis results (weaknesses and strengths)

[0654] Output: Generated homework

[0655] Step 6:

[0656] The server provides the generated homework to learning-related devices.

[0657] The server sends the generated homework to the user's educational device. The user can receive the provided homework and view it within the application.

[0658] Input: Generated homework

[0659] Output: Providing homework to educational devices

[0660] Step 7:

[0661] The user works on the homework assigned to them.

[0662] The user begins solving homework within the application. Progress and answer results are recorded on the device.

[0663] Input: Provided homework

[0664] Output: Progress and answer results

[0665] Step 8:

[0666] The device sends the progress and answer results to the server.

[0667] The device temporarily stores the user's answers and prepares to send them to the server. When the send button is pressed, the device sends the answer data to the server.

[0668] Input: Progress and answer results

[0669] Output: Sending data to the server

[0670] Step 9:

[0671] The server analyzes the received data and recommends the next learning step.

[0672] The server analyzes the received progress and answers, updates the learner's understanding, and recommends the next necessary learning content.

[0673] Input: Progress and answer results

[0674] Output: Recommendations for the following learning content

[0675] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0676] This invention is a system that combines an emotion engine with educational devices, analyzes learners' test results, provides individually optimized homework, and recognizes learners' emotions to improve learning efficiency. This system can be implemented as follows.

[0677] Upload test results

[0678] User:

[0679] Learners open a dedicated app on their educational device (such as a tablet or smartphone) and upload their test results.

[0680] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[0681] Terminal:

[0682] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[0683] The file is sent to the server.

[0684] Extracting and saving text data

[0685] server:

[0686] Check the received file and double-check that it is not in an invalid format.

[0687] OCR technology is used to extract text data from a file and save it to temporary storage.

[0688] Move text data stored in temporary storage to the database and save it permanently.

[0689] Data analysis and homework generation

[0690] server:

[0691] Text data is retrieved from a database and input into a machine learning model.

[0692] A machine learning model analyzes the test results to identify the learner's strengths and weaknesses.

[0693] Based on the analysis results, the system generates homework assignments optimized for each learner.

[0694] The system automatically generates homework assignments that take into account each student's strengths and weaknesses, and saves them in a database.

[0695] Using an Emotion Engine

[0696] server:

[0697] An emotion engine is used to collect emotional data in real time while learners are using educational devices.

[0698] Emotional data is obtained by analyzing the learner's facial expressions, voice tone, and behavioral patterns.

[0699] Based on the acquired emotional data, the difficulty and content of homework assignments will be appropriately adjusted.

[0700] Homework distribution and feedback

[0701] User:

[0702] Learners review the generated homework on the app and send correction instructions to the server as needed.

[0703] After confirmation, download and print the homework, or start answering directly within the app.

[0704] Terminal:

[0705] The learner's progress and answer data are temporarily saved and prepared to be sent to the server.

[0706] After completing your answer, press the submit button to send your answer to the server.

[0707] server:

[0708] The received answer data is analyzed and stored in a database.

[0709] Update learning progress information and recommend the next learning content to proceed with.

[0710] Based on user emotional data recognized by the emotion engine, feedback is provided to improve learner motivation. Specifically, this includes sending encouraging messages when learners are feeling stressed, and recommending breaks when concentration is low.

[0711] Specific example

[0712] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that B tends to struggle with division problems. Based on this, the server generates homework specifically focused on division and provides it to B's device. Furthermore, while B is working on the homework, the emotion engine recognizes B's facial expressions, and if it determines that B is experiencing stress, it displays advice and encouraging messages to reduce stress. B can receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[0713] The following describes the processing flow.

[0714] Step 1: Upload test results

[0715] User:

[0716] Learners open a dedicated app on their educational device (e.g., a tablet or smartphone) and proceed to a screen where they upload their test results.

[0717] Click the "Select File" button and choose the test result file (PDF or image) from your device.

[0718] Press the "Upload" button.

[0719] Step 2: Upload Process

[0720] Terminal:

[0721] Verify the selected file format (PDF or image) and check that it is a supported format.

[0722] The file is temporarily saved to storage and prepared for transfer to the server.

[0723] Send the file to the server.

[0724] server:

[0725] Check the received file and double-check that it is not in an invalid format.

[0726] The system sends a file to an OCR (Optical Character Recognition) system and extracts text data from the file.

[0727] The extracted text data is saved to temporary storage.

[0728] Step 3: Save text data

[0729] server:

[0730] Move text data stored in temporary storage to the database and save it permanently.

[0731] Step 4: Data Analysis

[0732] server:

[0733] Text data is retrieved from a database and input into a machine learning model.

[0734] The machine learning model analyzes the test results to identify the learner's strengths and weaknesses.

[0735] Based on the analysis results, the system generates homework assignments optimized for each learner.

[0736] Step 5: Homework Generation

[0737] server:

[0738] The system automatically generates homework assignments that take into account the learner's strengths and weaknesses, and saves them in a database.

[0739] Step 6: Analysis using the emotion engine

[0740] server:

[0741] An emotion engine is used to collect real-time emotional data from learners using educational devices.

[0742] Emotional data is acquired by analyzing the learner's facial expressions, voice tone, behavioral patterns, and other factors.

[0743] Based on the acquired emotional data, the difficulty level of homework and the feedback are adjusted.

[0744] Step 7: Homework Distribution

[0745] User:

[0746] Learners can view a preview of the homework generated through the app.

[0747] Send correction instructions to the server as needed.

[0748] After confirmation, download and print the homework, or start answering directly within the app.

[0749] Step 8: Answers to homework

[0750] User:

[0751] Students complete their homework at their own pace.

[0752] Once you have finished answering, press the "Submit" button to send your answer to the server.

[0753] Terminal:

[0754] The learner's answer data is temporarily stored and prepared for transmission to the server.

[0755] Send the answer data to the server.

[0756] Step 9: Analyze and save the solution

[0757] server:

[0758] Review and analyze the received answer data.

[0759] The answer data is saved to the database, and the learner's progress information is updated.

[0760] Based on user emotion data recognized by the emotion engine, feedback is provided to improve learner motivation.

[0761] Specific example

[0762] Learner C takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that C has difficulty with "division of fractions." Based on this, the server generates homework specifically focused on division of fractions and provides it to C's device.

[0763] Furthermore, while C is working on homework, the emotion engine recognizes C's facial expressions and, if it determines that C is experiencing stress, displays advice and encouraging messages to help reduce stress. C can then receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[0764] (Example 2)

[0765] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0766] Traditional education systems have struggled to efficiently identify specific areas of difficulty for learners and provide individually optimized homework based on those areas. Furthermore, because learning progresses without considering the learner's emotional state, learners may experience stress or lack concentration. This raises concerns about decreased learning effectiveness and reduced motivation. Additionally, the cumbersome process of uploading test results and the lack of real-time monitoring of learners' progress made efficient feedback difficult. Moreover, homework was not adjusted based on the learner's emotional state, resulting in ineffective learning support.

[0767] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0768] In this invention, the server includes means for uploading test results from educational equipment, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational equipment, means for recording the progress of the homework and storing it in a data storage device, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing emotional data in real time, and means for adjusting the difficulty and content of the homework based on the emotional data. This makes it possible to efficiently identify the learner's weaknesses and provide individually optimized homework. Furthermore, by understanding the learner's emotional state in real time and adjusting the difficulty and content of the homework based on it, it is possible to reduce the learner's stress and maintain their concentration. With this system, learners can receive effective learning support, and improvements in learning effectiveness and motivation can be expected.

[0769] "Educational equipment" refers to devices used by learners to conduct learning activities, and specifically includes tablets, smartphones, and laptop computers.

[0770] "Test results" refer to data showing the answers and scores of students when they take a test, and are recorded in formats such as PDF or image.

[0771] A "server" is a computer system used to process data operations over a network, including data storage, analysis, and distribution.

[0772] "OCR technology" is an abbreviation for Optical Character Recognition technology, which is a technology that reads character data from image files and other sources and converts it into text data.

[0773] "Text data" refers to data in a string format that can be electronically recognized using OCR technology or other conversion methods.

[0774] A "machine learning model" is a model that builds algorithms based on large amounts of data and automatically performs specific tasks by learning patterns and rules from that data.

[0775] "Individualized homework" refers to learning tasks optimized for each learner's learning situation and abilities, and is specifically designed to improve areas of weakness.

[0776] A "data storage device" is a device that includes hardware and software used to store and manage data for long periods of time.

[0777] "Emotional data" refers to data that indicates a learner's emotional state, obtained by analyzing their facial expressions, voice tone, behavioral patterns, and other factors.

[0778] "Real-time" refers to the immediate processing and reflection of events currently in progress, meaning that specific data or interactions are processed instantly without delay.

[0779] "Analyzing" means processing and evaluating data using various techniques in order to find specific patterns or trends.

[0780] This invention is a system that combines an emotion engine with educational equipment, analyzes learners' test results, and provides individually optimized homework. Furthermore, it is characterized by its ability to recognize the learner's emotional state in real time and make adjustments to improve learning efficiency. This system can be implemented specifically as follows.

[0781] Hardware and software configuration

[0782] Educational devices include tablets, smartphones, and laptops. These devices have dedicated apps installed, which learners can use to upload test results and download homework.

[0783] The server is a central management system that receives and analyzes data transmitted from these educational devices, and further collects and analyzes emotional data using an emotion engine. Specifically, the following software and technologies are used.

[0784] 1. OCR technology (e.g., Tesseract OCR): Used to extract text data from image data of test results.

[0785] 2. Machine learning models (e.g., TensorFlow, PyTorch): These are used to identify the learner's strengths and weaknesses based on the acquired text data.

[0786] 3. Emotion engine (e.g., Microsoft Azure Face API): Used to collect and analyze emotion data in real time from the learner's facial expressions and voice tone.

[0787] 4. Data storage devices (e.g., MySQL, PostgreSQL): Used to permanently store analytical data, homework data, sentiment data, etc.

[0788] Specific example

[0789] The following shows specific examples of how the system according to the present invention can be used.

[0790] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads them through a dedicated app. The device checks the test results, saves them to temporary storage, and then sends them to the server. The server checks the received image data and uses Tesseract OCR to convert the answers into text data.

[0791] Next, the server inputs the converted text data into a machine learning model and analyzes the test results. The analysis identifies that B tends to struggle with division problems. Based on this, the server uses a generative AI model to generate homework specifically focused on division. The following prompts are used during the generation process.

[0792] Example of a prompt:

[0793] "Please generate five homework problems related to division, a topic that learners often struggle with. Set the difficulty level of each problem to medium."

[0794] The generated homework assignments are stored in a database and provided to B's smartphone. While B is working on the assignments, an emotion engine recognizes B's facial expressions and collects emotional data in real time. For example, if the system determines that B is stressed, it displays advice and encouraging messages to help reduce stress.

[0795] B can accept this advice and proceed with learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in effective learning.

[0796] Thus, by combining educational equipment and an emotion engine, the present invention can simultaneously provide individually optimized homework and learning support tailored to the learner's emotional state. This system is expected to improve learning effectiveness and enhance learner motivation.

[0797] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0798] Step 1: Upload test results

[0799] User: The learner launches the dedicated app for the educational device and selects the "Upload Test Results" function. They either take a picture of the test results with the device's camera or select an existing PDF / image file and press the upload button.

[0800] Input: Image data or PDF file of the captured test results

[0801] Output: Upload of recorded image data or PDF file

[0802] Specific operation: The user takes a test result with the camera or selects an existing file and presses the upload button.

[0803] Terminal: The terminal verifies the file format selected by the user and saves it to temporary storage. It then prepares the saved file to send to the server and sends the file to the server.

[0804] Input: Uploaded image data or PDF file

[0805] Output: Image data or PDF file transferred to the server

[0806] Specific actions: Check file format, temporarily save file, send file to server

[0807] Step 2: Extract and save text data

[0808] Server: The server checks the received file and re-verifies that it is not in an invalid format. Then, it uses Tesseract OCR to extract text data from the file. After saving it to temporary storage, it moves it to the database for permanent storage.

[0809] Input: Image data or PDF file transferred to the server

[0810] Output: Permanently saved text data

[0811] Specific actions: Reconfirm file format, extract text data using OCR technology, save to temporary storage, move text data to database.

[0812] Step 3: Data Analysis and Homework Generation

[0813] Server: The server retrieves text data from the database and inputs it into a machine learning model. The machine learning model analyzes the test results and identifies areas of weakness and strength. Based on the analysis results, it generates homework using a generative AI model. It inputs prompts into the generative AI model, generates a set of homework problems, and saves them to the database.

[0814] Input: Text data stored in the database

[0815] Output: Homework assignment set saved in the database

[0816] Specific operations: Input text data into a machine learning model, obtain analysis results, input prompt sentences into an AI model, generate homework assignments, and save the assignments to a database.

[0817] Example prompt: "Generate 5 homework problems related to division, which is a difficult topic for learners. Set the difficulty level of each problem to medium."

[0818] Step 4: Utilizing the Emotional Engine

[0819] Server: The server uses an emotion engine to collect emotional data in real time while learners are using educational equipment. It analyzes facial expressions and voice tone to obtain emotional data and adjusts the difficulty and content of homework based on that data. The collected emotional data is stored in a database.

[0820] Input: Sentimental data collected in real time from educational equipment.

[0821] Output: Homework adjusted according to emotions, and emotional data stored in the database.

[0822] Specific actions: Analysis of facial expressions and voice tone, collection and storage of emotional data, adjustment of homework content.

[0823] Step 5: Homework distribution and feedback

[0824] User: Learners can view the generated homework in a dedicated app and begin working on it. Correction instructions can be sent to the server as needed, and homework can be downloaded and printed, or completed directly within the app.

[0825] Input: Homework confirmation and answer data from the dedicated app.

[0826] Output: Answer data and correction instructions sent to the server

[0827] Specific actions: Checking homework, sending correction instructions, entering answers.

[0828] Terminal: The terminal temporarily stores the learner's progress and answer data in storage and prepares to send it to the server. After completing the answer, it sends the answer data to the server.

[0829] Input: Learner progress and answer data

[0830] Output: Answer data sent to the server

[0831] Specific actions: Temporarily save progress and answer data, prepare to send to the server, send answer data.

[0832] Server: The server analyzes the received answer data and stores it in a database. It updates learning progress information and recommends the next learning content to proceed with. It provides feedback based on sentiment data recognized by the sentiment engine.

[0833] Input: Answer data sent to the server

[0834] Output: Analysis data and feedback stored in the database

[0835] Specific actions: Analysis and storage of answer data, updating of learning progress information, generation and provision of feedback.

[0836] The above outlines the specific processing steps for implementing the present invention. Through this process, learners can receive effective and personalized learning support.

[0837] (Application Example 2)

[0838] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0839] In factory production operations, worker fatigue and stress are major factors leading to decreased work efficiency and errors. While conventional automation systems monitor work content and progress, they lack the ability to respond in real time to consider the emotional state and stress levels of workers. Therefore, a system is needed that simultaneously optimizes worker health and work efficiency.

[0840] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0841] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing the worker's emotional data using an emotion engine, and means for providing the worker with individually optimized work instructions and break advice based on the analysis results. This makes it possible to monitor the worker's fatigue and stress in real time and maintain their health while improving work efficiency.

[0842] "Educational devices" refer to electronic devices and tools used in educational activities, and specifically include tablets, smartphones, and personal computers.

[0843] "Test results" refers to the performance data and answers of tests taken by learners, including those saved in PDF or image formats.

[0844] "Text data" refers to character information extracted from test results, which is processed using OCR technology, etc.

[0845] "Learner" refers to an individual who uses educational devices to learn, including those who are studying a specific curriculum or course.

[0846] "Individualized homework" refers to homework assignments that are generated individually based on each student's learning progress and level of understanding.

[0847] "Learning content" refers to educational materials and assignments that learners access through educational devices, and includes text, videos, and interactive questions.

[0848] An "emotion engine" refers to technologies for recognizing and analyzing the emotional state of learners and workers in real time, and includes facial recognition, voice analysis, and behavioral pattern analysis.

[0849] "Emotional data" refers to information related to the emotions of learners and workers acquired by the emotion engine, and includes data such as facial expressions, tone of voice, and movements.

[0850] "Worker" refers to an individual performing tasks in a factory or manufacturing site, including those assigned to specific production lines or tasks.

[0851] "Work instructions" refer to instructions that communicate specific work content and procedures to workers, and include information to ensure work efficiency and safety.

[0852] "Break advice" refers to instructions that recommend taking breaks at appropriate times based on the worker's fatigue and stress levels, with the aim of maintaining health and improving work efficiency.

[0853] This invention is a system that uses an emotional engine to support factory workers. A specific embodiment is described below.

[0854] Hardware and software to be used

[0855] This system uses the following hardware and software:

[0856] Hardware:

[0857] Smart glasses and smart device cameras

[0858] Factory robot (equipped with an emotional engine)

[0859] High-performance camera (for frame capture)

[0860] software:

[0861] OpenCV (image processing)

[0862] Dlib (face detection)

[0863] EmotionRecognitionModel

[0864] Server software (data management and analysis)

[0865] Program Processing Overview

[0866] The server provides a system for recognizing and analyzing workers' emotions in real time. This system includes the following key steps:

[0867] 1. Collection and analysis of sentiment data:

[0868] Camera footage of the worker is acquired, and the worker's face is detected using facial recognition technology (Dlib). Next, emotions are analyzed using an EmotionRecognitionModel. This model is pre-trained and identifies the emotions the worker is experiencing (e.g., stress, fatigue, etc.).

[0869] 2. Providing individually optimized work instructions:

[0870] Based on the analyzed emotional data, the server generates appropriate advice and work instructions according to the worker's state. For example, if a worker is feeling stressed, it can provide a message recommending that the worker take a break.

[0871] 3. Uploading test results from educational devices:

[0872] Workers use smart devices to input and upload their daily work plans and progress to an app. The server stores the data in storage and prepares it for later analysis.

[0873] Specific example

[0874] As a concrete example, consider a scenario where factory line workers wear smart glasses, and camera footage is transmitted to a server. The server's emotion engine analyzes the worker's facial expressions in real time, and if signs of stress are detected, it automatically provides advice on taking a break. Data on work status is also collected and used to optimize the next work instructions.

[0875] Example of a prompt

[0876] The following are examples of prompts to input into the generating AI model.

[0877] "Develop a system to analyze the emotions of factory line workers. It should recognize workers' facial expressions in real time and provide advice, such as recommending a break, if the worker is experiencing stress. Worker emotion data should be collected using cameras and analyzed using an emotion recognition model. This should include specific break advice and stress reduction methods."

[0878] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0879] Step 1:

[0880] The user wears smart glasses or a smart device and uses its camera to capture video of the work scene in real time. The camera footage is captured by a local device and transferred to the next step. The input is camera footage, and the output is real-time video data. Specifically, the device's camera is activated and continuously captures video data.

[0881] Step 2:

[0882] The terminal transfers the captured camera footage to the server. The device compresses the captured video data and sends it to the server over the network. The input is real-time video data, and the output is the data transferred to the server. Specifically, the process involves compressing the video data and transferring it over the network.

[0883] Step 3:

[0884] The server stores the received video data in storage for analysis and uses image processing techniques to detect the worker's face. Specifically, it extracts face regions from video frames using OpenCV or Dlib. The input is the transmitted video data, and the output is the result of the worker's face detection. The specific operations include reading video frames and applying face recognition algorithms.

[0885] Step 4:

[0886] The server uses an emotion recognition model (EmotionRecognitionModel) based on face detection results to identify the worker's emotions. The emotion recognition model is pre-trained, accepts face images as input data, and outputs an estimated emotion. The input is the face detection result, and the output is the emotion analysis result. Specifically, the operation involves inputting face images into the model and executing an estimation algorithm to classify emotions.

[0887] Step 5:

[0888] The server generates appropriate advice and work instructions for the worker based on the emotion analysis results. If stress is detected, it generates a message recommending that the worker take a break. The input is the emotion analysis results, and the output is an advice message. Specifically, it selects the appropriate advice based on the emotion analysis results and generates a message.

[0889] Step 6:

[0890] The server forwards the generated advice message to the terminal and displays it to the worker. The terminal receives the message and presents it to the user visually or audibly. The input is the advice message, and the output is the display to the user. Specific operations include receiving, decoding, and outputting the message to a display device.

[0891] Step 7:

[0892] The user acts according to the advice displayed on the device. For example, they might take a break or change their work procedure. The input is the advice message, and the output is the user's action. Specific actions include the user's decisions and actions based on the displayed information.

[0893] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0894] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0895] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0896] [Third Embodiment]

[0897] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0898] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0899] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0900] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0901] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0902] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0903] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0904] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0905] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0906] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0907] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0908] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0909] This invention relates to a system that uses educational devices to analyze learners' test results and provides individually optimized homework. This system can be specifically implemented as follows:

[0910] Upload test results

[0911] User:

[0912] Learners open a dedicated app on their educational device (e.g., a tablet or smartphone) and upload their test results.

[0913] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[0914] Terminal:

[0915] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[0916] The file is sent to the server.

[0917] server:

[0918] Check the received file and double-check that it is not in an invalid format.

[0919] OCR technology is used to extract text data from a file and save it to temporary storage.

[0920] Analysis of test results and homework generation

[0921] server:

[0922] Move the text data from temporary storage to the database and save it.

[0923] Text data stored in a database is input into a machine learning model, and the learner's response patterns are analyzed.

[0924] An algorithm is executed that identifies the learner's strengths and weaknesses and generates customized homework assignments.

[0925] The generated homework is provided to learning-related devices.

[0926] User:

[0927] Learners review the generated homework on the app and send correction instructions to the server as needed.

[0928] Download and print the corrected homework, or start answering it directly within the app.

[0929] Learning at your own pace

[0930] User:

[0931] Students complete their homework and answer questions at their own pace.

[0932] Once you have finished answering, press the submit button to send your answer to the server.

[0933] Terminal:

[0934] The answer data is temporarily stored and prepared for transmission to the server.

[0935] Send the answer data to the server.

[0936] server:

[0937] The received answer data is analyzed and stored in a database.

[0938] Update learning progress information and recommend the next learning content the learner needs.

[0939] Specific example

[0940] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue. This system allows learners to always receive optimal learning content tailored to their level of understanding, enabling effective learning.

[0941] The following describes the processing flow.

[0942] Step 1: Upload test results

[0943] User:

[0944] Open the dedicated app and proceed to the screen where you upload your test results.

[0945] Click the "Select File" button and choose the test result file (PDF or image) from your device.

[0946] Press the "Upload" button.

[0947] Step 2: Upload Process

[0948] Terminal:

[0949] Check the format of the selected file and verify that it is a supported format (PDF or image).

[0950] The file is temporarily saved to storage and prepared for transmission to the server.

[0951] Send the file to the server.

[0952] server:

[0953] Check the received file and double-check that it is not in an invalid format.

[0954] The system sends a file to an OCR (Optical Character Recognition) system and extracts text data from the file.

[0955] The extracted text data is saved to temporary storage.

[0956] Step 3: Save text data

[0957] server:

[0958] Move text data stored in temporary storage to the database and save it permanently.

[0959] Step 4: Data Analysis

[0960] server:

[0961] Text data is retrieved from a database and input into a machine learning model.

[0962] Machine learning models are used to analyze test results and identify learners' strengths and weaknesses.

[0963] Based on the analysis results, the system generates homework assignments optimized for each learner.

[0964] Step 5: Homework Generation

[0965] server:

[0966] Automatically generates homework assignments that take into account the student's strengths and weaknesses.

[0967] The generated homework assignment sets are saved in a database and reflected in the learner's progress.

[0968] Step 6: Homework Distribution

[0969] User:

[0970] View a preview of the homework generated through the app.

[0971] If necessary, send correction instructions to the server.

[0972] After confirmation, download and print the homework, or start answering directly within the app.

[0973] Step 7: Answers to homework

[0974] User:

[0975] Students complete their homework at their own pace.

[0976] Once you have finished answering, press the "Submit" button to send your answer to the server.

[0977] Terminal:

[0978] The answer data is temporarily stored and prepared for transmission to the server.

[0979] Send the answer data to the server.

[0980] Step 8: Analyze and save the solution

[0981] server:

[0982] Review and analyze the received answer data.

[0983] The answer data is saved to the database, and the learner's progress information is updated.

[0984] Based on the learner's progress and answer results, the system recommends the next learning content they should proceed to.

[0985] This process ensures that learners always receive optimal learning content based on their learning progress and understanding, allowing them to continue learning effectively.

[0986] (Example 1)

[0987] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0988] Traditional education systems have struggled to provide appropriate learning content based on each learner's individual abilities and level of understanding. This made it difficult for learners to effectively overcome their weaknesses and prevented them from receiving appropriate learning content tailored to their progress. Furthermore, there was a lack of efficient methods for analyzing which areas of weakness existed.

[0989] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0990] In this invention, the server includes means for inspecting learning evaluation results and extracting textual information, means for analyzing the learner's weaknesses and strengths based on the extracted textual information, and means for providing individualized learning tasks based on the analysis results. This makes it possible to provide learning content optimized for each learner and to support them in efficiently overcoming their areas of weakness.

[0991] "Educational devices" refer to devices used by learners for educational purposes, including, for example, tablets, smartphones, and PCs.

[0992] "Learning assessment results" refer to data showing the results of tests and assignments completed by learners, and are uploaded as PDF or image files.

[0993] "Textual information" refers to text data extracted using OCR technology, obtained from uploaded learning evaluation results.

[0994] "Areas of weakness" refers to information that indicates the subjects or types of problems that learners find difficult, and this is determined through analysis of test results.

[0995] "Strengths" refer to information that indicates the areas and types of problems a learner excels at, and this is determined through analysis of test results.

[0996] "Individualized learning assignments" refer to homework or practice problems optimized for specific learners based on analysis results.

[0997] "Information storage device" refers to hardware or software that functions as data storage, including servers and cloud storage.

[0998] "Optical character recognition technology" is a technology that extracts text information from images and PDFs, and uses software such as Tesseract OCR.

[0999] A "machine learning model" is an algorithm that uses AI technology to perform data analysis and prediction, and refers to models that use frameworks such as TensorFlow.

[1000] "Educational content" is a term that describes the content of learning materials and assignments provided to learners, including, for example, textbooks, videos, and practice problems.

[1001] Modes for carrying out the invention

[1002] This invention relates to a system that uses educational equipment to analyze learners' test results and provides individually optimized learning tasks. In this system, the user, terminal, and server each play important roles.

[1003] Hardware and software usage

[1004] This system utilizes tablets, smartphones, or PCs as educational devices. This allows learners to easily upload test results. The server-side uses a high-performance database (e.g., MySQL) and machine learning models (e.g., TensorFlow) to analyze learner data and generate individualized learning assignments. OCR technology (e.g., Tesseract OCR) is used for text data extraction.

[1005] Data processing and data calculation

[1006] 1. User Operation: Learners upload their learning assessment results from educational devices using a dedicated app. The uploaded files are often in PDF or image format.

[1007] 2. Terminal operation: The system checks the format of the uploaded file and temporarily saves it to storage. Next, it calculates a checksum to verify data integrity and prepares to send the file to the server.

[1008] 3. Server operation: Check the received files and recheck for any invalid formats. Use OCR technology to extract character information from the files. This converts the learning evaluation results into text data.

[1009] 4. Database Use: The extracted text data is stored in a database. The stored data will later be used to analyze it using a machine learning model.

[1010] 5. Data Analysis: The server inputs the stored text data into a machine learning model. This identifies the learner's strengths and weaknesses. Based on the analysis results, individual learning tasks are generated.

[1011] 6. Assignment Provision: The generated learning assignments are provided again to the educational device. Learners can check their homework through a dedicated app and make corrections as needed.

[1012] 7. Recording progress: The server records the learner's progress on assignments and saves it in a database. Based on this information, it recommends the next necessary learning content.

[1013] Specific examples and prompt statements

[1014] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates a task specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the task and sends the answer back to the server. The server analyzes the answer and, upon confirming that A's understanding of multiplication problems has deepened, suggests long division as the next learning topic. In this way, learner A can progress through their learning with appropriate content and timing.

[1015] Example of a prompt:

[1016] "Please describe the specific processing steps of a system that allows learners to upload their math test results, analyzes that data, and provides them with the most suitable homework."

[1017] This prompt prompts the generative AI model to explain how the system will process the learner's test results and provide the most appropriate learning content.

[1018] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1019] Step 1:

[1020] User: Learners use educational devices (e.g., tablets, smartphones) to launch a dedicated app and upload their test results. Input is a test result file in PDF or image format. Output is the transmission of these files to the device.

[1021] Step 2:

[1022] Terminal: Verify that the uploaded file format is correct. Specifically, analyze the file header information to verify that it is a PDF or image file. The input is the file uploaded by the user in step 1. The output is the file stored in temporary storage.

[1023] Step 3:

[1024] Terminal: Saves the verified file to temporary storage and calculates its checksum. After calculation, it verifies data integrity and prepares it for transmission to the server. Input is a verified file. Output is a file ready for transmission to the server.

[1025] Step 4:

[1026] Server: The server re-examines the received file and checks for any formatting errors. Then, it uses OCR technology (e.g., Tesseract OCR) to extract text information from the file. The input is the file sent from the terminal. The output is the extracted text data.

[1027] Step 5:

[1028] Server: Stores the text data extracted by OCR in temporary storage. Then, saves the text data to a database (e.g., MySQL). Input is the text data extracted by OCR. Output is the text data stored in the database.

[1029] Step 6:

[1030] Server: Inputs text data stored in a database into a machine learning model (e.g., TensorFlow) to analyze the learner's strengths and weaknesses. The input is text data stored in a database. The output is the analysis results regarding the learner's strengths and weaknesses.

[1031] Step 7:

[1032] Server: Generates individual learning tasks based on analysis results. For example, for a learner who struggles with "carrying over in multiplication," it generates homework specifically tailored to that problem. The input is the learner's analysis results. The output is the generated learning task.

[1033] Step 8:

[1034] Server: Sends the generated learning tasks to educational devices. Input is the generated learning tasks. Output is the tasks sent to the educational devices.

[1035] Step 9:

[1036] User: Learners use a dedicated app to review generated homework and provide correction instructions as needed. Input is the assignment sent from the server. Output is correction instructions (if any).

[1037] Step 10:

[1038] User: Learners solve generated learning tasks and submit their answers to the server via a dedicated app. The input is the completed task. The output is the answer data submitted to the server.

[1039] Step 11:

[1040] Server: Analyzes received answer data and stores it in a database. Based on the analysis results, it recommends the next learning content. Input is the learner's answer data. Output is the next recommended learning content.

[1041] (Application Example 1)

[1042] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1043] Conventional learning support systems using educational devices struggle to provide optimal homework tailored to each learner's individual weaknesses. Furthermore, the process of learners uploading test results and receiving automatically customized homework requires efficient and accurate information analysis and delivery. Additionally, flexibility is needed to allow learners to monitor their progress and learning outcomes and move on to the next learning step. This system aims to solve these challenges and provide a system that enables learners to progress effectively and efficiently.

[1044] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1045] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, and means for automatically generating homework corresponding to a specific theme from the learner's test results and providing it through a content distribution application. This makes it possible to provide optimal homework that meets the individual needs of the learner.

[1046] "Educational devices" is a general term for electronic devices used to run learning-related applications, such as tablets, smartphones, and computers.

[1047] "Means for uploading test results" refers to a function that allows learners to send test results to a server using educational devices.

[1048] "Methods for analyzing test results and extracting text data" refers to a function that analyzes test results received on a server and extracts them as text data using OCR technology or similar methods.

[1049] "Methods for analyzing learners' strengths and weaknesses" refers to a function that analyzes learners' answer patterns based on text data from test results to identify areas of strength and weakness.

[1050] "Means for generating individualized homework" refers to a function that automatically creates homework optimized for a particular learner based on the results of an analysis of that learner.

[1051] "Means of providing to learning-related devices" refers to a function that sends homework generated on the server to learners' educational devices, making it accessible to the learners.

[1052] "Means for recording progress and saving it to data storage" refers to a function that records the process by which learners complete their homework and saves that data to storage on a server.

[1053] The "means for recommending the next learning content" refer to a function that recommends what the learner should study next, based on their saved progress and analytical data.

[1054] "A means of automatically generating homework corresponding to a specific theme and providing it through a content distribution application" refers to a function that creates homework based on theme-specific analytical information obtained from test results and provides it to learners using a content distribution service.

[1055] This invention is a system that uses educational devices to analyze learners' test results and provide individually optimized homework. This system functions through the cooperation of a server, terminals, and users.

[1056] The server provides a means for users to upload test results from educational devices (e.g., tablets and smartphones). Users can take photos or scan test results and send them to the server via their device in image or PDF format. This allows users to easily provide test results in digital format.

[1057] Next, the server analyzes the test results. Specifically, it uses OCR technology (e.g., Tesseract OCR) to extract text data from images and PDF files. This text data is temporarily stored and then transferred to a database. The server inputs this data into a machine learning model to automatically analyze the learner's strengths and weaknesses. For example, if the analysis reveals that the learner struggles with "carrying over in multiplication," the server uses this information to generate personalized homework.

[1058] The generated homework is provided to educational devices. Users can review the homework on their devices and make corrections as needed. While the user works on the provided homework, the device records their progress and sends it to the server. The server stores this information in a database and recommends the learning content the learner needs next.

[1059] Specifically, the server is built using the Flask framework, and Tesseract OCR is used for OCR technology. PIL (Pillow) is used for image processing. These technologies enable the efficient and accurate conversion of test results into digital data for analysis and storage.

[1060] Specific example

[1061] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server uses OCR technology to convert the received image into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue.

[1062] Example of a prompt

[1063] "Analyze the test results and generate homework specifically tailored to your weaknesses (e.g., carrying over in multiplication)."

[1064] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1065] Step 1:

[1066] Users upload test results using educational devices.

[1067] Specifically, learners take a picture of their test results with their smartphone camera, select an image or PDF file format through the application, and press the upload button.

[1068] Input: Image or PDF file of test results

[1069] Output: Sending files to the server

[1070] Step 2:

[1071] The terminal prepares to send the test result file to the server.

[1072] The device checks the uploaded file format, and if it is a supported format, it saves the file to temporary storage and prepares it for transfer to the server.

[1073] Input: Uploaded test result file

[1074] Output: Files saved to temporary storage

[1075] Step 3:

[1076] The server receives the test results file and extracts the text data.

[1077] The server checks the received file and uses OCR technology (e.g., Tesseract OCR) to extract text data from the image or PDF. The extracted text data is temporarily stored.

[1078] Input: Image or PDF file of test results

[1079] Output: Extracted text data

[1080] Step 4:

[1081] The server analyzes the text data.

[1082] The extracted text data is stored in a database and then input into a machine learning model. The server analyzes the learner's response patterns to identify their weak and strong areas.

[1083] Input: Extracted text data

[1084] Output: Analysis results (weaknesses and strengths)

[1085] Step 5:

[1086] The server generates individual homework assignments.

[1087] Based on the analysis results, the server automatically generates homework tailored to the learner's areas of difficulty. For example, if a learner struggles with "carrying over in multiplication," the server will create problems specifically focused on that topic.

[1088] Input: Analysis results (weaknesses and strengths)

[1089] Output: Generated homework

[1090] Step 6:

[1091] The server provides the generated homework to learning-related devices.

[1092] The server sends the generated homework to the user's educational device. The user can receive the provided homework and view it within the application.

[1093] Input: Generated homework

[1094] Output: Providing homework to educational devices

[1095] Step 7:

[1096] The user works on the homework assigned to them.

[1097] The user begins solving homework within the application. Progress and answer results are recorded on the device.

[1098] Input: Provided homework

[1099] Output: Progress and answer results

[1100] Step 8:

[1101] The device sends the progress and answer results to the server.

[1102] The device temporarily stores the user's answers and prepares to send them to the server. When the send button is pressed, the device sends the answer data to the server.

[1103] Input: Progress and answer results

[1104] Output: Sending data to the server

[1105] Step 9:

[1106] The server analyzes the received data and recommends the next learning step.

[1107] The server analyzes the received progress and answers, updates the learner's understanding, and recommends the next necessary learning content.

[1108] Input: Progress and answer results

[1109] Output: Recommendations for the following learning content

[1110] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1111] This invention is a system that combines an emotion engine with educational devices, analyzes learners' test results, provides individually optimized homework, and recognizes learners' emotions to improve learning efficiency. This system can be implemented as follows.

[1112] Upload test results

[1113] User:

[1114] Learners open a dedicated app on their educational device (such as a tablet or smartphone) and upload their test results.

[1115] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[1116] Terminal:

[1117] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[1118] The file is sent to the server.

[1119] Extracting and saving text data

[1120] server:

[1121] Check the received file and double-check that it is not in an invalid format.

[1122] OCR technology is used to extract text data from a file and save it to temporary storage.

[1123] Move text data stored in temporary storage to the database and save it permanently.

[1124] Data analysis and homework generation

[1125] server:

[1126] Text data is retrieved from a database and input into a machine learning model.

[1127] A machine learning model analyzes the test results to identify the learner's strengths and weaknesses.

[1128] Based on the analysis results, the system generates homework assignments optimized for each learner.

[1129] The system automatically generates homework assignments that take into account each student's strengths and weaknesses, and saves them in a database.

[1130] Using an Emotion Engine

[1131] server:

[1132] An emotion engine is used to collect emotional data in real time while learners are using educational devices.

[1133] Emotional data is obtained by analyzing the learner's facial expressions, voice tone, and behavioral patterns.

[1134] Based on the acquired emotional data, the difficulty and content of homework assignments will be appropriately adjusted.

[1135] Homework distribution and feedback

[1136] User:

[1137] Learners review the generated homework on the app and send correction instructions to the server as needed.

[1138] After confirmation, download and print the homework, or start answering directly within the app.

[1139] Terminal:

[1140] The learner's progress and answer data are temporarily saved and prepared to be sent to the server.

[1141] After completing your answer, press the submit button to send your answer to the server.

[1142] server:

[1143] The received answer data is analyzed and stored in a database.

[1144] Update learning progress information and recommend the next learning content to proceed with.

[1145] Based on user emotional data recognized by the emotion engine, feedback is provided to improve learner motivation. Specifically, this includes sending encouraging messages when learners are feeling stressed, and recommending breaks when concentration is low.

[1146] Specific example

[1147] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that B tends to struggle with division problems. Based on this, the server generates homework specifically focused on division and provides it to B's device. Furthermore, while B is working on the homework, the emotion engine recognizes B's facial expressions, and if it determines that B is experiencing stress, it displays advice and encouraging messages to reduce stress. B can receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[1148] The following describes the processing flow.

[1149] Step 1: Upload test results

[1150] User:

[1151] Learners open a dedicated app on their educational device (e.g., a tablet or smartphone) and proceed to a screen where they upload their test results.

[1152] Click the "Select File" button and choose the test result file (PDF or image) from your device.

[1153] Press the "Upload" button.

[1154] Step 2: Upload Process

[1155] Terminal:

[1156] Verify the selected file format (PDF or image) and check that it is a supported format.

[1157] The file is temporarily saved to storage and prepared for transfer to the server.

[1158] Send the file to the server.

[1159] server:

[1160] Check the received file and double-check that it is not in an invalid format.

[1161] The system sends a file to an OCR (Optical Character Recognition) system and extracts text data from the file.

[1162] The extracted text data is saved to temporary storage.

[1163] Step 3: Save text data

[1164] server:

[1165] Move text data stored in temporary storage to the database and save it permanently.

[1166] Step 4: Data Analysis

[1167] server:

[1168] Text data is retrieved from a database and input into a machine learning model.

[1169] The machine learning model analyzes the test results to identify the learner's strengths and weaknesses.

[1170] Based on the analysis results, the system generates homework assignments optimized for each learner.

[1171] Step 5: Homework Generation

[1172] server:

[1173] The system automatically generates homework assignments that take into account the learner's strengths and weaknesses, and saves them in a database.

[1174] Step 6: Analysis using the emotion engine

[1175] server:

[1176] An emotion engine is used to collect real-time emotional data from learners using educational devices.

[1177] Emotional data is acquired by analyzing the learner's facial expressions, voice tone, behavioral patterns, and other factors.

[1178] Based on the acquired emotional data, the difficulty level of homework and the feedback are adjusted.

[1179] Step 7: Homework Distribution

[1180] User:

[1181] Learners can view a preview of the homework generated through the app.

[1182] Send correction instructions to the server as needed.

[1183] After confirmation, download and print the homework, or start answering directly within the app.

[1184] Step 8: Answers to homework

[1185] User:

[1186] Students complete their homework at their own pace.

[1187] Once you have finished answering, press the "Submit" button to send your answer to the server.

[1188] Terminal:

[1189] The learner's answer data is temporarily stored and prepared for transmission to the server.

[1190] Send the answer data to the server.

[1191] Step 9: Analyze and save the solution

[1192] server:

[1193] Review and analyze the received answer data.

[1194] The answer data is saved to the database, and the learner's progress information is updated.

[1195] Based on user emotion data recognized by the emotion engine, feedback is provided to improve learner motivation.

[1196] Specific example

[1197] Learner C takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that C has difficulty with "division of fractions." Based on this, the server generates homework specifically focused on division of fractions and provides it to C's device.

[1198] Furthermore, while C is working on homework, the emotion engine recognizes C's facial expressions and, if it determines that C is experiencing stress, displays advice and encouraging messages to help reduce stress. C can then receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[1199] (Example 2)

[1200] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1201] Traditional education systems have struggled to efficiently identify specific areas of difficulty for learners and provide individually optimized homework based on those areas. Furthermore, because learning progresses without considering the learner's emotional state, learners may experience stress or lack concentration. This raises concerns about decreased learning effectiveness and reduced motivation. Additionally, the cumbersome process of uploading test results and the lack of real-time monitoring of learners' progress made efficient feedback difficult. Moreover, homework was not adjusted based on the learner's emotional state, resulting in ineffective learning support.

[1202] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1203] In this invention, the server includes means for uploading test results from educational equipment, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational equipment, means for recording the progress of the homework and storing it in a data storage device, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing emotional data in real time, and means for adjusting the difficulty and content of the homework based on the emotional data. This makes it possible to efficiently identify the learner's weaknesses and provide individually optimized homework. Furthermore, by understanding the learner's emotional state in real time and adjusting the difficulty and content of the homework based on it, it is possible to reduce the learner's stress and maintain their concentration. With this system, learners can receive effective learning support, and improvements in learning effectiveness and motivation can be expected.

[1204] "Educational equipment" refers to devices used by learners to conduct learning activities, and specifically includes tablets, smartphones, and laptop computers.

[1205] "Test results" refer to data showing the answers and scores of students when they take a test, and are recorded in formats such as PDF or image.

[1206] A "server" is a computer system used to process data operations over a network, including data storage, analysis, and distribution.

[1207] "OCR technology" is an abbreviation for Optical Character Recognition technology, which is a technology that reads character data from image files and other sources and converts it into text data.

[1208] "Text data" refers to data in a string format that can be electronically recognized using OCR technology or other conversion methods.

[1209] A "machine learning model" is a model that builds algorithms based on large amounts of data and automatically performs specific tasks by learning patterns and rules from that data.

[1210] "Individualized homework" refers to learning tasks optimized for each learner's learning situation and abilities, and is specifically designed to improve areas of weakness.

[1211] A "data storage device" is a device that includes hardware and software used to store and manage data for long periods of time.

[1212] "Emotional data" refers to data that indicates a learner's emotional state, obtained by analyzing their facial expressions, voice tone, behavioral patterns, and other factors.

[1213] "Real-time" refers to the immediate processing and reflection of events currently in progress, meaning that specific data or interactions are processed instantly without delay.

[1214] "Analyzing" means processing and evaluating data using various techniques in order to find specific patterns or trends.

[1215] This invention is a system that combines an emotion engine with educational equipment, analyzes learners' test results, and provides individually optimized homework. Furthermore, it is characterized by its ability to recognize the learner's emotional state in real time and make adjustments to improve learning efficiency. This system can be implemented specifically as follows.

[1216] Hardware and software configuration

[1217] Educational devices include tablets, smartphones, and laptops. These devices have dedicated apps installed, which learners can use to upload test results and download homework.

[1218] The server is a central management system that receives and analyzes data transmitted from these educational devices, and further collects and analyzes emotional data using an emotion engine. Specifically, the following software and technologies are used.

[1219] 1. OCR technology (e.g., Tesseract OCR): Used to extract text data from image data of test results.

[1220] 2. Machine learning models (e.g., TensorFlow, PyTorch): These are used to identify the learner's strengths and weaknesses based on the acquired text data.

[1221] 3. Emotion engine (e.g., Microsoft Azure Face API): Used to collect and analyze emotion data in real time from the learner's facial expressions and voice tone.

[1222] 4. Data storage devices (e.g., MySQL, PostgreSQL): Used to permanently store analytical data, homework data, sentiment data, etc.

[1223] Specific example

[1224] The following shows specific examples of how the system according to the present invention can be used.

[1225] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads them through a dedicated app. The device checks the test results, saves them to temporary storage, and then sends them to the server. The server checks the received image data and uses Tesseract OCR to convert the answers into text data.

[1226] Next, the server inputs the converted text data into a machine learning model and analyzes the test results. The analysis identifies that B tends to struggle with division problems. Based on this, the server uses a generative AI model to generate homework specifically focused on division. The following prompts are used during the generation process.

[1227] Example of a prompt:

[1228] "Please generate five homework problems related to division, a topic that learners often struggle with. Set the difficulty level of each problem to medium."

[1229] The generated homework assignments are stored in a database and provided to B's smartphone. While B is working on the assignments, an emotion engine recognizes B's facial expressions and collects emotional data in real time. For example, if the system determines that B is stressed, it displays advice and encouraging messages to help reduce stress.

[1230] B can accept this advice and proceed with learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in effective learning.

[1231] Thus, by combining educational equipment and an emotion engine, the present invention can simultaneously provide individually optimized homework and learning support tailored to the learner's emotional state. This system is expected to improve learning effectiveness and enhance learner motivation.

[1232] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1233] Step 1: Upload test results

[1234] User: The learner launches the dedicated app for the educational device and selects the "Upload Test Results" function. They either take a picture of the test results with the device's camera or select an existing PDF / image file and press the upload button.

[1235] Input: Image data or PDF file of the captured test results

[1236] Output: Upload of recorded image data or PDF file

[1237] Specific operation: The user takes a test result with the camera or selects an existing file and presses the upload button.

[1238] Terminal: The terminal verifies the file format selected by the user and saves it to temporary storage. It then prepares the saved file to send to the server and sends the file to the server.

[1239] Input: Uploaded image data or PDF file

[1240] Output: Image data or PDF file transferred to the server

[1241] Specific actions: Check file format, temporarily save file, send file to server

[1242] Step 2: Extract and save text data

[1243] Server: The server checks the received file and re-verifies that it is not in an invalid format. Then, it uses Tesseract OCR to extract text data from the file. After saving it to temporary storage, it moves it to the database for permanent storage.

[1244] Input: Image data or PDF file transferred to the server

[1245] Output: Permanently saved text data

[1246] Specific actions: Reconfirm file format, extract text data using OCR technology, save to temporary storage, move text data to database.

[1247] Step 3: Data Analysis and Homework Generation

[1248] Server: The server retrieves text data from the database and inputs it into a machine learning model. The machine learning model analyzes the test results and identifies areas of weakness and strength. Based on the analysis results, it generates homework using a generative AI model. It inputs prompts into the generative AI model, generates a set of homework problems, and saves them to the database.

[1249] Input: Text data stored in the database

[1250] Output: Homework assignment set saved in the database

[1251] Specific operations: Input text data into a machine learning model, obtain analysis results, input prompt sentences into an AI model, generate homework assignments, and save the assignments to a database.

[1252] Example prompt: "Generate 5 homework problems related to division, which is a difficult topic for learners. Set the difficulty level of each problem to medium."

[1253] Step 4: Utilizing the Emotional Engine

[1254] Server: The server uses an emotion engine to collect emotional data in real time while learners are using educational equipment. It analyzes facial expressions and voice tone to obtain emotional data and adjusts the difficulty and content of homework based on that data. The collected emotional data is stored in a database.

[1255] Input: Sentimental data collected in real time from educational equipment.

[1256] Output: Homework adjusted according to emotions, and emotional data stored in the database.

[1257] Specific actions: Analysis of facial expressions and voice tone, collection and storage of emotional data, adjustment of homework content.

[1258] Step 5: Homework distribution and feedback

[1259] User: Learners can view the generated homework in a dedicated app and begin working on it. Correction instructions can be sent to the server as needed, and homework can be downloaded and printed, or completed directly within the app.

[1260] Input: Homework confirmation and answer data from the dedicated app.

[1261] Output: Answer data and correction instructions sent to the server

[1262] Specific actions: Checking homework, sending correction instructions, entering answers.

[1263] Terminal: The terminal temporarily stores the learner's progress and answer data in storage and prepares to send it to the server. After completing the answer, it sends the answer data to the server.

[1264] Input: Learner progress and answer data

[1265] Output: Answer data sent to the server

[1266] Specific actions: Temporarily save progress and answer data, prepare to send to the server, send answer data.

[1267] Server: The server analyzes the received answer data and stores it in a database. It updates learning progress information and recommends the next learning content to proceed with. It provides feedback based on sentiment data recognized by the sentiment engine.

[1268] Input: Answer data sent to the server

[1269] Output: Analysis data and feedback stored in the database

[1270] Specific actions: Analysis and storage of answer data, updating of learning progress information, generation and provision of feedback.

[1271] The above outlines the specific processing steps for implementing the present invention. Through this process, learners can receive effective and personalized learning support.

[1272] (Application Example 2)

[1273] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1274] In factory production operations, worker fatigue and stress are major factors leading to decreased work efficiency and errors. While conventional automation systems monitor work content and progress, they lack the ability to respond in real time to consider the emotional state and stress levels of workers. Therefore, a system is needed that simultaneously optimizes worker health and work efficiency.

[1275] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1276] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing the worker's emotional data using an emotion engine, and means for providing the worker with individually optimized work instructions and break advice based on the analysis results. This makes it possible to monitor the worker's fatigue and stress in real time and maintain their health while improving work efficiency.

[1277] "Educational devices" refer to electronic devices and tools used in educational activities, and specifically include tablets, smartphones, and personal computers.

[1278] "Test results" refers to the performance data and answers of tests taken by learners, including those saved in PDF or image formats.

[1279] "Text data" refers to character information extracted from test results, which is processed using OCR technology, etc.

[1280] "Learner" refers to an individual who uses educational devices to learn, including those who are studying a specific curriculum or course.

[1281] "Individualized homework" refers to homework assignments that are generated individually based on each student's learning progress and level of understanding.

[1282] "Learning content" refers to educational materials and assignments that learners access through educational devices, and includes text, videos, and interactive questions.

[1283] An "emotion engine" refers to technologies for recognizing and analyzing the emotional state of learners and workers in real time, and includes facial recognition, voice analysis, and behavioral pattern analysis.

[1284] "Emotional data" refers to information related to the emotions of learners and workers acquired by the emotion engine, and includes data such as facial expressions, tone of voice, and movements.

[1285] "Worker" refers to an individual performing tasks in a factory or manufacturing site, including those assigned to specific production lines or tasks.

[1286] "Work instructions" refer to instructions that communicate specific work content and procedures to workers, and include information to ensure work efficiency and safety.

[1287] "Break advice" refers to instructions that recommend taking breaks at appropriate times based on the worker's fatigue and stress levels, with the aim of maintaining health and improving work efficiency.

[1288] This invention is a system that uses an emotional engine to support factory workers. A specific embodiment is described below.

[1289] Hardware and software to be used

[1290] This system uses the following hardware and software:

[1291] Hardware:

[1292] Smart glasses and smart device cameras

[1293] Factory robot (equipped with an emotional engine)

[1294] High-performance camera (for frame capture)

[1295] software:

[1296] OpenCV (image processing)

[1297] Dlib (face detection)

[1298] EmotionRecognitionModel

[1299] Server software (data management and analysis)

[1300] Program Processing Overview

[1301] The server provides a system for recognizing and analyzing workers' emotions in real time. This system includes the following key steps:

[1302] 1. Collection and analysis of sentiment data:

[1303] Camera footage of the worker is acquired, and the worker's face is detected using facial recognition technology (Dlib). Next, emotions are analyzed using an EmotionRecognitionModel. This model is pre-trained and identifies the emotions the worker is experiencing (e.g., stress, fatigue, etc.).

[1304] 2. Providing individually optimized work instructions:

[1305] Based on the analyzed emotional data, the server generates appropriate advice and work instructions according to the worker's state. For example, if a worker is feeling stressed, it can provide a message recommending that the worker take a break.

[1306] 3. Uploading test results from educational devices:

[1307] Workers use smart devices to input and upload their daily work plans and progress to an app. The server stores the data in storage and prepares it for later analysis.

[1308] Specific example

[1309] As a concrete example, consider a scenario where factory line workers wear smart glasses, and camera footage is transmitted to a server. The server's emotion engine analyzes the worker's facial expressions in real time, and if signs of stress are detected, it automatically provides advice on taking a break. Data on work status is also collected and used to optimize the next work instructions.

[1310] Example of a prompt

[1311] The following are examples of prompts to input into the generating AI model.

[1312] "Develop a system to analyze the emotions of factory line workers. It should recognize workers' facial expressions in real time and provide advice, such as recommending a break, if the worker is experiencing stress. Worker emotion data should be collected using cameras and analyzed using an emotion recognition model. This should include specific break advice and stress reduction methods."

[1313] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1314] Step 1:

[1315] The user wears smart glasses or a smart device and uses its camera to capture video of the work scene in real time. The camera footage is captured by a local device and transferred to the next step. The input is camera footage, and the output is real-time video data. Specifically, the device's camera is activated and continuously captures video data.

[1316] Step 2:

[1317] The terminal transfers the captured camera footage to the server. The device compresses the captured video data and sends it to the server over the network. The input is real-time video data, and the output is the data transferred to the server. Specifically, the process involves compressing the video data and transferring it over the network.

[1318] Step 3:

[1319] The server stores the received video data in storage for analysis and uses image processing techniques to detect the worker's face. Specifically, it extracts face regions from video frames using OpenCV or Dlib. The input is the transmitted video data, and the output is the result of the worker's face detection. The specific operations include reading video frames and applying face recognition algorithms.

[1320] Step 4:

[1321] The server uses an emotion recognition model (EmotionRecognitionModel) based on face detection results to identify the worker's emotions. The emotion recognition model is pre-trained, accepts face images as input data, and outputs an estimated emotion. The input is the face detection result, and the output is the emotion analysis result. Specifically, the operation involves inputting face images into the model and executing an estimation algorithm to classify emotions.

[1322] Step 5:

[1323] The server generates appropriate advice and work instructions for the worker based on the emotion analysis results. If stress is detected, it generates a message recommending that the worker take a break. The input is the emotion analysis results, and the output is an advice message. Specifically, it selects the appropriate advice based on the emotion analysis results and generates a message.

[1324] Step 6:

[1325] The server forwards the generated advice message to the terminal and displays it to the worker. The terminal receives the message and presents it to the user visually or audibly. The input is the advice message, and the output is the display to the user. Specific operations include receiving, decoding, and outputting the message to a display device.

[1326] Step 7:

[1327] The user acts according to the advice displayed on the device. For example, they might take a break or change their work procedure. The input is the advice message, and the output is the user's action. Specific actions include the user's decisions and actions based on the displayed information.

[1328] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1329] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1330] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1331] [Fourth Embodiment]

[1332] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1333] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1334] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1335] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1336] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1337] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1338] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1339] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1340] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1341] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1342] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1343] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1344] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1345] This invention relates to a system that uses educational devices to analyze learners' test results and provides individually optimized homework. This system can be specifically implemented as follows:

[1346] Upload test results

[1347] User:

[1348] Learners open a dedicated app on their educational device (e.g., a tablet or smartphone) and upload their test results.

[1349] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[1350] Terminal:

[1351] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[1352] The file is sent to the server.

[1353] server:

[1354] Check the received file and double-check that it is not in an invalid format.

[1355] OCR technology is used to extract text data from a file and save it to temporary storage.

[1356] Analysis of test results and homework generation

[1357] server:

[1358] Move the text data from temporary storage to the database and save it.

[1359] Text data stored in a database is input into a machine learning model, and the learner's response patterns are analyzed.

[1360] An algorithm is executed that identifies the learner's strengths and weaknesses and generates customized homework assignments.

[1361] The generated homework is provided to learning-related devices.

[1362] User:

[1363] Learners review the generated homework on the app and send correction instructions to the server as needed.

[1364] Download and print the corrected homework, or start answering it directly within the app.

[1365] Learning at your own pace

[1366] User:

[1367] Students complete their homework and answer questions at their own pace.

[1368] Once you have finished answering, press the submit button to send your answer to the server.

[1369] Terminal:

[1370] The answer data is temporarily stored and prepared for transmission to the server.

[1371] Send the answer data to the server.

[1372] server:

[1373] The received answer data is analyzed and stored in a database.

[1374] Update learning progress information and recommend the next learning content the learner needs.

[1375] Specific example

[1376] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue. This system allows learners to always receive optimal learning content tailored to their level of understanding, enabling effective learning.

[1377] The following describes the processing flow.

[1378] Step 1: Upload test results

[1379] User:

[1380] Open the dedicated app and proceed to the screen where you upload your test results.

[1381] Click the "Select File" button and choose the test result file (PDF or image) from your device.

[1382] Press the "Upload" button.

[1383] Step 2: Upload Process

[1384] Terminal:

[1385] Check the format of the selected file and verify that it is a supported format (PDF or image).

[1386] The file is temporarily saved to storage and prepared for transmission to the server.

[1387] Send the file to the server.

[1388] server:

[1389] Check the received file and double-check that it is not in an invalid format.

[1390] The system sends a file to an OCR (Optical Character Recognition) system and extracts text data from the file.

[1391] The extracted text data is saved to temporary storage.

[1392] Step 3: Save text data

[1393] server:

[1394] Move text data stored in temporary storage to the database and save it permanently.

[1395] Step 4: Data Analysis

[1396] server:

[1397] Text data is retrieved from a database and input into a machine learning model.

[1398] Machine learning models are used to analyze test results and identify learners' strengths and weaknesses.

[1399] Based on the analysis results, the system generates homework assignments optimized for each learner.

[1400] Step 5: Homework Generation

[1401] server:

[1402] Automatically generates homework assignments that take into account the student's strengths and weaknesses.

[1403] The generated homework assignment sets are saved in a database and reflected in the learner's progress.

[1404] Step 6: Homework Distribution

[1405] User:

[1406] View a preview of the homework generated through the app.

[1407] If necessary, send correction instructions to the server.

[1408] After confirmation, download and print the homework, or start answering directly within the app.

[1409] Step 7: Answers to homework

[1410] User:

[1411] Students complete their homework at their own pace.

[1412] Once you have finished answering, press the "Submit" button to send your answer to the server.

[1413] Terminal:

[1414] The answer data is temporarily stored and prepared for transmission to the server.

[1415] Send the answer data to the server.

[1416] Step 8: Analyze and save the solution

[1417] server:

[1418] Review and analyze the received answer data.

[1419] The answer data is saved to the database, and the learner's progress information is updated.

[1420] Based on the learner's progress and answer results, the system recommends the next learning content they should proceed to.

[1421] This process ensures that learners always receive optimal learning content based on their learning progress and understanding, allowing them to continue learning effectively.

[1422] (Example 1)

[1423] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1424] Traditional education systems have struggled to provide appropriate learning content based on each learner's individual abilities and level of understanding. This made it difficult for learners to effectively overcome their weaknesses and prevented them from receiving appropriate learning content tailored to their progress. Furthermore, there was a lack of efficient methods for analyzing which areas of weakness existed.

[1425] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1426] In this invention, the server includes means for inspecting learning evaluation results and extracting textual information, means for analyzing the learner's weaknesses and strengths based on the extracted textual information, and means for providing individualized learning tasks based on the analysis results. This makes it possible to provide learning content optimized for each learner and to support them in efficiently overcoming their areas of weakness.

[1427] "Educational devices" refer to devices used by learners for educational purposes, including, for example, tablets, smartphones, and PCs.

[1428] "Learning assessment results" refer to data showing the results of tests and assignments completed by learners, and are uploaded as PDF or image files.

[1429] "Textual information" refers to text data extracted using OCR technology, obtained from uploaded learning evaluation results.

[1430] "Areas of weakness" refers to information that indicates the subjects or types of problems that learners find difficult, and this is determined through analysis of test results.

[1431] "Strengths" refer to information that indicates the areas and types of problems a learner excels at, and this is determined through analysis of test results.

[1432] "Individualized learning assignments" refer to homework or practice problems optimized for specific learners based on analysis results.

[1433] "Information storage device" refers to hardware or software that functions as data storage, including servers and cloud storage.

[1434] "Optical character recognition technology" is a technology that extracts text information from images and PDFs, and uses software such as Tesseract OCR.

[1435] A "machine learning model" is an algorithm that uses AI technology to perform data analysis and prediction, and refers to models that use frameworks such as TensorFlow.

[1436] "Educational content" is a term that describes the content of learning materials and assignments provided to learners, including, for example, textbooks, videos, and practice problems.

[1437] Modes for carrying out the invention

[1438] This invention relates to a system that uses educational equipment to analyze learners' test results and provides individually optimized learning tasks. In this system, the user, terminal, and server each play important roles.

[1439] Hardware and software usage

[1440] This system utilizes tablets, smartphones, or PCs as educational devices. This allows learners to easily upload test results. The server-side uses a high-performance database (e.g., MySQL) and machine learning models (e.g., TensorFlow) to analyze learner data and generate individualized learning assignments. OCR technology (e.g., Tesseract OCR) is used for text data extraction.

[1441] Data processing and data calculation

[1442] 1. User Operation: Learners upload their learning assessment results from educational devices using a dedicated app. The uploaded files are often in PDF or image format.

[1443] 2. Terminal operation: The system checks the format of the uploaded file and temporarily saves it to storage. Next, it calculates a checksum to verify data integrity and prepares to send the file to the server.

[1444] 3. Server operation: Check the received files and recheck for any invalid formats. Use OCR technology to extract character information from the files. This converts the learning evaluation results into text data.

[1445] 4. Database Use: The extracted text data is stored in a database. The stored data will later be used to analyze it using a machine learning model.

[1446] 5. Data Analysis: The server inputs the stored text data into a machine learning model. This identifies the learner's strengths and weaknesses. Based on the analysis results, individual learning tasks are generated.

[1447] 6. Assignment Provision: The generated learning assignments are provided again to the educational device. Learners can check their homework through a dedicated app and make corrections as needed.

[1448] 7. Recording progress: The server records the learner's progress on assignments and saves it in a database. Based on this information, it recommends the next necessary learning content.

[1449] Specific examples and prompt statements

[1450] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates a task specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the task and sends the answer back to the server. The server analyzes the answer and, upon confirming that A's understanding of multiplication problems has deepened, suggests long division as the next learning topic. In this way, learner A can progress through their learning with appropriate content and timing.

[1451] Example of a prompt:

[1452] "Please describe the specific processing steps of a system that allows learners to upload their math test results, analyzes that data, and provides them with the most suitable homework."

[1453] This prompt prompts the generative AI model to explain how the system will process the learner's test results and provide the most appropriate learning content.

[1454] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1455] Step 1:

[1456] User: Learners use educational devices (e.g., tablets, smartphones) to launch a dedicated app and upload their test results. Input is a test result file in PDF or image format. Output is the transmission of these files to the device.

[1457] Step 2:

[1458] Terminal: Verify that the uploaded file format is correct. Specifically, analyze the file header information to verify that it is a PDF or image file. The input is the file uploaded by the user in step 1. The output is the file stored in temporary storage.

[1459] Step 3:

[1460] Terminal: Saves the verified file to temporary storage and calculates its checksum. After calculation, it verifies data integrity and prepares it for transmission to the server. Input is a verified file. Output is a file ready for transmission to the server.

[1461] Step 4:

[1462] Server: The server re-examines the received file and checks for any formatting errors. Then, it uses OCR technology (e.g., Tesseract OCR) to extract text information from the file. The input is the file sent from the terminal. The output is the extracted text data.

[1463] Step 5:

[1464] Server: Stores the text data extracted by OCR in temporary storage. Then, saves the text data to a database (e.g., MySQL). Input is the text data extracted by OCR. Output is the text data stored in the database.

[1465] Step 6:

[1466] Server: Inputs text data stored in a database into a machine learning model (e.g., TensorFlow) to analyze the learner's strengths and weaknesses. The input is text data stored in a database. The output is the analysis results regarding the learner's strengths and weaknesses.

[1467] Step 7:

[1468] Server: Generates individual learning tasks based on analysis results. For example, for a learner who struggles with "carrying over in multiplication," it generates homework specifically tailored to that problem. The input is the learner's analysis results. The output is the generated learning task.

[1469] Step 8:

[1470] Server: Sends the generated learning tasks to educational devices. Input is the generated learning tasks. Output is the tasks sent to the educational devices.

[1471] Step 9:

[1472] User: Learners use a dedicated app to review generated homework and provide correction instructions as needed. Input is the assignment sent from the server. Output is correction instructions (if any).

[1473] Step 10:

[1474] User: Learners solve generated learning tasks and submit their answers to the server via a dedicated app. The input is the completed task. The output is the answer data submitted to the server.

[1475] Step 11:

[1476] Server: Analyzes received answer data and stores it in a database. Based on the analysis results, it recommends the next learning content. Input is the learner's answer data. Output is the next recommended learning content.

[1477] (Application Example 1)

[1478] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1479] Conventional learning support systems using educational devices struggle to provide optimal homework tailored to each learner's individual weaknesses. Furthermore, the process of learners uploading test results and receiving automatically customized homework requires efficient and accurate information analysis and delivery. Additionally, flexibility is needed to allow learners to monitor their progress and learning outcomes and move on to the next learning step. This system aims to solve these challenges and provide a system that enables learners to progress effectively and efficiently.

[1480] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1481] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, and means for automatically generating homework corresponding to a specific theme from the learner's test results and providing it through a content distribution application. This makes it possible to provide optimal homework that meets the individual needs of the learner.

[1482] "Educational devices" is a general term for electronic devices used to run learning-related applications, such as tablets, smartphones, and computers.

[1483] "Means for uploading test results" refers to a function that allows learners to send test results to a server using educational devices.

[1484] "Methods for analyzing test results and extracting text data" refers to a function that analyzes test results received on a server and extracts them as text data using OCR technology or similar methods.

[1485] "Methods for analyzing learners' strengths and weaknesses" refers to a function that analyzes learners' answer patterns based on text data from test results to identify areas of strength and weakness.

[1486] "Means for generating individualized homework" refers to a function that automatically creates homework optimized for a particular learner based on the results of an analysis of that learner.

[1487] "Means of providing to learning-related devices" refers to a function that sends homework generated on the server to learners' educational devices, making it accessible to the learners.

[1488] "Means for recording progress and saving it to data storage" refers to a function that records the process by which learners complete their homework and saves that data to storage on a server.

[1489] The "means for recommending the next learning content" refer to a function that recommends what the learner should study next, based on their saved progress and analytical data.

[1490] "A means of automatically generating homework corresponding to a specific theme and providing it through a content distribution application" refers to a function that creates homework based on theme-specific analytical information obtained from test results and provides it to learners using a content distribution service.

[1491] This invention is a system that uses educational devices to analyze learners' test results and provide individually optimized homework. This system functions through the cooperation of a server, terminals, and users.

[1492] The server provides a means for users to upload test results from educational devices (e.g., tablets and smartphones). Users can take photos or scan test results and send them to the server via their device in image or PDF format. This allows users to easily provide test results in digital format.

[1493] Next, the server analyzes the test results. Specifically, it uses OCR technology (e.g., Tesseract OCR) to extract text data from images and PDF files. This text data is temporarily stored and then transferred to a database. The server inputs this data into a machine learning model to automatically analyze the learner's strengths and weaknesses. For example, if the analysis reveals that the learner struggles with "carrying over in multiplication," the server uses this information to generate personalized homework.

[1494] The generated homework is provided to educational devices. Users can review the homework on their devices and make corrections as needed. While the user works on the provided homework, the device records their progress and sends it to the server. The server stores this information in a database and recommends the learning content the learner needs next.

[1495] Specifically, the server is built using the Flask framework, and Tesseract OCR is used for OCR technology. PIL (Pillow) is used for image processing. These technologies enable the efficient and accurate conversion of test results into digital data for analysis and storage.

[1496] Specific example

[1497] For example, learner A takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server uses OCR technology to convert the received image into text data. The analysis identifies that A tends to struggle with multiplication problems involving carrying over. Based on this, the server generates homework specifically focused on multiplication problems involving carrying over and provides it to A's device. A solves the homework and sends the answers back to the server. The server analyzes the answers and provides the next learning step based on the results. For example, if it is determined that A's understanding of multiplication problems has deepened, the server suggests the next learning content to pursue.

[1498] Example of a prompt

[1499] "Analyze the test results and generate homework specifically tailored to your weaknesses (e.g., carrying over in multiplication)."

[1500] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1501] Step 1:

[1502] Users upload test results using educational devices.

[1503] Specifically, learners take a picture of their test results with their smartphone camera, select an image or PDF file format through the application, and press the upload button.

[1504] Input: Image or PDF file of test results

[1505] Output: Sending files to the server

[1506] Step 2:

[1507] The terminal prepares to send the test result file to the server.

[1508] The device checks the uploaded file format, and if it is a supported format, it saves the file to temporary storage and prepares it for transfer to the server.

[1509] Input: Uploaded test result file

[1510] Output: Files saved to temporary storage

[1511] Step 3:

[1512] The server receives the test results file and extracts the text data.

[1513] The server checks the received file and uses OCR technology (e.g., Tesseract OCR) to extract text data from the image or PDF. The extracted text data is temporarily stored.

[1514] Input: Image or PDF file of test results

[1515] Output: Extracted text data

[1516] Step 4:

[1517] The server analyzes the text data.

[1518] The extracted text data is stored in a database and then input into a machine learning model. The server analyzes the learner's response patterns to identify their weak and strong areas.

[1519] Input: Extracted text data

[1520] Output: Analysis results (weaknesses and strengths)

[1521] Step 5:

[1522] The server generates individual homework assignments.

[1523] Based on the analysis results, the server automatically generates homework tailored to the learner's areas of difficulty. For example, if a learner struggles with "carrying over in multiplication," the server will create problems specifically focused on that topic.

[1524] Input: Analysis results (weaknesses and strengths)

[1525] Output: Generated homework

[1526] Step 6:

[1527] The server provides the generated homework to learning-related devices.

[1528] The server sends the generated homework to the user's educational device. The user can receive the provided homework and view it within the application.

[1529] Input: Generated homework

[1530] Output: Providing homework to educational devices

[1531] Step 7:

[1532] The user works on the homework assigned to them.

[1533] The user begins solving homework within the application. Progress and answer results are recorded on the device.

[1534] Input: Provided homework

[1535] Output: Progress and answer results

[1536] Step 8:

[1537] The device sends the progress and answer results to the server.

[1538] The device temporarily stores the user's answers and prepares to send them to the server. When the send button is pressed, the device sends the answer data to the server.

[1539] Input: Progress and answer results

[1540] Output: Sending data to the server

[1541] Step 9:

[1542] The server analyzes the received data and recommends the next learning step.

[1543] The server analyzes the received progress and answers, updates the learner's understanding, and recommends the next necessary learning content.

[1544] Input: Progress and answer results

[1545] Output: Recommendations for the following learning content

[1546] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1547] This invention is a system that combines an emotion engine with educational devices, analyzes learners' test results, provides individually optimized homework, and recognizes learners' emotions to improve learning efficiency. This system can be implemented as follows.

[1548] Upload test results

[1549] User:

[1550] Learners open a dedicated app on their educational device (such as a tablet or smartphone) and upload their test results.

[1551] The test results file can be selected as either a PDF or an image file, and then sent from the device to the server by pressing the upload button.

[1552] Terminal:

[1553] The terminal checks the selected file format, saves it to temporary storage if it is a supported format, and prepares it for transfer to the server.

[1554] The file is sent to the server.

[1555] Extracting and saving text data

[1556] server:

[1557] Check the received file and double-check that it is not in an invalid format.

[1558] OCR technology is used to extract text data from a file and save it to temporary storage.

[1559] Move text data stored in temporary storage to the database and save it permanently.

[1560] Data analysis and homework generation

[1561] server:

[1562] Text data is retrieved from a database and input into a machine learning model.

[1563] A machine learning model analyzes the test results to identify the learner's strengths and weaknesses.

[1564] Based on the analysis results, the system generates homework assignments optimized for each learner.

[1565] The system automatically generates homework assignments that take into account each student's strengths and weaknesses, and saves them in a database.

[1566] Using an Emotion Engine

[1567] server:

[1568] An emotion engine is used to collect emotional data in real time while learners are using educational devices.

[1569] Emotional data is obtained by analyzing the learner's facial expressions, voice tone, and behavioral patterns.

[1570] Based on the acquired emotional data, the difficulty and content of homework assignments will be appropriately adjusted.

[1571] Homework distribution and feedback

[1572] User:

[1573] Learners review the generated homework on the app and send correction instructions to the server as needed.

[1574] After confirmation, download and print the homework, or start answering directly within the app.

[1575] Terminal:

[1576] The learner's progress and answer data are temporarily saved and prepared to be sent to the server.

[1577] After completing your answer, press the submit button to send your answer to the server.

[1578] server:

[1579] The received answer data is analyzed and stored in a database.

[1580] Update learning progress information and recommend the next learning content to proceed with.

[1581] Based on user emotional data recognized by the emotion engine, feedback is provided to improve learner motivation. Specifically, this includes sending encouraging messages when learners are feeling stressed, and recommending breaks when concentration is low.

[1582] Specific example

[1583] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that B tends to struggle with division problems. Based on this, the server generates homework specifically focused on division and provides it to B's device. Furthermore, while B is working on the homework, the emotion engine recognizes B's facial expressions, and if it determines that B is experiencing stress, it displays advice and encouraging messages to reduce stress. B can receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[1584] The following describes the processing flow.

[1585] Step 1: Upload test results

[1586] User:

[1587] Learners open a dedicated app on their educational device (e.g., a tablet or smartphone) and proceed to a screen where they upload their test results.

[1588] Click the "Select File" button and choose the test result file (PDF or image) from your device.

[1589] Press the "Upload" button.

[1590] Step 2: Upload Process

[1591] Terminal:

[1592] Verify the selected file format (PDF or image) and check that it is a supported format.

[1593] The file is temporarily saved to storage and prepared for transfer to the server.

[1594] Send the file to the server.

[1595] server:

[1596] Check the received file and double-check that it is not in an invalid format.

[1597] The system sends a file to an OCR (Optical Character Recognition) system and extracts text data from the file.

[1598] The extracted text data is saved to temporary storage.

[1599] Step 3: Save text data

[1600] server:

[1601] Move text data stored in temporary storage to the database and save it permanently.

[1602] Step 4: Data Analysis

[1603] server:

[1604] Text data is retrieved from a database and input into a machine learning model.

[1605] The machine learning model analyzes the test results to identify the learner's strengths and weaknesses.

[1606] Based on the analysis results, the system generates homework assignments optimized for each learner.

[1607] Step 5: Homework Generation

[1608] server:

[1609] The system automatically generates homework assignments that take into account the learner's strengths and weaknesses, and saves them in a database.

[1610] Step 6: Analysis using the emotion engine

[1611] server:

[1612] An emotion engine is used to collect real-time emotional data from learners using educational devices.

[1613] Emotional data is acquired by analyzing the learner's facial expressions, voice tone, behavioral patterns, and other factors.

[1614] Based on the acquired emotional data, the difficulty level of homework and the feedback are adjusted.

[1615] Step 7: Homework Distribution

[1616] User:

[1617] Learners can view a preview of the homework generated through the app.

[1618] Send correction instructions to the server as needed.

[1619] After confirmation, download and print the homework, or start answering directly within the app.

[1620] Step 8: Answers to homework

[1621] User:

[1622] Students complete their homework at their own pace.

[1623] Once you have finished answering, press the "Submit" button to send your answer to the server.

[1624] Terminal:

[1625] The learner's answer data is temporarily stored and prepared for transmission to the server.

[1626] Send the answer data to the server.

[1627] Step 9: Analyze and save the solution

[1628] server:

[1629] Review and analyze the received answer data.

[1630] The answer data is saved to the database, and the learner's progress information is updated.

[1631] Based on user emotion data recognized by the emotion engine, feedback is provided to improve learner motivation.

[1632] Specific example

[1633] Learner C takes a math test, takes a picture of the results with their smartphone camera, and uploads it. The server receives the image and uses OCR technology to convert the answers into text data. The analysis identifies that C has difficulty with "division of fractions." Based on this, the server generates homework specifically focused on division of fractions and provides it to C's device.

[1634] Furthermore, while C is working on homework, the emotion engine recognizes C's facial expressions and, if it determines that C is experiencing stress, displays advice and encouraging messages to help reduce stress. C can then receive this advice and continue learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in more effective learning.

[1635] (Example 2)

[1636] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1637] Traditional education systems have struggled to efficiently identify specific areas of difficulty for learners and provide individually optimized homework based on those areas. Furthermore, because learning progresses without considering the learner's emotional state, learners may experience stress or lack concentration. This raises concerns about decreased learning effectiveness and reduced motivation. Additionally, the cumbersome process of uploading test results and the lack of real-time monitoring of learners' progress made efficient feedback difficult. Moreover, homework was not adjusted based on the learner's emotional state, resulting in ineffective learning support.

[1638] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1639] In this invention, the server includes means for uploading test results from educational equipment, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational equipment, means for recording the progress of the homework and storing it in a data storage device, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing emotional data in real time, and means for adjusting the difficulty and content of the homework based on the emotional data. This makes it possible to efficiently identify the learner's weaknesses and provide individually optimized homework. Furthermore, by understanding the learner's emotional state in real time and adjusting the difficulty and content of the homework based on it, it is possible to reduce the learner's stress and maintain their concentration. With this system, learners can receive effective learning support, and improvements in learning effectiveness and motivation can be expected.

[1640] "Educational equipment" refers to devices used by learners to conduct learning activities, and specifically includes tablets, smartphones, and laptop computers.

[1641] "Test results" refer to data showing the answers and scores of students when they take a test, and are recorded in formats such as PDF or image.

[1642] A "server" is a computer system used to process data operations over a network, including data storage, analysis, and distribution.

[1643] "OCR technology" is an abbreviation for Optical Character Recognition technology, which is a technology that reads character data from image files and other sources and converts it into text data.

[1644] "Text data" refers to data in a string format that can be electronically recognized using OCR technology or other conversion methods.

[1645] A "machine learning model" is a model that builds algorithms based on large amounts of data and automatically performs specific tasks by learning patterns and rules from that data.

[1646] "Individualized homework" refers to learning tasks optimized for each learner's learning situation and abilities, and is specifically designed to improve areas of weakness.

[1647] A "data storage device" is a device that includes hardware and software used to store and manage data for long periods of time.

[1648] "Emotional data" refers to data that indicates a learner's emotional state, obtained by analyzing their facial expressions, voice tone, behavioral patterns, and other factors.

[1649] "Real-time" refers to the immediate processing and reflection of events currently in progress, meaning that specific data or interactions are processed instantly without delay.

[1650] "Analyzing" means processing and evaluating data using various techniques in order to find specific patterns or trends.

[1651] This invention is a system that combines an emotion engine with educational equipment, analyzes learners' test results, and provides individually optimized homework. Furthermore, it is characterized by its ability to recognize the learner's emotional state in real time and make adjustments to improve learning efficiency. This system can be implemented specifically as follows.

[1652] Hardware and software configuration

[1653] Educational devices include tablets, smartphones, and laptops. These devices have dedicated apps installed, which learners can use to upload test results and download homework.

[1654] The server is a central management system that receives and analyzes data transmitted from these educational devices, and further collects and analyzes emotional data using an emotion engine. Specifically, the following software and technologies are used.

[1655] 1. OCR technology (e.g., Tesseract OCR): Used to extract text data from image data of test results.

[1656] 2. Machine learning models (e.g., TensorFlow, PyTorch): These are used to identify the learner's strengths and weaknesses based on the acquired text data.

[1657] 3. Emotion engine (e.g., Microsoft Azure Face API): Used to collect and analyze emotion data in real time from the learner's facial expressions and voice tone.

[1658] 4. Data storage devices (e.g., MySQL, PostgreSQL): Used to permanently store analytical data, homework data, sentiment data, etc.

[1659] Specific example

[1660] The following shows specific examples of how the system according to the present invention can be used.

[1661] For example, learner B takes a math test, takes a picture of the results with their smartphone camera, and uploads them through a dedicated app. The device checks the test results, saves them to temporary storage, and then sends them to the server. The server checks the received image data and uses Tesseract OCR to convert the answers into text data.

[1662] Next, the server inputs the converted text data into a machine learning model and analyzes the test results. The analysis identifies that B tends to struggle with division problems. Based on this, the server uses a generative AI model to generate homework specifically focused on division. The following prompts are used during the generation process.

[1663] Example of a prompt:

[1664] "Please generate five homework problems related to division, a topic that learners often struggle with. Set the difficulty level of each problem to medium."

[1665] The generated homework assignments are stored in a database and provided to B's smartphone. While B is working on the assignments, an emotion engine recognizes B's facial expressions and collects emotional data in real time. For example, if the system determines that B is stressed, it displays advice and encouraging messages to help reduce stress.

[1666] B can accept this advice and proceed with learning in a relaxed state. This system allows learners to receive flexible support tailored to their emotional state, resulting in effective learning.

[1667] Thus, by combining educational equipment and an emotion engine, the present invention can simultaneously provide individually optimized homework and learning support tailored to the learner's emotional state. This system is expected to improve learning effectiveness and enhance learner motivation.

[1668] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1669] Step 1: Upload test results

[1670] User: The learner launches the dedicated app for the educational device and selects the "Upload Test Results" function. They either take a picture of the test results with the device's camera or select an existing PDF / image file and press the upload button.

[1671] Input: Image data or PDF file of the captured test results

[1672] Output: Upload of recorded image data or PDF file

[1673] Specific operation: The user takes a test result with the camera or selects an existing file and presses the upload button.

[1674] Terminal: The terminal verifies the file format selected by the user and saves it to temporary storage. It then prepares the saved file to send to the server and sends the file to the server.

[1675] Input: Uploaded image data or PDF file

[1676] Output: Image data or PDF file transferred to the server

[1677] Specific actions: Check file format, temporarily save file, send file to server

[1678] Step 2: Extract and save text data

[1679] Server: The server checks the received file and re-verifies that it is not in an invalid format. Then, it uses Tesseract OCR to extract text data from the file. After saving it to temporary storage, it moves it to the database for permanent storage.

[1680] Input: Image data or PDF file transferred to the server

[1681] Output: Permanently saved text data

[1682] Specific actions: Reconfirm file format, extract text data using OCR technology, save to temporary storage, move text data to database.

[1683] Step 3: Data Analysis and Homework Generation

[1684] Server: The server retrieves text data from the database and inputs it into a machine learning model. The machine learning model analyzes the test results and identifies areas of weakness and strength. Based on the analysis results, it generates homework using a generative AI model. It inputs prompts into the generative AI model, generates a set of homework problems, and saves them to the database.

[1685] Input: Text data stored in the database

[1686] Output: Homework assignment set saved in the database

[1687] Specific operations: Input text data into a machine learning model, obtain analysis results, input prompt sentences into an AI model, generate homework assignments, and save the assignments to a database.

[1688] Example prompt: "Generate 5 homework problems related to division, which is a difficult topic for learners. Set the difficulty level of each problem to medium."

[1689] Step 4: Utilizing the Emotional Engine

[1690] Server: The server uses an emotion engine to collect emotional data in real time while learners are using educational equipment. It analyzes facial expressions and voice tone to obtain emotional data and adjusts the difficulty and content of homework based on that data. The collected emotional data is stored in a database.

[1691] Input: Sentimental data collected in real time from educational equipment.

[1692] Output: Homework adjusted according to emotions, and emotional data stored in the database.

[1693] Specific actions: Analysis of facial expressions and voice tone, collection and storage of emotional data, adjustment of homework content.

[1694] Step 5: Homework distribution and feedback

[1695] User: Learners can view the generated homework in a dedicated app and begin working on it. Correction instructions can be sent to the server as needed, and homework can be downloaded and printed, or completed directly within the app.

[1696] Input: Homework confirmation and answer data from the dedicated app.

[1697] Output: Answer data and correction instructions sent to the server

[1698] Specific actions: Checking homework, sending correction instructions, entering answers.

[1699] Terminal: The terminal temporarily stores the learner's progress and answer data in storage and prepares to send it to the server. After completing the answer, it sends the answer data to the server.

[1700] Input: Learner progress and answer data

[1701] Output: Answer data sent to the server

[1702] Specific actions: Temporarily save progress and answer data, prepare to send to the server, send answer data.

[1703] Server: The server analyzes the received answer data and stores it in a database. It updates learning progress information and recommends the next learning content to proceed with. It provides feedback based on sentiment data recognized by the sentiment engine.

[1704] Input: Answer data sent to the server

[1705] Output: Analysis data and feedback stored in the database

[1706] Specific actions: Analysis and storage of answer data, updating of learning progress information, generation and provision of feedback.

[1707] The above outlines the specific processing steps for implementing the present invention. Through this process, learners can receive effective and personalized learning support.

[1708] (Application Example 2)

[1709] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1710] In factory production operations, worker fatigue and stress are major factors leading to decreased work efficiency and errors. While conventional automation systems monitor work content and progress, they lack the ability to respond in real time to consider the emotional state and stress levels of workers. Therefore, a system is needed that simultaneously optimizes worker health and work efficiency.

[1711] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1712] In this invention, the server includes means for uploading test results from educational devices, means for analyzing test results and extracting text data, means for analyzing the learner's strengths and weaknesses based on the extracted text data, means for generating individualized homework based on the analysis results, means for providing the generated homework to educational devices, means for recording the progress of the homework and saving it to data storage, means for recommending the next learning content based on the progress and analysis data, means for collecting and analyzing the worker's emotional data using an emotion engine, and means for providing the worker with individually optimized work instructions and break advice based on the analysis results. This makes it possible to monitor the worker's fatigue and stress in real time and maintain their health while improving work efficiency.

[1713] "Educational devices" refer to electronic devices and tools used in educational activities, and specifically include tablets, smartphones, and personal computers.

[1714] "Test results" refers to the performance data and answers of tests taken by learners, including those saved in PDF or image formats.

[1715] "Text data" refers to character information extracted from test results, which is processed using OCR technology, etc.

[1716] "Learner" refers to an individual who uses educational devices to learn, including those who are studying a specific curriculum or course.

[1717] "Individualized homework" refers to homework assignments that are generated individually based on each student's learning progress and level of understanding.

[1718] "Learning content" refers to educational materials and assignments that learners access through educational devices, and includes text, videos, and interactive questions.

[1719] An "emotion engine" refers to technologies for recognizing and analyzing the emotional state of learners and workers in real time, and includes facial recognition, voice analysis, and behavioral pattern analysis.

[1720] "Emotional data" refers to information related to the emotions of learners and workers acquired by the emotion engine, and includes data such as facial expressions, tone of voice, and movements.

[1721] "Worker" refers to an individual performing tasks in a factory or manufacturing site, including those assigned to specific production lines or tasks.

[1722] "Work instructions" refer to instructions that communicate specific work content and procedures to workers, and include information to ensure work efficiency and safety.

[1723] "Break advice" refers to instructions that recommend taking breaks at appropriate times based on the worker's fatigue and stress levels, with the aim of maintaining health and improving work efficiency.

[1724] This invention is a system that uses an emotional engine to support factory workers. A specific embodiment is described below.

[1725] Hardware and software to be used

[1726] This system uses the following hardware and software:

[1727] Hardware:

[1728] Smart glasses and smart device cameras

[1729] Factory robot (equipped with an emotional engine)

[1730] High-performance camera (for frame capture)

[1731] software:

[1732] OpenCV (image processing)

[1733] Dlib (face detection)

[1734] EmotionRecognitionModel

[1735] Server software (data management and analysis)

[1736] Program Processing Overview

[1737] The server provides a system for recognizing and analyzing workers' emotions in real time. This system includes the following key steps:

[1738] 1. Collection and analysis of sentiment data:

[1739] Camera footage of the worker is acquired, and the worker's face is detected using facial recognition technology (Dlib). Next, emotions are analyzed using an EmotionRecognitionModel. This model is pre-trained and identifies the emotions the worker is experiencing (e.g., stress, fatigue, etc.).

[1740] 2. Providing individually optimized work instructions:

[1741] Based on the analyzed emotional data, the server generates appropriate advice and work instructions according to the worker's state. For example, if a worker is feeling stressed, it can provide a message recommending that the worker take a break.

[1742] 3. Uploading test results from educational devices:

[1743] Workers use smart devices to input and upload their daily work plans and progress to an app. The server stores the data in storage and prepares it for later analysis.

[1744] Specific example

[1745] As a concrete example, consider a scenario where factory line workers wear smart glasses, and camera footage is transmitted to a server. The server's emotion engine analyzes the worker's facial expressions in real time, and if signs of stress are detected, it automatically provides advice on taking a break. Data on work status is also collected and used to optimize the next work instructions.

[1746] Example of a prompt

[1747] The following are examples of prompts to input into the generating AI model.

[1748] "Develop a system to analyze the emotions of factory line workers. It should recognize workers' facial expressions in real time and provide advice, such as recommending a break, if the worker is experiencing stress. Worker emotion data should be collected using cameras and analyzed using an emotion recognition model. This should include specific break advice and stress reduction methods."

[1749] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1750] Step 1:

[1751] The user wears smart glasses or a smart device and uses its camera to capture video of the work scene in real time. The camera footage is captured by a local device and transferred to the next step. The input is camera footage, and the output is real-time video data. Specifically, the device's camera is activated and continuously captures video data.

[1752] Step 2:

[1753] The terminal transfers the captured camera footage to the server. The device compresses the captured video data and sends it to the server over the network. The input is real-time video data, and the output is the data transferred to the server. Specifically, the process involves compressing the video data and transferring it over the network.

[1754] Step 3:

[1755] The server stores the received video data in storage for analysis and uses image processing techniques to detect the worker's face. Specifically, it extracts face regions from video frames using OpenCV or Dlib. The input is the transmitted video data, and the output is the result of the worker's face detection. The specific operations include reading video frames and applying face recognition algorithms.

[1756] Step 4:

[1757] The server uses an emotion recognition model (EmotionRecognitionModel) based on face detection results to identify the worker's emotions. The emotion recognition model is pre-trained, accepts face images as input data, and outputs an estimated emotion. The input is the face detection result, and the output is the emotion analysis result. Specifically, the operation involves inputting face images into the model and executing an estimation algorithm to classify emotions.

[1758] Step 5:

[1759] The server generates appropriate advice and work instructions for the worker based on the emotion analysis results. If stress is detected, it generates a message recommending that the worker take a break. The input is the emotion analysis results, and the output is an advice message. Specifically, it selects the appropriate advice based on the emotion analysis results and generates a message.

[1760] Step 6:

[1761] The server forwards the generated advice message to the terminal and displays it to the worker. The terminal receives the message and presents it to the user visually or audibly. The input is the advice message, and the output is the display to the user. Specific operations include receiving, decoding, and outputting the message to a display device.

[1762] Step 7:

[1763] The user acts according to the advice displayed on the device. For example, they might take a break or change their work procedure. The input is the advice message, and the output is the user's action. Specific actions include the user's decisions and actions based on the displayed information.

[1764] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1765] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1766] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1767] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1768] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1769] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1770] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1771] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1772] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1773] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1774] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1775] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1776] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1777] 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.

[1778] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1779] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1780] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1781] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1782] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1783] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1784] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1785] The following is further disclosed regarding the embodiments described above.

[1786] (Claim 1)

[1787] A means of uploading test results from educational devices,

[1788] A method for analyzing test results and extracting text data,

[1789] A method for analyzing learners' strengths and weaknesses based on extracted text data,

[1790] A means of generating individual homework assignments based on analysis results,

[1791] A means of providing the generated homework to learning-related devices,

[1792] A means of recording the progress of homework and saving it to data storage,

[1793] A method for recommending the next learning content based on progress and analytical data,

[1794] A system that includes this.

[1795] (Claim 2)

[1796] The system according to claim 1, which identifies the types of questions that learners repeatedly get wrong based on their answer patterns.

[1797] (Claim 3)

[1798] The system according to claim 1, which allows learners to preview and make corrections before homework is generated.

[1799] "Example 1"

[1800] (Claim 1)

[1801] A means for transmitting learning assessment results from educational equipment,

[1802] A means of examining learning assessment results and extracting textual information,

[1803] A method for analyzing learners' weaknesses and strengths based on extracted textual information,

[1804] A means of providing individualized learning tasks based on the analysis results,

[1805] A means of providing the generated tasks to educational devices,

[1806] A means for recording the progress of a task and saving it to an information storage device,

[1807] A means of recommending the next educational content based on progress and analytical data,

[1808] A means for converting learning evaluation results into character information using optical character recognition technology,

[1809] A means of using machine learning models to generate individual learning tasks,

[1810] A system that includes this.

[1811] (Claim 2)

[1812] The system according to claim 1, which identifies the types of questions that learners repeatedly answer incorrectly based on their answer patterns.

[1813] (Claim 3)

[1814] The system according to claim 1, which allows learners to check a preview and make correction instructions before the assignment is generated.

[1815] "Application Example 1"

[1816] (Claim 1)

[1817] A means of uploading test results from educational devices,

[1818] A method for analyzing test results and extracting text data,

[1819] A method for analyzing learners' strengths and weaknesses based on extracted text data,

[1820] A means of generating individual homework assignments based on analysis results,

[1821] A means of providing the generated homework to learning-related devices,

[1822] A means of recording the progress of homework and saving it to data storage,

[1823] A method for recommending the next learning content based on progress and analytical data,

[1824] A means of automatically generating homework on a specific theme based on learners' test results and providing it through a content distribution application,

[1825] A system that includes this.

[1826] (Claim 2)

[1827] The system according to claim 1, which identifies the types of questions that learners repeatedly get wrong based on their answer patterns.

[1828] (Claim 3)

[1829] The system according to claim 1, which allows learners to preview and make corrections before homework is generated.

[1830] "Example 2 of combining an emotion engine"

[1831] (Claim 1)

[1832] A means of uploading test results from educational equipment,

[1833] A method for analyzing test results and extracting text data,

[1834] A method for analyzing learners' strengths and weaknesses based on extracted text data,

[1835] A means of generating individual homework assignments based on analysis results,

[1836] A means of providing the generated homework to educational equipment,

[1837] A means of recording the progress of homework and saving it to a data storage device,

[1838] A method for recommending the next learning content based on progress and analytical data,

[1839] A means of collecting and analyzing emotional data in real time,

[1840] A method for adjusting the difficulty and content of homework based on emotional data,

[1841] A system that includes this.

[1842] (Claim 2)

[1843] The system according to claim 1, which identifies the types of questions that learners repeatedly get wrong based on their answer patterns.

[1844] (Claim 3)

[1845] The system according to claim 1, which allows learners to preview and make corrections before homework is generated.

[1846] "Application example 2 when combining with an emotional engine"

[1847] (Claim 1)

[1848] A means of uploading test results from educational devices,

[1849] A method for analyzing test results and extracting text data,

[1850] A method for analyzing learners' strengths and weaknesses based on extracted text data,

[1851] A means of generating individual homework assignments based on analysis results,

[1852] A means of providing the generated homework to learning-related devices,

[1853] A means of recording the progress of homework and saving it to data storage,

[1854] A method for recommending the next learning content based on progress and analytical data,

[1855] A means of collecting and analyzing worker emotional data using an emotion engine,

[1856] A means of providing workers with individually optimized work instructions and break advice based on analysis results,

[1857] A system that includes this.

[1858] (Claim 2)

[1859] The system according to claim 1, which identifies the types of questions that learners repeatedly get wrong based on their answer patterns.

[1860] (Claim 3)

[1861] The system according to claim 1, which allows learners to preview and make corrections before homework is generated. [Explanation of Symbols]

[1862] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of uploading test results from educational devices, A method for analyzing test results and extracting text data, A method for analyzing learners' strengths and weaknesses based on extracted text data, A means of generating individual homework assignments based on analysis results, A means of providing the generated homework to learning-related devices, A means of recording the progress of homework and saving it to data storage, A method for recommending the next learning content based on progress and analytical data, A system that includes this.

2. The system according to claim 1, which identifies the types of problems that learners repeatedly get wrong based on their answer patterns.

3. The system according to claim 1, which allows learners to preview and make corrections before homework is generated.

Images