System

Abstract

A system is provided.SOLUTION: A system comprising: input means; receiving means; analyzing means; determining means; feedback generating means; and transmitting means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's world, children's homework load is increasing, but parents have limited support, making it difficult to provide effective learning support. Furthermore, children often experience difficulty completing their homework, and spending a lot of time checking the correct answers reduces their learning efficiency. A solution to this problem is needed. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, and a transmitting means. Specifically, the system provides an input means for users to input their homework in image or text format, a receiving means for receiving the input data, and an analyzing means for converting the received image data into text data. The system further provides a determining means for comparing the analyzed data with a correct answer database to determine the correct answer, a feedback generating means for generating feedback based on the determination result, and a transmitting means for sending the generated feedback to the user. This provides efficient support for children's homework and improves their learning effectiveness.

[0006] "Input means" refers to an interface that allows a user to input homework in image or text format.

[0007] The "receiving means" is a device or software for receiving data sent from the input means.

[0008] The "analysis means" is a processing means including OCR technology for converting the image data received by the receiving means into text data.

[0009] The "determination means" is a processing means for checking the text data analyzed by the analysis means against the correct answer database to determine whether the answer is correct or incorrect.

[0010] The "feedback generating means" is a means for generating feedback to the user based on the result of the determination made by the determining means.

[0011] "Transmission means" refers to a device or software for transmitting the generated feedback to the user's input means.

[0012] "OCR technology" is a general term for optical character recognition technology used to extract text data from image data.

[0013] The "correct answer database" is a database that stores data on the correct answers to each homework question.

[0014] "Usage history" refers to the input data, answer data, feedback data, and question and answer history information when a user uses the system.

[0015] "Personalization" means individualizing the next learning content and presented information based on usage history and adjusting it to suit the user's needs. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, and a transmitting means.

[0038] System programs and their processing

[0039] 1. Input Method

[0040] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[0041] Examples:

[0042] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[0043] 2. Receiving Method

[0044] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[0045] Examples:

[0046] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[0047] 3. Analysis method

[0048] The server analyzes the received data. If it is image data, it is converted into text data using OCR technology. If it is text data, it is divided into questions using natural language processing. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[0049] Examples:

[0050] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[0051] 4. Judgment means

[0052] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[0053] Examples:

[0054] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[0055] 5. Feedback Generation Methods

[0056] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[0057] Examples:

[0058] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[0059] 6. Transmission Method

[0060] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[0061] Examples:

[0062] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[0063] Specific usage scenarios

[0064] 1. User enters homework

[0065] The user takes a photo of their homework using a smartphone app and sends it to the server.

[0066] 2. The server analyzes the data

[0067] The server extracts text data from the image and analyzes the content of the homework.

[0068] 3. The server determines the correct answer

[0069] The server checks the homework answers against a database to determine the correct answer.

[0070] 4. The server generates feedback

[0071] The server generates explanations and additional questions based on the results of the assessment.

[0072] 5. The server sends feedback

[0073] The server generates feedback and sends it to the terminal for display to the user.

[0074] In this way, the user can quickly and effectively receive feedback on the content of their homework and deepen their understanding.

[0075] The processing flow will be explained below.

[0076] Specific processing steps of the program

[0077] Step 1:

[0078] The user launches the smartphone app and enters the homework content. Homework can be done by taking a photo or by entering it directly as text.

[0079] Step 2:

[0080] To process the input data, the device sends the data to a server on the cloud. If it is image data, it is sent as an image file, and if it is text data, it is sent as character data.

[0081] Step 3:

[0082] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[0083] Step 4:

[0084] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[0085] Step 5:

[0086] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[0087] Step 6:

[0088] The server uses an internal database to compare the analyzed data with a database of correct answers, thereby determining the correct answer for each question.

[0089] Step 7:

[0090] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[0091] Step 8:

[0092] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[0093] Step 9:

[0094] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[0095] Step 10:

[0096] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[0097] Step 11:

[0098] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[0099] Step 12:

[0100] If the user enters an additional question, the terminal sends the question to the server again.

[0101] Step 13:

[0102] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[0103] Step 14:

[0104] The server generates a response and sends it to the terminal, which displays it to the user.

[0105] Step 15:

[0106] The server records all usage history and uses it to personalize the learning content for the next time. Usage history includes homework content, answer results, feedback, questions and answers.

[0107] Step 16:

[0108] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[0109] Through the above process, users can efficiently complete their homework and deepen their understanding. The server also personalizes the next session based on the user's usage history, providing more effective learning support.

[0110] Example 1

[0111] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0112] Conventional homework support systems are inefficient because they often rely on manual grading and feedback. They also lack a mechanism for quickly identifying the homework a user has completed and providing appropriate feedback on the content. Therefore, an effective system that can improve children's learning efficiency and provide appropriate feedback quickly is needed.

[0113] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0114] In this invention, the server includes an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means, which enable the server to quickly analyze the content of the homework and provide accurate feedback.

[0115] "Input means" refers to a device or function that allows a user to input the contents of the homework in image or text format.

[0116] The "receiving means" is a device or function for receiving the homework data sent from the input means.

[0117] "Image analysis means" refers to a device or function that analyzes image data and converts the contents of the homework into text data.

[0118] The "text analysis means" is a device or function that analyzes text data and divides the homework content into questions.

[0119] The "content identification means" is a device or function that identifies the type of homework (mathematics, Japanese, etc.) from the analyzed data.

[0120] The "answer determination means" is a device or function that compares homework data with correct answer data in an internal database and determines whether each question is correct or incorrect.

[0121] The "feedback generating means" is a device or function that generates feedback (such as whether the answer is correct or incorrect, an explanation for an incorrect answer, or additional practice questions) based on the judgment result.

[0122] The "transmitting means" is a device or function that transmits the generated feedback to the user's terminal.

[0123] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means.

[0124] First, a user opens a dedicated application on a smartphone or tablet. There, the user takes a picture of the homework content with the camera or enters it directly in text format. The application used for this input method is implemented as a general smart device app. For example, this includes a case where a user launches a smartphone app and takes a picture of the arithmetic problem "5 + 3 = ?" with the camera.

[0125] Next, the device sends the input data to a cloud server via the Internet. The device assigns a user ID to the sent data to make it uniquely identifiable. For example, the device uploads "homework image data" or "text data" to the server and sends it with the user ID "12345" attached.

[0126] The received data is analyzed by the server. In the case of image data, it is converted into text data using OCR technology, and in the case of text data, it is divided into questions using natural language processing. At this time, image analysis software such as Google Cloud Vision API is used. For example, the image data received by the server, "5 + 3 = ?", is converted into text data using OCR technology and then analyzed.

[0127] Next, the server identifies the type of homework from the analyzed data (e.g., math, Japanese, etc.). This allows it to determine the appropriate answer. The answer determination means compares the correct answer data in an internal database to determine whether each question is correct. For example, the server receives an answer such as "5 + 3 = 9," compares it with the correct answer "8" in the database, and determines that it is incorrect.

[0128] The server then generates feedback based on the results. This feedback includes not only the correct answer, but also explanations and additional practice questions for incorrect answers. For example, for the incorrect answer "5 + 3 = 9," the server might explain that "the correct answer is 8" and present another addition problem, "4 + 2 = ?". This generation process uses an AI model, and an example prompt might be, "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it's incorrect and provide additional practice questions."

[0129] Finally, the feedback is sent from the server to the device, which receives it and displays it within the application. For example, the server sends the generated explanation and additional questions to the device, which receives them and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8" and also presents a new question "4 + 2 = ?"

[0130] This allows users to receive prompt and effective feedback on their homework and deepen their understanding of the material. This system helps users save time and effort and study efficiently.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] The user enters the details of the homework using a smartphone or tablet.

[0134] Specifically, the user takes a picture of the homework using the smartphone camera or enters the homework content into a text input field within the app.

[0135] Input: Homework question (image or text format)

[0136] Output: Homework problem data

[0137] Specific example of how it works: A user launches a homework app and takes a photo of the problem "5 + 3 = ?" with their camera, or types in the text "The weather is sunny today."

[0138] Step 2:

[0139] The terminal transmits the data input by the user to the cloud server.

[0140] The device transmits data via an Internet connection, and the data is given an identifying user ID.

[0141] Input: Homework problem data (image or text format) and user ID

[0142] Output: Homework data and user ID on the server

[0143] Specific example of operation: The device uploads "homework image data" and "user ID 12345" to the server.

[0144] Step 3:

[0145] The server parses the received data.

[0146] The server converts the image data into text data using OCR technology, and then divides the text data into questions using natural language processing. It also identifies the type of homework.

[0147] Input: Homework data on the server (image or text format) and user ID

[0148] Output: Parsed text data and homework type

[0149] Specific example of operation: The server uses the Google Cloud Vision API to convert the image data "5 + 3 = ?" into text, and then performs natural language processing using NLTK to recognize it as an arithmetic problem.

[0150] Step 4:

[0151] The server compares the analyzed text data with correct data in an internal database to determine whether it is correct or not.

[0152] The server temporarily stores the judgment result and uses it to generate the next feedback.

[0153] Input: Parsed text data and homework type

[0154] Output: Judgment results and answer data

[0155] Specific example of operation: The server compares the answer "5 + 3 = 9" with the correct answer "8" in the database and determines that it is incorrect.

[0156] Step 5:

[0157] The server generates feedback based on the result of the determination.

[0158] The generated feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. It is generated using a generative AI model.

[0159] Input: Judgment results and answer data

[0160] Output: Feedback data

[0161] Specific example of operation: The server inputs the prompt "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it is incorrect and provide additional practice questions" into the generative AI model, which generates feedback including an explanation and the practice question "4 + 2 = ?".

[0162] Step 6:

[0163] The server generates feedback and sends it to the device.

[0164] The terminal displays the received feedback within the application and provides it to the user.

[0165] Input: Feedback data

[0166] Output: Feedback that is displayed to the user

[0167] Specific example of operation: The server sends an explanation and additional questions in JSON format to the device, which receives it and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8," and then presents a new question, "4 + 2 = ?"

[0168] (Application example 1)

[0169] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0170] Conventional homework support systems have many shortcomings in effectively improving children's learning efficiency. In particular, they lack the ability to analyze homework answers in real time and provide prompt, appropriate feedback, making it difficult for children to progress effectively. Furthermore, conventional systems may not accurately analyze input data, resulting in the provision of incorrect feedback.

[0171] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0172] In this invention, the server includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, and a transmitting unit. This allows homework images and text data to be input via a smartphone device, analyzed by the cloud server, and the generated feedback provided to the user in real time. Furthermore, by interpreting the input data using a generative AI model, accurate analysis of the data and generation of appropriate feedback are possible.

[0173] The "input means" is a means for inputting image or text data of homework into the smartphone device.

[0174] The "receiving means" is a means for transmitting data sent from the input means to the cloud server together with the user ID.

[0175] "Analysis means" refers to a means for analyzing received data on a cloud server and interpreting the homework content using OCR technology and natural language processing.

[0176] The "judging means" is a means for comparing the text data extracted by the analyzing means with the correct answer data in the internal database to judge whether the answer is correct or incorrect.

[0177] The "feedback generating means" is a means for generating explanations and additional questions based on the judgment results and providing feedback to the user.

[0178] The "transmission means" is a means for transmitting the generated feedback to the user's smartphone device in real time.

[0179] A "cloud server" is a remote server that stores and processes data via the Internet and generates analysis results and feedback.

[0180] A "generative AI model" is an artificial intelligence model that interprets input data and generates appropriate feedback through natural language processing and template generation.

[0181] The present invention relates to a system that effectively and efficiently supports children in completing their homework. The system includes an input means using a smartphone device, an analysis means and a judgment means using a cloud server, a feedback generation means using a generative AI model, and a transmission means.

[0182] System programs and their processing

[0183] 1. Input Method

[0184] Users can take pictures of their homework or enter the details of their homework in text format using a dedicated application on their smartphone device. Using this application makes it easy to enter the homework and ensures that the data is sent accurately to the server.

[0185] 2. Receiving Method

[0186] The smartphone device sends the captured image and input text data along with the user ID to a cloud server. This receiving means requires an internet connection, and the data is uniquely identified on the cloud.

[0187] 3. Analysis method

[0188] The cloud server analyzes the received data using OCR technology (e.g., Google Vision API) or natural language processing (e.g., Google NLP, Azure Text Analytics). Image data is converted into text data, and text data is divided into questions.

[0189] 4. Judgment means

[0190] The cloud server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) and determines whether the answer is correct or incorrect. A calculation algorithm is used to make the determination.

[0191] 5. Feedback Generation Methods

[0192] The cloud server generates feedback based on the results using a generative AI model (e.g., OpenAI GPT-3). This feedback includes a correct or incorrect result, an explanation if the answer is incorrect, and additional practice questions. Templates and AI-generated explanations are used to generate the feedback.

[0193] 6. Transmission Method

[0194] The cloud server sends the generated feedback in JSON format to the smartphone device, where an application parses it and displays it to the user.

[0195] Specific usage scenarios

[0196] 1. User enters homework

[0197] The user takes a photo of their homework using a smartphone app and sends it to the server.

[0198] 2. The cloud server analyzes the data

[0199] The cloud server extracts text data from the images and analyzes the content of the homework.

[0200] 3. The cloud server determines the correct answer

[0201] The cloud server checks the homework answers against a database to determine the correct answer.

[0202] 4. The cloud server generates feedback

[0203] The cloud server generates explanations and additional questions based on the assessment results.

[0204] 5. The cloud server sends feedback

[0205] The cloud server transmits the generated feedback to the smartphone device and displays it to the user.

[0206] Prompt Sentence Examples

[0207] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[0208] Prompt statement:

[0209] Homework problem: 5 + 3 = 9

[0210] Correct answer: 8

[0211] Generate a description.

[0212]

[0213] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0214] Step 1:

[0215] The user takes a photo of their homework using their smartphone device or enters it in text format. The entered data is sent to a dedicated application along with their user ID. The entered data includes image data or text data. The user's specific action is to open the application and take a photo of their homework or enter it in text format.

[0216] Step 2:

[0217] The device uploads the data sent from the input means along with the user ID to the cloud server. At this time, the data is transferred via an internet connection. Specifically, the data is processed by converting image and text data into JSON format and sending it to the cloud server.

[0218] Step 3:

[0219] The server analyzes the received data using OCR technology and natural language processing. In the case of image data, OCR technology (e.g., Google Vision API) is used to convert it into text data, and in the case of text data, natural language processing technology (e.g., Google NLP, Azure Text Analytics) is used to separate it into questions. Specifically, the data is processed such that after the image data is converted into text data, each question is identified.

[0220] Step 4:

[0221] The server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) to determine whether the answer is correct or incorrect. The algorithm used here collates the correct answers in the analyzed text data with the correct answers in the database. The specific data calculation involves setting a correct or incorrect flag for each question.

[0222] Step 5:

[0223] The server generates feedback using a generative AI model (e.g., OpenAI GPT-3) based on the judgment results. The feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. The server sends input data to the generative AI model using prompt sentences to generate appropriate feedback. Specifically, the model generates appropriate explanation sentences and additional questions based on templates.

[0224] Step 6:

[0225] The server sends the generated feedback in JSON format to the smartphone device, where the smartphone device's application analyzes it and displays it to the user. The specific operation is to analyze the feedback data and display it to the user in a visually easy-to-understand format.

[0226] Specific prompt examples

[0227] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[0228] Prompt statement:

[0229] Homework problem: 5 + 3 = 9

[0230] Correct answer: 8

[0231] Generate a description.

[0232] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0233] The present invention provides a homework support system for children that improves children's learning efficiency and provides feedback that takes into account the user's emotions. The system includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, a transmitting unit, and an emotion engine.

[0234] System programs and their processing

[0235] 1. Input Method

[0236] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[0237] Examples:

[0238] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[0239] 2. Receiving Method

[0240] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[0241] Examples:

[0242] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[0243] 3. Analysis method

[0244] The server analyzes the received data. In particular, in the case of image data, OCR technology is used to convert the image data into text data, and in the case of text data, natural language processing is used to divide it into questions. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[0245] Examples:

[0246] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[0247] 4. Judgment means

[0248] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[0249] Examples:

[0250] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[0251] 5. Feedback Generation Methods

[0252] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[0253] Examples:

[0254] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[0255] 6. Transmission Method

[0256] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[0257] Examples:

[0258] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[0259] 7. Emotion Engine

[0260] The server uses an emotion engine to recognize the user's emotions. The emotion engine uses face recognition technology and voice analysis technology to determine the user's emotions.

[0261] Examples:

[0262] The server recognizes the user's face through the smartphone camera and determines that the user is confused, and analyzes the tone of the user's voice through the voice assistant and determines that the user is irritated.

[0263] 8. Feedback adjustment

[0264] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle and detailed explanations if the user is confused.

[0265] Examples:

[0266] If the user is confused when the server generates the feedback, it adds encouraging words such as "Try solving the problem again slowly."

[0267] Specific usage scenarios

[0268] 1. User enters homework

[0269] The user takes a photo of their homework using a smartphone app and sends it to the server.

[0270] 2. The server analyzes the data

[0271] The server extracts text data from the image and analyzes the content of the homework.

[0272] 3. The server determines the correct answer

[0273] The server checks the homework answers against a database to determine the correct answer.

[0274] 4. The server generates feedback

[0275] The server generates explanations and additional questions based on the results of the assessment.

[0276] 5. The server analyzes emotions

[0277] The server uses an emotion engine to analyze the user's emotions.

[0278] 6. The server moderates the feedback

[0279] The server adjusts the content and tone of the feedback based on the emotional data.

[0280] 7. The server sends feedback

[0281] The server generates feedback and sends it to the terminal for display to the user.

[0282] This series of processes allows users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[0283] The processing flow will be explained below.

[0284] Specific processing steps of the program

[0285] Step 1:

[0286] The user launches the smartphone app and enters the homework content. The homework can be entered by taking a photo or by entering it directly in text format.

[0287] Step 2:

[0288] To process the input data, the device sends the data to a server on the cloud. Image data is sent as an image file, and text data is sent as character data.

[0289] Step 3:

[0290] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[0291] Step 4:

[0292] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[0293] Step 5:

[0294] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[0295] Step 6:

[0296] The server uses an internal database to compare the analyzed data with the correct answer database, thereby determining the correct answer for each question.

[0297] Step 7:

[0298] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[0299] Step 8:

[0300] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[0301] Step 9:

[0302] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[0303] Step 10:

[0304] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[0305] Step 11:

[0306] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[0307] Step 12:

[0308] If the user enters an additional question, the terminal sends the question to the server again.

[0309] Step 13:

[0310] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[0311] Step 14:

[0312] The server generates a response and sends it to the terminal, which displays it to the user.

[0313] Step 15:

[0314] The server then uses an emotion engine to recognize the user's emotions. The emotion engine uses facial recognition technology to analyze the user's facial expressions and voice analysis technology to analyze the tone of voice and the way words are used.

[0315] Step 16:

[0316] The server recognizes the user's emotions based on the analysis results, determines their level of understanding and stress, and adjusts the feedback accordingly.

[0317] Step 17:

[0318] The server generates feedback, including detailed and friendly explanations and simple questions, if the user is confused.

[0319] Step 18:

[0320] The adjusted feedback is then transmitted back to the device using the transmission means, and the transmitted content includes detailed explanations and encouraging messages.

[0321] Step 19:

[0322] The device displays new feedback to the user, who receives emotion-based adjusted feedback to continue learning.

[0323] Step 20:

[0324] The server records all usage history and emotional data, which is used to personalize the next learning content. Usage history includes homework content, answer results, feedback, questions and answers, and emotional data.

[0325] Step 21:

[0326] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[0327] These processes enable users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[0328] Example 2

[0329] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0330] Previous learning support systems for children were limited to simply determining whether their homework was correct or incorrect, and were unable to provide feedback that took the user's emotions into consideration. Furthermore, they often lacked additional practice questions or detailed explanations to improve the user's learning efficiency. This led to a decline in children's motivation to learn, and made it difficult to provide effective learning support.

[0331] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0332] In this invention, the server includes an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, a transmitting means, an emotion engine, and a feedback adjusting means. After a user inputs their homework, the server analyzes the data and not only determines whether the data is correct or incorrect, but also provides feedback that takes the user's emotions into consideration. This improves the user's learning efficiency and maintains their motivation to learn. Furthermore, by providing additional practice questions and detailed explanations, more effective learning support is realized.

[0333] "Input means" refers to a device or application that allows a user to input homework in image or text format.

[0334] The "receiving means" is a device or system for receiving data sent from the input means to a server on the cloud.

[0335] "Analysis means" refers to optical character recognition technology that analyzes received data and converts image data into text data, and technology that analyzes text data using natural language processing to identify the type of question.

[0336] The "judging means" refers to an algorithm or system that compares the data extracted by the analyzing means with an internal database to judge whether the homework is correct or incorrect.

[0337] "Feedback generation means" refers to a device or software that generates feedback based on the assessment results and provides correct / incorrect results, explanations, and additional practice questions.

[0338] The "transmission means" is a device or system for transmitting the generated feedback to the user's terminal and displaying the feedback.

[0339] An "emotion engine" is a device or software that uses facial recognition and voice analysis technology to analyze a user's emotions and appropriately adjust feedback based on the emotional data.

[0340] A "feedback adjustment means" is a system or algorithm that adjusts the content and tone of feedback based on emotional data recognized by the emotion engine.

[0341] The present invention provides a homework support system that improves the efficiency of learning support for children and provides feedback that takes emotions into consideration. This system includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. The specific operation of each means is described below.

[0342] Input Method

[0343] Users use their smartphones or tablets to take pictures of their homework or input the details of their homework in text format. This input method is implemented as a dedicated application. The application provides a menu for users to select the type of homework (e.g., math, Japanese, etc.) and guides them in inputting the homework correctly.

[0344] Examples:

[0345] The user launches the smartphone app and takes a photo of their math homework, or types in the details of their Japanese homework using a keyboard. The app displays a menu for selecting the type of homework and navigates them to ensure smooth photo and input.

[0346] Receiving means

[0347] The device sends the data entered by the user to a server in the cloud. This communication is via an internet connection, and the data is uniquely identified by a user ID.

[0348] Examples:

[0349] The device uploads homework photos and text data to the cloud server in real time and assigns a user ID. A progress bar is displayed during the upload, and a notification is displayed when the upload is complete.

[0350] Analysis means

[0351] The server analyzes the data it receives. In the case of image data, it uses OCR technology to convert it into text data, and in the case of text data, it uses natural language processing to separate it into questions. It also identifies the type of question. Specifically, it uses the OCR engine and natural language processing engine installed on the server.

[0352] Examples:

[0353] The server analyzes the image of the received arithmetic problem using OCR and converts the handwritten "5 + 3 =" into text data. After conversion, it identifies it as an arithmetic addition problem.

[0354] Judgment means

[0355] The server compares the text data extracted by the analysis means with an internal database to determine whether the question is correct. This determination is made using a calculation algorithm. Specifically, a program is used to compare the answers to the questions with the database in the server.

[0356] Examples:

[0357] The server receives the answer "5 + 3 = 9" entered by the user and determines that it is incorrect by comparing it with the correct answer "8" in the database.

[0358] Feedback Generation Method

[0359] The server generates feedback based on the results. The feedback includes correct and incorrect answers, explanations for incorrect answers, and additional practice questions. Specifically, the feedback is created using templates and AI-generated explanations.

[0360] Examples:

[0361] For the incorrect answer "5 + 3 = 9," the system explains, "5 and 3 add up to 8," and then presents an additional addition problem, "4 + 2 =?"

[0362] Transmission method

[0363] The server generates feedback that is sent to the device and displayed to the user, who can then view the feedback within the app, where detailed explanations and additional questions are provided.

[0364] Examples:

[0365] The server sends the explanation and additional questions in JSON format to the device, which the device app parses and displays to the user. When the user resumes the app, a notification is displayed prompting them to view the feedback.

[0366] Emotion Engine

[0367] The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions, using facial recognition and voice analysis technologies.

[0368] Examples:

[0369] The server takes a picture of the user's face through the smartphone camera and recognizes confused expressions. It also analyzes the tone of the voice through the microphone to determine whether the user is feeling irritated.

[0370] Feedback Adjustment Means

[0371] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle, detailed explanations if the user is confused.

[0372] Examples:

[0373] If the user is stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the additional practice questions to be easier.

[0374] Prompt Sentence Examples

[0375] The homework support app screen displays the message, "Open the camera and take a photo of your math homework. Alternatively, enter the homework details in text."

[0376] In this way, the children's homework support system of the present invention can provide effective learning support while also taking into consideration the user's emotions. The overall system flow is as follows: data is acquired from the input means, sent to the server by the receiving means, analyzed by the analyzing means, judged correct or incorrect by the judging means, feedback is created by the feedback generating means, and finally provided to the user by the transmitting means. Furthermore, by using the emotion engine and feedback adjusting means, it is possible to provide optimal feedback according to the user's emotions.

[0377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0378] Step 1:

[0379] The user enters the homework data.

[0380] Input: The user uses a smartphone app to take a picture of the homework or enter the homework content in text format.

[0381] How it works: Select the type of homework (e.g., math, Japanese) in the app, then take a photo or enter text. The app will temporarily save the image and text data.

[0382] Output: Image data or text data of the homework is generated.

[0383] Step 2:

[0384] The device sends the homework data to the server.

[0385] Input: The image or text data of the homework generated in Step 1.

[0386] How it works: Your device uploads data to a cloud server via your internet connection and assigns you a user ID. A progress bar is displayed during the upload, and you're notified when the transfer is complete.

[0387] Output: Image data or text data is saved on the cloud server.

[0388] Step 3:

[0389] The server parses the received data.

[0390] Input: Image or text data of homework stored on the server.

[0391] How it works: In the case of image data, OCR technology is used to convert it into text data. In the case of text data, natural language processing is used to divide it into questions and identify the type of question. Specifically, an OCR engine or natural language processing engine on the server is used.

[0392] Output: The analyzed text data and the type of question (math, Japanese, etc.) are obtained.

[0393] Step 4:

[0394] The server determines whether the answer is correct.

[0395] Input: The text data parsed in step 3 and the question type.

[0396] How it works: The server compares the text data with an internal database to determine whether the question is correct or incorrect, and uses a computational algorithm to evaluate the answer.

[0397] Output: Correct / incorrect results for each question are obtained.

[0398] Step 5:

[0399] The server generates the feedback.

[0400] Input: The correct / incorrect result obtained in step 4.

[0401] How it works: The server generates feedback based on the results. The feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. Templates and AI-generated explanations are used.

[0402] Output: Feedback data (explanation, additional questions) is generated.

[0403] Step 6:

[0404] The server generates feedback and sends it to the device.

[0405] Input: Feedback data generated in step 5.

[0406] How it works: The cloud server sends feedback data in JSON format to the device, which the device application parses and displays to the user.

[0407] Output: Feedback is displayed on the terminal.

[0408] Step 7:

[0409] The server analyzes the user's emotions using an emotion engine.

[0410] Input: User facial expression and voice data sent from the device.

[0411] How it works: The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions. It uses facial recognition and voice analysis technology.

[0412] Output: User emotion data (e.g., confusion, irritation).

[0413] Step 8:

[0414] The server moderates the feedback.

[0415] Input: Emotion data obtained in step 7 and feedback data generated in step 5.

[0416] What it does: The server adjusts the content and tone of the feedback based on the emotion data, for example adding a gentler, more detailed explanation.

[0417] Output: Emotionally sensitive feedback is generated and sent back to the device.

[0418] Examples:

[0419] If users are stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the difficulty of additional practice problems to be easier.

[0420] This allows users to receive efficient and emotionally sensitive homework support.

[0421] (Application example 2)

[0422] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0423] To improve children's learning efficiency and provide personalized feedback according to the emotions of each individual user.

[0424] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. This enables children to study their homework effectively and receive feedback that takes their emotions into consideration.

[0425] "Input means" refers to a means by which a user inputs the contents of his / her homework in image or text format.

[0426] The "receiving means" is a means for receiving data transmitted from the input means.

[0427] "Analysis means" refers to means for analyzing received data and identifying the content and type of the problem.

[0428] The "judging means" is a means for judging whether the answer is correct or incorrect based on the analyzed data.

[0429] The "feedback generating means" is a means for generating feedback to be provided to the user based on the determination result.

[0430] The "transmitting means" is a means for transmitting the generated feedback to the user's terminal.

[0431] The "emotion engine" is a function for recognizing and analyzing the user's emotional state.

[0432] The "feedback adjustment means" is a means for adjusting the content and tone of feedback based on the emotional data recognized by the emotion engine.

[0433] This invention provides a system for supporting children's homework, and in particular generates feedback according to the emotional state of each user. This system works in cooperation with terminals, a server, and a network.

[0434] System Configuration

[0435] The system includes the following means:

[0436] Input Method

[0437] Receiving means

[0438] Analysis means

[0439] Judgment means

[0440] Feedback Generation Method

[0441] Transmission method

[0442] Emotion Engine

[0443] Feedback Adjustment Means

[0444] Input Method

[0445] Users input the contents of their homework using devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs). Users can take photos of their homework or input it in text format. This input method is implemented as a dedicated application.

[0446] Receiving means

[0447] The data entered on the terminal is transmitted to a server on the cloud via an internet connection, and the receiving means is used to allow the server to receive this data.

[0448] Analysis means

[0449] The server analyzes the received data. In the case of image data, OCR technology is used to convert the image into text. In the case of text data, natural language processing (NLP) technology is used to segment the data into questions and identify the question type (e.g., math, Japanese, science, etc.).

[0450] Judgment means

[0451] The server compares the analyzed data with the correct answer data in its internal database and determines whether it is correct or not, using database matching and calculation algorithms.

[0452] Feedback Generation Method

[0453] Feedback is generated based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[0454] Transmission method

[0455] The generated feedback is sent from the server to the device, which receives it and displays it to the user. The feedback content is in a format that can be viewed within the application.

[0456] Emotion Engine

[0457] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[0458] Feedback Adjustment Means

[0459] The emotion engine recognizes emotional data and adjusts the content and tone of the feedback, for example, providing a gentle and detailed explanation if it recognizes the user as confused.

[0460] Specific examples

[0461] The user takes a photo of their homework using a smartphone app and sends it to the server. The server then uses OCR technology to convert the handwritten homework into text and analyzes it. For example, for an incorrect problem like "5 + 3 = 9," the system provides an explanation: "5 and 3 add up to 8." Furthermore, the system recognizes the user's facial expression through the camera, and if it determines that the user is confused, it adds encouraging feedback such as, "Try solving the problem again slowly."

[0462] Example prompts for generative AI models

[0463] Homework problem: 5 + 3 = 9

[0464] The user made this mistake. Please generate appropriate feedback.

[0465] feedback:

[0466] Wrong: 5 + 3 = 9 is incorrect. The correct answer is 8. Try this question: "4 + 2 = ?"

[0467] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0468] Step 1:

[0469] Users launch the application using a smartphone, tablet, smart glasses, or head-mounted display (HMD), take a photo of their homework, or enter the homework details in text format. The entered data is stored in temporary storage on the device.

[0470] Input: Homework image or text data

[0471] Output: Input homework data (saved in temporary storage)

[0472] Specific actions: The user selects the "Enter Homework" menu in the dedicated application, and either takes a photo of the homework using the camera or enters the homework content directly into the text box.

[0473] Step 2:

[0474] The device sends the entered data to a cloud server, where it is assigned a user ID and sent via an internet connection.

[0475] Input: Homework data saved in temporary storage

[0476] Output: Homework data sent to the cloud server

[0477] What it does: The application bundles the stored data and the user ID into a single data packet and uploads it to a server over the Internet.

[0478] Step 3:

[0479] The server analyzes the received data. For image data, OCR technology is used to convert the image into text data. For text data, natural language processing (NLP) technology is used to segment the data into questions and identify the type of question.

[0480] Input: Homework data received by the server

[0481] Output: Parsed text data and identified problem types

[0482] Specific operation: The server passes the received data to the analysis module, which analyzes the data using an OCR engine or NLP engine. For example, the image data is converted into text using the OCR engine, and the text data is divided into questions using the NLP engine and identified as type (math, Japanese, etc.).

[0483] Step 4:

[0484] The server compares the analyzed text data with the correct data in an internal database to determine whether it is correct or not.

[0485] Input: Parsed text data and identified problem types

[0486] Output: Correct / incorrect result for each question

[0487] Specific operation: The server uses an "algorithm module" to compare the user's answer with the correct answer data in the database and determine whether the answer is correct or incorrect.

[0488] Step 5:

[0489] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[0490] Input: Correct / incorrect result

[0491] Output: Feedback message

[0492] Specific operation: The server's "feedback generation module" uses templates and generative AI models to generate appropriate explanations based on correct and incorrect answers. For example, if the answer is incorrect, an explanation such as "5 and 3 add up to 8" is added.

[0493] Step 6:

[0494] The server sends the generated feedback to the terminal, and the user can check the feedback through the terminal application.

[0495] Input: The generated feedback message

[0496] Output: Feedback displayed on the user's terminal

[0497] Specific operation: The server's sending module sends a feedback message in JSON format to the device, and the device application parses and displays it.

[0498] Step 7:

[0499] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[0500] Input: User's facial image and voice data

[0501] Output: Recognized emotion data

[0502] Specific operation: The server's "emotion analysis module" uses facial recognition technology and voice analysis algorithms to analyze the user's emotional state (e.g., confusion, irritation, etc.).

[0503] Step 8:

[0504] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is confused, it provides a gentle and detailed explanation.

[0505] Input: Recognized emotion data and feedback message

[0506] Output: Adjusted feedback message

[0507] What happens: The feedback adjustment module uses emotion data to fine-tune the tone and content of existing feedback messages, for example adding encouraging messages like "Try solving the problem again slowly."

[0508] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0509] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0510] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0511] [Second embodiment]

[0512] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0513] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0514] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0515] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0516] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0517] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0518] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0519] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0520] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0521] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0522] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0523] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0524] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, and a transmitting means.

[0525] System programs and their processing

[0526] 1. Input Method

[0527] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[0528] Examples:

[0529] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[0530] 2. Receiving Method

[0531] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[0532] Examples:

[0533] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[0534] 3. Analysis method

[0535] The server analyzes the received data. If it is image data, it is converted into text data using OCR technology. If it is text data, it is divided into questions using natural language processing. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[0536] Examples:

[0537] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[0538] 4. Judgment means

[0539] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[0540] Examples:

[0541] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[0542] 5. Feedback Generation Methods

[0543] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[0544] Examples:

[0545] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[0546] 6. Transmission Method

[0547] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[0548] Examples:

[0549] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[0550] Specific usage scenarios

[0551] 1. User enters homework

[0552] The user takes a photo of their homework using a smartphone app and sends it to the server.

[0553] 2. The server analyzes the data

[0554] The server extracts text data from the image and analyzes the content of the homework.

[0555] 3. The server determines the correct answer

[0556] The server checks the homework answers against a database to determine the correct answer.

[0557] 4. The server generates feedback

[0558] The server generates explanations and additional questions based on the results of the assessment.

[0559] 5. The server sends feedback

[0560] The server generates feedback and sends it to the terminal for display to the user.

[0561] In this way, the user can quickly and effectively receive feedback on the content of their homework and deepen their understanding.

[0562] The processing flow will be explained below.

[0563] Specific processing steps of the program

[0564] Step 1:

[0565] The user launches the smartphone app and enters the homework content. Homework can be done by taking a photo or by entering it directly as text.

[0566] Step 2:

[0567] To process the input data, the device sends the data to a server on the cloud. If it is image data, it is sent as an image file, and if it is text data, it is sent as character data.

[0568] Step 3:

[0569] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[0570] Step 4:

[0571] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[0572] Step 5:

[0573] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[0574] Step 6:

[0575] The server uses an internal database to compare the analyzed data with a database of correct answers, thereby determining the correct answer for each question.

[0576] Step 7:

[0577] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[0578] Step 8:

[0579] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[0580] Step 9:

[0581] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[0582] Step 10:

[0583] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[0584] Step 11:

[0585] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[0586] Step 12:

[0587] If the user enters an additional question, the terminal sends the question to the server again.

[0588] Step 13:

[0589] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[0590] Step 14:

[0591] The server generates a response and sends it to the terminal, which displays it to the user.

[0592] Step 15:

[0593] The server records all usage history and uses it to personalize the learning content for the next time. Usage history includes homework content, answer results, feedback, questions and answers.

[0594] Step 16:

[0595] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[0596] Through the above process, users can efficiently complete their homework and deepen their understanding. The server also personalizes the next session based on the user's usage history, providing more effective learning support.

[0597] Example 1

[0598] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0599] Conventional homework support systems are inefficient because they often rely on manual grading and feedback. They also lack a mechanism for quickly identifying the homework a user has completed and providing appropriate feedback on the content. Therefore, an effective system that can improve children's learning efficiency and provide appropriate feedback quickly is needed.

[0600] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0601] In this invention, the server includes an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means, which enable the server to quickly analyze the content of the homework and provide accurate feedback.

[0602] "Input means" refers to a device or function that allows a user to input the contents of the homework in image or text format.

[0603] The "receiving means" is a device or function for receiving the homework data sent from the input means.

[0604] "Image analysis means" refers to a device or function that analyzes image data and converts the contents of the homework into text data.

[0605] The "text analysis means" is a device or function that analyzes text data and divides the homework content into questions.

[0606] The "content identification means" is a device or function that identifies the type of homework (mathematics, Japanese, etc.) from the analyzed data.

[0607] The "answer determination means" is a device or function that compares homework data with correct answer data in an internal database and determines whether each question is correct or incorrect.

[0608] The "feedback generating means" is a device or function that generates feedback (such as whether the answer is correct or incorrect, an explanation for an incorrect answer, or additional practice questions) based on the judgment result.

[0609] The "transmitting means" is a device or function that transmits the generated feedback to the user's terminal.

[0610] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means.

[0611] First, a user opens a dedicated application on a smartphone or tablet. There, the user takes a picture of the homework content with the camera or enters it directly in text format. The application used for this input method is implemented as a general smart device app. For example, this includes a case where a user launches a smartphone app and takes a picture of the arithmetic problem "5 + 3 = ?" with the camera.

[0612] Next, the device sends the input data to a cloud server via the Internet. The device assigns a user ID to the sent data to make it uniquely identifiable. For example, the device uploads "homework image data" or "text data" to the server and sends it with the user ID "12345" attached.

[0613] The received data is analyzed by the server. In the case of image data, it is converted into text data using OCR technology, and in the case of text data, it is divided into questions using natural language processing. At this time, image analysis software such as Google Cloud Vision API is used. For example, the image data received by the server, "5 + 3 = ?", is converted into text data using OCR technology and then analyzed.

[0614] Next, the server identifies the type of homework from the analyzed data (e.g., math, Japanese, etc.). This allows it to determine the appropriate answer. The answer determination means compares the correct answer data in an internal database to determine whether each question is correct. For example, the server receives an answer such as "5 + 3 = 9," compares it with the correct answer "8" in the database, and determines that it is incorrect.

[0615] The server then generates feedback based on the results. This feedback includes not only the correct answer, but also explanations and additional practice questions for incorrect answers. For example, for the incorrect answer "5 + 3 = 9," the server might explain that "the correct answer is 8" and present another addition problem, "4 + 2 = ?". This generation process uses an AI model, and an example prompt might be, "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it's incorrect and provide additional practice questions."

[0616] Finally, the feedback is sent from the server to the device, which receives it and displays it within the application. For example, the server sends the generated explanation and additional questions to the device, which receives them and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8" and also presents a new question "4 + 2 = ?"

[0617] This allows users to receive prompt and effective feedback on their homework and deepen their understanding of the material. This system helps users save time and effort and study efficiently.

[0618] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0619] Step 1:

[0620] The user enters the details of the homework using a smartphone or tablet.

[0621] Specifically, the user takes a picture of the homework using the smartphone camera or enters the homework content into a text input field within the app.

[0622] Input: Homework question (image or text format)

[0623] Output: Homework problem data

[0624] Specific example of how it works: A user launches a homework app and takes a photo of the problem "5 + 3 = ?" with their camera, or types in the text "The weather is sunny today."

[0625] Step 2:

[0626] The terminal transmits the data input by the user to the cloud server.

[0627] The device transmits data via an Internet connection, and the data is given an identifying user ID.

[0628] Input: Homework problem data (image or text format) and user ID

[0629] Output: Homework data and user ID on the server

[0630] Specific example of operation: The device uploads "homework image data" and "user ID 12345" to the server.

[0631] Step 3:

[0632] The server parses the received data.

[0633] The server converts the image data into text data using OCR technology, and then divides the text data into questions using natural language processing. It also identifies the type of homework.

[0634] Input: Homework data on the server (image or text format) and user ID

[0635] Output: Parsed text data and homework type

[0636] Specific example of operation: The server uses the Google Cloud Vision API to convert the image data "5 + 3 = ?" into text, and then performs natural language processing using NLTK to recognize it as an arithmetic problem.

[0637] Step 4:

[0638] The server compares the analyzed text data with correct data in an internal database to determine whether it is correct or not.

[0639] The server temporarily stores the judgment result and uses it to generate the next feedback.

[0640] Input: Parsed text data and homework type

[0641] Output: Judgment results and answer data

[0642] Specific example of operation: The server compares the answer "5 + 3 = 9" with the correct answer "8" in the database and determines that it is incorrect.

[0643] Step 5:

[0644] The server generates feedback based on the result of the determination.

[0645] The generated feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. It is generated using a generative AI model.

[0646] Input: Judgment results and answer data

[0647] Output: Feedback data

[0648] Specific example of operation: The server inputs the prompt "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it is incorrect and provide additional practice questions" into the generative AI model, which generates feedback including an explanation and the practice question "4 + 2 = ?".

[0649] Step 6:

[0650] The server generates feedback and sends it to the device.

[0651] The terminal displays the received feedback within the application and provides it to the user.

[0652] Input: Feedback data

[0653] Output: Feedback that is displayed to the user

[0654] Specific example of operation: The server sends an explanation and additional questions in JSON format to the device, which receives it and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8," and then presents a new question, "4 + 2 = ?"

[0655] (Application example 1)

[0656] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0657] Conventional homework support systems have many shortcomings in effectively improving children's learning efficiency. In particular, they lack the ability to analyze homework answers in real time and provide prompt, appropriate feedback, making it difficult for children to progress effectively. Furthermore, conventional systems may not accurately analyze input data, resulting in the provision of incorrect feedback.

[0658] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0659] In this invention, the server includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, and a transmitting unit. This allows homework images and text data to be input via a smartphone device, analyzed by the cloud server, and the generated feedback provided to the user in real time. Furthermore, by interpreting the input data using a generative AI model, accurate analysis of the data and generation of appropriate feedback are possible.

[0660] The "input means" is a means for inputting image or text data of homework into the smartphone device.

[0661] The "receiving means" is a means for transmitting data sent from the input means to the cloud server together with the user ID.

[0662] "Analysis means" refers to a means for analyzing received data on a cloud server and interpreting the homework content using OCR technology and natural language processing.

[0663] The "judging means" is a means for comparing the text data extracted by the analyzing means with the correct answer data in the internal database to judge whether the answer is correct or incorrect.

[0664] The "feedback generating means" is a means for generating explanations and additional questions based on the judgment results and providing feedback to the user.

[0665] The "transmission means" is a means for transmitting the generated feedback to the user's smartphone device in real time.

[0666] A "cloud server" is a remote server that stores and processes data via the Internet and generates analysis results and feedback.

[0667] A "generative AI model" is an artificial intelligence model that interprets input data and generates appropriate feedback through natural language processing and template generation.

[0668] The present invention relates to a system that effectively and efficiently supports children in completing their homework. The system includes an input means using a smartphone device, an analysis means and a judgment means using a cloud server, a feedback generation means using a generative AI model, and a transmission means.

[0669] System programs and their processing

[0670] 1. Input Method

[0671] Users can take pictures of their homework or enter the details of their homework in text format using a dedicated application on their smartphone device. Using this application makes it easy to enter the homework and ensures that the data is sent accurately to the server.

[0672] 2. Receiving Method

[0673] The smartphone device sends the captured image and input text data along with the user ID to a cloud server. This receiving means requires an internet connection, and the data is uniquely identified on the cloud.

[0674] 3. Analysis method

[0675] The cloud server analyzes the received data using OCR technology (e.g., Google Vision API) or natural language processing (e.g., Google NLP, Azure Text Analytics). Image data is converted into text data, and text data is divided into questions.

[0676] 4. Judgment means

[0677] The cloud server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) and determines whether the answer is correct or incorrect. A calculation algorithm is used to make the determination.

[0678] 5. Feedback Generation Methods

[0679] The cloud server generates feedback based on the results using a generative AI model (e.g., OpenAI GPT-3). This feedback includes a correct or incorrect result, an explanation if the answer is incorrect, and additional practice questions. Templates and AI-generated explanations are used to generate the feedback.

[0680] 6. Transmission Method

[0681] The cloud server sends the generated feedback in JSON format to the smartphone device, where an application parses it and displays it to the user.

[0682] Specific usage scenarios

[0683] 1. User enters homework

[0684] The user takes a photo of their homework using a smartphone app and sends it to the server.

[0685] 2. The cloud server analyzes the data

[0686] The cloud server extracts text data from the images and analyzes the content of the homework.

[0687] 3. The cloud server determines the correct answer

[0688] The cloud server checks the homework answers against a database to determine the correct answer.

[0689] 4. The cloud server generates feedback

[0690] The cloud server generates explanations and additional questions based on the assessment results.

[0691] 5. The cloud server sends feedback

[0692] The cloud server transmits the generated feedback to the smartphone device and displays it to the user.

[0693] Prompt Sentence Examples

[0694] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[0695] Prompt statement:

[0696] Homework problem: 5 + 3 = 9

[0697] Correct answer: 8

[0698] Generate a description.

[0699]

[0700] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0701] Step 1:

[0702] The user takes a photo of their homework using their smartphone device or enters it in text format. The entered data is sent to a dedicated application along with their user ID. The entered data includes image data or text data. The user's specific action is to open the application and take a photo of their homework or enter it in text format.

[0703] Step 2:

[0704] The device uploads the data sent from the input means along with the user ID to the cloud server. At this time, the data is transferred via an internet connection. Specifically, the data is processed by converting image and text data into JSON format and sending it to the cloud server.

[0705] Step 3:

[0706] The server analyzes the received data using OCR technology and natural language processing. In the case of image data, OCR technology (e.g., Google Vision API) is used to convert it into text data, and in the case of text data, natural language processing technology (e.g., Google NLP, Azure Text Analytics) is used to separate it into questions. Specifically, the data is processed such that after the image data is converted into text data, each question is identified.

[0707] Step 4:

[0708] The server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) to determine whether the answer is correct or incorrect. The algorithm used here collates the correct answers in the analyzed text data with the correct answers in the database. The specific data calculation involves setting a correct or incorrect flag for each question.

[0709] Step 5:

[0710] The server generates feedback using a generative AI model (e.g., OpenAI GPT-3) based on the judgment results. The feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. The server sends input data to the generative AI model using prompt sentences to generate appropriate feedback. Specifically, the model generates appropriate explanation sentences and additional questions based on templates.

[0711] Step 6:

[0712] The server sends the generated feedback in JSON format to the smartphone device, where the smartphone device's application analyzes it and displays it to the user. The specific operation is to analyze the feedback data and display it to the user in a visually easy-to-understand format.

[0713] Specific prompt examples

[0714] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[0715] Prompt statement:

[0716] Homework problem: 5 + 3 = 9

[0717] Correct answer: 8

[0718] Generate a description.

[0719] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0720] The present invention provides a homework support system for children that improves children's learning efficiency and provides feedback that takes into account the user's emotions. The system includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, a transmitting unit, and an emotion engine.

[0721] System programs and their processing

[0722] 1. Input Method

[0723] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[0724] Examples:

[0725] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[0726] 2. Receiving Method

[0727] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[0728] Examples:

[0729] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[0730] 3. Analysis method

[0731] The server analyzes the received data. In particular, in the case of image data, OCR technology is used to convert the image data into text data, and in the case of text data, natural language processing is used to divide it into questions. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[0732] Examples:

[0733] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[0734] 4. Judgment means

[0735] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[0736] Examples:

[0737] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[0738] 5. Feedback Generation Methods

[0739] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[0740] Examples:

[0741] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[0742] 6. Transmission Method

[0743] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[0744] Examples:

[0745] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[0746] 7. Emotion Engine

[0747] The server uses an emotion engine to recognize the user's emotions. The emotion engine uses face recognition technology and voice analysis technology to determine the user's emotions.

[0748] Examples:

[0749] The server recognizes the user's face through the smartphone camera and determines that the user is confused, and analyzes the tone of the user's voice through the voice assistant and determines that the user is irritated.

[0750] 8. Feedback adjustment

[0751] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle and detailed explanations if the user is confused.

[0752] Examples:

[0753] If the user is confused when the server generates the feedback, it adds encouraging words such as "Try solving the problem again slowly."

[0754] Specific usage scenarios

[0755] 1. User enters homework

[0756] The user takes a photo of their homework using a smartphone app and sends it to the server.

[0757] 2. The server analyzes the data

[0758] The server extracts text data from the image and analyzes the content of the homework.

[0759] 3. The server determines the correct answer

[0760] The server checks the homework answers against a database to determine the correct answer.

[0761] 4. The server generates feedback

[0762] The server generates explanations and additional questions based on the results of the assessment.

[0763] 5. The server analyzes emotions

[0764] The server uses an emotion engine to analyze the user's emotions.

[0765] 6. The server moderates the feedback

[0766] The server adjusts the content and tone of the feedback based on the emotional data.

[0767] 7. The server sends feedback

[0768] The server generates feedback and sends it to the terminal for display to the user.

[0769] This series of processes allows users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[0770] The processing flow will be explained below.

[0771] Specific processing steps of the program

[0772] Step 1:

[0773] The user launches the smartphone app and enters the homework content. The homework can be entered by taking a photo or by entering it directly in text format.

[0774] Step 2:

[0775] To process the input data, the device sends the data to a server on the cloud. Image data is sent as an image file, and text data is sent as character data.

[0776] Step 3:

[0777] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[0778] Step 4:

[0779] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[0780] Step 5:

[0781] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[0782] Step 6:

[0783] The server uses an internal database to compare the analyzed data with the correct answer database, thereby determining the correct answer for each question.

[0784] Step 7:

[0785] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[0786] Step 8:

[0787] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[0788] Step 9:

[0789] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[0790] Step 10:

[0791] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[0792] Step 11:

[0793] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[0794] Step 12:

[0795] If the user enters an additional question, the terminal sends the question to the server again.

[0796] Step 13:

[0797] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[0798] Step 14:

[0799] The server generates a response and sends it to the terminal, which displays it to the user.

[0800] Step 15:

[0801] The server then uses an emotion engine to recognize the user's emotions. The emotion engine uses facial recognition technology to analyze the user's facial expressions and voice analysis technology to analyze the tone of voice and the way words are used.

[0802] Step 16:

[0803] The server recognizes the user's emotions based on the analysis results, determines their level of understanding and stress, and adjusts the feedback accordingly.

[0804] Step 17:

[0805] The server generates feedback, including detailed and friendly explanations and simple questions, if the user is confused.

[0806] Step 18:

[0807] The adjusted feedback is then transmitted back to the device using the transmission means, and the transmitted content includes detailed explanations and encouraging messages.

[0808] Step 19:

[0809] The device displays new feedback to the user, who receives emotion-based adjusted feedback to continue learning.

[0810] Step 20:

[0811] The server records all usage history and emotional data, which is used to personalize the next learning content. Usage history includes homework content, answer results, feedback, questions and answers, and emotional data.

[0812] Step 21:

[0813] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[0814] These processes enable users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[0815] Example 2

[0816] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0817] Previous learning support systems for children were limited to simply determining whether their homework was correct or incorrect, and were unable to provide feedback that took the user's emotions into consideration. Furthermore, they often lacked additional practice questions or detailed explanations to improve the user's learning efficiency. This led to a decline in children's motivation to learn, and made it difficult to provide effective learning support.

[0818] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0819] In this invention, the server includes an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, a transmitting means, an emotion engine, and a feedback adjusting means. After a user inputs their homework, the server analyzes the data and not only determines whether the data is correct or incorrect, but also provides feedback that takes the user's emotions into consideration. This improves the user's learning efficiency and maintains their motivation to learn. Furthermore, by providing additional practice questions and detailed explanations, more effective learning support is realized.

[0820] "Input means" refers to a device or application that allows a user to input homework in image or text format.

[0821] The "receiving means" is a device or system for receiving data sent from the input means to a server on the cloud.

[0822] "Analysis means" refers to optical character recognition technology that analyzes received data and converts image data into text data, and technology that analyzes text data using natural language processing to identify the type of question.

[0823] The "judging means" refers to an algorithm or system that compares the data extracted by the analyzing means with an internal database to judge whether the homework is correct or incorrect.

[0824] "Feedback generation means" refers to a device or software that generates feedback based on the assessment results and provides correct / incorrect results, explanations, and additional practice questions.

[0825] The "transmission means" is a device or system for transmitting the generated feedback to the user's terminal and displaying the feedback.

[0826] An "emotion engine" is a device or software that uses facial recognition and voice analysis technology to analyze a user's emotions and appropriately adjust feedback based on the emotional data.

[0827] A "feedback adjustment means" is a system or algorithm that adjusts the content and tone of feedback based on emotional data recognized by the emotion engine.

[0828] The present invention provides a homework support system that improves the efficiency of learning support for children and provides feedback that takes emotions into consideration. This system includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. The specific operation of each means is described below.

[0829] Input Method

[0830] Users use their smartphones or tablets to take pictures of their homework or input the details of their homework in text format. This input method is implemented as a dedicated application. The application provides a menu for users to select the type of homework (e.g., math, Japanese, etc.) and guides them in inputting the homework correctly.

[0831] Examples:

[0832] The user launches the smartphone app and takes a photo of their math homework, or types in the details of their Japanese homework using a keyboard. The app displays a menu for selecting the type of homework and navigates them to ensure smooth photo and input.

[0833] Receiving means

[0834] The device sends the data entered by the user to a server in the cloud. This communication is via an internet connection, and the data is uniquely identified by a user ID.

[0835] Examples:

[0836] The device uploads homework photos and text data to the cloud server in real time and assigns a user ID. A progress bar is displayed during the upload, and a notification is displayed when the upload is complete.

[0837] Analysis means

[0838] The server analyzes the data it receives. In the case of image data, it uses OCR technology to convert it into text data, and in the case of text data, it uses natural language processing to separate it into questions. It also identifies the type of question. Specifically, it uses the OCR engine and natural language processing engine installed on the server.

[0839] Examples:

[0840] The server analyzes the image of the received arithmetic problem using OCR and converts the handwritten "5 + 3 =" into text data. After conversion, it identifies it as an arithmetic addition problem.

[0841] Judgment means

[0842] The server compares the text data extracted by the analysis means with an internal database to determine whether the question is correct. This determination is made using a calculation algorithm. Specifically, a program is used to compare the answers to the questions with the database in the server.

[0843] Examples:

[0844] The server receives the answer "5 + 3 = 9" entered by the user and determines that it is incorrect by comparing it with the correct answer "8" in the database.

[0845] Feedback Generation Method

[0846] The server generates feedback based on the results. The feedback includes correct and incorrect answers, explanations for incorrect answers, and additional practice questions. Specifically, the feedback is created using templates and AI-generated explanations.

[0847] Examples:

[0848] For the incorrect answer "5 + 3 = 9," the system explains, "5 and 3 add up to 8," and then presents an additional addition problem, "4 + 2 =?"

[0849] Transmission method

[0850] The server generates feedback that is sent to the device and displayed to the user, who can then view the feedback within the app, where detailed explanations and additional questions are provided.

[0851] Examples:

[0852] The server sends the explanation and additional questions in JSON format to the device, which the device app parses and displays to the user. When the user resumes the app, a notification is displayed prompting them to view the feedback.

[0853] Emotion Engine

[0854] The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions, using facial recognition and voice analysis technologies.

[0855] Examples:

[0856] The server takes a picture of the user's face through the smartphone camera and recognizes confused expressions. It also analyzes the tone of the voice through the microphone to determine whether the user is feeling irritated.

[0857] Feedback Adjustment Means

[0858] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle, detailed explanations if the user is confused.

[0859] Examples:

[0860] If the user is stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the additional practice questions to be easier.

[0861] Prompt Sentence Examples

[0862] The homework support app screen displays the message, "Open the camera and take a photo of your math homework. Alternatively, enter the homework details in text."

[0863] In this way, the children's homework support system of the present invention can provide effective learning support while also taking into consideration the user's emotions. The overall system flow is as follows: data is acquired from the input means, sent to the server by the receiving means, analyzed by the analyzing means, judged correct or incorrect by the judging means, feedback is created by the feedback generating means, and finally provided to the user by the transmitting means. Furthermore, by using the emotion engine and feedback adjusting means, it is possible to provide optimal feedback according to the user's emotions.

[0864] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] The user enters the homework data.

[0867] Input: The user uses a smartphone app to take a picture of the homework or enter the homework content in text format.

[0868] How it works: Select the type of homework (e.g., math, Japanese) in the app, then take a photo or enter text. The app will temporarily save the image and text data.

[0869] Output: Image data or text data of the homework is generated.

[0870] Step 2:

[0871] The device sends the homework data to the server.

[0872] Input: The image or text data of the homework generated in Step 1.

[0873] How it works: Your device uploads data to a cloud server via your internet connection and assigns you a user ID. A progress bar is displayed during the upload, and you're notified when the transfer is complete.

[0874] Output: Image data or text data is saved on the cloud server.

[0875] Step 3:

[0876] The server parses the received data.

[0877] Input: Image or text data of homework stored on the server.

[0878] How it works: In the case of image data, OCR technology is used to convert it into text data. In the case of text data, natural language processing is used to divide it into questions and identify the type of question. Specifically, an OCR engine or natural language processing engine on the server is used.

[0879] Output: The analyzed text data and the type of question (math, Japanese, etc.) are obtained.

[0880] Step 4:

[0881] The server determines whether the answer is correct.

[0882] Input: The text data parsed in step 3 and the question type.

[0883] How it works: The server compares the text data with an internal database to determine whether the question is correct or incorrect, and uses a computational algorithm to evaluate the answer.

[0884] Output: Correct / incorrect results for each question are obtained.

[0885] Step 5:

[0886] The server generates the feedback.

[0887] Input: The correct / incorrect result obtained in step 4.

[0888] How it works: The server generates feedback based on the results. The feedback includes correct / incorrect answers, explanations for incorrect answers, and additional practice questions. Templates and AI-generated explanations are used.

[0889] Output: Feedback data (explanation, additional questions) is generated.

[0890] Step 6:

[0891] The server generates feedback and sends it to the device.

[0892] Input: Feedback data generated in step 5.

[0893] How it works: The cloud server sends feedback data in JSON format to the device, which the device application parses and displays to the user.

[0894] Output: Feedback is displayed on the terminal.

[0895] Step 7:

[0896] The server analyzes the user's emotions using an emotion engine.

[0897] Input: User facial expression and voice data sent from the device.

[0898] How it works: The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions. It uses facial recognition and voice analysis technology.

[0899] Output: User emotion data (e.g., confusion, irritation).

[0900] Step 8:

[0901] The server moderates the feedback.

[0902] Input: Emotion data obtained in step 7 and feedback data generated in step 5.

[0903] What it does: The server adjusts the content and tone of the feedback based on the emotion data, for example adding a gentler, more detailed explanation.

[0904] Output: Emotionally sensitive feedback is generated and sent back to the device.

[0905] Examples:

[0906] If users are stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the difficulty of additional practice problems to be easier.

[0907] This allows users to receive efficient and emotionally sensitive homework support.

[0908] (Application example 2)

[0909] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0910] To improve children's learning efficiency and provide personalized feedback according to the emotions of each individual user.

[0911] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. This enables children to study their homework effectively and receive feedback that takes their emotions into consideration.

[0912] "Input means" refers to a means by which a user inputs the contents of his / her homework in image or text format.

[0913] The "receiving means" is a means for receiving data transmitted from the input means.

[0914] "Analysis means" refers to means for analyzing received data and identifying the content and type of the problem.

[0915] The "judging means" is a means for judging whether the answer is correct or incorrect based on the analyzed data.

[0916] The "feedback generating means" is a means for generating feedback to be provided to the user based on the determination result.

[0917] The "transmitting means" is a means for transmitting the generated feedback to the user's terminal.

[0918] The "emotion engine" is a function for recognizing and analyzing the user's emotional state.

[0919] The "feedback adjustment means" is a means for adjusting the content and tone of feedback based on the emotional data recognized by the emotion engine.

[0920] This invention provides a system for supporting children's homework, and in particular generates feedback according to the emotional state of each user. This system is interconnected through terminals, a server, and a network.

[0921] System Configuration

[0922] The system includes the following means:

[0923] Input Method

[0924] Receiving means

[0925] Analysis means

[0926] Judgment means

[0927] Feedback Generation Method

[0928] Transmission method

[0929] Emotion Engine

[0930] Feedback Adjustment Means

[0931] Input Method

[0932] Users input the contents of their homework using devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs). Users can take photos of their homework or input it in text format. This input method is implemented as a dedicated application.

[0933] Receiving means

[0934] The data entered on the terminal is transmitted to a server on the cloud via an internet connection, and the receiving means is used to allow the server to receive this data.

[0935] Analysis means

[0936] The server analyzes the received data. In the case of image data, OCR technology is used to convert the image into text. In the case of text data, natural language processing (NLP) technology is used to segment the data into questions and identify the question type (e.g., math, Japanese, science, etc.).

[0937] Judgment means

[0938] The server compares the analyzed data with the correct answer data in its internal database and determines whether it is correct or not, using database matching and calculation algorithms.

[0939] Feedback Generation Method

[0940] Feedback is generated based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[0941] Transmission method

[0942] The generated feedback is sent from the server to the device, which receives it and displays it to the user. The feedback content is in a format that can be viewed within the application.

[0943] Emotion Engine

[0944] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[0945] Feedback Adjustment Means

[0946] The emotion engine recognizes emotional data and adjusts the content and tone of the feedback, for example, providing a gentle and detailed explanation if it recognizes the user as confused.

[0947] Specific examples

[0948] The user takes a photo of their homework using a smartphone app and sends it to the server. The server then uses OCR technology to convert the handwritten homework into text and analyzes it. For example, for an incorrect problem like "5 + 3 = 9," the system provides an explanation: "5 and 3 add up to 8." Furthermore, the system recognizes the user's facial expression through the camera, and if it determines that the user is confused, it adds encouraging feedback such as, "Try solving the problem again slowly."

[0949] Example prompts for generative AI models

[0950] Homework problem: 5 + 3 = 9

[0951] The user made this mistake. Please generate appropriate feedback.

[0952] feedback:

[0953] Wrong: 5 + 3 = 9 is incorrect. The correct answer is 8. Try this question: "4 + 2 = ?"

[0954] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0955] Step 1:

[0956] Users launch the application using a smartphone, tablet, smart glasses, or head-mounted display (HMD), take a photo of their homework, or enter the homework details in text format. The entered data is stored in temporary storage on the device.

[0957] Input: Homework image or text data

[0958] Output: Input homework data (saved in temporary storage)

[0959] Specific actions: The user selects the "Enter Homework" menu in the dedicated application, and either takes a photo of the homework using the camera or enters the homework content directly into the text box.

[0960] Step 2:

[0961] The device sends the entered data to a cloud server, where it is assigned a user ID and sent via an internet connection.

[0962] Input: Homework data saved in temporary storage

[0963] Output: Homework data sent to the cloud server

[0964] What it does: The application bundles the stored data and the user ID into a single data packet and uploads it to a server over the Internet.

[0965] Step 3:

[0966] The server analyzes the received data. For image data, OCR technology is used to convert the image into text data. For text data, natural language processing (NLP) technology is used to segment the data into questions and identify the type of question.

[0967] Input: Homework data received by the server

[0968] Output: Parsed text data and identified problem types

[0969] Specific operation: The server passes the received data to the analysis module, which analyzes the data using an OCR engine or NLP engine. For example, the image data is converted into text using the OCR engine, and the text data is divided into questions using the NLP engine and identified as type (math, Japanese, etc.).

[0970] Step 4:

[0971] The server compares the analyzed text data with the correct data in an internal database to determine whether it is correct or not.

[0972] Input: Parsed text data and identified problem types

[0973] Output: Correct / incorrect result for each question

[0974] Specific operation: The server uses an "algorithm module" to compare the user's answer with the correct answer data in the database and determine whether the answer is correct or incorrect.

[0975] Step 5:

[0976] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[0977] Input: Correct / incorrect result

[0978] Output: Feedback message

[0979] Specific operation: The server's "feedback generation module" uses templates and generative AI models to generate appropriate explanations based on correct and incorrect answers. For example, if the answer is incorrect, an explanation such as "5 and 3 add up to 8" is added.

[0980] Step 6:

[0981] The server sends the generated feedback to the terminal, and the user can check the feedback through the terminal application.

[0982] Input: The generated feedback message

[0983] Output: Feedback displayed on the user's terminal

[0984] Specific operation: The server's sending module sends a feedback message in JSON format to the device, and the device application parses and displays it.

[0985] Step 7:

[0986] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[0987] Input: User's facial image and voice data

[0988] Output: Recognized emotion data

[0989] Specific operation: The server's "emotion analysis module" uses facial recognition technology and voice analysis algorithms to analyze the user's emotional state (e.g., confusion, irritation, etc.).

[0990] Step 8:

[0991] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is confused, it provides a gentle and detailed explanation.

[0992] Input: Recognized emotion data and feedback message

[0993] Output: Adjusted feedback message

[0994] What happens: The feedback adjustment module uses emotion data to fine-tune the tone and content of existing feedback messages, for example adding an encouraging message like "Try solving the problem again slowly."

[0995] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0996] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0997] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0998] [Third embodiment]

[0999] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1000] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1001] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1002] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1003] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1004] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1005] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1006] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1007] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1008] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1009] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1010] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1011] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, and a transmitting means.

[1012] System programs and their processing

[1013] 1. Input Method

[1014] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[1015] Examples:

[1016] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[1017] 2. Receiving Method

[1018] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[1019] Examples:

[1020] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[1021] 3. Analysis method

[1022] The server analyzes the received data. If it is image data, it is converted into text data using OCR technology. If it is text data, it is divided into questions using natural language processing. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[1023] Examples:

[1024] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[1025] 4. Judgment means

[1026] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[1027] Examples:

[1028] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[1029] 5. Feedback Generation Methods

[1030] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[1031] Examples:

[1032] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[1033] 6. Transmission Method

[1034] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[1035] Examples:

[1036] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[1037] Specific usage scenarios

[1038] 1. User enters homework

[1039] The user takes a photo of their homework using a smartphone app and sends it to the server.

[1040] 2. The server analyzes the data

[1041] The server extracts text data from the image and analyzes the content of the homework.

[1042] 3. The server determines the correct answer

[1043] The server checks the homework answers against a database to determine the correct answer.

[1044] 4. The server generates feedback

[1045] The server generates explanations and additional questions based on the results of the assessment.

[1046] 5. The server sends feedback

[1047] The server generates feedback and sends it to the terminal for display to the user.

[1048] In this way, the user can quickly and effectively receive feedback on the content of their homework and deepen their understanding.

[1049] The processing flow will be explained below.

[1050] Specific processing steps of the program

[1051] Step 1:

[1052] The user launches the smartphone app and enters the homework content. Homework can be done by taking a photo or by entering it directly as text.

[1053] Step 2:

[1054] To process the input data, the device sends the data to a server on the cloud. If it is image data, it is sent as an image file, and if it is text data, it is sent as character data.

[1055] Step 3:

[1056] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[1057] Step 4:

[1058] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[1059] Step 5:

[1060] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[1061] Step 6:

[1062] The server uses an internal database to compare the analyzed data with a database of correct answers, thereby determining the correct answer for each question.

[1063] Step 7:

[1064] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[1065] Step 8:

[1066] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[1067] Step 9:

[1068] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[1069] Step 10:

[1070] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[1071] Step 11:

[1072] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[1073] Step 12:

[1074] If the user enters an additional question, the terminal sends the question to the server again.

[1075] Step 13:

[1076] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[1077] Step 14:

[1078] The server generates a response and sends it to the terminal, which displays it to the user.

[1079] Step 15:

[1080] The server records all usage history and uses it to personalize the learning content for the next time. Usage history includes homework content, answer results, feedback, questions and answers.

[1081] Step 16:

[1082] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[1083] Through the above process, users can efficiently complete their homework and deepen their understanding. The server also personalizes the next session based on the user's usage history, providing more effective learning support.

[1084] Example 1

[1085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1086] Conventional homework support systems are inefficient because they often rely on manual grading and feedback. They also lack a mechanism for quickly identifying the homework a user has completed and providing appropriate feedback on the content. Therefore, an effective system that can improve children's learning efficiency and provide appropriate feedback quickly is needed.

[1087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1088] In this invention, the server includes an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means, which enable the server to quickly analyze the content of the homework and provide accurate feedback.

[1089] "Input means" refers to a device or function that allows a user to input the contents of the homework in image or text format.

[1090] The "receiving means" is a device or function for receiving the homework data sent from the input means.

[1091] "Image analysis means" refers to a device or function that analyzes image data and converts the contents of the homework into text data.

[1092] The "text analysis means" is a device or function that analyzes text data and divides the homework content into questions.

[1093] The "content identification means" is a device or function that identifies the type of homework (mathematics, Japanese, etc.) from the analyzed data.

[1094] The "answer determination means" is a device or function that compares homework data with correct answer data in an internal database and determines whether each question is correct or incorrect.

[1095] The "feedback generating means" is a device or function that generates feedback (such as whether the answer is correct or incorrect, an explanation for an incorrect answer, or additional practice questions) based on the judgment result.

[1096] The "transmitting means" is a device or function that transmits the generated feedback to the user's terminal.

[1097] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means.

[1098] First, a user opens a dedicated application on a smartphone or tablet. There, the user takes a picture of the homework content with the camera or enters it directly in text format. The application used for this input method is implemented as a general smart device app. For example, this includes a case where a user launches a smartphone app and takes a picture of the arithmetic problem "5 + 3 = ?" with the camera.

[1099] Next, the device sends the input data to a cloud server via the Internet. The device assigns a user ID to the sent data to make it uniquely identifiable. For example, the device uploads "homework image data" or "text data" to the server and sends it with the user ID "12345" attached.

[1100] The received data is analyzed by the server. In the case of image data, it is converted into text data using OCR technology, and in the case of text data, it is divided into questions using natural language processing. At this time, image analysis software such as Google Cloud Vision API is used. For example, the image data received by the server, "5 + 3 = ?", is converted into text data using OCR technology and then analyzed.

[1101] Next, the server identifies the type of homework from the analyzed data (e.g., math, Japanese, etc.). This allows it to determine the appropriate answer. The answer determination means compares the correct answer data in an internal database to determine whether each question is correct. For example, the server receives an answer such as "5 + 3 = 9," compares it with the correct answer "8" in the database, and determines that it is incorrect.

[1102] The server then generates feedback based on the results. This feedback includes not only the correct answer, but also explanations and additional practice questions for incorrect answers. For example, for the incorrect answer "5 + 3 = 9," the server might explain that "the correct answer is 8" and present another addition problem, "4 + 2 = ?". This generation process uses an AI model, and an example prompt might be, "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it's incorrect and provide additional practice questions."

[1103] Finally, the feedback is sent from the server to the device, which receives it and displays it within the application. For example, the server sends the generated explanation and additional questions to the device, which receives them and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8" and also presents a new question "4 + 2 = ?"

[1104] This allows users to receive prompt and effective feedback on their homework and deepen their understanding of the material. This system helps users save time and effort and study efficiently.

[1105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1106] Step 1:

[1107] The user enters the details of the homework using a smartphone or tablet.

[1108] Specifically, the user takes a picture of the homework using the smartphone camera or enters the homework content into a text input field within the app.

[1109] Input: Homework question (image or text format)

[1110] Output: Homework problem data

[1111] Specific example of how it works: A user launches a homework app and takes a photo of the problem "5 + 3 = ?" with their camera, or types in the text "The weather is sunny today."

[1112] Step 2:

[1113] The terminal transmits the data input by the user to the cloud server.

[1114] The device transmits data via an Internet connection, and the data is given an identifying user ID.

[1115] Input: Homework problem data (image or text format) and user ID

[1116] Output: Homework data and user ID on the server

[1117] Specific example of operation: The device uploads "homework image data" and "user ID 12345" to the server.

[1118] Step 3:

[1119] The server parses the received data.

[1120] The server converts the image data into text data using OCR technology, and then divides the text data into questions using natural language processing. It also identifies the type of homework.

[1121] Input: Homework data on the server (image or text format) and user ID

[1122] Output: Parsed text data and homework type

[1123] Specific example of operation: The server uses the Google Cloud Vision API to convert the image data "5 + 3 = ?" into text, and then performs natural language processing using NLTK to recognize it as an arithmetic problem.

[1124] Step 4:

[1125] The server compares the analyzed text data with correct data in an internal database to determine whether it is correct or not.

[1126] The server temporarily stores the judgment result and uses it to generate the next feedback.

[1127] Input: Parsed text data and homework type

[1128] Output: Judgment results and answer data

[1129] Specific example of operation: The server compares the answer "5 + 3 = 9" with the correct answer "8" in the database and determines that it is incorrect.

[1130] Step 5:

[1131] The server generates feedback based on the result of the determination.

[1132] The generated feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. It is generated using a generative AI model.

[1133] Input: Judgment results and answer data

[1134] Output: Feedback data

[1135] Specific example of operation: The server inputs the prompt "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it is incorrect and provide additional practice questions" into the generative AI model, which generates feedback including an explanation and the practice question "4 + 2 = ?".

[1136] Step 6:

[1137] The server generates feedback and sends it to the device.

[1138] The terminal displays the received feedback within the application and provides it to the user.

[1139] Input: Feedback data

[1140] Output: Feedback that is displayed to the user

[1141] Specific example of operation: The server sends an explanation and additional questions in JSON format to the device, which receives it and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8," and then presents a new question, "4 + 2 = ?"

[1142] (Application example 1)

[1143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1144] Conventional homework support systems have many shortcomings in effectively improving children's learning efficiency. In particular, they lack the ability to analyze homework answers in real time and provide prompt, appropriate feedback, making it difficult for children to progress effectively. Furthermore, conventional systems may not accurately analyze input data, resulting in the provision of incorrect feedback.

[1145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1146] In this invention, the server includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, and a transmitting unit. This allows homework images and text data to be input via a smartphone device, analyzed by the cloud server, and the generated feedback provided to the user in real time. Furthermore, by interpreting the input data using a generative AI model, accurate analysis of the data and generation of appropriate feedback are possible.

[1147] The "input means" is a means for inputting image or text data of homework into the smartphone device.

[1148] The "receiving means" is a means for transmitting data sent from the input means to the cloud server together with the user ID.

[1149] "Analysis means" refers to a means for analyzing received data on a cloud server and interpreting the homework content using OCR technology and natural language processing.

[1150] The "judging means" is a means for comparing the text data extracted by the analyzing means with the correct answer data in the internal database to judge whether the answer is correct or incorrect.

[1151] The "feedback generating means" is a means for generating explanations and additional questions based on the judgment results and providing feedback to the user.

[1152] The "transmission means" is a means for transmitting the generated feedback to the user's smartphone device in real time.

[1153] A "cloud server" is a remote server that stores and processes data via the Internet and generates analysis results and feedback.

[1154] A "generative AI model" is an artificial intelligence model that interprets input data and generates appropriate feedback through natural language processing and template generation.

[1155] The present invention relates to a system that effectively and efficiently supports children in completing their homework. The system includes an input means using a smartphone device, an analysis means and a judgment means using a cloud server, a feedback generation means using a generative AI model, and a transmission means.

[1156] System programs and their processing

[1157] 1. Input Method

[1158] Users can take pictures of their homework or enter the details of their homework in text format using a dedicated application on their smartphone device. Using this application makes it easy to enter the homework and ensures that the data is sent accurately to the server.

[1159] 2. Receiving Method

[1160] The smartphone device sends the captured image and input text data along with the user ID to a cloud server. This receiving means requires an internet connection, and the data is uniquely identified on the cloud.

[1161] 3. Analysis method

[1162] The cloud server analyzes the received data using OCR technology (e.g., Google Vision API) or natural language processing (e.g., Google NLP, Azure Text Analytics). Image data is converted into text data, and text data is divided into questions.

[1163] 4. Judgment means

[1164] The cloud server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) and determines whether the answer is correct or incorrect. A calculation algorithm is used to make the determination.

[1165] 5. Feedback Generation Methods

[1166] The cloud server generates feedback based on the results using a generative AI model (e.g., OpenAI GPT-3). This feedback includes a correct or incorrect result, an explanation if the answer is incorrect, and additional practice questions. Templates and AI-generated explanations are used to generate the feedback.

[1167] 6. Transmission Method

[1168] The cloud server sends the generated feedback in JSON format to the smartphone device, where an application parses it and displays it to the user.

[1169] Specific usage scenarios

[1170] 1. User enters homework

[1171] The user takes a photo of their homework using a smartphone app and sends it to the server.

[1172] 2. The cloud server analyzes the data

[1173] The cloud server extracts text data from the images and analyzes the content of the homework.

[1174] 3. The cloud server determines the correct answer

[1175] The cloud server checks the homework answers against a database to determine the correct answer.

[1176] 4. The cloud server generates feedback

[1177] The cloud server generates explanations and additional questions based on the assessment results.

[1178] 5. The cloud server sends feedback

[1179] The cloud server transmits the generated feedback to the smartphone device and displays it to the user.

[1180] Prompt Sentence Examples

[1181] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[1182] Prompt statement:

[1183] Homework problem: 5 + 3 = 9

[1184] Correct answer: 8

[1185] Generate a description.

[1186]

[1187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1188] Step 1:

[1189] The user takes a photo of their homework using their smartphone device or enters it in text format. The entered data is sent to a dedicated application along with their user ID. The entered data includes image data or text data. The user's specific action is to open the application and take a photo of their homework or enter it in text format.

[1190] Step 2:

[1191] The device uploads the data sent from the input means along with the user ID to the cloud server. At this time, the data is transferred via an internet connection. Specifically, the data is processed by converting image and text data into JSON format and sending it to the cloud server.

[1192] Step 3:

[1193] The server analyzes the received data using OCR technology and natural language processing. In the case of image data, OCR technology (e.g., Google Vision API) is used to convert it into text data, and in the case of text data, natural language processing technology (e.g., Google NLP, Azure Text Analytics) is used to separate it into questions. Specifically, the data is processed such that after the image data is converted into text data, each question is identified.

[1194] Step 4:

[1195] The server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) to determine whether the answer is correct or incorrect. The algorithm used here collates the correct answers in the analyzed text data with the correct answers in the database. The specific data calculation involves setting a correct or incorrect flag for each question.

[1196] Step 5:

[1197] The server generates feedback using a generative AI model (e.g., OpenAI GPT-3) based on the judgment results. The feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. The server sends input data to the generative AI model using prompt sentences to generate appropriate feedback. Specifically, the model generates appropriate explanation sentences and additional questions based on templates.

[1198] Step 6:

[1199] The server sends the generated feedback in JSON format to the smartphone device, where the smartphone device's application analyzes it and displays it to the user. The specific operation is to analyze the feedback data and display it to the user in a visually easy-to-understand format.

[1200] Specific prompt examples

[1201] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[1202] Prompt statement:

[1203] Homework problem: 5 + 3 = 9

[1204] Correct answer: 8

[1205] Generate a description.

[1206] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1207] The present invention provides a homework support system for children that improves children's learning efficiency and provides feedback that takes into account the user's emotions. The system includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, a transmitting unit, and an emotion engine.

[1208] System programs and their processing

[1209] 1. Input Method

[1210] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[1211] Examples:

[1212] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[1213] 2. Receiving Method

[1214] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[1215] Examples:

[1216] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[1217] 3. Analysis method

[1218] The server analyzes the received data. In particular, in the case of image data, OCR technology is used to convert the image data into text data, and in the case of text data, natural language processing is used to divide it into questions. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[1219] Examples:

[1220] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[1221] 4. Judgment means

[1222] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[1223] Examples:

[1224] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[1225] 5. Feedback Generation Methods

[1226] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[1227] Examples:

[1228] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[1229] 6. Transmission Method

[1230] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[1231] Examples:

[1232] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[1233] 7. Emotion Engine

[1234] The server uses an emotion engine to recognize the user's emotions. The emotion engine uses face recognition technology and voice analysis technology to determine the user's emotions.

[1235] Examples:

[1236] The server recognizes the user's face through the smartphone camera and determines that the user is confused, and analyzes the tone of the user's voice through the voice assistant and determines that the user is irritated.

[1237] 8. Feedback adjustment

[1238] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle and detailed explanations if the user is confused.

[1239] Examples:

[1240] If the user is confused when the server generates the feedback, it adds encouraging words such as "Try solving the problem again slowly."

[1241] Specific usage scenarios

[1242] 1. User enters homework

[1243] The user takes a photo of their homework using a smartphone app and sends it to the server.

[1244] 2. The server analyzes the data

[1245] The server extracts text data from the image and analyzes the content of the homework.

[1246] 3. The server determines the correct answer

[1247] The server checks the homework answers against a database to determine the correct answer.

[1248] 4. The server generates feedback

[1249] The server generates explanations and additional questions based on the results of the assessment.

[1250] 5. The server analyzes emotions

[1251] The server uses an emotion engine to analyze the user's emotions.

[1252] 6. The server moderates the feedback

[1253] The server adjusts the content and tone of the feedback based on the emotional data.

[1254] 7. The server sends feedback

[1255] The server generates feedback and sends it to the terminal for display to the user.

[1256] This series of processes allows users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[1257] The processing flow will be explained below.

[1258] Specific processing steps of the program

[1259] Step 1:

[1260] The user launches the smartphone app and enters the homework content. The homework can be entered by taking a photo or by entering it directly in text format.

[1261] Step 2:

[1262] To process the input data, the device sends the data to a server on the cloud. Image data is sent as an image file, and text data is sent as character data.

[1263] Step 3:

[1264] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[1265] Step 4:

[1266] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[1267] Step 5:

[1268] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[1269] Step 6:

[1270] The server uses an internal database to compare the analyzed data with the correct answer database, thereby determining the correct answer for each question.

[1271] Step 7:

[1272] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[1273] Step 8:

[1274] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[1275] Step 9:

[1276] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[1277] Step 10:

[1278] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[1279] Step 11:

[1280] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[1281] Step 12:

[1282] If the user enters an additional question, the terminal sends the question to the server again.

[1283] Step 13:

[1284] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[1285] Step 14:

[1286] The server generates a response and sends it to the terminal, which displays it to the user.

[1287] Step 15:

[1288] The server then uses an emotion engine to recognize the user's emotions. The emotion engine uses facial recognition technology to analyze the user's facial expressions and voice analysis technology to analyze the tone of voice and the way words are used.

[1289] Step 16:

[1290] The server recognizes the user's emotions based on the analysis results, determines their level of understanding and stress, and adjusts the feedback accordingly.

[1291] Step 17:

[1292] The server generates feedback, including detailed and friendly explanations and simple questions, if the user is confused.

[1293] Step 18:

[1294] The adjusted feedback is then transmitted back to the device using the transmission means, and the transmitted content includes detailed explanations and encouraging messages.

[1295] Step 19:

[1296] The device displays new feedback to the user, who receives emotion-based adjusted feedback to continue learning.

[1297] Step 20:

[1298] The server records all usage history and emotional data, which is used to personalize the next learning content. Usage history includes homework content, answer results, feedback, questions and answers, and emotional data.

[1299] Step 21:

[1300] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[1301] These processes enable users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[1302] Example 2

[1303] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1304] Previous learning support systems for children were limited to simply determining whether their homework was correct or incorrect, and were unable to provide feedback that took the user's emotions into consideration. Furthermore, they often lacked additional practice questions or detailed explanations to improve the user's learning efficiency. This led to a decline in children's motivation to learn, and made it difficult to provide effective learning support.

[1305] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1306] In this invention, the server includes an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, a transmitting means, an emotion engine, and a feedback adjusting means. After a user inputs their homework, the server analyzes the data and not only determines whether the data is correct or incorrect, but also provides feedback that takes the user's emotions into consideration. This improves the user's learning efficiency and maintains their motivation to learn. Furthermore, by providing additional practice questions and detailed explanations, more effective learning support is realized.

[1307] "Input means" refers to a device or application that allows a user to input homework in image or text format.

[1308] The "receiving means" is a device or system for receiving data sent from the input means to a server on the cloud.

[1309] "Analysis means" refers to optical character recognition technology that analyzes received data and converts image data into text data, and technology that analyzes text data using natural language processing to identify the type of question.

[1310] The "judging means" refers to an algorithm or system that compares the data extracted by the analyzing means with an internal database to judge whether the homework is correct or incorrect.

[1311] "Feedback generation means" refers to a device or software that generates feedback based on the assessment results and provides correct / incorrect results, explanations, and additional practice questions.

[1312] The "transmission means" is a device or system for transmitting the generated feedback to the user's terminal and displaying the feedback.

[1313] An "emotion engine" is a device or software that uses facial recognition and voice analysis technology to analyze a user's emotions and appropriately adjust feedback based on the emotional data.

[1314] A "feedback adjustment means" is a system or algorithm that adjusts the content and tone of feedback based on emotional data recognized by the emotion engine.

[1315] The present invention provides a homework support system that improves the efficiency of learning support for children and provides feedback that takes emotions into consideration. This system includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. The specific operation of each means is described below.

[1316] Input Method

[1317] Users use their smartphones or tablets to take pictures of their homework or input the details of their homework in text format. This input method is implemented as a dedicated application. The application provides a menu for users to select the type of homework (e.g., math, Japanese, etc.) and guides them in inputting the homework correctly.

[1318] Examples:

[1319] The user launches the smartphone app and takes a photo of their math homework, or types in the details of their Japanese homework using a keyboard. The app displays a menu for selecting the type of homework and navigates them to ensure smooth photo and input.

[1320] Receiving means

[1321] The device sends the data entered by the user to a server in the cloud. This communication is via an internet connection, and the data is uniquely identified by a user ID.

[1322] Examples:

[1323] The device uploads homework photos and text data to the cloud server in real time and assigns a user ID. A progress bar is displayed during the upload, and a notification is displayed when the upload is complete.

[1324] Analysis means

[1325] The server analyzes the data it receives. In the case of image data, it uses OCR technology to convert it into text data, and in the case of text data, it uses natural language processing to separate it into questions. It also identifies the type of question. Specifically, it uses the OCR engine and natural language processing engine installed on the server.

[1326] Examples:

[1327] The server analyzes the image of the received arithmetic problem using OCR and converts the handwritten "5 + 3 =" into text data. After conversion, it identifies it as an arithmetic addition problem.

[1328] Judgment means

[1329] The server compares the text data extracted by the analysis means with an internal database to determine whether the question is correct. This determination is made using a calculation algorithm. Specifically, a program is used to compare the answers to the questions with the database in the server.

[1330] Examples:

[1331] The server receives the answer "5 + 3 = 9" entered by the user and determines that it is incorrect by comparing it with the correct answer "8" in the database.

[1332] Feedback Generation Method

[1333] The server generates feedback based on the results. The feedback includes correct and incorrect answers, explanations for incorrect answers, and additional practice questions. Specifically, the feedback is created using templates and AI-generated explanations.

[1334] Examples:

[1335] For the incorrect answer "5 + 3 = 9," the system explains, "5 and 3 add up to 8," and then presents an additional addition problem, "4 + 2 =?"

[1336] Transmission method

[1337] The server generates feedback that is sent to the device and displayed to the user, who can then view the feedback within the app, where detailed explanations and additional questions are provided.

[1338] Examples:

[1339] The server sends the explanation and additional questions in JSON format to the device, which the device app parses and displays to the user. When the user resumes the app, a notification is displayed prompting them to view the feedback.

[1340] Emotion Engine

[1341] The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions, using facial recognition and voice analysis technologies.

[1342] Examples:

[1343] The server takes a picture of the user's face through the smartphone camera and recognizes confused expressions. It also analyzes the tone of the voice through the microphone to determine whether the user is feeling irritated.

[1344] Feedback Adjustment Means

[1345] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle, detailed explanations if the user is confused.

[1346] Examples:

[1347] If the user is stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the additional practice questions to be easier.

[1348] Prompt Sentence Examples

[1349] The homework support app screen displays the message, "Open the camera and take a photo of your math homework. Alternatively, enter the homework details in text."

[1350] In this way, the children's homework support system of the present invention can provide effective learning support while also taking into consideration the user's emotions. The overall system flow is as follows: data is acquired from the input means, sent to the server by the receiving means, analyzed by the analyzing means, judged correct or incorrect by the judging means, feedback is created by the feedback generating means, and finally provided to the user by the transmitting means. Furthermore, by using the emotion engine and feedback adjusting means, it is possible to provide optimal feedback according to the user's emotions.

[1351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1352] Step 1:

[1353] The user enters the homework data.

[1354] Input: The user uses a smartphone app to take a picture of the homework or enter the homework content in text format.

[1355] How it works: Select the type of homework (e.g., math, Japanese) in the app, then take a photo or enter text. The app will temporarily save the image and text data.

[1356] Output: Image data or text data of the homework is generated.

[1357] Step 2:

[1358] The device sends the homework data to the server.

[1359] Input: The image or text data of the homework generated in Step 1.

[1360] How it works: Your device uploads data to a cloud server via your internet connection and assigns you a user ID. A progress bar is displayed during the upload, and you're notified when the transfer is complete.

[1361] Output: Image data or text data is saved on the cloud server.

[1362] Step 3:

[1363] The server parses the received data.

[1364] Input: Image or text data of homework stored on the server.

[1365] How it works: In the case of image data, OCR technology is used to convert it into text data. In the case of text data, natural language processing is used to divide it into questions and identify the type of question. Specifically, an OCR engine or natural language processing engine on the server is used.

[1366] Output: The analyzed text data and the type of question (math, Japanese, etc.) are obtained.

[1367] Step 4:

[1368] The server determines whether the answer is correct.

[1369] Input: The text data parsed in step 3 and the question type.

[1370] How it works: The server compares the text data with an internal database to determine whether the question is correct or incorrect, and uses a computational algorithm to evaluate the answer.

[1371] Output: Correct / incorrect results for each question are obtained.

[1372] Step 5:

[1373] The server generates the feedback.

[1374] Input: The correct / incorrect result obtained in step 4.

[1375] How it works: The server generates feedback based on the results. The feedback includes correct / incorrect answers, explanations for incorrect answers, and additional practice questions. Templates and AI-generated explanations are used.

[1376] Output: Feedback data (explanation, additional questions) is generated.

[1377] Step 6:

[1378] The server generates feedback and sends it to the device.

[1379] Input: Feedback data generated in step 5.

[1380] How it works: The cloud server sends feedback data in JSON format to the device, which the device application parses and displays to the user.

[1381] Output: Feedback is displayed on the terminal.

[1382] Step 7:

[1383] The server analyzes the user's emotions using an emotion engine.

[1384] Input: User facial expression and voice data sent from the device.

[1385] How it works: The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions. It uses facial recognition and voice analysis technology.

[1386] Output: User emotion data (e.g., confusion, irritation).

[1387] Step 8:

[1388] The server moderates the feedback.

[1389] Input: Emotion data obtained in step 7 and feedback data generated in step 5.

[1390] What it does: The server adjusts the content and tone of the feedback based on the emotion data, for example adding a gentler, more detailed explanation.

[1391] Output: Emotionally sensitive feedback is generated and sent back to the device.

[1392] Examples:

[1393] If users are stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the difficulty of additional practice problems to be easier.

[1394] This allows users to receive efficient and emotionally sensitive homework support.

[1395] (Application example 2)

[1396] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1397] To improve children's learning efficiency and provide personalized feedback according to the emotions of each individual user.

[1398] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. This enables children to study their homework effectively and receive feedback that takes their emotions into consideration.

[1399] "Input means" refers to a means by which a user inputs the contents of his / her homework in image or text format.

[1400] The "receiving means" is a means for receiving data transmitted from the input means.

[1401] "Analysis means" refers to means for analyzing received data and identifying the content and type of the problem.

[1402] The "judging means" is a means for judging whether the answer is correct or incorrect based on the analyzed data.

[1403] The "feedback generating means" is a means for generating feedback to be provided to the user based on the determination result.

[1404] The "transmitting means" is a means for transmitting the generated feedback to the user's terminal.

[1405] The "emotion engine" is a function for recognizing and analyzing the user's emotional state.

[1406] The "feedback adjustment means" is a means for adjusting the content and tone of feedback based on the emotional data recognized by the emotion engine.

[1407] This invention provides a system for supporting children's homework, and in particular generates feedback according to the emotional state of each user. This system is interconnected through terminals, a server, and a network.

[1408] System Configuration

[1409] The system includes the following means:

[1410] Input Method

[1411] Receiving means

[1412] Analysis means

[1413] Judgment means

[1414] Feedback Generation Method

[1415] Transmission method

[1416] Emotion Engine

[1417] Feedback Adjustment Means

[1418] Input Method

[1419] Users input the contents of their homework using devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs). Users can take photos of their homework or input it in text format. This input method is implemented as a dedicated application.

[1420] Receiving means

[1421] The data entered on the terminal is transmitted to a server on the cloud via an internet connection, and the receiving means is used to allow the server to receive this data.

[1422] Analysis means

[1423] The server analyzes the received data. In the case of image data, OCR technology is used to convert the image into text. In the case of text data, natural language processing (NLP) technology is used to segment the data into questions and identify the question type (e.g., math, Japanese, science, etc.).

[1424] Judgment means

[1425] The server compares the analyzed data with the correct answer data in its internal database and determines whether it is correct or not, using database matching and calculation algorithms.

[1426] Feedback Generation Method

[1427] Feedback is generated based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[1428] Transmission method

[1429] The generated feedback is sent from the server to the device, which receives it and displays it to the user. The feedback content is in a format that can be viewed within the application.

[1430] Emotion Engine

[1431] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[1432] Feedback Adjustment Means

[1433] The emotion engine recognizes emotional data and adjusts the content and tone of the feedback, for example, providing a gentle and detailed explanation if it recognizes the user as confused.

[1434] Specific examples

[1435] The user takes a photo of their homework using a smartphone app and sends it to the server. The server then uses OCR technology to convert the handwritten homework into text and analyzes it. For example, for an incorrect problem like "5 + 3 = 9," the system provides an explanation: "5 and 3 add up to 8." Furthermore, the system recognizes the user's facial expression through the camera, and if it determines that the user is confused, it adds encouraging feedback such as, "Try solving the problem again slowly."

[1436] Example prompts for generative AI models

[1437] Homework problem: 5 + 3 = 9

[1438] The user made this mistake. Please generate appropriate feedback.

[1439] feedback:

[1440] Wrong: 5 + 3 = 9 is incorrect. The correct answer is 8. Try this question: "4 + 2 = ?"

[1441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1442] Step 1:

[1443] Users launch the application using a smartphone, tablet, smart glasses, or head-mounted display (HMD), take a photo of their homework, or enter the homework details in text format. The entered data is stored in temporary storage on the device.

[1444] Input: Homework image or text data

[1445] Output: Input homework data (saved in temporary storage)

[1446] Specific actions: The user selects the "Enter Homework" menu in the dedicated application, and either takes a photo of the homework using the camera or enters the homework content directly into the text box.

[1447] Step 2:

[1448] The device sends the entered data to a cloud server, where it is assigned a user ID and sent via an internet connection.

[1449] Input: Homework data saved in temporary storage

[1450] Output: Homework data sent to the cloud server

[1451] What it does: The application bundles the stored data and the user ID into a single data packet and uploads it to a server over the Internet.

[1452] Step 3:

[1453] The server analyzes the received data. For image data, OCR technology is used to convert the image into text data. For text data, natural language processing (NLP) technology is used to segment the data into questions and identify the type of question.

[1454] Input: Homework data received by the server

[1455] Output: Parsed text data and identified problem types

[1456] Specific operation: The server passes the received data to the analysis module, which analyzes the data using an OCR engine or NLP engine. For example, the image data is converted into text using the OCR engine, and the text data is divided into questions using the NLP engine and identified as type (math, Japanese, etc.).

[1457] Step 4:

[1458] The server compares the analyzed text data with the correct data in an internal database to determine whether it is correct or not.

[1459] Input: Parsed text data and identified problem types

[1460] Output: Correct / incorrect result for each question

[1461] Specific operation: The server uses an "algorithm module" to compare the user's answer with the correct answer data in the database and determine whether the answer is correct or incorrect.

[1462] Step 5:

[1463] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[1464] Input: Correct / incorrect result

[1465] Output: Feedback message

[1466] Specific operation: The server's "feedback generation module" uses templates and generative AI models to generate appropriate explanations based on correct and incorrect answers. For example, if the answer is incorrect, an explanation such as "5 and 3 add up to 8" is added.

[1467] Step 6:

[1468] The server sends the generated feedback to the terminal, and the user can check the feedback through the terminal application.

[1469] Input: The generated feedback message

[1470] Output: Feedback displayed on the user's terminal

[1471] Specific operation: The server's sending module sends a feedback message in JSON format to the device, and the device application parses and displays it.

[1472] Step 7:

[1473] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[1474] Input: User's facial image and voice data

[1475] Output: Recognized emotion data

[1476] Specific operation: The server's "emotion analysis module" uses facial recognition technology and voice analysis algorithms to analyze the user's emotional state (e.g., confusion, irritation, etc.).

[1477] Step 8:

[1478] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is confused, it provides a gentle and detailed explanation.

[1479] Input: Recognized emotion data and feedback message

[1480] Output: Adjusted feedback message

[1481] What happens: The feedback adjustment module uses emotion data to fine-tune the tone and content of existing feedback messages, for example adding an encouraging message like "Try solving the problem again slowly."

[1482] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1483] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1484] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1485] [Fourth embodiment]

[1486] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1487] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1488] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1489] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1490] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1491] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1492] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1493] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1494] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1495] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1496] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1497] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1498] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1499] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, and a transmitting means.

[1500] System programs and their processing

[1501] 1. Input Method

[1502] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[1503] Examples:

[1504] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[1505] 2. Receiving Method

[1506] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[1507] Examples:

[1508] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[1509] 3. Analysis method

[1510] The server analyzes the received data. If it is image data, it is converted into text data using OCR technology. If it is text data, it is divided into questions using natural language processing. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[1511] Examples:

[1512] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[1513] 4. Judgment means

[1514] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[1515] Examples:

[1516] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[1517] 5. Feedback Generation Methods

[1518] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[1519] Examples:

[1520] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[1521] 6. Transmission Method

[1522] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[1523] Examples:

[1524] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[1525] Specific usage scenarios

[1526] 1. User enters homework

[1527] The user takes a photo of their homework using a smartphone app and sends it to the server.

[1528] 2. The server analyzes the data

[1529] The server extracts text data from the image and analyzes the content of the homework.

[1530] 3. The server determines the correct answer

[1531] The server checks the homework answers against a database to determine the correct answer.

[1532] 4. The server generates feedback

[1533] The server generates explanations and additional questions based on the results of the assessment.

[1534] 5. The server sends feedback

[1535] The server generates feedback and sends it to the terminal for display to the user.

[1536] In this way, the user can quickly and effectively receive feedback on the content of their homework and deepen their understanding.

[1537] The processing flow will be explained below.

[1538] Specific processing steps of the program

[1539] Step 1:

[1540] The user launches the smartphone app and enters the homework content. Homework can be done by taking a photo or by entering it directly as text.

[1541] Step 2:

[1542] To process the input data, the device sends the data to a server on the cloud. If it is image data, it is sent as an image file, and if it is text data, it is sent as character data.

[1543] Step 3:

[1544] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[1545] Step 4:

[1546] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[1547] Step 5:

[1548] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[1549] Step 6:

[1550] The server uses an internal database to compare the analyzed data with a database of correct answers, thereby determining the correct answer for each question.

[1551] Step 7:

[1552] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[1553] Step 8:

[1554] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[1555] Step 9:

[1556] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[1557] Step 10:

[1558] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[1559] Step 11:

[1560] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[1561] Step 12:

[1562] If the user enters an additional question, the terminal sends the question to the server again.

[1563] Step 13:

[1564] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[1565] Step 14:

[1566] The server generates a response and sends it to the terminal, which displays it to the user.

[1567] Step 15:

[1568] The server records all usage history and uses it to personalize the learning content for the next time. Usage history includes homework content, answer results, feedback, questions and answers.

[1569] Step 16:

[1570] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[1571] Through the above process, users can efficiently complete their homework and deepen their understanding. The server also personalizes the next session based on the user's usage history, providing more effective learning support.

[1572] Example 1

[1573] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1574] Conventional homework support systems are inefficient because they often rely on manual grading and feedback. They also lack a mechanism for quickly identifying the homework a user has completed and providing appropriate feedback on the content. Therefore, an effective system that can improve children's learning efficiency and provide appropriate feedback quickly is needed.

[1575] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1576] In this invention, the server includes an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means, which enable the server to quickly analyze the content of the homework and provide accurate feedback.

[1577] "Input means" refers to a device or function that allows a user to input the contents of the homework in image or text format.

[1578] The "receiving means" is a device or function for receiving the homework data sent from the input means.

[1579] "Image analysis means" refers to a device or function that analyzes image data and converts the contents of the homework into text data.

[1580] The "text analysis means" is a device or function that analyzes text data and divides the homework content into questions.

[1581] The "content identification means" is a device or function that identifies the type of homework (mathematics, Japanese, etc.) from the analyzed data.

[1582] The "answer determination means" is a device or function that compares homework data with correct answer data in an internal database and determines whether each question is correct or incorrect.

[1583] The "feedback generating means" is a device or function that generates feedback (such as whether the answer is correct or incorrect, an explanation for an incorrect answer, or additional practice questions) based on the judgment result.

[1584] The "transmitting means" is a device or function that transmits the generated feedback to the user's terminal.

[1585] The present invention provides a homework support system for children to improve their learning efficiency. This system mainly comprises an input means, a receiving means, an image analysis means, a text analysis means, a content identification means, an answer determination means, a feedback generation means, and a transmission means.

[1586] First, a user opens a dedicated application on a smartphone or tablet. There, the user takes a picture of the homework content with the camera or enters it directly in text format. The application used for this input method is implemented as a general smart device app. For example, this includes a case where a user launches a smartphone app and takes a picture of the arithmetic problem "5 + 3 = ?" with the camera.

[1587] Next, the device sends the input data to a cloud server via the Internet. The device assigns a user ID to the sent data to make it uniquely identifiable. For example, the device uploads "homework image data" or "text data" to the server and sends it with the user ID "12345" attached.

[1588] The received data is analyzed by the server. In the case of image data, it is converted into text data using OCR technology, and in the case of text data, it is divided into questions using natural language processing. At this time, image analysis software such as Google Cloud Vision API is used. For example, the image data received by the server, "5 + 3 = ?", is converted into text data using OCR technology and then analyzed.

[1589] Next, the server identifies the type of homework from the analyzed data (e.g., math, Japanese, etc.). This allows it to determine the appropriate answer. The answer determination means compares the correct answer data in an internal database to determine whether each question is correct. For example, the server receives an answer such as "5 + 3 = 9," compares it with the correct answer "8" in the database, and determines that it is incorrect.

[1590] The server then generates feedback based on the results. This feedback includes not only the correct answer, but also explanations and additional practice questions for incorrect answers. For example, for the incorrect answer "5 + 3 = 9," the server might explain that "the correct answer is 8" and present another addition problem, "4 + 2 = ?". This generation process uses an AI model, and an example prompt might be, "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it's incorrect and provide additional practice questions."

[1591] Finally, the feedback is sent from the server to the device, which receives it and displays it within the application. For example, the server sends the generated explanation and additional questions to the device, which receives them and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8" and also presents a new question "4 + 2 = ?"

[1592] This allows users to receive prompt and effective feedback on their homework and deepen their understanding of the material. This system helps users save time and effort and study efficiently.

[1593] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1594] Step 1:

[1595] The user enters the details of the homework using a smartphone or tablet.

[1596] Specifically, the user takes a picture of the homework using the smartphone camera or enters the homework content into a text input field within the app.

[1597] Input: Homework question (image or text format)

[1598] Output: Homework problem data

[1599] Specific example of how it works: A user launches a homework app and takes a photo of the problem "5 + 3 = ?" with their camera, or types in the text "The weather is sunny today."

[1600] Step 2:

[1601] The terminal transmits the data input by the user to the cloud server.

[1602] The device transmits data via an Internet connection, and the data is given an identifying user ID.

[1603] Input: Homework problem data (image or text format) and user ID

[1604] Output: Homework data and user ID on the server

[1605] Specific example of operation: The device uploads "homework image data" and "user ID 12345" to the server.

[1606] Step 3:

[1607] The server parses the received data.

[1608] The server converts the image data into text data using OCR technology, and then divides the text data into questions using natural language processing. It also identifies the type of homework.

[1609] Input: Homework data on the server (image or text format) and user ID

[1610] Output: Parsed text data and homework type

[1611] Specific example of operation: The server uses the Google Cloud Vision API to convert the image data "5 + 3 = ?" into text, and then performs natural language processing using NLTK to recognize it as an arithmetic problem.

[1612] Step 4:

[1613] The server compares the analyzed text data with correct data in an internal database to determine whether it is correct or not.

[1614] The server temporarily stores the judgment result and uses it to generate the next feedback.

[1615] Input: Parsed text data and homework type

[1616] Output: Judgment results and answer data

[1617] Specific example of operation: The server compares the answer "5 + 3 = 9" with the correct answer "8" in the database and determines that it is incorrect.

[1618] Step 5:

[1619] The server generates feedback based on the result of the determination.

[1620] The generated feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. It is generated using a generative AI model.

[1621] Input: Judgment results and answer data

[1622] Output: Feedback data

[1623] Specific example of operation: The server inputs the prompt "The answer 5 + 3 = 9 is incorrect. The correct answer is 8. Please explain why it is incorrect and provide additional practice questions" into the generative AI model, which generates feedback including an explanation and the practice question "4 + 2 = ?".

[1624] Step 6:

[1625] The server generates feedback and sends it to the device.

[1626] The terminal displays the received feedback within the application and provides it to the user.

[1627] Input: Feedback data

[1628] Output: Feedback that is displayed to the user

[1629] Specific example of operation: The server sends an explanation and additional questions in JSON format to the device, which receives it and displays to the user "5 + 3 = 9 is incorrect. The correct answer is 8," and then presents a new question, "4 + 2 = ?"

[1630] (Application example 1)

[1631] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1632] Conventional homework support systems have many shortcomings in effectively improving children's learning efficiency. In particular, they lack the ability to analyze homework answers in real time and provide prompt, appropriate feedback, making it difficult for children to progress effectively. Furthermore, conventional systems may not accurately analyze input data, resulting in the provision of incorrect feedback.

[1633] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1634] In this invention, the server includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, and a transmitting unit. This allows homework images and text data to be input via a smartphone device, analyzed by the cloud server, and the generated feedback provided to the user in real time. Furthermore, by interpreting the input data using a generative AI model, accurate analysis of the data and generation of appropriate feedback are possible.

[1635] The "input means" is a means for inputting image or text data of homework into the smartphone device.

[1636] The "receiving means" is a means for transmitting data sent from the input means to the cloud server together with the user ID.

[1637] "Analysis means" refers to a means for analyzing received data on a cloud server and interpreting the homework content using OCR technology and natural language processing.

[1638] The "judging means" is a means for comparing the text data extracted by the analyzing means with the correct answer data in the internal database to judge whether the answer is correct or incorrect.

[1639] The "feedback generating means" is a means for generating explanations and additional questions based on the judgment results and providing feedback to the user.

[1640] The "transmission means" is a means for transmitting the generated feedback to the user's smartphone device in real time.

[1641] A "cloud server" is a remote server that stores and processes data via the Internet and generates analysis results and feedback.

[1642] A "generative AI model" is an artificial intelligence model that interprets input data and generates appropriate feedback through natural language processing and template generation.

[1643] The present invention relates to a system that effectively and efficiently supports children in completing their homework. The system includes an input means using a smartphone device, an analysis means and a judgment means using a cloud server, a feedback generation means using a generative AI model, and a transmission means.

[1644] System programs and their processing

[1645] 1. Input Method

[1646] Users can take pictures of their homework or enter the details of their homework in text format using a dedicated application on their smartphone device. Using this application makes it easy to enter the homework and ensures that the data is sent accurately to the server.

[1647] 2. Receiving Method

[1648] The smartphone device sends the captured image and input text data along with the user ID to a cloud server. This receiving means requires an internet connection, and the data is uniquely identified on the cloud.

[1649] 3. Analysis method

[1650] The cloud server analyzes the received data using OCR technology (e.g., Google Vision API) or natural language processing (e.g., Google NLP, Azure Text Analytics). Image data is converted into text data, and text data is divided into questions.

[1651] 4. Judgment means

[1652] The cloud server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) and determines whether the answer is correct or incorrect. A calculation algorithm is used to make the determination.

[1653] 5. Feedback Generation Methods

[1654] The cloud server generates feedback based on the results using a generative AI model (e.g., OpenAI GPT-3). This feedback includes a correct or incorrect result, an explanation if the answer is incorrect, and additional practice questions. Templates and AI-generated explanations are used to generate the feedback.

[1655] 6. Transmission Method

[1656] The cloud server sends the generated feedback in JSON format to the smartphone device, where an application parses it and displays it to the user.

[1657] Specific usage scenarios

[1658] 1. User enters homework

[1659] The user takes a photo of their homework using a smartphone app and sends it to the server.

[1660] 2. The cloud server analyzes the data

[1661] The cloud server extracts text data from the images and analyzes the content of the homework.

[1662] 3. The cloud server determines the correct answer

[1663] The cloud server checks the homework answers against a database to determine the correct answer.

[1664] 4. The cloud server generates feedback

[1665] The cloud server generates explanations and additional questions based on the assessment results.

[1666] 5. The cloud server sends feedback

[1667] The cloud server transmits the generated feedback to the smartphone device and displays it to the user.

[1668] Prompt Sentence Examples

[1669] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[1670] Prompt statement:

[1671] Homework problem: 5 + 3 = 9

[1672] Correct answer: 8

[1673] Generate a description.

[1674]

[1675] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1676] Step 1:

[1677] The user takes a photo of their homework using their smartphone device or enters it in text format. The entered data is sent to a dedicated application along with their user ID. The entered data includes image data or text data. The user's specific action is to open the application and take a photo of their homework or enter it in text format.

[1678] Step 2:

[1679] The device uploads the data sent from the input means along with the user ID to the cloud server. At this time, the data is transferred via an internet connection. Specifically, the data is processed by converting image and text data into JSON format and sending it to the cloud server.

[1680] Step 3:

[1681] The server analyzes the received data using OCR technology and natural language processing. In the case of image data, OCR technology (e.g., Google Vision API) is used to convert it into text data, and in the case of text data, natural language processing technology (e.g., Google NLP, Azure Text Analytics) is used to separate it into questions. Specifically, the data is processed such that after the image data is converted into text data, each question is identified.

[1682] Step 4:

[1683] The server compares the analyzed text data with the correct answer data stored in an internal database (e.g., MySQL, MongoDB) to determine whether the answer is correct or incorrect. The algorithm used here collates the correct answers in the analyzed text data with the correct answers in the database. The specific data calculation involves setting a correct or incorrect flag for each question.

[1684] Step 5:

[1685] The server generates feedback using a generative AI model (e.g., OpenAI GPT-3) based on the judgment results. The feedback includes correct / incorrect results, explanations for incorrect answers, and additional practice questions. The server sends input data to the generative AI model using prompt sentences to generate appropriate feedback. Specifically, the model generates appropriate explanation sentences and additional questions based on templates.

[1686] Step 6:

[1687] The server sends the generated feedback in JSON format to the smartphone device, where the smartphone device's application analyzes it and displays it to the user. The specific operation is to analyze the feedback data and display it to the user in a visually easy-to-understand format.

[1688] Specific prompt examples

[1689] "Generate the correct answer and explanation for the following homework problem. If the answer is "5 + 3 = 9," please show that the correct answer is "8" and generate an explanation."

[1690] Prompt statement:

[1691] Homework problem: 5 + 3 = 9

[1692] Correct answer: 8

[1693] Generate a description.

[1694] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1695] The present invention provides a homework support system for children that improves children's learning efficiency and provides feedback that takes into account the user's emotions. The system includes an input unit, a receiving unit, an analyzing unit, a determining unit, a feedback generating unit, a transmitting unit, and an emotion engine.

[1696] System programs and their processing

[1697] 1. Input Method

[1698] Users can use their smartphones or tablets to take pictures of their homework and input the details of their homework in text format. This input method is implemented as a dedicated application.

[1699] Examples:

[1700] The user opens the smartphone app and takes a photo of their math homework, or enters the details of their Japanese homework directly into the app.

[1701] 2. Receiving Method

[1702] The device sends the data entered by the user to a server in the cloud. This communication is done via an internet connection, and the data is assigned a user ID.

[1703] Examples:

[1704] The device uploads photos and text data to the server and uniquely identifies the data by assigning a user ID.

[1705] 3. Analysis method

[1706] The server analyzes the received data. In particular, in the case of image data, OCR technology is used to convert the image data into text data, and in the case of text data, natural language processing is used to divide it into questions. The analysis method identifies the type of question (e.g., mathematics, Japanese, science, etc.).

[1707] Examples:

[1708] The server uses OCR technology to parse handwritten math problems and convert them to text, for example recognizing "5 + 3 =" as "5 + 3 =".

[1709] 4. Judgment means

[1710] The server compares the text data extracted by the analysis means with the correct answer data in an internal database, thereby determining whether each question is correct or incorrect. This determination method uses database collation and calculation algorithms.

[1711] Examples:

[1712] The server receives the answer "5 + 3 = 9" and checks it against the correct answer "8" in the database, determining that it is incorrect.

[1713] 5. Feedback Generation Methods

[1714] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and additional practice questions. This generation method uses templates and AI-generated explanations.

[1715] Examples:

[1716] For the incorrect answer "5 + 3 = 9," an explanation such as "5 and 3 add up to 8" and a similar addition problem "4 + 2 =?" are provided.

[1717] 6. Transmission Method

[1718] The server sends the generated feedback to the device, which receives it and displays it to the user. The feedback content is in a format that can be confirmed within the application.

[1719] Examples:

[1720] The server sends explanations and additional questions in JSON format to the terminal, which the terminal application parses and displays to the user.

[1721] 7. Emotion Engine

[1722] The server uses an emotion engine to recognize the user's emotions. The emotion engine uses face recognition technology and voice analysis technology to determine the user's emotions.

[1723] Examples:

[1724] The server recognizes the user's face through the smartphone camera and determines that the user is confused, and analyzes the tone of the user's voice through the voice assistant and determines that the user is irritated.

[1725] 8. Feedback adjustment

[1726] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle and detailed explanations if the user is confused.

[1727] Examples:

[1728] If the user is confused when the server generates the feedback, it adds encouraging words such as "Try solving the problem again slowly."

[1729] Specific usage scenarios

[1730] 1. User enters homework

[1731] The user takes a photo of their homework using a smartphone app and sends it to the server.

[1732] 2. The server analyzes the data

[1733] The server extracts text data from the image and analyzes the content of the homework.

[1734] 3. The server determines the correct answer

[1735] The server checks the homework answers against a database to determine the correct answer.

[1736] 4. The server generates feedback

[1737] The server generates explanations and additional questions based on the results of the assessment.

[1738] 5. The server analyzes emotions

[1739] The server uses an emotion engine to analyze the user's emotions.

[1740] 6. The server moderates the feedback

[1741] The server adjusts the content and tone of the feedback based on the emotional data.

[1742] 7. The server sends feedback

[1743] The server generates feedback and sends it to the terminal for display to the user.

[1744] This series of processes allows users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[1745] The processing flow will be explained below.

[1746] Specific processing steps of the program

[1747] Step 1:

[1748] The user launches the smartphone app and enters the homework content. The homework can be entered by taking a photo or by entering it directly in text format.

[1749] Step 2:

[1750] To process the input data, the device sends the data to a server on the cloud. Image data is sent as an image file, and text data is sent as character data.

[1751] Step 3:

[1752] The server receives the data sent from the user using the receiving means. Each piece of data is assigned a user ID.

[1753] Step 4:

[1754] In the case of image data, the server uses OCR technology as an analysis means to convert the image data into text data, and extracts each homework question as text data.

[1755] Step 5:

[1756] The server analyzes the text data using natural language processing technology and separates each homework question into its type (e.g., math, Japanese, science, etc.).

[1757] Step 6:

[1758] The server uses an internal database to compare the analyzed data with the correct answer database, thereby determining the correct answer for each question.

[1759] Step 7:

[1760] The server uses a determination means to determine whether each question is correct or incorrect based on the collation results. If the answer is incorrect, it identifies which part is incorrect.

[1761] Step 8:

[1762] Based on the results of the evaluation, the server uses a feedback generation means to generate feedback for the user, including information on whether the answer was correct or incorrect, and a detailed explanation if the answer was incorrect.

[1763] Step 9:

[1764] The server generates explanations and additional sample questions for incorrectly answered questions, allowing users to understand their mistakes and study again.

[1765] Step 10:

[1766] After generating the feedback, the server uses the transmission means to transmit the feedback to the terminal, the transmitted content including explanations and additional questions.

[1767] Step 11:

[1768] The device displays the received feedback to the user, who can review it and ask additional questions if necessary.

[1769] Step 12:

[1770] If the user enters an additional question, the terminal sends the question to the server again.

[1771] Step 13:

[1772] The server analyzes the received question and searches a relevant knowledge database to generate an appropriate answer.

[1773] Step 14:

[1774] The server generates a response and sends it to the terminal, which displays it to the user.

[1775] Step 15:

[1776] The server then uses an emotion engine to recognize the user's emotions. The emotion engine uses facial recognition technology to analyze the user's facial expressions and voice analysis technology to analyze the tone of voice and the way words are used.

[1777] Step 16:

[1778] The server recognizes the user's emotions based on the analysis results, determines their level of understanding and stress, and adjusts the feedback accordingly.

[1779] Step 17:

[1780] The server generates feedback, including detailed and friendly explanations and simple questions, if the user is confused.

[1781] Step 18:

[1782] The adjusted feedback is then transmitted back to the device using the transmission means, and the transmitted content includes detailed explanations and encouraging messages.

[1783] Step 19:

[1784] The device displays new feedback to the user, who receives emotion-based adjusted feedback to continue learning.

[1785] Step 20:

[1786] The server records all usage history and emotional data, which is used to personalize the next learning content. Usage history includes homework content, answer results, feedback, questions and answers, and emotional data.

[1787] Step 21:

[1788] At the end of the month, the server calculates the fee based on the number of times and duration of use and issues a bill to the user.

[1789] These processes enable users to receive efficient and emotionally sensitive homework support. The server personalizes the next session based on usage history and emotional data, providing more effective learning support.

[1790] Example 2

[1791] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1792] Previous learning support systems for children were limited to simply determining whether their homework was correct or incorrect, and were unable to provide feedback that took the user's emotions into consideration. Furthermore, they often lacked additional practice questions or detailed explanations to improve the user's learning efficiency. This led to a decline in children's motivation to learn, and made it difficult to provide effective learning support.

[1793] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1794] In this invention, the server includes an input means, a receiving means, an analyzing means, a determining means, a feedback generating means, a transmitting means, an emotion engine, and a feedback adjusting means. After a user inputs their homework, the server analyzes the data and not only determines whether the data is correct or incorrect, but also provides feedback that takes the user's emotions into consideration. This improves the user's learning efficiency and maintains their motivation to learn. Furthermore, by providing additional practice questions and detailed explanations, more effective learning support is realized.

[1795] "Input means" refers to a device or application that allows a user to input homework in image or text format.

[1796] The "receiving means" is a device or system for receiving data sent from the input means to a server on the cloud.

[1797] "Analysis means" refers to optical character recognition technology that analyzes received data and converts image data into text data, and technology that analyzes text data using natural language processing to identify the type of question.

[1798] The "judging means" refers to an algorithm or system that compares the data extracted by the analyzing means with an internal database to judge whether the homework is correct or incorrect.

[1799] "Feedback generation means" refers to a device or software that generates feedback based on the assessment results and provides correct / incorrect results, explanations, and additional practice questions.

[1800] The "transmission means" is a device or system for transmitting the generated feedback to the user's terminal and displaying the feedback.

[1801] An "emotion engine" is a device or software that uses facial recognition and voice analysis technology to analyze a user's emotions and appropriately adjust feedback based on the emotional data.

[1802] A "feedback adjustment means" is a system or algorithm that adjusts the content and tone of feedback based on emotional data recognized by the emotion engine.

[1803] The present invention provides a homework support system that improves the efficiency of learning support for children and provides feedback that takes emotions into consideration. This system includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. The specific operation of each means is described below.

[1804] Input Method

[1805] Users use their smartphones or tablets to take pictures of their homework or input the details of their homework in text format. This input method is implemented as a dedicated application. The application provides a menu for users to select the type of homework (e.g., math, Japanese, etc.) and guides them in inputting the homework correctly.

[1806] Examples:

[1807] The user launches the smartphone app and takes a photo of their math homework, or types in the details of their Japanese homework using a keyboard. The app displays a menu for selecting the type of homework and navigates them to ensure smooth photo and input.

[1808] Receiving means

[1809] The device sends the data entered by the user to a server in the cloud. This communication is via an internet connection, and the data is uniquely identified by a user ID.

[1810] Examples:

[1811] The device uploads homework photos and text data to the cloud server in real time and assigns a user ID. A progress bar is displayed during the upload, and a notification is displayed when the upload is complete.

[1812] Analysis means

[1813] The server analyzes the data it receives. In the case of image data, it uses OCR technology to convert it into text data, and in the case of text data, it uses natural language processing to separate it into questions. It also identifies the type of question. Specifically, it uses the OCR engine and natural language processing engine installed on the server.

[1814] Examples:

[1815] The server analyzes the image of the received arithmetic problem using OCR and converts the handwritten "5 + 3 =" into text data. After conversion, it identifies it as an arithmetic addition problem.

[1816] Judgment means

[1817] The server compares the text data extracted by the analysis means with an internal database to determine whether the question is correct. This determination is made using a calculation algorithm. Specifically, a program is used to compare the answers to the questions with the database in the server.

[1818] Examples:

[1819] The server receives the answer "5 + 3 = 9" entered by the user and determines that it is incorrect by comparing it with the correct answer "8" in the database.

[1820] Feedback Generation Method

[1821] The server generates feedback based on the results. The feedback includes correct and incorrect answers, explanations for incorrect answers, and additional practice questions. Specifically, the feedback is created using templates and AI-generated explanations.

[1822] Examples:

[1823] For the incorrect answer "5 + 3 = 9," the system explains, "5 and 3 add up to 8," and then presents an additional addition problem, "4 + 2 =?"

[1824] Transmission method

[1825] The server generates feedback that is sent to the device and displayed to the user, who can then view the feedback within the app, where detailed explanations and additional questions are provided.

[1826] Examples:

[1827] The server sends the explanation and additional questions in JSON format to the device, which the device app parses and displays to the user. When the user resumes the app, a notification is displayed prompting them to view the feedback.

[1828] Emotion Engine

[1829] The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions, using facial recognition and voice analysis technologies.

[1830] Examples:

[1831] The server takes a picture of the user's face through the smartphone camera and recognizes confused expressions. It also analyzes the tone of the voice through the microphone to determine whether the user is feeling irritated.

[1832] Feedback Adjustment Means

[1833] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine, for example, providing gentle, detailed explanations if the user is confused.

[1834] Examples:

[1835] If the user is stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the additional practice questions to be easier.

[1836] Prompt Sentence Examples

[1837] The homework support app screen displays the message, "Open the camera and take a photo of your math homework. Alternatively, enter the homework details in text."

[1838] In this way, the children's homework support system of the present invention can provide effective learning support while also taking into consideration the user's emotions. The overall system flow is as follows: data is acquired from the input means, sent to the server by the receiving means, analyzed by the analyzing means, judged correct or incorrect by the judging means, feedback is created by the feedback generating means, and finally provided to the user by the transmitting means. Furthermore, by using the emotion engine and feedback adjusting means, it is possible to provide optimal feedback according to the user's emotions.

[1839] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1840] Step 1:

[1841] The user enters the homework data.

[1842] Input: The user uses a smartphone app to take a picture of the homework or enter the homework content in text format.

[1843] How it works: Select the type of homework (e.g., math, Japanese) in the app, then take a photo or enter text. The app will temporarily save the image and text data.

[1844] Output: Image data or text data of the homework is generated.

[1845] Step 2:

[1846] The device sends the homework data to the server.

[1847] Input: The image or text data of the homework generated in Step 1.

[1848] How it works: Your device uploads data to a cloud server via your internet connection and assigns you a user ID. A progress bar is displayed during the upload, and you're notified when the transfer is complete.

[1849] Output: Image data or text data is saved on the cloud server.

[1850] Step 3:

[1851] The server parses the received data.

[1852] Input: Image or text data of homework stored on the server.

[1853] How it works: In the case of image data, OCR technology is used to convert it into text data. In the case of text data, natural language processing is used to divide it into questions and identify the type of question. Specifically, an OCR engine or natural language processing engine on the server is used.

[1854] Output: The analyzed text data and the type of question (math, Japanese, etc.) are obtained.

[1855] Step 4:

[1856] The server determines whether the answer is correct.

[1857] Input: The text data parsed in step 3 and the question type.

[1858] How it works: The server compares the text data with an internal database to determine whether the question is correct or incorrect, and uses a computational algorithm to evaluate the answer.

[1859] Output: Correct / incorrect results for each question are obtained.

[1860] Step 5:

[1861] The server generates the feedback.

[1862] Input: The correct / incorrect result obtained in step 4.

[1863] How it works: The server generates feedback based on the results. The feedback includes correct / incorrect answers, explanations for incorrect answers, and additional practice questions. Templates and AI-generated explanations are used.

[1864] Output: Feedback data (explanation, additional questions) is generated.

[1865] Step 6:

[1866] The server generates feedback and sends it to the device.

[1867] Input: Feedback data generated in step 5.

[1868] How it works: The cloud server sends feedback data in JSON format to the device, which the device application parses and displays to the user.

[1869] Output: Feedback is displayed on the terminal.

[1870] Step 7:

[1871] The server analyzes the user's emotions using an emotion engine.

[1872] Input: User facial expression and voice data sent from the device.

[1873] How it works: The server uses the smartphone's camera and microphone to analyze the user's facial expressions and tone of voice to determine their emotions. It uses facial recognition and voice analysis technology.

[1874] Output: User emotion data (e.g., confusion, irritation).

[1875] Step 8:

[1876] The server moderates the feedback.

[1877] Input: Emotion data obtained in step 7 and feedback data generated in step 5.

[1878] What it does: The server adjusts the content and tone of the feedback based on the emotion data, for example adding a gentler, more detailed explanation.

[1879] Output: Emotionally sensitive feedback is generated and sent back to the device.

[1880] Examples:

[1881] If users are stumped, add gentle encouragement to the feedback, such as "Try again slowly," and adjust the difficulty of additional practice problems to be easier.

[1882] This allows users to receive efficient and emotionally sensitive homework support.

[1883] (Application example 2)

[1884] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1885] To improve children's learning efficiency and provide personalized feedback according to the emotions of each individual user.

[1886] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes input means, receiving means, analysis means, determination means, feedback generation means, transmission means, an emotion engine, and feedback adjustment means. This enables children to study their homework effectively and receive feedback that takes their emotions into consideration.

[1887] "Input means" refers to a means by which a user inputs the contents of his / her homework in image or text format.

[1888] The "receiving means" is a means for receiving data transmitted from the input means.

[1889] "Analysis means" refers to means for analyzing received data and identifying the content and type of the problem.

[1890] The "judging means" is a means for judging whether the answer is correct or incorrect based on the analyzed data.

[1891] The "feedback generating means" is a means for generating feedback to be provided to the user based on the determination result.

[1892] The "transmitting means" is a means for transmitting the generated feedback to the user's terminal.

[1893] The "emotion engine" is a function for recognizing and analyzing the user's emotional state.

[1894] The "feedback adjustment means" is a means for adjusting the content and tone of feedback based on the emotional data recognized by the emotion engine.

[1895] This invention provides a system for supporting children's homework, and in particular generates feedback according to the emotional state of each user. This system is interconnected through terminals, a server, and a network.

[1896] System Configuration

[1897] The system includes the following means:

[1898] Input Method

[1899] Receiving means

[1900] Analysis means

[1901] Judgment means

[1902] Feedback Generation Method

[1903] Transmission method

[1904] Emotion Engine

[1905] Feedback Adjustment Means

[1906] Input Method

[1907] Users input the contents of their homework using devices such as smartphones, tablets, smart glasses, and head-mounted displays (HMDs). Users can take photos of their homework or input it in text format. This input method is implemented as a dedicated application.

[1908] Receiving means

[1909] The data entered on the terminal is transmitted to a server on the cloud via an internet connection, and the receiving means is used to allow the server to receive this data.

[1910] Analysis means

[1911] The server analyzes the received data. In the case of image data, OCR technology is used to convert the image into text. In the case of text data, natural language processing (NLP) technology is used to segment the data into questions and identify the question type (e.g., math, Japanese, science, etc.).

[1912] Judgment means

[1913] The server compares the analyzed data with the correct answer data in its internal database and determines whether it is correct or not, using database matching and calculation algorithms.

[1914] Feedback Generation Method

[1915] Feedback is generated based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[1916] Transmission method

[1917] The generated feedback is sent from the server to the device, which receives it and displays it to the user. The feedback content is in a format that can be viewed within the application.

[1918] Emotion Engine

[1919] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[1920] Feedback Adjustment Means

[1921] The emotion engine recognizes emotional data and adjusts the content and tone of the feedback, for example, providing a gentle and detailed explanation if it recognizes the user as confused.

[1922] Specific examples

[1923] The user takes a photo of their homework using a smartphone app and sends it to the server. The server then uses OCR technology to convert the handwritten homework into text and analyzes it. For example, for an incorrect problem like "5 + 3 = 9," the system provides an explanation: "5 and 3 add up to 8." Furthermore, the system recognizes the user's facial expression through the camera, and if it determines that the user is confused, it adds encouraging feedback such as, "Try solving the problem again slowly."

[1924] Example prompts for generative AI models

[1925] Homework problem: 5 + 3 = 9

[1926] The user made this mistake. Please generate appropriate feedback.

[1927] feedback:

[1928] Wrong: 5 + 3 = 9 is incorrect. The correct answer is 8. Try this question: "4 + 2 = ?"

[1929] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1930] Step 1:

[1931] Users launch the application using a smartphone, tablet, smart glasses, or head-mounted display (HMD), take a photo of their homework, or enter the homework details in text format. The entered data is stored in temporary storage on the device.

[1932] Input: Homework image or text data

[1933] Output: Input homework data (saved in temporary storage)

[1934] Specific actions: The user selects the "Enter Homework" menu in the dedicated application, and either takes a photo of the homework using the camera or enters the homework content directly into the text box.

[1935] Step 2:

[1936] The device sends the entered data to a cloud server, where it is assigned a user ID and sent via an internet connection.

[1937] Input: Homework data saved in temporary storage

[1938] Output: Homework data sent to the cloud server

[1939] What it does: The application bundles the stored data and the user ID into a single data packet and uploads it to a server over the Internet.

[1940] Step 3:

[1941] The server analyzes the received data. For image data, OCR technology is used to convert the image into text data. For text data, natural language processing (NLP) technology is used to segment the data into questions and identify the type of question.

[1942] Input: Homework data received by the server

[1943] Output: Parsed text data and identified problem types

[1944] Specific operation: The server passes the received data to the analysis module, which analyzes the data using an OCR engine or NLP engine. For example, the image data is converted into text using the OCR engine, and the text data is divided into questions using the NLP engine and identified as type (math, Japanese, etc.).

[1945] Step 4:

[1946] The server compares the analyzed text data with the correct data in an internal database to determine whether it is correct or not.

[1947] Input: Parsed text data and identified problem types

[1948] Output: Correct / incorrect result for each question

[1949] Specific operation: The server uses an "algorithm module" to compare the user's answer with the correct answer data in the database and determine whether the answer is correct or incorrect.

[1950] Step 5:

[1951] The server generates feedback based on the results, including correct / incorrect results, explanations for incorrect answers, and even additional practice questions, using templates and generative AI models.

[1952] Input: Correct / incorrect result

[1953] Output: Feedback message

[1954] Specific operation: The server's "feedback generation module" uses templates and generative AI models to generate appropriate explanations based on correct and incorrect answers. For example, if the answer is incorrect, an explanation such as "5 and 3 add up to 8" is added.

[1955] Step 6:

[1956] The server sends the generated feedback to the terminal, and the user can check the feedback through the terminal application.

[1957] Input: The generated feedback message

[1958] Output: Feedback displayed on the user's terminal

[1959] Specific operation: The server's sending module sends a feedback message in JSON format to the device, and the device application parses and displays it.

[1960] Step 7:

[1961] The server recognizes the user's emotional state using an emotion engine, which uses facial recognition and voice analysis technologies to determine the user's emotions.

[1962] Input: User's facial image and voice data

[1963] Output: Recognized emotion data

[1964] Specific operation: The server's "emotion analysis module" uses facial recognition technology and voice analysis algorithms to analyze the user's emotional state (e.g., confusion, irritation, etc.).

[1965] Step 8:

[1966] The server adjusts the content and tone of the feedback based on the emotional data recognized by the emotion engine. For example, if the server determines that the user is confused, it provides a gentle and detailed explanation.

[1967] Input: Recognized emotion data and feedback message

[1968] Output: Adjusted feedback message

[1969] What happens: The feedback adjustment module uses emotion data to fine-tune the tone and content of existing feedback messages, for example adding an encouraging message like "Try solving the problem again slowly."

[1970] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1971] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1972] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1973] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1974] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1975] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1976] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1977] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1978] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1979] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1980] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1981] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1982] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1983] 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.

[1984] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1985] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1986] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1987] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1988] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1989] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1990] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1991] The following is further disclosed regarding the above embodiment.

[1992] (Claim 1)

[1993] An input means;

[1994] receiving means;

[1995] Analysis means;

[1996] A determination means;

[1997] a feedback generating means;

[1998] A transmitting means;

[1999] A system including:

[2000] (Claim 2)

[2001] 2. The system according to claim 1, wherein the input means is for the user to input the homework in image or text format.

[2002] (Claim 3)

[2003] 2. The system according to claim 1, wherein the receiving means is for receiving data transmitted from the input means.

[2004] (Claim 4)

[2005] 2. The system according to claim 1, wherein the analyzing means uses OCR technology to convert the image data received by the receiving means into text data.

[2006] (Claim 5)

[2007] 2. The system according to claim 1, wherein the determining means checks the text data analyzed by the analyzing means against a correct answer database to determine whether the answer is correct or incorrect.

[2008] (Claim 6)

[2009] 2. The system according to claim 1, wherein the feedback generating means generates feedback to the user based on the result of the determination made by the determining means.

[2010] (Claim 7)

[2011] 2. The system according to claim 1, wherein the transmitting means transmits the generated feedback to the input means of the user.

[2012] (Claim 8)

[2013] 2. The system according to claim 1, wherein the analyzing means analyzes text data of homework input by the user and divides the data into question types.

[2014] (Claim 9)

[2015] 10. The system of claim 1, wherein the feedback generating means generates explanations for incorrectly answered questions and provides additional sample questions.

[2016] (Claim 10)

[2017] 2. The system according to claim 1, wherein the transmitting means receives a question from a user and transmits an answer to the question.

[2018] (Claim 11)

[2019] 2. The system according to claim 1, wherein the input means records the user's usage history and is used to personalize the next learning content.

[2020] "Example 1"

[2021] (Claim 1)

[2022] An input means;

[2023] receiving means;

[2024] Image analysis means;

[2025] A text analysis means;

[2026] content identification means;

[2027] An answer determination means;

[2028] a feedback generating means;

[2029] A transmitting means;

[2030] A system including:

[2031] (Claim 2)

[2032] 2. The system according to claim 1, further comprising an input means for a user to input homework in image or text form.

[2033] (Claim 3)

[2034] 2. The system of claim 1, further comprising receiving means for receiving data transmitted from the input means.

[2035] "Application Example 1"

[2036] (Claim 1)

[2037] An input means;

[2038] receiving means;

[2039] Analysis means;

[2040] A determination means;

[2041] a feedback generating means;

[2042] A transmitting means;

[2043] The system includes a means for inputting image or text data of homework via a smartphone device, analyzing it on a cloud server, and providing the generated feedback to the user in real time.

[2044] (Claim 2)

[2045] The system of claim 1, wherein the input means is for the user to input homework in image or text format, and the input data is interpreted using a generative AI model.

[2046] (Claim 3)

[2047] 2. The system according to claim 1, wherein the receiving means receives the data transmitted from the input means and transmits the data together with the user ID to the cloud server.

[2048] "Example 2: Combining Emotion Engines"

[2049] (Claim 1)

[2050] An input means;

[2051] receiving means;

[2052] Analysis means;

[2053] A determination means;

[2054] a feedback generating means;

[2055] A transmitting means;

[2056] Emotion engine and

[2057] a feedback adjustment means;

[2058] A system including:

[2059] (Claim 2)

[2060] 2. The system according to claim 1, wherein the input means is for a user to input homework in image or text format, and the receiving means is for transmitting data sent from the input means to a server on the cloud.

[2061] (Claim 3)

[2062] 2. The system according to claim 1, wherein the analysis means uses optical character recognition technology to convert image data into character data and technology to analyze text data using natural language processing to identify the type of problem.

[2063] "Application example 2 when combining emotion engines"

[2064] (Claim 1)

[2065] An input means;

[2066] receiving means;

[2067] Analysis means;

[2068] A determination means;

[2069] a feedback generating means;

[2070] A transmitting means;

[2071] Emotion engine and

[2072] a feedback adjustment means;

[2073] A system including:

[2074] (Claim 2)

[2075] 2. The system according to claim 1, wherein the input means is for the user to input the homework in image or text format.

[2076] (Claim 3)

[2077] 2. The system according to claim 1, wherein the receiving means is for receiving data transmitted from the input means. [Explanation of symbols]

[2078] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. An input means; receiving means; Analysis means; A determination means; a feedback generating means; A transmitting means; A system including:

2. 2. The system according to claim 1, wherein the input means allows the user to input the homework in image or text format.

3. 2. The system of claim 1, wherein the receiving means is for receiving data transmitted from the input means.

4. 2. The system according to claim 1, wherein the analyzing means uses OCR technology to convert the image data received by the receiving means into text data.

5. 2. The system according to claim 1, wherein the determining means checks the text data analyzed by the analyzing means against a correct answer database to determine whether the answer is correct or incorrect.

6. 2. The system according to claim 1, wherein the feedback generating means generates feedback to the user based on the result of the determination made by the determining means.

7. 2. The system according to claim 1, wherein the transmitting means transmits the generated feedback to the input means of the user.

8. 2. The system according to claim 1, wherein the analyzing means analyzes the text data of the homework input by the user and divides the data into question types.

9. 10. The system of claim 1, wherein the feedback generating means generates explanations for incorrectly answered questions and provides additional sample questions.

10. 2. The system according to claim 1, wherein the transmitting means receives a question from a user and transmits an answer to the question.

11. 2. The system according to claim 1, wherein the input means records the user's usage history and is used to personalize the next learning content.

Images