System

Abstract

A system is provided.SOLUTION: A system, comprising: camera means for a terminal to capture a character image of a user; transmitting means for transmitting the captured image to a server; server means for receiving the image; analyzing means for analyzing the received image and evaluating handwriting, shape and stroke order; feedback generating means for generating personalized feedback based on the analysis result; returning means for returning the feedback to the terminal; and displaying means for displaying the feedback.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] When children practice writing, they face difficulties in self-evaluating and correcting their writing, and they lack the motivation to continue practicing. In particular, parents' evaluation of their children's handwriting tends to be subjective and inaccurate, and there are no concrete tools to help parents and children continue learning in a fun way. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system including a camera means for a terminal to capture an image of a user's characters, a transmission means for transmitting the captured image to a server, a server means for receiving the image, an analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, a return means for returning the feedback to the terminal, and a display means for displaying the feedback. This makes it possible to provide a mechanism for providing objective and specific feedback on a child's handwriting and encouraging continuous learning. Furthermore, the feedback generation means includes a means for generating a personalized learning plan based on the user's past feedback history, thereby providing an efficient and individualized learning experience.

[0006] A "terminal" is an electronic device operated by a user that captures and transmits images and displays feedback.

[0007] The "camera means" is a device or function that uses the camera function installed in the terminal to capture an image of the characters entered by the user.

[0008] "Transmission means" refers to the function and protocol for transmitting the captured image to the server via the network.

[0009] "Server means" refers to a computer system for receiving and processing data sent from a terminal via the Internet or other network.

[0010] "Analysis means" refers to algorithms, programs, and AI models that analyze image data received by the server and evaluate the handwriting, shape, and stroke order of characters.

[0011] The "feedback generation means" refers to a function or algorithm that generates specific feedback to the user based on the analyzed information.

[0012] The "returning means" refers to a function or interface for sending the generated feedback to the terminal and returning it to the user.

[0013] "Display means" refers to a screen or interface for visually displaying the feedback received by the terminal to the user.

[0014] "Feedback history" is a database or recording system that shows a record of the feedback a user has received and stores past evaluations and findings.

[0015] A "personalized learning plan" provides an optimized learning plan and practice method based on the user's individual progress and past feedback history. [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 relates to a system for analyzing images of characters written by a child and providing feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, and a display means.

[0038] User inputs image of text

[0039] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[0040] The device sends the image to the server

[0041] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[0042] The server receives the image

[0043] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used in the next analysis step.

[0044] The server analyzes the image

[0045] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[0046] Feedback Generation

[0047] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[0048] Sending and Viewing Feedback

[0049] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[0050] Track progress and generate study plans

[0051] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[0052] Specific examples

[0053] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is a bit awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. The user can see this feedback and instruct the child to practice writing "ri" again.

[0054] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to study together in a fun and effective way.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The device captures the user's image of the text. The user launches the device's camera app and takes a picture of the text written by the child. The device temporarily stores the captured image in memory.

[0058] Step 2:

[0059] The device sends the captured image to the server. The device converts the captured image into Base64 format and sends it to the server using an HTTP POST request. The image data is encrypted using a network connection.

[0060] Step 3:

[0061] The server receives the image. The server receives the HTTP request and obtains the transmitted image data. It decodes the image data and saves it as a file. The saved image is used for subsequent processing.

[0062] Step 4:

[0063] The server analyzes the image. It reads the saved image file and uses an AI model to detect character regions within the image. After the character regions are detected, it performs character recognition and evaluates the handwriting, shape, and stroke order. Image processing algorithms and deep learning technology are applied for character recognition.

[0064] Step 5:

[0065] The server generates feedback. Based on the analysis results, the server generates specific feedback to the user in text format. The feedback includes evaluations such as "Excellent!" or "Needs improvement."

[0066] Step 6:

[0067] The server returns the generated feedback to the device. The server encodes the feedback in text format and sends it to the device as an HTTP response. The feedback is saved in the user's past feedback history.

[0068] Step 7:

[0069] The device receives and displays the feedback. The device decodes the feedback received from the server and displays it in a format that is easy for the user to read. The user can check this feedback and use it to improve their next practice.

[0070] Step 8:

[0071] The server tracks the user's progress. The server records and analyzes the user's learning progress based on the user's feedback history. If necessary, it generates a personalized learning plan.

[0072] Step 9:

[0073] The server generates a personalized learning plan. The server takes into account the user's past feedback history and generates a learning plan that includes the optimal practice method and character practice order. This learning plan is provided as feedback the next time the user practices.

[0074] The above are the specific processing steps of the system based on the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[0075] Example 1

[0076] 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."

[0077] In conventional character practice systems, evaluation of a child's handwriting is subjective, making it difficult to obtain objective feedback. Furthermore, the feedback is temporary, making it difficult to obtain continuous learning benefits. Furthermore, feedback and learning plans tailored to individual learning progress are not provided, preventing efficient learning.

[0078] 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.

[0079] In this invention, the server includes an analysis means for analyzing the received image data and evaluating character identification, handwriting, shape, and stroke order; a feedback generation means for generating feedback based on the analysis results; and a return means for returning the generated feedback to the terminal. This allows the user to receive objective and specific feedback on the child's character practice. Furthermore, by providing a personalized learning plan based on past feedback history, continuous and individualized learning can be achieved.

[0080] "User" refers to a person who uses the system, specifically a parent or educator who supports children in practicing writing.

[0081] "Text image" refers to image data of text written by a child that is captured by the user using the device's camera.

[0082] "Photographing means" refers to the camera function built into the device, which the user uses to capture an image of the child's text.

[0083] "Transmission means" refers to the means for transmitting image data from a terminal to a server via the Internet. Specifically, an HTTP POST request is used.

[0084] The term "server device" refers to a combination of hardware and software for receiving, storing, and analyzing image data sent from a terminal.

[0085] "Analysis means" refers to the algorithms and AI models that analyze image data within the server device and evaluate character identification, handwriting, shape, and stroke order.

[0086] "Feedback generation means" refers to the means for generating feedback to be provided to users based on the analysis results, specifically using an AI model or a rule-based engine.

[0087] The "returning means" refers to a means for transmitting the generated feedback information from the server to the terminal. Specifically, an HTTP response is used.

[0088] The "display means" refers to a UI (user interface) for displaying the feedback information received by the terminal to the user.

[0089] The "text area" refers to the part of the text image where text is actually written, and is detected by the analysis means.

[0090] "Character recognition" refers to OCR (optical character recognition) processing performed on detected character areas.

[0091] "Study Plan" refers to a personalized learning menu created based on the user's past feedback history.

[0092] "Feedback History" refers to a record of feedback previously provided to a user, used to track progress and generate a study plan.

[0093] The present invention is a system that uses a user's terminal to capture an image of characters written by a child, analyzes the image on a server, and provides feedback. This system includes a terminal, a server, a camera means, a transmission means, an analysis means, a feedback generation means, a return means, and a display means.

[0094] User inputs image of text

[0095] The user uses the device's camera to capture an image of the characters written by the child. Specifically, the device's built-in camera is used. The image data captured by this camera is saved in the device's memory. When saving, the image resolution may be adjusted or compressed.

[0096] The device sends the image to the server

[0097] The device sends the captured image data to the server via an HTTP POST request over the Internet. The image data is encoded in Base64 format and encrypted using secure communication (e.g., TLS / SSL).

[0098] The server receives the image

[0099] The server receives the HTTP POST request and obtains the image data from the request body. The obtained data is decoded from Base64 format and saved in the server's storage with a file name that can be uniquely identified.

[0100] The server analyzes the image

[0101] The server loads the saved image files and starts the analysis process, using deep learning techniques (e.g., CNN models using TENSORFLOW (registered trademark) or PyTorch) and image processing algorithms. The analysis process includes the following steps:

[0102] Character region detection (e.g., YOLO algorithm)

[0103] Identification of each character (OCR character recognition)

[0104] Evaluation of handwriting, shape, and stroke order (feature extraction)

[0105] Feedback Generation

[0106] The server generates feedback based on the analysis results. The generated feedback includes an evaluation of the character shape and handwriting, and the appropriateness of the stroke order. For example, specific comments such as "Excellent!" or "Needs improvement" are added. This feedback is saved in text format and is reflected in the user's past feedback history.

[0107] Sending and Viewing Feedback

[0108] The server sends the generated feedback back to the device. It is serialized in JSON format and sent back as an HTTP response. The device deserializes the received feedback and displays it to the user using a UI framework (e.g., React Native or Flutter (registered trademark)).

[0109] Track progress and generate study plans

[0110] The server tracks the user's progress and generates a personalized learning plan based on past feedback. For example, if a specific character or stroke order needs continuous improvement, a practice menu will be generated accordingly. This learning plan is presented to the user upon login and periodically to support efficient learning.

[0111] Specific examples

[0112] For example, consider the case where a child writes the character "thank you" and the user captures it with the device's camera. At this time, the device sends the image data to the server, which analyzes the image data and recognizes the word "thank you." The handwriting, shape, and stroke order of each character are evaluated, and since the shape of "a" is correct but "ri" is somewhat distorted, feedback "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. Based on this feedback, the user can instruct the child to practice writing "ri" again.

[0113] Prompt Sentence Examples

[0114] A camera captures a child writing "thank you." Analyze the image to assess the correctness of each character's handwriting, shape, and stroke order, and provide feedback.

[0115] The above is an embodiment of the present invention. The user can receive objective and specific feedback on the child's character practice, enabling the child to progress in learning effectively.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The user uses the device's camera to capture an image of the child's writing. Specifically, the user opens the camera app, frames the appropriate part of the writing, and presses the shutter button. The captured image data is saved in the device's internal memory in an appropriate resolution, such as JPEG format. The input in this step is the child's writing, and the output is the captured image data.

[0119] Step 2:

[0120] The device uses its Internet connection to send the stored image data to the server. The image data is encoded in Base64 format and sent to the server as an HTTP POST request. Specifically, the following request is generated:

[0121] POST / upload HTTP / 1.1

[0122] Host: example.com

[0123] Content-Type: application / json

[0124] {

[0125] "imageData": "base64_encoded_image_data"

[0126] }

[0127] The input is the captured image data (a file in memory) and the output is an HTTP request to the server.

[0128] Step 3:

[0129] The server analyzes the received HTTP POST request and extracts the image data from the request body. Specifically, it decodes the Base64 format data and saves it as an image file. For example, the following process is performed:

[0130] decoded_image_data = base64.b64decode(request.json['imageData'])

[0131] with open("path / to / save / image.jpg", "wb") as f:

[0132] f.write(decoded_image_data)

[0133] The input is the HTTP request data, and the output is an image file in the server storage.

[0134] Step 4:

[0135] The server reads the saved image file and performs analysis. It uses a deep learning model (e.g., a CNN model using TensorFlow or PyTorch) to detect character regions, identify characters, and evaluate handwriting, shape, and stroke order. Specific processing examples are as follows:

[0136] image = load_image("path / to / save / image.jpg")

[0137] bounding_boxes = detect_text_regions(image)

[0138] for box in bounding_boxes:

[0139] character_image = crop_image(image, box)

[0140] recognized_character = recognizer_model.predict(character_image)

[0141] evaluate_characteristics(recognized_character)

[0142] The input is an image file stored in the server, and the output is the analysis results (character identification and characteristic evaluation).

[0143] Step 5:

[0144] The server generates feedback based on the analysis results. The feedback generation algorithm compiles the evaluation results of the handwriting and shape of each character and generates a comment to be provided to the user. For example, feedback such as "Excellent!" or "Needs improvement" is generated. The generated feedback is converted into text format and saved as follows:

[0145] feedback = {

[0146] "character": "ri",

[0147] "evaluation": "Needs improvement",

[0148] "comment": "The shape is out of order and needs to be rewritten."

[0149] }

[0150] The input is the analysis results and the output is the generated feedback data.

[0151] Step 6:

[0152] The server returns the generated feedback to the device by serializing the feedback data in JSON format and sending it to the device via an HTTP response. Specifically, the following response is returned:

[0153] HTTP / 1.1 200 OK

[0154] Content-Type: application / json

[0155] {

[0156] "feedback": {

[0157] "character": "ri",

[0158] "evaluation": "Needs improvement",

[0159] "comment": "The shape is out of order and needs to be rewritten."

[0160] }

[0161] }

[0162] The input is the generated feedback data, and the output is the HTTP response to the terminal.

[0163] Step 7:

[0164] The device deserializes the received feedback and displays it to the user, using a UI framework (e.g., React Native or Flutter) to display a message like this:

[0165] "Evaluation result: The shape of the 'ri' character is broken, so practice 'ri' again."

[0166] The input is the received feedback data and the output is the feedback message that is displayed to the user.

[0167] (Application example 1)

[0168] 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."

[0169] Conventional product quality inspection systems often require manual inspection or complex, specialized equipment, which can be inefficient and costly. Furthermore, detailed analysis, such as evaluating handwriting, shape, and stroke order, requires specialized knowledge, making it difficult to provide accurate feedback. Furthermore, generating a personalized learning plan based on feedback is not easy. To address these challenges, a more efficient and versatile system is needed.

[0170] 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.

[0171] In this invention, the server includes an analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, and a factory robot control means for inspecting the quality of the product. This improves the efficiency of product quality inspection, particularly enabling accurate confirmation of the marking of product lot numbers and quality control symbols. It also makes it possible to provide highly accurate feedback based on detailed analysis such as handwriting evaluation.

[0172] "Capture means" refers to a device or method for capturing an image of an object or scene, such as a digital camera or a smartphone camera.

[0173] A "transmission mechanism" is a system or protocol for sending data from one device to another, such as an HTTP POST request over the Internet.

[0174] A "server means" is a computer system that receives a request and executes a specific process. Examples include a web server and a database server.

[0175] "Analysis means" refers to a method or device that analyzes input data and extracts useful information. Examples of this include image processing algorithms and deep learning models.

[0176] The "feedback generation means" refers to a method or device for creating feedback to be provided to a user based on the analysis results. For example, this includes software that generates evaluation comments or recommendations.

[0177] A "return mechanism" is a system or protocol for returning the generated feedback to the sending device, such as an HTTP response from the server to the client.

[0178] "Display means" refers to a device or method for displaying the received feedback in a form that can be confirmed by the user. Examples include a monitor or a smartphone display.

[0179] "Factory robot control means" refers to a system that controls the robots used in factories and performs operations such as product quality inspections and line changes. Specifically, this refers to the software and hardware that controls the operation of the robot arm.

[0180] The present invention relates to a system for automating product quality inspections by factory robots and providing efficient feedback. The system includes an image capturing unit, a transmission unit, a server unit, an analysis unit, a feedback generating unit, a return unit, a display unit, and a factory robot control unit.

[0181] Recording method and image transmission

[0182] First, the factory robot uses its on-board camera to capture images of lot numbers and quality control symbols engraved on products. This camera has high resolution and can accurately capture even small markings. The captured image is then sent to a server via the Internet using a transmission method. To ensure security, the image data is converted to Base64 format and encrypted and sent via an HTTP POST request.

[0183] Image analysis on the server

[0184] The server receives the transmitted images and analyzes the image data using analytical methods, including the latest AI models and deep learning algorithms. This analysis process involves detecting character regions, recognizing characters, and evaluating handwriting and shape. Specifically, OpenCV is used for image processing, and character recognition is performed using a generative AI model such as TensorFlow.

[0185] Generate and return feedback

[0186] Based on the analysis results, the feedback generation means generates appropriate feedback. The feedback includes evaluations such as "Excellent!" or "Needs improvement," and if a defective product is detected, special instructions are generated. The generated feedback is then sent back to the terminal using the transmission means.

[0187] Feedback display and robot control

[0188] The terminal displays the received feedback using a display means. The user can check this feedback and understand the quality status of the product. The factory robot control means automatically controls the operation based on the feedback. If a defective product is detected, the robot is operated to send the product to another line.

[0189] Specific examples

[0190] For example, when checking the lot number "1234" engraved on a product manufactured in a factory, the system works as follows: First, the factory robot's camera captures an image of the product with the lot number "1234" engraved on it and sends the image to the server. The server analyzes the image, generates feedback, and returns a "Needs improvement" rating. The user confirms this feedback, and the robot automatically sends the product to another line.

[0191] Prompt Sentence Examples

[0192] Capture an image of the lot number "1234" stamped on the product, send it to the server, and get the analysis results. Based on the feedback, you can decide whether to send it to the defective line.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] Image capture by device

[0196] The terminal uses a camera mounted on the factory robot to capture images of lot numbers and quality control symbols engraved on products. In this step, a high-resolution camera is used to accurately capture even the finest markings.

[0197] Input: Physical product

[0198] Output: High-resolution image of the product

[0199] Step 2:

[0200] Sending images

[0201] The device then sends the captured image to a server over the Internet, where it is converted to Base64 format and encrypted via an HTTP POST request to ensure secure communication.

[0202] Input: High-resolution image of product

[0203] Output: Encrypted image data in Base64 format

[0204] Step 3:

[0205] Image reception on the server

[0206] The server receives the transmitted image data, decodes it from Base64 format, and saves it as an image file, which allows subsequent analysis.

[0207] Input: Encrypted Base64 image data

[0208] Output: Decoded image file

[0209] Step 4:

[0210] Image analysis

[0211] The server analyzes the received image using an analysis method. In this step, image processing algorithms and generative AI models are used to detect character regions, recognize characters, and evaluate handwriting and shape. For example, character regions are extracted using OpenCV, and character recognition is performed using TensorFlow or similar.

[0212] Input: Decoded image file

[0213] Output: Character area coordinates and character recognition results

[0214] Step 5:

[0215] Feedback Generation

[0216] The server generates feedback based on the results of image analysis, including an assessment of the product's quality and whether it is defective. Specifically, the server generates assessments such as "Excellent!" or "Needs improvement."

[0217] Input: Character recognition result

[0218] Output: Feedback text

[0219] Step 6:

[0220] Sending feedback

[0221] The server sends the generated feedback to the device using a standard data format such as JSON.

[0222] Input: Feedback text

[0223] Output: Feedback data in JSON format

[0224] Step 7:

[0225] View Feedback

[0226] The device displays the received feedback for the user to review. The display is done on the device's screen or display. Based on this feedback, the user can judge the quality of the product.

[0227] Input: Feedback data in JSON format

[0228] Output: The displayed feedback text

[0229] Step 8:

[0230] Robot Control

[0231] Based on the feedback, the factory robot control system automatically controls its operation. If a defective product is detected, the robot will take action such as sending the product to another line.

[0232] Input: Feedback text

[0233] Output: Robot operation instructions (e.g., move to defective product line)

[0234] Through the above processing steps, a product quality inspection system using a factory robot is realized.

[0235] 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.

[0236] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[0237] User inputs image of text

[0238] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[0239] The device sends the image to the server

[0240] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[0241] The server receives the image

[0242] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used for subsequent processing.

[0243] The server analyzes the image

[0244] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[0245] Feedback Generation

[0246] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[0247] Emotion recognition by emotion engine

[0248] The server is equipped with an emotion engine that analyzes the emotion data (e.g., facial expression data, voice data) sent by the user. The emotion engine identifies the user's emotion and adjusts the content and tone of the feedback based on that emotion. For example, if the user is feeling discouraged, a message of encouragement and motivation will be generated.

[0249] Sending and Viewing Feedback

[0250] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[0251] Track progress and generate study plans

[0252] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[0253] Specific examples

[0254] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to the server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is somewhat awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion engine will generate an encouraging message such as "Good job! Just keep practicing and you'll improve your 'ri' in no time!". The user can see this feedback and encouraging message and instruct the child to practice writing "ri" again.

[0255] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[0256] The processing flow will be explained below.

[0257] Step 1:

[0258] The user uses the device's camera to capture an image of the child's writing. The device then activates the camera and captures the image of the writing. The device then saves the image at the appropriate resolution.

[0259] Step 2:

[0260] The device sends the captured image to the server. The image data is converted to Base64 format and sent to the server using an HTTP POST request. The data is encrypted to ensure security.

[0261] Step 3:

[0262] The server receives the HTTP POST request and retrieves the image data. The server decodes the Base64 data and saves it as an image file for further analysis.

[0263] Step 4:

[0264] The server reads the saved image file and uses the AI ​​model to detect text areas within the image, then performs character recognition on the detected text areas, using deep learning technology.

[0265] Step 5:

[0266] Based on the results of character recognition, the server evaluates the user's handwriting, shape, and stroke order, for example, determining whether the characters are written in the correct shape and stroke order.

[0267] Step 6:

[0268] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, and the correctness of the stroke order. Specific examples of feedback include "Excellent!" and "Needs improvement."

[0269] Step 7:

[0270] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes facial expression and voice data sent from the device to identify the user's emotions. The emotion data is used to adjust the feedback.

[0271] Step 8:

[0272] The server takes emotional data into account and adjusts the content and tone of the feedback, for example, if the user is feeling discouraged it might include an encouraging message like "Great effort! Keep it up!"

[0273] Step 9:

[0274] The server returns the generated feedback to the device. The feedback is sent to the device as an HTTP response. The feedback data is also encrypted before being sent.

[0275] Step 10:

[0276] The device decodes the received feedback and displays it to the user in a visually friendly format. The user can review the feedback and use it to improve their next practice.

[0277] Step 11:

[0278] The server tracks the user's progress and generates a personalized learning plan based on past feedback, suggesting the best practice method and order for practicing characters.

[0279] Step 12:

[0280] The device displays a personalized learning plan to the user, allowing the user to effectively practice writing with their child based on this plan.

[0281] The above are the specific processing steps for implementing the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively. Furthermore, by combining it with an emotion engine, flexible feedback is provided that responds to the user's emotions.

[0282] Example 2

[0283] 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."

[0284] Previous character learning systems were unable to objectively evaluate a child's handwriting and provide specific feedback. They also lacked an effective way to maintain user motivation, as they were unable to analyze the user's emotions and adjust the content and tone of the feedback. Furthermore, their ability to generate and provide individual learning plans to users was limited, making it difficult to provide an efficient and personalized learning experience.

[0285] 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.

[0286] In this invention, the server includes an image analysis means, a feedback generation means, and an emotion recognition means. This allows the server to analyze image data to evaluate the handwriting, shape, and stroke order of characters, and to analyze the user's emotions to adjust the tone of the feedback. It also tracks the user's progress and generates a personalized learning plan, providing an efficient and individualized learning experience.

[0287] "Image acquisition means" is a function that allows the terminal to capture a character image of the user.

[0288] The "data transmission means" is a function for transmitting the captured character image to the server.

[0289] The "receiving means" is a function that allows the server to receive a character image sent from a user.

[0290] The "image analysis means" is a function for analyzing received character images and evaluating the handwriting, shape, and stroke order.

[0291] The "feedback generation means" is a function for generating feedback to be provided to the user based on the results of image analysis.

[0292] The "data return means" is a function for returning the generated feedback to the terminal.

[0293] The "display means" is a function for displaying the feedback received by the terminal to the user.

[0294] The "emotion recognition means" is a function for analyzing the user's emotional data and adjusting the tone of the feedback.

[0295] The "study plan generator" is a function for tracking a user's progress and generating a personalized study plan based on past feedback history.

[0296] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[0297] Hardware and software used

[0298] The user uses a device as image acquisition means, such as a smartphone or tablet, to capture an image of the characters written by the child. The captured image is sent to a server via the Internet via the device's data transmission means. The server receives the image data using the data receiving means and then analyzes the image using the analysis means. Image processing algorithms and deep learning techniques are used for this analysis. Feedback is generated by the feedback generation means based on the analysis results, and the generated feedback is sent back to the device via the data return means. Furthermore, the emotion recognition means analyzes the user's emotion data and adjusts the tone of the feedback. A personalized learning plan based on the user's progress is generated by the study plan generation means.

[0299] A specific example is the following flow.

[0300] First, the user uses the device's camera to capture an image of the character "Thank you" written by the child. The image is temporarily saved on the device and then sent to the server using the data transmission means. Communication is performed using a secure protocol (e.g., SSL / TLS). The server receives the image using the receiving means, detects character regions using the analysis means, and evaluates the handwriting, shape, and stroke order of each character. For example, the server may use a deep learning model (e.g., YOLOv3) to detect character regions, and then use the Tesseract OCR engine to perform character recognition. Based on the analysis results, the feedback generation means generates feedback such as, "The character 'あ' is well-formed. 'り' needs improvement."

[0301] Next, the emotion recognition means analyzes the user's facial expression data, and if it is determined that the user is depressed, it generates feedback including an encouraging tone such as "Don't worry! You're doing great!" The generated feedback is returned to the terminal through the data return means and displayed to the user by the display means. Furthermore, the learning plan generation means generates a practice plan for writing the character "ri" based on the past feedback history and proposes it to the user.

[0302] Prompt Sentence Examples

[0303] "Please explain in detail the process flow of a system that analyzes images of children's handwriting captured by a camera and generates feedback using an AI model."

[0304] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0305] Step 1:

[0306] User inputs image of text

[0307] The user uses the device's camera to capture an image of the child's writing.

[0308] Specific behavior:

[0309] The user launches the camera app and takes a picture of the characters written by the child (for example, "aiueo").

[0310] Input: Child's writing

[0311] Output: Image file saved on device

[0312] Step 2:

[0313] The device sends the image to the server

[0314] The device uses a transmission means over the Internet to send the captured image to the server, where the image data is encoded in Base64 format and sent to the server using an HTTP POST request.

[0315] Specific behavior:

[0316] The terminal performs an encoding process and converts the image data into Base64 format.

[0317] Use an HTTP client library to create a POST request containing the encoded image data.

[0318] Input: Captured character image

[0319] Output: Encoded image data sent to the server

[0320] Step 3:

[0321] The server receives the image

[0322] The server receives the HTTP POST request, obtains the image data contained therein, decodes the image data, and saves it as a file.

[0323] Specific behavior:

[0324] The server decodes the encoded image data and returns it to the original JPEG image format.

[0325] Save the image to a file path such as " / uploads / unique_id.jpg".

[0326] Input: POST request with encoded image data

[0327] Output: Decoded JPEG image file

[0328] Step 4:

[0329] The server analyzes the image

[0330] The server uses AI models to analyze the stored image data, detecting character regions, identifying characters, and evaluating handwriting, shape, and stroke order.

[0331] Specific behavior:

[0332] Use a deep learning model (e.g., YOLOv3) to detect character regions in an image.

[0333] The detected character area is input to an OCR engine (e.g., Tesseract) for character recognition.

[0334] Input: Saved image file

[0335] Output: Analysis results of handwriting, shape, and stroke order of characters

[0336] Step 5:

[0337] Server generates feedback

[0338] The server generates feedback based on the analysis results, including the quality of the handwriting, shape, and the correctness of the stroke order.

[0339] Specific behavior:

[0340] Based on the analysis results, a feedback message is created. For example, a message such as "The character 'あ' is well-formed. 'り' needs improvement." is generated.

[0341] Input: Character analysis result

[0342] Output: Textual feedback message

[0343] Step 6:

[0344] Emotion recognition by emotion engine

[0345] The server is equipped with an emotion engine that analyzes the emotional data (facial expression data, voice data) sent by the user and adjusts the content and tone of the feedback.

[0346] Specific behavior:

[0347] The server analyzes facial expression and voice data to identify emotions.

[0348] Adjust the tone and message of your feedback based on the emotion, for example, "Don't worry! You're doing great!"

[0349] Input: User emotion data

[0350] Output: Adjusted feedback message

[0351] Step 7:

[0352] Server sends feedback

[0353] The server transmits the generated feedback back to the terminal, and the terminal displays the received feedback so that the user can confirm it.

[0354] Specific behavior:

[0355] The server generates an HTTP response including a feedback message and sends it to the terminal.

[0356] The terminal receives the response and displays a feedback message on the screen.

[0357] Input: Feedback message

[0358] Output: Feedback message displayed on the terminal

[0359] Step 8:

[0360] Track progress and generate study plans

[0361] The server tracks the user's progress and generates a personalized learning plan based on past feedback history.

[0362] Specific behavior:

[0363] The server consults a database of user feedback history and determines whether specific characters or stroke orders require ongoing improvement.

[0364] It generates and suggests to the user practice plans for characters that require continuous improvement.

[0365] Input: User feedback history data

[0366] Output: Personalized study plan

[0367] (Application example 2)

[0368] 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."

[0369] Modern educational settings require rapid and specific feedback on children's character practice. However, it is difficult for parents and teachers to provide appropriate guidance on the spot, and in many cases, children continue practicing on their own. Furthermore, to increase children's motivation to learn, encouragement and advice that takes into account their emotional state is necessary. However, recognizing emotions and generating feedback based on them requires advanced technology, which has been difficult to achieve with conventional systems.

[0370] 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 an optical sensor means for the terminal to capture a character image of the user, a data transmission means for transmitting the captured image to the server, a data receiving means for receiving the image, a data analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, a data return means for returning the feedback to the terminal, a display means for displaying the feedback, an emotion analysis means for analyzing the user's facial expressions and voice to recognize emotions, and a feedback adjustment means for adjusting the feedback content based on the emotions. This makes it possible to provide quick and specific feedback to a child's writing practice and to generate encouragement and advice according to the emotional state of the user (child or parent).

[0371] "Optical sensor means" refers to equipment and technology that uses light to capture images of objects.

[0372] "Data transmission means" refers to a function or method for transmitting acquired data to another device or system.

[0373] "Data receiving means" refers to equipment or technology that receives data sent from outside.

[0374] "Data analysis means" refers to algorithms or software that analyzes received data and evaluates the characteristics of the target object.

[0375] "Feedback generation means" refers to a system or technology that automatically generates feedback for subjects based on the results of data analysis.

[0376] The "data return means" is a function for returning the generated feedback to the original destination.

[0377] "Display means" refers to a device or technology that displays the received feedback in a form that can be confirmed by the user.

[0378] "Emotion analysis means" refers to technology or algorithms that analyze a user's facial expressions and voice data and identify their emotions.

[0379] "Feedback adjustment means" refers to a system or technology for adjusting the content of feedback based on the results of emotion analysis.

[0380] System Program

[0381] This invention is a system for providing feedback to children's writing practice, and uses the following means:

[0382] 1. Terminal hardware and software:

[0383] Optical sensor means: Uses the camera built into a smartphone or tablet to capture an image of the letters written by the child.

[0384] Data transmission means: A network communication function for transmitting captured images to a server. The image data is encoded in Base64 format or other appropriate format.

[0385] Data receiving means: A function for receiving feedback data returned from the server.

[0386] 2. Server-side hardware and software:

[0387] Data receiving means: A function that receives image data sent from a terminal. Protocols such as HTTP POST are used.

[0388] Data analysis method: An algorithm that analyzes received image data and evaluates character recognition, handwriting, shape, and stroke order. It uses AI models and image processing technology.

[0389] Feedback generator: An algorithm that generates personalized feedback based on the analysis results, including specific suggestions for improvement.

[0390] Emotion analysis means: Analyzes the user's facial expressions and voice data to recognize emotions. For example, facial expression recognition technology and voice analysis technology are used.

[0391] Feedback adjustment measures: Based on the results of sentiment analysis, the content of the feedback is adjusted, for example, by adding encouraging words or changing the tone to a gentler one.

[0392] 3. Display means: A function to display feedback on the device's display, including text and images.

[0393] Natural language explanation of the process

[0394] The device uses the camera built into the smartphone or tablet to capture an image of the characters written by the child. The captured image is then sent to a server via the Internet using a data transmission means. At this time, the image data is encoded in a compressed format such as Base64 format and sent using an HTTP POST request.

[0395] The server decodes the received image data and detects character regions within the image using a data analysis means. The server then uses a character recognition algorithm to identify characters within the detected character regions and evaluates their handwriting, shape, and stroke order. Based on the evaluation results, a feedback generation means generates individual feedback.

[0396] Next, the emotion analysis means analyzes the user's facial expression data and voice data to identify the user's emotions (e.g., joy, sadness, lack of motivation, etc.). The feedback adjustment means adjusts the feedback content based on the identified emotions. For example, if the user is feeling down, an encouraging message such as "Great progress! You'll get even better if you practice more!" is added.

[0397] Finally, the generated feedback is sent to the terminal using the data return means and visually displayed to the user through the display means, allowing the user to support the child's practice based on this feedback.

[0398] Examples of concrete examples and prompts

[0399] Examples:

[0400] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, feedback is generated, such as "the shape of the character "a" is accurate, but the character "ri" is a little awkward, so it's "inaccurate." This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion analysis engine generates an encouraging message such as "Great progress! You can do better next time!" The user can see this feedback and encouraging message and instruct the child to practice writing the character "ri" again.

[0401] Example prompt sentence:

[0402] 1. Take a picture of the letters your child has written with your camera.

[0403] 2. Send the captured image for analysis within the app.

[0404] 3. Emotional feedback for the child will also be displayed along with the analysis results.

[0405] example:

[0406] Photo taken: "Thank you.jpg"

[0407] Submitted response: "Feedback: The shape is accurate, but the stroke order needs improvement. Great progress! More practice will help you improve even more!"

[0408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0409] Step 1:

[0410] The user uses the camera on their smartphone or tablet to capture an image of the letters written by the child. Specifically, the user launches the camera app, adjusts the exposure so that the letters are clearly visible, and presses the shutter. The input is the "letters written by the child," and the output is a "letter image file."

[0411] Step 2:

[0412] The terminal sends the captured text image to the server using a data transmission means. At this time, the image data is encoded in a format such as Base64, encrypted, and sent using an HTTP POST request. The input is a "text image file," and the output is "request data sent to the server."

[0413] Step 3:

[0414] The server receives the HTTP POST request and obtains the image data using the data receiving means. Specifically, the server decodes the Base64-encoded image data from the request and saves it as a file. The input is the "request data" and the output is the "decoded image file."

[0415] Step 4:

[0416] The server analyzes the stored image data using data analysis means. First, it uses an image processing algorithm to detect character regions, then performs character recognition using an AI model. It then evaluates the handwriting, shape, and stroke order. The input is the "decoded image file," and the output is the "character recognition and evaluation results."

[0417] Step 5:

[0418] The server generates feedback based on the analysis results using a feedback generation means. Specifically, it generates feedback in text format based on the evaluation results, including suggestions for improvement and encouraging messages. The input is "character recognition and evaluation results," and the output is "feedback text."

[0419] Step 6:

[0420] The server analyzes the user's facial expression data and voice data using emotion analysis means. The server uses an AI model to identify emotions from facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the emotion identification result.

[0421] Step 7:

[0422] The server adjusts the feedback content using a feedback adjustment means based on the emotion analysis results. Specifically, it adds encouraging or advice messages to the feedback according to the emotion. The input is the "feedback text" and the "emotion identification result," and the output is the "adjusted feedback text."

[0423] Step 8:

[0424] The server sends the generated adjusted feedback to the terminal using the data return means, where the input is the "adjusted feedback text" and the output is the "feedback data to be sent to the terminal".

[0425] Step 9:

[0426] The terminal displays the received feedback using a display means. Specifically, the received feedback text is displayed on the screen so that the user can easily check it. The input is "feedback data" and the output is "feedback displayed on the terminal display."

[0427] 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.

[0428] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0429] 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.

[0430] [Second embodiment]

[0431] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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."

[0443] The present invention relates to a system for analyzing images of characters written by a child and providing feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, and a display means.

[0444] User inputs image of text

[0445] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[0446] The device sends the image to the server

[0447] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[0448] The server receives the image

[0449] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used in the next analysis step.

[0450] The server analyzes the image

[0451] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[0452] Feedback Generation

[0453] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[0454] Sending and Viewing Feedback

[0455] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[0456] Track progress and generate study plans

[0457] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[0458] Specific examples

[0459] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is a bit awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. The user can see this feedback and instruct the child to practice writing "ri" again.

[0460] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to study together in a fun and effective way.

[0461] The processing flow will be explained below.

[0462] Step 1:

[0463] The device captures the user's image of the text. The user launches the device's camera app and takes a picture of the text written by the child. The device temporarily stores the captured image in memory.

[0464] Step 2:

[0465] The device sends the captured image to the server. The device converts the captured image into Base64 format and sends it to the server using an HTTP POST request. The image data is encrypted using a network connection.

[0466] Step 3:

[0467] The server receives the image. The server receives the HTTP request and obtains the transmitted image data. It decodes the image data and saves it as a file. The saved image is used for subsequent processing.

[0468] Step 4:

[0469] The server analyzes the image. It reads the saved image file and uses an AI model to detect character regions within the image. After the character regions are detected, it performs character recognition and evaluates the handwriting, shape, and stroke order. Image processing algorithms and deep learning technology are applied for character recognition.

[0470] Step 5:

[0471] The server generates feedback. Based on the analysis results, the server generates specific feedback to the user in text format. The feedback includes evaluations such as "Excellent!" or "Needs improvement."

[0472] Step 6:

[0473] The server returns the generated feedback to the device. The server encodes the feedback in text format and sends it to the device as an HTTP response. The feedback is saved in the user's past feedback history.

[0474] Step 7:

[0475] The device receives and displays the feedback. The device decodes the feedback received from the server and displays it in a format that is easy for the user to read. The user can check this feedback and use it to improve their next practice.

[0476] Step 8:

[0477] The server tracks the user's progress. The server records and analyzes the user's learning progress based on the user's feedback history. If necessary, it generates a personalized learning plan.

[0478] Step 9:

[0479] The server generates a personalized learning plan. The server takes into account the user's past feedback history and generates a learning plan that includes the optimal practice method and character practice order. This learning plan is provided as feedback the next time the user practices.

[0480] The above are the specific processing steps of the system based on the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[0481] Example 1

[0482] 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."

[0483] In conventional character practice systems, evaluation of a child's handwriting is subjective, making it difficult to obtain objective feedback. Furthermore, the feedback is temporary, making it difficult to obtain continuous learning benefits. Furthermore, feedback and learning plans tailored to individual learning progress are not provided, preventing efficient learning.

[0484] 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.

[0485] In this invention, the server includes an analysis means for analyzing the received image data and evaluating character identification, handwriting, shape, and stroke order; a feedback generation means for generating feedback based on the analysis results; and a return means for returning the generated feedback to the terminal. This allows the user to receive objective and specific feedback on the child's character practice. Furthermore, by providing a personalized learning plan based on past feedback history, continuous and individualized learning can be achieved.

[0486] "User" refers to a person who uses the system, specifically a parent or educator who supports children in practicing writing.

[0487] "Text image" refers to image data of text written by a child that is captured by the user using the device's camera.

[0488] "Photographing means" refers to the camera function built into the device, which the user uses to capture an image of the child's text.

[0489] "Transmission means" refers to the means for transmitting image data from a terminal to a server via the Internet. Specifically, an HTTP POST request is used.

[0490] The term "server device" refers to a combination of hardware and software for receiving, storing, and analyzing image data sent from a terminal.

[0491] "Analysis means" refers to the algorithms and AI models that analyze image data within the server device and evaluate character identification, handwriting, shape, and stroke order.

[0492] "Feedback generation means" refers to the means for generating feedback to be provided to users based on the analysis results, specifically using an AI model or a rule-based engine.

[0493] The "returning means" refers to a means for transmitting the generated feedback information from the server to the terminal. Specifically, an HTTP response is used.

[0494] The "display means" refers to a UI (user interface) for displaying the feedback information received by the terminal to the user.

[0495] The "text area" refers to the part of the text image where text is actually written, and is detected by the analysis means.

[0496] "Character recognition" refers to OCR (optical character recognition) processing performed on detected character areas.

[0497] "Study Plan" refers to a personalized learning menu created based on the user's past feedback history.

[0498] "Feedback History" refers to a record of feedback previously provided to a user, used to track progress and generate a study plan.

[0499] The present invention is a system that uses a user's terminal to capture an image of characters written by a child, analyzes the image on a server, and provides feedback. This system includes a terminal, a server, a camera means, a transmission means, an analysis means, a feedback generation means, a return means, and a display means.

[0500] User inputs image of text

[0501] The user uses the device's camera to capture an image of the characters written by the child. Specifically, the device's built-in camera is used. The image data captured by this camera is saved in the device's memory. When saving, the image resolution may be adjusted or compressed.

[0502] The device sends the image to the server

[0503] The device sends the captured image data to the server via an HTTP POST request over the Internet. The image data is encoded in Base64 format and encrypted using secure communication (e.g., TLS / SSL).

[0504] The server receives the image

[0505] The server receives the HTTP POST request and obtains the image data from the request body. The obtained data is decoded from Base64 format and saved in the server's storage with a file name that can be uniquely identified.

[0506] The server analyzes the image

[0507] The server loads the saved image files and starts the analysis process, using deep learning techniques (e.g., CNN models using TensorFlow or PyTorch) and image processing algorithms. The analysis process includes the following steps:

[0508] Character region detection (e.g., YOLO algorithm)

[0509] Identification of each character (OCR character recognition)

[0510] Evaluation of handwriting, shape, and stroke order (feature extraction)

[0511] Feedback Generation

[0512] The server generates feedback based on the analysis results. The generated feedback includes an evaluation of the character shape and handwriting, and the appropriateness of the stroke order. For example, specific comments such as "Excellent!" or "Needs improvement" are added. This feedback is saved in text format and is reflected in the user's past feedback history.

[0513] Sending and Viewing Feedback

[0514] The server then sends the generated feedback back to the device. It is serialized in JSON format and sent back as an HTTP response. The device then deserializes the received feedback and displays it to the user using a UI framework (e.g., React Native or Flutter).

[0515] Track progress and generate study plans

[0516] The server tracks the user's progress and generates a personalized learning plan based on past feedback. For example, if a specific character or stroke order needs continuous improvement, a practice menu will be generated accordingly. This learning plan is presented to the user upon login and periodically to support efficient learning.

[0517] Specific examples

[0518] For example, consider the case where a child writes the character "thank you" and the user captures it with the device's camera. At this time, the device sends the image data to the server, which analyzes the image data and recognizes the word "thank you." The handwriting, shape, and stroke order of each character are evaluated, and since the shape of "a" is correct but "ri" is somewhat distorted, feedback "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. Based on this feedback, the user can instruct the child to practice writing "ri" again.

[0519] Prompt Sentence Examples

[0520] A camera captures a child writing "thank you." Analyze the image to assess the correctness of each character's handwriting, shape, and stroke order, and provide feedback.

[0521] The above is an embodiment of the present invention. The user can receive objective and specific feedback on the child's character practice, enabling the child to progress in learning effectively.

[0522] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0523] Step 1:

[0524] The user uses the device's camera to capture an image of the child's writing. Specifically, the user opens the camera app, frames the appropriate part of the writing, and presses the shutter button. The captured image data is saved in the device's internal memory in an appropriate resolution, such as JPEG format. The input in this step is the child's writing, and the output is the captured image data.

[0525] Step 2:

[0526] The device uses its Internet connection to send the stored image data to the server. The image data is encoded in Base64 format and sent to the server as an HTTP POST request. Specifically, the following request is generated:

[0527] POST / upload HTTP / 1.1

[0528] Host: example.com

[0529] Content-Type: application / json

[0530] {

[0531] "imageData": "base64_encoded_image_data"

[0532] }

[0533] The input is the captured image data (a file in memory) and the output is an HTTP request to the server.

[0534] Step 3:

[0535] The server analyzes the received HTTP POST request and extracts the image data from the request body. Specifically, it decodes the Base64 format data and saves it as an image file. For example, the following process is performed:

[0536] decoded_image_data = base64.b64decode(request.json['imageData'])

[0537] with open("path / to / save / image.jpg", "wb") as f:

[0538] f.write(decoded_image_data)

[0539] The input is the HTTP request data, and the output is an image file in the server storage.

[0540] Step 4:

[0541] The server reads the saved image file and performs analysis. It uses a deep learning model (e.g., a CNN model using TensorFlow or PyTorch) to detect character regions, identify characters, and evaluate handwriting, shape, and stroke order. Specific processing examples are as follows:

[0542] image = load_image("path / to / save / image.jpg")

[0543] bounding_boxes = detect_text_regions(image)

[0544] for box in bounding_boxes:

[0545] character_image = crop_image(image, box)

[0546] recognized_character = recognizer_model.predict(character_image)

[0547] evaluate_characteristics(recognized_character)

[0548] The input is an image file stored in the server, and the output is the analysis results (character identification and characteristic evaluation).

[0549] Step 5:

[0550] The server generates feedback based on the analysis results. The feedback generation algorithm compiles the evaluation results of the handwriting and shape of each character and generates a comment to be provided to the user. For example, feedback such as "Excellent!" or "Needs improvement" is generated. The generated feedback is converted into text format and saved as follows:

[0551] feedback = {

[0552] "character": "ri",

[0553] "evaluation": "Needs improvement",

[0554] "comment": "The shape is out of order and needs to be rewritten."

[0555] }

[0556] The input is the analysis results and the output is the generated feedback data.

[0557] Step 6:

[0558] The server returns the generated feedback to the device by serializing the feedback data in JSON format and sending it to the device via an HTTP response. Specifically, the following response is returned:

[0559] HTTP / 1.1 200 OK

[0560] Content-Type: application / json

[0561] {

[0562] "feedback": {

[0563] "character": "ri",

[0564] "evaluation": "Needs improvement",

[0565] "comment": "The shape is out of order and needs to be rewritten."

[0566] }

[0567] }

[0568] The input is the generated feedback data, and the output is the HTTP response to the terminal.

[0569] Step 7:

[0570] The device deserializes the received feedback and displays it to the user, using a UI framework (e.g., React Native or Flutter) to display a message like this:

[0571] "Evaluation result: The shape of the 'ri' character is broken, so practice 'ri' again."

[0572] The input is the received feedback data and the output is the feedback message that is displayed to the user.

[0573] (Application example 1)

[0574] 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."

[0575] Conventional product quality inspection systems often require manual inspection or complex, specialized equipment, which can be inefficient and costly. Furthermore, detailed analysis, such as evaluating handwriting, shape, and stroke order, requires specialized knowledge, making it difficult to provide accurate feedback. Furthermore, generating a personalized learning plan based on feedback is not easy. To address these challenges, a more efficient and versatile system is needed.

[0576] 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.

[0577] In this invention, the server includes an analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, and a factory robot control means for inspecting the quality of the product. This improves the efficiency of product quality inspection, particularly enabling accurate confirmation of the marking of product lot numbers and quality control symbols. It also makes it possible to provide highly accurate feedback based on detailed analysis such as handwriting evaluation.

[0578] "Capture means" refers to a device or method for capturing an image of an object or scene, such as a digital camera or a smartphone camera.

[0579] A "transmission mechanism" is a system or protocol for sending data from one device to another, such as an HTTP POST request over the Internet.

[0580] A "server means" is a computer system that receives a request and executes a specific process. Examples include a web server and a database server.

[0581] "Analysis means" refers to a method or device that analyzes input data and extracts useful information. Examples of this include image processing algorithms and deep learning models.

[0582] The "feedback generation means" refers to a method or device for creating feedback to be provided to a user based on the analysis results. For example, this includes software that generates evaluation comments or recommendations.

[0583] A "return mechanism" is a system or protocol for returning the generated feedback to the sending device, such as an HTTP response from the server to the client.

[0584] "Display means" refers to a device or method for displaying the received feedback in a form that can be confirmed by the user. Examples include a monitor or a smartphone display.

[0585] "Factory robot control means" refers to a system that controls the robots used in factories and performs operations such as product quality inspections and line changes. Specifically, this refers to the software and hardware that controls the operation of the robot arm.

[0586] The present invention relates to a system for automating product quality inspections by factory robots and providing efficient feedback. The system includes an image capturing unit, a transmission unit, a server unit, an analysis unit, a feedback generating unit, a return unit, a display unit, and a factory robot control unit.

[0587] Recording method and image transmission

[0588] First, the factory robot uses its on-board camera to capture images of lot numbers and quality control symbols engraved on products. This camera has high resolution and can accurately capture even small markings. The captured image is then sent to a server via the Internet using a transmission method. To ensure security, the image data is converted to Base64 format and encrypted and sent via an HTTP POST request.

[0589] Image analysis on the server

[0590] The server receives the transmitted images and analyzes the image data using analytical methods, including the latest AI models and deep learning algorithms. This analysis process involves detecting character regions, recognizing characters, and evaluating handwriting and shape. Specifically, OpenCV is used for image processing, and character recognition is performed using a generative AI model such as TensorFlow.

[0591] Generate and return feedback

[0592] Based on the analysis results, the feedback generation means generates appropriate feedback. The feedback includes evaluations such as "Excellent!" or "Needs improvement," and if a defective product is detected, special instructions are generated. The generated feedback is then sent back to the terminal using the transmission means.

[0593] Feedback display and robot control

[0594] The terminal displays the received feedback using a display means. The user can check this feedback and understand the quality status of the product. The factory robot control means automatically controls the operation based on the feedback. If a defective product is detected, the robot is operated to send the product to another line.

[0595] Specific examples

[0596] For example, when checking the lot number "1234" engraved on a product manufactured in a factory, the system works as follows: First, the factory robot's camera captures an image of the product with the lot number "1234" engraved on it and sends the image to the server. The server analyzes the image, generates feedback, and returns a "Needs improvement" rating. The user confirms this feedback, and the robot automatically sends the product to another line.

[0597] Prompt Sentence Examples

[0598] Capture an image of the lot number "1234" stamped on the product, send it to the server, and get the analysis results. Based on the feedback, you can decide whether to send it to the defective line.

[0599] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0600] Step 1:

[0601] Image capture by device

[0602] The terminal uses a camera mounted on the factory robot to capture images of lot numbers and quality control symbols engraved on products. In this step, a high-resolution camera is used to accurately capture even the finest markings.

[0603] Input: Physical product

[0604] Output: High-resolution image of the product

[0605] Step 2:

[0606] Sending images

[0607] The device then sends the captured image to a server over the Internet, where it is converted to Base64 format and encrypted via an HTTP POST request to ensure secure communication.

[0608] Input: High-resolution image of product

[0609] Output: Encrypted image data in Base64 format

[0610] Step 3:

[0611] Image reception on the server

[0612] The server receives the transmitted image data, decodes it from Base64 format, and saves it as an image file, which allows subsequent analysis.

[0613] Input: Encrypted Base64 image data

[0614] Output: Decoded image file

[0615] Step 4:

[0616] Image analysis

[0617] The server analyzes the received image using an analysis method. In this step, image processing algorithms and generative AI models are used to detect character regions, recognize characters, and evaluate handwriting and shape. For example, character regions are extracted using OpenCV, and character recognition is performed using TensorFlow or similar.

[0618] Input: Decoded image file

[0619] Output: Character area coordinates and character recognition results

[0620] Step 5:

[0621] Feedback Generation

[0622] The server generates feedback based on the results of image analysis, including an assessment of the product's quality and whether it is defective. Specifically, the server generates assessments such as "Excellent!" or "Needs improvement."

[0623] Input: Character recognition result

[0624] Output: Feedback text

[0625] Step 6:

[0626] Sending feedback

[0627] The server sends the generated feedback to the device using a standard data format such as JSON.

[0628] Input: Feedback text

[0629] Output: Feedback data in JSON format

[0630] Step 7:

[0631] View Feedback

[0632] The device displays the received feedback for the user to review. The display is done on the device's screen or display. Based on this feedback, the user can judge the quality of the product.

[0633] Input: Feedback data in JSON format

[0634] Output: The displayed feedback text

[0635] Step 8:

[0636] Robot Control

[0637] Based on the feedback, the factory robot control system automatically controls its operation. If a defective product is detected, the robot will take action such as sending the product to another line.

[0638] Input: Feedback text

[0639] Output: Robot operation instructions (e.g., move to defective product line)

[0640] Through the above processing steps, a product quality inspection system using a factory robot is realized.

[0641] 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.

[0642] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[0643] User inputs image of text

[0644] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[0645] The device sends the image to the server

[0646] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[0647] The server receives the image

[0648] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used for subsequent processing.

[0649] The server analyzes the image

[0650] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[0651] Feedback Generation

[0652] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[0653] Emotion recognition by emotion engine

[0654] The server is equipped with an emotion engine that analyzes the emotion data (e.g., facial expression data, voice data) sent by the user. The emotion engine identifies the user's emotion and adjusts the content and tone of the feedback based on that emotion. For example, if the user is feeling discouraged, a message of encouragement and motivation will be generated.

[0655] Sending and Viewing Feedback

[0656] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[0657] Track progress and generate study plans

[0658] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[0659] Specific examples

[0660] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to the server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is somewhat awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion engine will generate an encouraging message such as "Good job! Just keep practicing and you'll improve your 'ri' in no time!". The user can see this feedback and encouraging message and instruct the child to practice writing "ri" again.

[0661] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[0662] The processing flow will be explained below.

[0663] Step 1:

[0664] The user uses the device's camera to capture an image of the child's writing. The device then activates the camera and captures the image of the writing. The device then saves the image at the appropriate resolution.

[0665] Step 2:

[0666] The device sends the captured image to the server. The image data is converted to Base64 format and sent to the server using an HTTP POST request. The data is encrypted to ensure security.

[0667] Step 3:

[0668] The server receives the HTTP POST request and retrieves the image data. The server decodes the Base64 data and saves it as an image file for further analysis.

[0669] Step 4:

[0670] The server reads the saved image file and uses the AI ​​model to detect text areas within the image, then performs character recognition on the detected text areas, using deep learning technology.

[0671] Step 5:

[0672] Based on the results of character recognition, the server evaluates the user's handwriting, shape, and stroke order, for example, determining whether the characters are written in the correct shape and stroke order.

[0673] Step 6:

[0674] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, and the correctness of the stroke order. Specific examples of feedback include "Excellent!" and "Needs improvement."

[0675] Step 7:

[0676] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes facial expression and voice data sent from the device to identify the user's emotions. The emotion data is used to adjust the feedback.

[0677] Step 8:

[0678] The server takes emotional data into account and adjusts the content and tone of the feedback, for example, if the user is feeling discouraged it might include an encouraging message like "Great effort! Keep it up!"

[0679] Step 9:

[0680] The server returns the generated feedback to the device. The feedback is sent to the device as an HTTP response. The feedback data is also encrypted before being sent.

[0681] Step 10:

[0682] The device decodes the received feedback and displays it to the user in a visually friendly format. The user can review the feedback and use it to improve their next practice.

[0683] Step 11:

[0684] The server tracks the user's progress and generates a personalized learning plan based on past feedback, suggesting the best practice method and order for practicing characters.

[0685] Step 12:

[0686] The device displays a personalized learning plan to the user, allowing the user to effectively practice writing with their child based on this plan.

[0687] The above are the specific processing steps for implementing the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively. Furthermore, by combining it with an emotion engine, flexible feedback is provided that responds to the user's emotions.

[0688] Example 2

[0689] 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."

[0690] Previous character learning systems were unable to objectively evaluate a child's handwriting and provide specific feedback. They also lacked an effective way to maintain user motivation, as they were unable to analyze the user's emotions and adjust the content and tone of the feedback. Furthermore, their ability to generate and provide individual learning plans to users was limited, making it difficult to provide an efficient and personalized learning experience.

[0691] 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.

[0692] In this invention, the server includes an image analysis means, a feedback generation means, and an emotion recognition means. This allows the server to analyze image data to evaluate the handwriting, shape, and stroke order of characters, and to analyze the user's emotions to adjust the tone of the feedback. It also tracks the user's progress and generates a personalized learning plan, providing an efficient and individualized learning experience.

[0693] "Image acquisition means" is a function that allows the terminal to capture a character image of the user.

[0694] The "data transmission means" is a function for transmitting the captured character image to the server.

[0695] The "receiving means" is a function that allows the server to receive a character image sent from a user.

[0696] The "image analysis means" is a function for analyzing received character images and evaluating the handwriting, shape, and stroke order.

[0697] The "feedback generation means" is a function for generating feedback to be provided to the user based on the results of image analysis.

[0698] The "data return means" is a function for returning the generated feedback to the terminal.

[0699] The "display means" is a function for displaying the feedback received by the terminal to the user.

[0700] The "emotion recognition means" is a function for analyzing the user's emotional data and adjusting the tone of the feedback.

[0701] The "study plan generator" is a function for tracking a user's progress and generating a personalized study plan based on past feedback history.

[0702] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[0703] Hardware and software used

[0704] The user uses a device as image acquisition means, such as a smartphone or tablet, to capture an image of the characters written by the child. The captured image is sent to a server via the Internet via the device's data transmission means. The server receives the image data using the data receiving means and then analyzes the image using the analysis means. Image processing algorithms and deep learning techniques are used for this analysis. Feedback is generated by the feedback generation means based on the analysis results, and the generated feedback is sent back to the device via the data return means. Furthermore, the emotion recognition means analyzes the user's emotion data and adjusts the tone of the feedback. A personalized learning plan based on the user's progress is generated by the study plan generation means.

[0705] A specific example is the following flow.

[0706] First, the user uses the device's camera to capture an image of the character "Thank you" written by the child. The image is temporarily saved on the device and then sent to the server using the data transmission means. Communication is performed using a secure protocol (e.g., SSL / TLS). The server receives the image using the receiving means, detects character regions using the analysis means, and evaluates the handwriting, shape, and stroke order of each character. For example, the server may use a deep learning model (e.g., YOLOv3) to detect character regions, and then use the Tesseract OCR engine to perform character recognition. Based on the analysis results, the feedback generation means generates feedback such as, "The character 'あ' is well-formed. 'り' needs improvement."

[0707] Next, the emotion recognition means analyzes the user's facial expression data, and if it is determined that the user is depressed, it generates feedback including an encouraging tone such as "Don't worry! You're doing great!" The generated feedback is returned to the terminal through the data return means and displayed to the user by the display means. Furthermore, the learning plan generation means generates a practice plan for writing the character "ri" based on the past feedback history and proposes it to the user.

[0708] Prompt Sentence Examples

[0709] "Please explain in detail the process flow of a system that analyzes images of children's handwriting captured by a camera and generates feedback using an AI model."

[0710] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0711] Step 1:

[0712] User inputs image of text

[0713] The user uses the device's camera to capture an image of the child's writing.

[0714] Specific behavior:

[0715] The user launches the camera app and takes a picture of the characters written by the child (for example, "aiueo").

[0716] Input: Child's writing

[0717] Output: Image file saved on device

[0718] Step 2:

[0719] The device sends the image to the server

[0720] The device uses a transmission means over the Internet to send the captured image to the server, where the image data is encoded in Base64 format and sent to the server using an HTTP POST request.

[0721] Specific behavior:

[0722] The terminal performs an encoding process and converts the image data into Base64 format.

[0723] Use an HTTP client library to create a POST request containing the encoded image data.

[0724] Input: Captured character image

[0725] Output: Encoded image data sent to the server

[0726] Step 3:

[0727] The server receives the image

[0728] The server receives the HTTP POST request, obtains the image data contained therein, decodes the image data, and saves it as a file.

[0729] Specific behavior:

[0730] The server decodes the encoded image data and returns it to the original JPEG image format.

[0731] Save the image to a file path such as " / uploads / unique_id.jpg".

[0732] Input: POST request with encoded image data

[0733] Output: Decoded JPEG image file

[0734] Step 4:

[0735] The server analyzes the image

[0736] The server uses AI models to analyze the stored image data, detecting character regions, identifying characters, and evaluating handwriting, shape, and stroke order.

[0737] Specific behavior:

[0738] Use a deep learning model (e.g., YOLOv3) to detect character regions in an image.

[0739] The detected character area is input to an OCR engine (e.g., Tesseract) for character recognition.

[0740] Input: Saved image file

[0741] Output: Analysis results of handwriting, shape, and stroke order of characters

[0742] Step 5:

[0743] Server generates feedback

[0744] The server generates feedback based on the analysis results, including the quality of the handwriting, shape, and the correctness of the stroke order.

[0745] Specific behavior:

[0746] Based on the analysis results, a feedback message is created. For example, a message such as "The character 'あ' is well-formed. 'り' needs improvement." is generated.

[0747] Input: Character analysis result

[0748] Output: Textual feedback message

[0749] Step 6:

[0750] Emotion recognition by emotion engine

[0751] The server is equipped with an emotion engine that analyzes the emotional data (facial expression data, voice data) sent by the user and adjusts the content and tone of the feedback.

[0752] Specific behavior:

[0753] The server analyzes facial expression and voice data to identify emotions.

[0754] Adjust the tone and message of your feedback based on the emotion, for example, "Don't worry! You're doing great!"

[0755] Input: User emotion data

[0756] Output: Adjusted feedback message

[0757] Step 7:

[0758] Server sends feedback

[0759] The server transmits the generated feedback back to the terminal, and the terminal displays the received feedback so that the user can confirm it.

[0760] Specific behavior:

[0761] The server generates an HTTP response including a feedback message and sends it to the terminal.

[0762] The terminal receives the response and displays a feedback message on the screen.

[0763] Input: Feedback message

[0764] Output: Feedback message displayed on the terminal

[0765] Step 8:

[0766] Track progress and generate study plans

[0767] The server tracks the user's progress and generates a personalized learning plan based on past feedback history.

[0768] Specific behavior:

[0769] The server consults a database of user feedback history and determines whether specific characters or stroke orders require ongoing improvement.

[0770] It generates and suggests to the user practice plans for characters that require continuous improvement.

[0771] Input: User feedback history data

[0772] Output: Personalized study plan

[0773] (Application example 2)

[0774] 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."

[0775] Modern educational settings require rapid and specific feedback on children's character practice. However, it is difficult for parents and teachers to provide appropriate guidance on the spot, and in many cases, children continue practicing on their own. Furthermore, to increase children's motivation to learn, encouragement and advice that takes into account their emotional state is necessary. However, recognizing emotions and generating feedback based on them requires advanced technology, which has been difficult to achieve with conventional systems.

[0776] 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 an optical sensor means for the terminal to capture a character image of the user, a data transmission means for transmitting the captured image to the server, a data receiving means for receiving the image, a data analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, a data return means for returning the feedback to the terminal, a display means for displaying the feedback, an emotion analysis means for analyzing the user's facial expressions and voice to recognize emotions, and a feedback adjustment means for adjusting the feedback content based on the emotions. This makes it possible to provide quick and specific feedback to a child's writing practice and to generate encouragement and advice according to the emotional state of the user (child or parent).

[0777] "Optical sensor means" refers to equipment and technology that uses light to capture images of objects.

[0778] "Data transmission means" refers to a function or method for transmitting acquired data to another device or system.

[0779] "Data receiving means" refers to equipment or technology that receives data sent from outside.

[0780] "Data analysis means" refers to algorithms or software that analyzes received data and evaluates the characteristics of the target object.

[0781] "Feedback generation means" refers to a system or technology that automatically generates feedback for subjects based on the results of data analysis.

[0782] The "data return means" is a function for returning the generated feedback to the original destination.

[0783] "Display means" refers to a device or technology that displays the received feedback in a form that can be confirmed by the user.

[0784] "Emotion analysis means" refers to technology or algorithms that analyze a user's facial expressions and voice data and identify their emotions.

[0785] "Feedback adjustment means" refers to a system or technology for adjusting the content of feedback based on the results of emotion analysis.

[0786] System Program

[0787] This invention is a system for providing feedback to children's writing practice, and uses the following means:

[0788] 1. Terminal hardware and software:

[0789] Optical sensor means: Uses the camera built into a smartphone or tablet to capture an image of the letters written by the child.

[0790] Data transmission means: A network communication function for transmitting captured images to a server. The image data is encoded in Base64 format or other appropriate format.

[0791] Data receiving means: A function for receiving feedback data returned from the server.

[0792] 2. Server-side hardware and software:

[0793] Data receiving means: A function that receives image data sent from a terminal. Protocols such as HTTP POST are used.

[0794] Data analysis method: An algorithm that analyzes received image data and evaluates character recognition, handwriting, shape, and stroke order. It uses AI models and image processing technology.

[0795] Feedback generator: An algorithm that generates personalized feedback based on the analysis results, including specific suggestions for improvement.

[0796] Emotion analysis means: Analyzes the user's facial expressions and voice data to recognize emotions. For example, facial expression recognition technology and voice analysis technology are used.

[0797] Feedback adjustment measures: Based on the results of sentiment analysis, the content of the feedback is adjusted, for example, by adding encouraging words or changing the tone to a gentler one.

[0798] 3. Display means: A function to display feedback on the device's display, including text and images.

[0799] Natural language explanation of the process

[0800] The device uses the camera built into the smartphone or tablet to capture an image of the characters written by the child. The captured image is then sent to a server via the Internet using a data transmission means. At this time, the image data is encoded in a compressed format such as Base64 format and sent using an HTTP POST request.

[0801] The server decodes the received image data and detects character regions within the image using a data analysis means. The server then uses a character recognition algorithm to identify characters within the detected character regions and evaluates their handwriting, shape, and stroke order. Based on the evaluation results, a feedback generation means generates individual feedback.

[0802] Next, the emotion analysis means analyzes the user's facial expression data and voice data to identify the user's emotions (e.g., joy, sadness, lack of motivation, etc.). The feedback adjustment means adjusts the feedback content based on the identified emotions. For example, if the user is feeling down, an encouraging message such as "Great progress! You'll get even better if you practice more!" is added.

[0803] Finally, the generated feedback is sent to the terminal using the data return means and visually displayed to the user through the display means, allowing the user to support the child's practice based on this feedback.

[0804] Examples of concrete examples and prompts

[0805] Examples:

[0806] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, feedback is generated, such as "the shape of the character "a" is accurate, but the character "ri" is a little awkward, so it's "inaccurate." This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion analysis engine generates an encouraging message such as "Great progress! You can do better next time!" The user can see this feedback and encouraging message and instruct the child to practice writing the character "ri" again.

[0807] Example prompt sentence:

[0808] 1. Take a picture of the letters your child has written with your camera.

[0809] 2. Send the captured image for analysis within the app.

[0810] 3. Emotional feedback for the child will also be displayed along with the analysis results.

[0811] example:

[0812] Photo taken: "Thank you.jpg"

[0813] Submitted response: "Feedback: The shape is accurate, but the stroke order needs improvement. Great progress! More practice will help you improve even more!"

[0814] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0815] Step 1:

[0816] The user uses the camera on their smartphone or tablet to capture an image of the letters written by the child. Specifically, the user launches the camera app, adjusts the exposure so that the letters are clearly visible, and presses the shutter. The input is the "letters written by the child," and the output is a "letter image file."

[0817] Step 2:

[0818] The terminal sends the captured text image to the server using a data transmission means. At this time, the image data is encoded in a format such as Base64, encrypted, and sent using an HTTP POST request. The input is a "text image file," and the output is "request data sent to the server."

[0819] Step 3:

[0820] The server receives the HTTP POST request and obtains the image data using the data receiving means. Specifically, the server decodes the Base64-encoded image data from the request and saves it as a file. The input is the "request data" and the output is the "decoded image file."

[0821] Step 4:

[0822] The server analyzes the stored image data using data analysis means. First, it uses an image processing algorithm to detect character regions, then performs character recognition using an AI model. It then evaluates the handwriting, shape, and stroke order. The input is the "decoded image file," and the output is the "character recognition and evaluation results."

[0823] Step 5:

[0824] The server generates feedback based on the analysis results using a feedback generation means. Specifically, it generates feedback in text format based on the evaluation results, including suggestions for improvement and encouraging messages. The input is "character recognition and evaluation results," and the output is "feedback text."

[0825] Step 6:

[0826] The server analyzes the user's facial expression data and voice data using emotion analysis means. The server uses an AI model to identify emotions from facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the emotion identification result.

[0827] Step 7:

[0828] The server adjusts the feedback content using a feedback adjustment means based on the emotion analysis results. Specifically, it adds encouraging or advice messages to the feedback according to the emotion. The input is the "feedback text" and the "emotion identification result," and the output is the "adjusted feedback text."

[0829] Step 8:

[0830] The server sends the generated adjusted feedback to the terminal using the data return means, where the input is the "adjusted feedback text" and the output is the "feedback data to be sent to the terminal".

[0831] Step 9:

[0832] The terminal displays the received feedback using a display means. Specifically, the received feedback text is displayed on the screen so that the user can easily check it. The input is "feedback data" and the output is "feedback displayed on the terminal display."

[0833] 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.

[0834] 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.

[0835] 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.

[0836] [Third embodiment]

[0837] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0838] 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.

[0839] 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).

[0840] 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.

[0841] 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.

[0842] 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).

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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."

[0849] The present invention relates to a system for analyzing images of characters written by a child and providing feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, and a display means.

[0850] User inputs image of text

[0851] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[0852] The device sends the image to the server

[0853] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[0854] The server receives the image

[0855] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used in the next analysis step.

[0856] The server analyzes the image

[0857] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[0858] Feedback Generation

[0859] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[0860] Sending and Viewing Feedback

[0861] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[0862] Track progress and generate study plans

[0863] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[0864] Specific examples

[0865] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is a bit awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. The user can see this feedback and instruct the child to practice writing "ri" again.

[0866] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to study together in a fun and effective way.

[0867] The processing flow will be explained below.

[0868] Step 1:

[0869] The device captures the user's image of the text. The user launches the device's camera app and takes a picture of the text written by the child. The device temporarily stores the captured image in memory.

[0870] Step 2:

[0871] The device sends the captured image to the server. The device converts the captured image into Base64 format and sends it to the server using an HTTP POST request. The image data is encrypted using a network connection.

[0872] Step 3:

[0873] The server receives the image. The server receives the HTTP request and obtains the transmitted image data. It decodes the image data and saves it as a file. The saved image is used for subsequent processing.

[0874] Step 4:

[0875] The server analyzes the image. It reads the saved image file and uses an AI model to detect character regions within the image. After the character regions are detected, it performs character recognition and evaluates the handwriting, shape, and stroke order. Image processing algorithms and deep learning technology are applied for character recognition.

[0876] Step 5:

[0877] The server generates feedback. Based on the analysis results, the server generates specific feedback to the user in text format. The feedback includes evaluations such as "Excellent!" or "Needs improvement."

[0878] Step 6:

[0879] The server returns the generated feedback to the device. The server encodes the feedback in text format and sends it to the device as an HTTP response. The feedback is saved in the user's past feedback history.

[0880] Step 7:

[0881] The device receives and displays the feedback. The device decodes the feedback received from the server and displays it in a format that is easy for the user to read. The user can check this feedback and use it to improve their next practice.

[0882] Step 8:

[0883] The server tracks the user's progress. The server records and analyzes the user's learning progress based on the user's feedback history. If necessary, it generates a personalized learning plan.

[0884] Step 9:

[0885] The server generates a personalized learning plan. The server takes into account the user's past feedback history and generates a learning plan that includes the optimal practice method and character practice order. This learning plan is provided as feedback the next time the user practices.

[0886] The above are the specific processing steps of the system based on the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[0887] Example 1

[0888] 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."

[0889] In conventional character practice systems, evaluation of a child's handwriting is subjective, making it difficult to obtain objective feedback. Furthermore, the feedback is temporary, making it difficult to obtain continuous learning benefits. Furthermore, feedback and learning plans tailored to individual learning progress are not provided, preventing efficient learning.

[0890] 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.

[0891] In this invention, the server includes an analysis means for analyzing the received image data and evaluating character identification, handwriting, shape, and stroke order; a feedback generation means for generating feedback based on the analysis results; and a return means for returning the generated feedback to the terminal. This allows the user to receive objective and specific feedback on the child's character practice. Furthermore, by providing a personalized learning plan based on past feedback history, continuous and individualized learning can be achieved.

[0892] "User" refers to a person who uses the system, specifically a parent or educator who supports children in practicing writing.

[0893] "Text image" refers to image data of text written by a child that is captured by the user using the device's camera.

[0894] "Photographing means" refers to the camera function built into the device, which the user uses to capture an image of the child's text.

[0895] "Transmission means" refers to the means for transmitting image data from a terminal to a server via the Internet. Specifically, an HTTP POST request is used.

[0896] The term "server device" refers to a combination of hardware and software for receiving, storing, and analyzing image data sent from a terminal.

[0897] "Analysis means" refers to the algorithms and AI models that analyze image data within the server device and evaluate character identification, handwriting, shape, and stroke order.

[0898] "Feedback generation means" refers to the means for generating feedback to be provided to users based on the analysis results, specifically using an AI model or a rule-based engine.

[0899] The "returning means" refers to a means for transmitting the generated feedback information from the server to the terminal. Specifically, an HTTP response is used.

[0900] The "display means" refers to a UI (user interface) for displaying the feedback information received by the terminal to the user.

[0901] The "text area" refers to the part of the text image where text is actually written, and is detected by the analysis means.

[0902] "Character recognition" refers to OCR (optical character recognition) processing performed on detected character areas.

[0903] "Study Plan" refers to a personalized learning menu created based on the user's past feedback history.

[0904] "Feedback History" refers to a record of feedback previously provided to a user, used to track progress and generate a study plan.

[0905] The present invention is a system that uses a user's terminal to capture an image of characters written by a child, analyzes the image on a server, and provides feedback. This system includes a terminal, a server, a camera means, a transmission means, an analysis means, a feedback generation means, a return means, and a display means.

[0906] User inputs image of text

[0907] The user uses the device's camera to capture an image of the characters written by the child. Specifically, the device's built-in camera is used. The image data captured by this camera is saved in the device's memory. When saving, the image resolution may be adjusted or compressed.

[0908] The device sends the image to the server

[0909] The device sends the captured image data to the server via an HTTP POST request over the Internet. The image data is encoded in Base64 format and encrypted using secure communication (e.g., TLS / SSL).

[0910] The server receives the image

[0911] The server receives the HTTP POST request and obtains the image data from the request body. The obtained data is decoded from Base64 format and saved in the server's storage with a file name that can be uniquely identified.

[0912] The server analyzes the image

[0913] The server loads the saved image files and starts the analysis process, using deep learning techniques (e.g., CNN models using TensorFlow or PyTorch) and image processing algorithms. The analysis process includes the following steps:

[0914] Character region detection (e.g., YOLO algorithm)

[0915] Identification of each character (OCR character recognition)

[0916] Evaluation of handwriting, shape, and stroke order (feature extraction)

[0917] Feedback Generation

[0918] The server generates feedback based on the analysis results. The generated feedback includes an evaluation of the character shape and handwriting, and the appropriateness of the stroke order. For example, specific comments such as "Excellent!" or "Needs improvement" are added. This feedback is saved in text format and is reflected in the user's past feedback history.

[0919] Sending and Viewing Feedback

[0920] The server then sends the generated feedback back to the device. It is serialized in JSON format and sent back as an HTTP response. The device then deserializes the received feedback and displays it to the user using a UI framework (e.g., React Native or Flutter).

[0921] Track progress and generate study plans

[0922] The server tracks the user's progress and generates a personalized learning plan based on past feedback. For example, if a specific character or stroke order needs continuous improvement, a practice menu will be generated accordingly. This learning plan is presented to the user upon login and periodically to support efficient learning.

[0923] Specific examples

[0924] For example, consider the case where a child writes the character "thank you" and the user captures it with the device's camera. At this time, the device sends the image data to the server, which analyzes the image data and recognizes the word "thank you." The handwriting, shape, and stroke order of each character are evaluated, and since the shape of "a" is correct but "ri" is somewhat distorted, feedback "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. Based on this feedback, the user can instruct the child to practice writing "ri" again.

[0925] Prompt Sentence Examples

[0926] A camera captures a child writing "thank you." Analyze the image to assess the correctness of each character's handwriting, shape, and stroke order, and provide feedback.

[0927] The above is an embodiment of the present invention. The user can receive objective and specific feedback on the child's character practice, enabling the child to progress in learning effectively.

[0928] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0929] Step 1:

[0930] The user uses the device's camera to capture an image of the child's writing. Specifically, the user opens the camera app, frames the appropriate part of the writing, and presses the shutter button. The captured image data is saved in the device's internal memory in an appropriate resolution, such as JPEG format. The input in this step is the child's writing, and the output is the captured image data.

[0931] Step 2:

[0932] The device uses its Internet connection to send the stored image data to the server. The image data is encoded in Base64 format and sent to the server as an HTTP POST request. Specifically, the following request is generated:

[0933] POST / upload HTTP / 1.1

[0934] Host: example.com

[0935] Content-Type: application / json

[0936] {

[0937] "imageData": "base64_encoded_image_data"

[0938] }

[0939] The input is the captured image data (a file in memory) and the output is an HTTP request to the server.

[0940] Step 3:

[0941] The server analyzes the received HTTP POST request and extracts the image data from the request body. Specifically, it decodes the Base64 format data and saves it as an image file. For example, the following process is performed:

[0942] decoded_image_data = base64.b64decode(request.json['imageData'])

[0943] with open("path / to / save / image.jpg", "wb") as f:

[0944] f.write(decoded_image_data)

[0945] The input is the HTTP request data, and the output is an image file in the server storage.

[0946] Step 4:

[0947] The server reads the saved image file and performs analysis. It uses a deep learning model (e.g., a CNN model using TensorFlow or PyTorch) to detect character regions, identify characters, and evaluate handwriting, shape, and stroke order. Specific processing examples are as follows:

[0948] image = load_image("path / to / save / image.jpg")

[0949] bounding_boxes = detect_text_regions(image)

[0950] for box in bounding_boxes:

[0951] character_image = crop_image(image, box)

[0952] recognized_character = recognizer_model.predict(character_image)

[0953] evaluate_characteristics(recognized_character)

[0954] The input is an image file stored in the server, and the output is the analysis results (character identification and characteristic evaluation).

[0955] Step 5:

[0956] The server generates feedback based on the analysis results. The feedback generation algorithm compiles the evaluation results of the handwriting and shape of each character and generates a comment to be provided to the user. For example, feedback such as "Excellent!" or "Needs improvement" is generated. The generated feedback is converted into text format and saved as follows:

[0957] feedback = {

[0958] "character": "ri",

[0959] "evaluation": "Needs improvement",

[0960] "comment": "The shape is out of order and needs to be rewritten."

[0961] }

[0962] The input is the analysis results and the output is the generated feedback data.

[0963] Step 6:

[0964] The server returns the generated feedback to the device by serializing the feedback data in JSON format and sending it to the device via an HTTP response. Specifically, the following response is returned:

[0965] HTTP / 1.1 200 OK

[0966] Content-Type: application / json

[0967] {

[0968] "feedback": {

[0969] "character": "ri",

[0970] "evaluation": "Needs improvement",

[0971] "comment": "The shape is out of order and needs to be rewritten."

[0972] }

[0973] }

[0974] The input is the generated feedback data, and the output is the HTTP response to the terminal.

[0975] Step 7:

[0976] The device deserializes the received feedback and displays it to the user, using a UI framework (e.g., React Native or Flutter) to display a message like this:

[0977] "Evaluation result: The shape of the 'ri' character is broken, so practice 'ri' again."

[0978] The input is the received feedback data and the output is the feedback message that is displayed to the user.

[0979] (Application example 1)

[0980] 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."

[0981] Conventional product quality inspection systems often require manual inspection or complex, specialized equipment, which can be inefficient and costly. Furthermore, detailed analysis, such as evaluating handwriting, shape, and stroke order, requires specialized knowledge, making it difficult to provide accurate feedback. Furthermore, generating a personalized learning plan based on feedback is not easy. To address these challenges, a more efficient and versatile system is needed.

[0982] 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.

[0983] In this invention, the server includes an analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, and a factory robot control means for inspecting the quality of the product. This improves the efficiency of product quality inspection, particularly enabling accurate confirmation of the marking of product lot numbers and quality control symbols. It also makes it possible to provide highly accurate feedback based on detailed analysis such as handwriting evaluation.

[0984] "Capture means" refers to a device or method for capturing an image of an object or scene, such as a digital camera or a smartphone camera.

[0985] A "transmission mechanism" is a system or protocol for sending data from one device to another, such as an HTTP POST request over the Internet.

[0986] A "server means" is a computer system that receives a request and executes a specific process. Examples include a web server and a database server.

[0987] "Analysis means" refers to a method or device that analyzes input data and extracts useful information. Examples of this include image processing algorithms and deep learning models.

[0988] The "feedback generation means" refers to a method or device for creating feedback to be provided to a user based on the analysis results. For example, this includes software that generates evaluation comments or recommendations.

[0989] A "return mechanism" is a system or protocol for returning the generated feedback to the sending device, such as an HTTP response from the server to the client.

[0990] "Display means" refers to a device or method for displaying the received feedback in a form that can be confirmed by the user. Examples include a monitor or a smartphone display.

[0991] "Factory robot control means" refers to a system that controls the robots used in factories and performs operations such as product quality inspections and line changes. Specifically, this refers to the software and hardware that controls the operation of the robot arm.

[0992] The present invention relates to a system for automating product quality inspections by factory robots and providing efficient feedback. The system includes an image capturing unit, a transmission unit, a server unit, an analysis unit, a feedback generating unit, a return unit, a display unit, and a factory robot control unit.

[0993] Recording method and image transmission

[0994] First, the factory robot uses its on-board camera to capture images of lot numbers and quality control symbols engraved on products. This camera has high resolution and can accurately capture even small markings. The captured image is then sent to a server via the Internet using a transmission method. To ensure security, the image data is converted to Base64 format and encrypted and sent via an HTTP POST request.

[0995] Image analysis on the server

[0996] The server receives the transmitted images and analyzes the image data using analytical methods, including the latest AI models and deep learning algorithms. This analysis process involves detecting character regions, recognizing characters, and evaluating handwriting and shape. Specifically, OpenCV is used for image processing, and character recognition is performed using a generative AI model such as TensorFlow.

[0997] Generate and return feedback

[0998] Based on the analysis results, the feedback generation means generates appropriate feedback. The feedback includes evaluations such as "Excellent!" or "Needs improvement," and if a defective product is detected, special instructions are generated. The generated feedback is then sent back to the terminal using the transmission means.

[0999] Feedback display and robot control

[1000] The terminal displays the received feedback using a display means. The user can check this feedback and understand the quality status of the product. The factory robot control means automatically controls the operation based on the feedback. If a defective product is detected, the robot is operated to send the product to another line.

[1001] Specific examples

[1002] For example, when checking the lot number "1234" engraved on a product manufactured in a factory, the system works as follows: First, the factory robot's camera captures an image of the product with the lot number "1234" engraved on it and sends the image to the server. The server analyzes the image, generates feedback, and returns a "Needs improvement" rating. The user confirms this feedback, and the robot automatically sends the product to another line.

[1003] Prompt Sentence Examples

[1004] Capture an image of the lot number "1234" stamped on the product, send it to the server, and get the analysis results. Based on the feedback, you can decide whether to send it to the defective line.

[1005] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1006] Step 1:

[1007] Image capture by device

[1008] The terminal uses a camera mounted on the factory robot to capture images of lot numbers and quality control symbols engraved on products. In this step, a high-resolution camera is used to accurately capture even the finest markings.

[1009] Input: Physical product

[1010] Output: High-resolution image of the product

[1011] Step 2:

[1012] Sending images

[1013] The device then sends the captured image to a server over the Internet, where it is converted to Base64 format and encrypted via an HTTP POST request to ensure secure communication.

[1014] Input: High-resolution image of product

[1015] Output: Encrypted image data in Base64 format

[1016] Step 3:

[1017] Image reception on the server

[1018] The server receives the transmitted image data, decodes it from Base64 format, and saves it as an image file, which allows subsequent analysis.

[1019] Input: Encrypted Base64 image data

[1020] Output: Decoded image file

[1021] Step 4:

[1022] Image analysis

[1023] The server analyzes the received image using an analysis method. In this step, image processing algorithms and generative AI models are used to detect character regions, recognize characters, and evaluate handwriting and shape. For example, character regions are extracted using OpenCV, and character recognition is performed using TensorFlow or similar.

[1024] Input: Decoded image file

[1025] Output: Character area coordinates and character recognition results

[1026] Step 5:

[1027] Feedback Generation

[1028] The server generates feedback based on the results of image analysis, including an assessment of the product's quality and whether it is defective. Specifically, the server generates assessments such as "Excellent!" or "Needs improvement."

[1029] Input: Character recognition result

[1030] Output: Feedback text

[1031] Step 6:

[1032] Sending feedback

[1033] The server sends the generated feedback to the device using a standard data format such as JSON.

[1034] Input: Feedback text

[1035] Output: Feedback data in JSON format

[1036] Step 7:

[1037] View Feedback

[1038] The device displays the received feedback for the user to review. The display is done on the device's screen or display. Based on this feedback, the user can judge the quality of the product.

[1039] Input: Feedback data in JSON format

[1040] Output: The displayed feedback text

[1041] Step 8:

[1042] Robot Control

[1043] Based on the feedback, the factory robot control system automatically controls its operation. If a defective product is detected, the robot will take action such as sending the product to another line.

[1044] Input: Feedback text

[1045] Output: Robot operation instructions (e.g., move to defective product line)

[1046] Through the above processing steps, a product quality inspection system using a factory robot is realized.

[1047] 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.

[1048] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[1049] User inputs image of text

[1050] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[1051] The device sends the image to the server

[1052] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[1053] The server receives the image

[1054] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used for subsequent processing.

[1055] The server analyzes the image

[1056] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[1057] Feedback Generation

[1058] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[1059] Emotion recognition by emotion engine

[1060] The server is equipped with an emotion engine that analyzes the emotion data (e.g., facial expression data, voice data) sent by the user. The emotion engine identifies the user's emotion and adjusts the content and tone of the feedback based on that emotion. For example, if the user is feeling discouraged, a message of encouragement and motivation will be generated.

[1061] Sending and Viewing Feedback

[1062] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[1063] Track progress and generate study plans

[1064] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[1065] Specific examples

[1066] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to the server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is somewhat awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion engine will generate an encouraging message such as "Good job! Just keep practicing and you'll improve your 'ri' in no time!". The user can see this feedback and encouraging message and instruct the child to practice writing "ri" again.

[1067] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[1068] The processing flow will be explained below.

[1069] Step 1:

[1070] The user uses the device's camera to capture an image of the child's writing. The device then activates the camera and captures the image of the writing. The device then saves the image at the appropriate resolution.

[1071] Step 2:

[1072] The device sends the captured image to the server. The image data is converted to Base64 format and sent to the server using an HTTP POST request. The data is encrypted to ensure security.

[1073] Step 3:

[1074] The server receives the HTTP POST request and retrieves the image data. The server decodes the Base64 data and saves it as an image file for further analysis.

[1075] Step 4:

[1076] The server reads the saved image file and uses the AI ​​model to detect text areas within the image, then performs character recognition on the detected text areas, using deep learning technology.

[1077] Step 5:

[1078] Based on the results of character recognition, the server evaluates the user's handwriting, shape, and stroke order, for example, determining whether the characters are written in the correct shape and stroke order.

[1079] Step 6:

[1080] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, and the correctness of the stroke order. Specific examples of feedback include "Excellent!" and "Needs improvement."

[1081] Step 7:

[1082] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes facial expression and voice data sent from the device to identify the user's emotions. The emotion data is used to adjust the feedback.

[1083] Step 8:

[1084] The server takes emotional data into account and adjusts the content and tone of the feedback, for example, if the user is feeling discouraged it might include an encouraging message like "Great effort! Keep it up!"

[1085] Step 9:

[1086] The server returns the generated feedback to the device. The feedback is sent to the device as an HTTP response. The feedback data is also encrypted before being sent.

[1087] Step 10:

[1088] The device decodes the received feedback and displays it to the user in a visually friendly format. The user can review the feedback and use it to improve their next practice.

[1089] Step 11:

[1090] The server tracks the user's progress and generates a personalized learning plan based on past feedback, suggesting the best practice method and order for practicing characters.

[1091] Step 12:

[1092] The device displays a personalized learning plan to the user, allowing the user to effectively practice writing with their child based on this plan.

[1093] The above are the specific processing steps for implementing the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively. Furthermore, by combining it with an emotion engine, flexible feedback is provided that responds to the user's emotions.

[1094] Example 2

[1095] 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."

[1096] Previous character learning systems were unable to objectively evaluate a child's handwriting and provide specific feedback. They also lacked an effective way to maintain user motivation, as they were unable to analyze the user's emotions and adjust the content and tone of the feedback. Furthermore, their ability to generate and provide individual learning plans to users was limited, making it difficult to provide an efficient and personalized learning experience.

[1097] 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.

[1098] In this invention, the server includes an image analysis means, a feedback generation means, and an emotion recognition means. This allows the server to analyze image data to evaluate the handwriting, shape, and stroke order of characters, and to analyze the user's emotions to adjust the tone of the feedback. It also tracks the user's progress and generates a personalized learning plan, providing an efficient and individualized learning experience.

[1099] "Image acquisition means" is a function that allows the terminal to capture a character image of the user.

[1100] The "data transmission means" is a function for transmitting the captured character image to the server.

[1101] The "receiving means" is a function that allows the server to receive a character image sent from a user.

[1102] The "image analysis means" is a function for analyzing received character images and evaluating the handwriting, shape, and stroke order.

[1103] The "feedback generation means" is a function for generating feedback to be provided to the user based on the results of image analysis.

[1104] The "data return means" is a function for returning the generated feedback to the terminal.

[1105] The "display means" is a function for displaying the feedback received by the terminal to the user.

[1106] The "emotion recognition means" is a function for analyzing the user's emotional data and adjusting the tone of the feedback.

[1107] The "study plan generator" is a function for tracking a user's progress and generating a personalized study plan based on past feedback history.

[1108] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[1109] Hardware and software used

[1110] The user uses a device as image acquisition means, such as a smartphone or tablet, to capture an image of the characters written by the child. The captured image is sent to a server via the Internet via the device's data transmission means. The server receives the image data using the data receiving means and then analyzes the image using the analysis means. Image processing algorithms and deep learning techniques are used for this analysis. Feedback is generated by the feedback generation means based on the analysis results, and the generated feedback is sent back to the device via the data return means. Furthermore, the emotion recognition means analyzes the user's emotion data and adjusts the tone of the feedback. A personalized learning plan based on the user's progress is generated by the study plan generation means.

[1111] A specific example is the following flow.

[1112] First, the user uses the device's camera to capture an image of the character "Thank you" written by the child. The image is temporarily saved on the device and then sent to the server using the data transmission means. Communication is performed using a secure protocol (e.g., SSL / TLS). The server receives the image using the receiving means, detects character regions using the analysis means, and evaluates the handwriting, shape, and stroke order of each character. For example, the server may use a deep learning model (e.g., YOLOv3) to detect character regions, and then use the Tesseract OCR engine to perform character recognition. Based on the analysis results, the feedback generation means generates feedback such as, "The character 'あ' is well-formed. 'り' needs improvement."

[1113] Next, the emotion recognition means analyzes the user's facial expression data, and if it is determined that the user is depressed, it generates feedback including an encouraging tone such as "Don't worry! You're doing great!" The generated feedback is returned to the terminal through the data return means and displayed to the user by the display means. Furthermore, the learning plan generation means generates a practice plan for writing the character "ri" based on the past feedback history and proposes it to the user.

[1114] Prompt Sentence Examples

[1115] "Please explain in detail the process flow of a system that analyzes images of children's handwriting captured by a camera and generates feedback using an AI model."

[1116] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] User inputs image of text

[1119] The user uses the device's camera to capture an image of the child's writing.

[1120] Specific behavior:

[1121] The user launches the camera app and takes a picture of the characters written by the child (for example, "aiueo").

[1122] Input: Child's writing

[1123] Output: Image file saved on device

[1124] Step 2:

[1125] The device sends the image to the server

[1126] The device uses a transmission means over the Internet to send the captured image to the server, where the image data is encoded in Base64 format and sent to the server using an HTTP POST request.

[1127] Specific behavior:

[1128] The terminal performs an encoding process and converts the image data into Base64 format.

[1129] Use an HTTP client library to create a POST request containing the encoded image data.

[1130] Input: Captured character image

[1131] Output: Encoded image data sent to the server

[1132] Step 3:

[1133] The server receives the image

[1134] The server receives the HTTP POST request, obtains the image data contained therein, decodes the image data, and saves it as a file.

[1135] Specific behavior:

[1136] The server decodes the encoded image data and returns it to the original JPEG image format.

[1137] Save the image to a file path such as " / uploads / unique_id.jpg".

[1138] Input: POST request with encoded image data

[1139] Output: Decoded JPEG image file

[1140] Step 4:

[1141] The server analyzes the image

[1142] The server uses AI models to analyze the stored image data, detecting character regions, identifying characters, and evaluating handwriting, shape, and stroke order.

[1143] Specific behavior:

[1144] Use a deep learning model (e.g., YOLOv3) to detect character regions in an image.

[1145] The detected character area is input to an OCR engine (e.g., Tesseract) for character recognition.

[1146] Input: Saved image file

[1147] Output: Analysis results of handwriting, shape, and stroke order of characters

[1148] Step 5:

[1149] Server generates feedback

[1150] The server generates feedback based on the analysis results, including the quality of the handwriting, shape, and the correctness of the stroke order.

[1151] Specific behavior:

[1152] Based on the analysis results, a feedback message is created. For example, a message such as "The character 'あ' is well-formed. 'り' needs improvement." is generated.

[1153] Input: Character analysis result

[1154] Output: Textual feedback message

[1155] Step 6:

[1156] Emotion recognition by emotion engine

[1157] The server is equipped with an emotion engine that analyzes the emotional data (facial expression data, voice data) sent by the user and adjusts the content and tone of the feedback.

[1158] Specific behavior:

[1159] The server analyzes facial expression and voice data to identify emotions.

[1160] Adjust the tone and message of your feedback based on the emotion, for example, "Don't worry! You're doing great!"

[1161] Input: User emotion data

[1162] Output: Adjusted feedback message

[1163] Step 7:

[1164] Server sends feedback

[1165] The server transmits the generated feedback back to the terminal, and the terminal displays the received feedback so that the user can confirm it.

[1166] Specific behavior:

[1167] The server generates an HTTP response including a feedback message and sends it to the terminal.

[1168] The terminal receives the response and displays a feedback message on the screen.

[1169] Input: Feedback message

[1170] Output: Feedback message displayed on the terminal

[1171] Step 8:

[1172] Track progress and generate study plans

[1173] The server tracks the user's progress and generates a personalized learning plan based on past feedback history.

[1174] Specific behavior:

[1175] The server consults a database of user feedback history and determines whether specific characters or stroke orders require ongoing improvement.

[1176] It generates and suggests to the user practice plans for characters that require continuous improvement.

[1177] Input: User feedback history data

[1178] Output: Personalized study plan

[1179] (Application example 2)

[1180] 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."

[1181] Modern educational settings require rapid and specific feedback on children's character practice. However, it is difficult for parents and teachers to provide appropriate guidance on the spot, and in many cases, children continue practicing on their own. Furthermore, to increase children's motivation to learn, encouragement and advice that takes into account their emotional state is necessary. However, recognizing emotions and generating feedback based on them requires advanced technology, which has been difficult to achieve with conventional systems.

[1182] 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 an optical sensor means for the terminal to capture a character image of the user, a data transmission means for transmitting the captured image to the server, a data receiving means for receiving the image, a data analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, a data return means for returning the feedback to the terminal, a display means for displaying the feedback, an emotion analysis means for analyzing the user's facial expressions and voice to recognize emotions, and a feedback adjustment means for adjusting the feedback content based on the emotions. This makes it possible to provide quick and specific feedback to a child's writing practice and to generate encouragement and advice according to the emotional state of the user (child or parent).

[1183] "Optical sensor means" refers to equipment and technology that uses light to capture images of objects.

[1184] "Data transmission means" refers to a function or method for transmitting acquired data to another device or system.

[1185] "Data receiving means" refers to equipment or technology that receives data sent from outside.

[1186] "Data analysis means" refers to algorithms or software that analyzes received data and evaluates the characteristics of the target object.

[1187] "Feedback generation means" refers to a system or technology that automatically generates feedback for subjects based on the results of data analysis.

[1188] The "data return means" is a function for returning the generated feedback to the original destination.

[1189] "Display means" refers to a device or technology that displays the received feedback in a form that can be confirmed by the user.

[1190] "Emotion analysis means" refers to technology or algorithms that analyze a user's facial expressions and voice data and identify their emotions.

[1191] "Feedback adjustment means" refers to a system or technology for adjusting the content of feedback based on the results of emotion analysis.

[1192] System Program

[1193] This invention is a system for providing feedback to children's writing practice, and uses the following means:

[1194] 1. Terminal hardware and software:

[1195] Optical sensor means: Uses the camera built into a smartphone or tablet to capture an image of the letters written by the child.

[1196] Data transmission means: A network communication function for transmitting captured images to a server. The image data is encoded in Base64 format or other appropriate format.

[1197] Data receiving means: A function for receiving feedback data returned from the server.

[1198] 2. Server-side hardware and software:

[1199] Data receiving means: A function that receives image data sent from a terminal. Protocols such as HTTP POST are used.

[1200] Data analysis method: An algorithm that analyzes received image data and evaluates character recognition, handwriting, shape, and stroke order. It uses AI models and image processing technology.

[1201] Feedback generator: An algorithm that generates personalized feedback based on the analysis results, including specific suggestions for improvement.

[1202] Emotion analysis means: Analyzes the user's facial expressions and voice data to recognize emotions. For example, facial expression recognition technology and voice analysis technology are used.

[1203] Feedback adjustment measures: Based on the results of sentiment analysis, the content of the feedback is adjusted, for example, by adding encouraging words or changing the tone to a gentler one.

[1204] 3. Display means: A function to display feedback on the device's display, including text and images.

[1205] Natural language explanation of the process

[1206] The device uses the camera built into the smartphone or tablet to capture an image of the characters written by the child. The captured image is then sent to a server via the Internet using a data transmission means. At this time, the image data is encoded in a compressed format such as Base64 format and sent using an HTTP POST request.

[1207] The server decodes the received image data and detects character regions within the image using a data analysis means. The server then uses a character recognition algorithm to identify characters within the detected character regions and evaluates their handwriting, shape, and stroke order. Based on the evaluation results, a feedback generation means generates individual feedback.

[1208] Next, the emotion analysis means analyzes the user's facial expression data and voice data to identify the user's emotions (e.g., joy, sadness, lack of motivation, etc.). The feedback adjustment means adjusts the feedback content based on the identified emotions. For example, if the user is feeling down, an encouraging message such as "Great progress! You'll get even better if you practice more!" is added.

[1209] Finally, the generated feedback is sent to the terminal using the data return means and visually displayed to the user through the display means, allowing the user to support the child's practice based on this feedback.

[1210] Examples of concrete examples and prompts

[1211] Examples:

[1212] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, feedback is generated, such as "the shape of the character "a" is accurate, but the character "ri" is a little awkward, so it's "inaccurate." This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion analysis engine generates an encouraging message such as "Great progress! You can do better next time!" The user can see this feedback and encouraging message and instruct the child to practice writing the character "ri" again.

[1213] Example prompt sentence:

[1214] 1. Take a picture of the letters your child has written with your camera.

[1215] 2. Send the captured image for analysis within the app.

[1216] 3. Emotional feedback for the child will also be displayed along with the analysis results.

[1217] example:

[1218] Photo taken: "Thank you.jpg"

[1219] Submitted response: "Feedback: The shape is accurate, but the stroke order needs improvement. Great progress! More practice will help you improve even more!"

[1220] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1221] Step 1:

[1222] The user uses the camera on their smartphone or tablet to capture an image of the letters written by the child. Specifically, the user launches the camera app, adjusts the exposure so that the letters are clearly visible, and presses the shutter. The input is the "letters written by the child," and the output is a "letter image file."

[1223] Step 2:

[1224] The terminal sends the captured text image to the server using a data transmission means. At this time, the image data is encoded in a format such as Base64, encrypted, and sent using an HTTP POST request. The input is a "text image file," and the output is "request data sent to the server."

[1225] Step 3:

[1226] The server receives the HTTP POST request and obtains the image data using the data receiving means. Specifically, the server decodes the Base64-encoded image data from the request and saves it as a file. The input is the "request data" and the output is the "decoded image file."

[1227] Step 4:

[1228] The server analyzes the stored image data using data analysis means. First, it uses an image processing algorithm to detect character regions, then performs character recognition using an AI model. It then evaluates the handwriting, shape, and stroke order. The input is the "decoded image file," and the output is the "character recognition and evaluation results."

[1229] Step 5:

[1230] The server generates feedback based on the analysis results using a feedback generation means. Specifically, it generates feedback in text format based on the evaluation results, including suggestions for improvement and encouraging messages. The input is "character recognition and evaluation results," and the output is "feedback text."

[1231] Step 6:

[1232] The server analyzes the user's facial expression data and voice data using emotion analysis means. The server uses an AI model to identify emotions from facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the emotion identification result.

[1233] Step 7:

[1234] The server adjusts the feedback content using a feedback adjustment means based on the emotion analysis results. Specifically, it adds encouraging or advice messages to the feedback according to the emotion. The input is the "feedback text" and the "emotion identification result," and the output is the "adjusted feedback text."

[1235] Step 8:

[1236] The server sends the generated adjusted feedback to the terminal using the data return means, where the input is the "adjusted feedback text" and the output is the "feedback data to be sent to the terminal".

[1237] Step 9:

[1238] The terminal displays the received feedback using a display means. Specifically, the received feedback text is displayed on the screen so that the user can easily check it. The input is "feedback data" and the output is "feedback displayed on the terminal display."

[1239] 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.

[1240] 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.

[1241] 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.

[1242] [Fourth embodiment]

[1243] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1244] 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.

[1245] 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).

[1246] 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.

[1247] 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.

[1248] 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).

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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."

[1256] The present invention relates to a system for analyzing images of characters written by a child and providing feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, and a display means.

[1257] User inputs image of text

[1258] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[1259] The device sends the image to the server

[1260] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[1261] The server receives the image

[1262] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used in the next analysis step.

[1263] The server analyzes the image

[1264] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[1265] Feedback Generation

[1266] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[1267] Sending and Viewing Feedback

[1268] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[1269] Track progress and generate study plans

[1270] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[1271] Specific examples

[1272] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is a bit awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. The user can see this feedback and instruct the child to practice writing "ri" again.

[1273] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to study together in a fun and effective way.

[1274] The processing flow will be explained below.

[1275] Step 1:

[1276] The device captures the user's image of the text. The user launches the device's camera app and takes a picture of the text written by the child. The device temporarily stores the captured image in memory.

[1277] Step 2:

[1278] The device sends the captured image to the server. The device converts the captured image into Base64 format and sends it to the server using an HTTP POST request. The image data is encrypted using a network connection.

[1279] Step 3:

[1280] The server receives the image. The server receives the HTTP request and obtains the transmitted image data. It decodes the image data and saves it as a file. The saved image is used for subsequent processing.

[1281] Step 4:

[1282] The server analyzes the image. It reads the saved image file and uses an AI model to detect character regions within the image. After the character regions are detected, it performs character recognition and evaluates the handwriting, shape, and stroke order. Image processing algorithms and deep learning technology are applied for character recognition.

[1283] Step 5:

[1284] The server generates feedback. Based on the analysis results, the server generates specific feedback to the user in text format. The feedback includes evaluations such as "Excellent!" or "Needs improvement."

[1285] Step 6:

[1286] The server returns the generated feedback to the device. The server encodes the feedback in text format and sends it to the device as an HTTP response. The feedback is saved in the user's past feedback history.

[1287] Step 7:

[1288] The device receives and displays the feedback. The device decodes the feedback received from the server and displays it in a format that is easy for the user to read. The user can check this feedback and use it to improve their next practice.

[1289] Step 8:

[1290] The server tracks the user's progress. The server records and analyzes the user's learning progress based on the user's feedback history. If necessary, it generates a personalized learning plan.

[1291] Step 9:

[1292] The server generates a personalized learning plan. The server takes into account the user's past feedback history and generates a learning plan that includes the optimal practice method and character practice order. This learning plan is provided as feedback the next time the user practices.

[1293] The above are the specific processing steps of the system based on the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[1294] Example 1

[1295] 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."

[1296] In conventional character practice systems, evaluation of a child's handwriting is subjective, making it difficult to obtain objective feedback. Furthermore, the feedback is temporary, making it difficult to obtain continuous learning benefits. Furthermore, feedback and learning plans tailored to individual learning progress are not provided, preventing efficient learning.

[1297] 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.

[1298] In this invention, the server includes an analysis means for analyzing the received image data and evaluating character identification, handwriting, shape, and stroke order; a feedback generation means for generating feedback based on the analysis results; and a return means for returning the generated feedback to the terminal. This allows the user to receive objective and specific feedback on the child's character practice. Furthermore, by providing a personalized learning plan based on past feedback history, continuous and individualized learning can be achieved.

[1299] "User" refers to a person who uses the system, specifically a parent or educator who supports children in practicing writing.

[1300] "Text image" refers to image data of text written by a child that is captured by the user using the device's camera.

[1301] "Photographing means" refers to the camera function built into the device, which the user uses to capture an image of the child's text.

[1302] "Transmission means" refers to the means for transmitting image data from a terminal to a server via the Internet. Specifically, an HTTP POST request is used.

[1303] The term "server device" refers to a combination of hardware and software for receiving, storing, and analyzing image data sent from a terminal.

[1304] "Analysis means" refers to the algorithms and AI models that analyze image data within the server device and evaluate character identification, handwriting, shape, and stroke order.

[1305] "Feedback generation means" refers to the means for generating feedback to be provided to users based on the analysis results, specifically using an AI model or a rule-based engine.

[1306] The "returning means" refers to a means for transmitting the generated feedback information from the server to the terminal. Specifically, an HTTP response is used.

[1307] The "display means" refers to a UI (user interface) for displaying the feedback information received by the terminal to the user.

[1308] The "text area" refers to the part of the text image where text is actually written, and is detected by the analysis means.

[1309] "Character recognition" refers to OCR (optical character recognition) processing performed on detected character areas.

[1310] "Study Plan" refers to a personalized learning menu created based on the user's past feedback history.

[1311] "Feedback History" refers to a record of feedback previously provided to a user, used to track progress and generate a study plan.

[1312] The present invention is a system that uses a user's terminal to capture an image of characters written by a child, analyzes the image on a server, and provides feedback. This system includes a terminal, a server, a camera means, a transmission means, an analysis means, a feedback generation means, a return means, and a display means.

[1313] User inputs image of text

[1314] The user uses the device's camera to capture an image of the characters written by the child. Specifically, the device's built-in camera is used. The image data captured by this camera is saved in the device's memory. When saving, the image resolution may be adjusted or compressed.

[1315] The device sends the image to the server

[1316] The device sends the captured image data to the server via an HTTP POST request over the Internet. The image data is encoded in Base64 format and encrypted using secure communication (e.g., TLS / SSL).

[1317] The server receives the image

[1318] The server receives the HTTP POST request and obtains the image data from the request body. The obtained data is decoded from Base64 format and saved in the server's storage with a file name that can be uniquely identified.

[1319] The server analyzes the image

[1320] The server loads the saved image files and starts the analysis process, using deep learning techniques (e.g., CNN models using TensorFlow or PyTorch) and image processing algorithms. The analysis process includes the following steps:

[1321] Character region detection (e.g., YOLO algorithm)

[1322] Identification of each character (OCR character recognition)

[1323] Evaluation of handwriting, shape, and stroke order (feature extraction)

[1324] Feedback Generation

[1325] The server generates feedback based on the analysis results. The generated feedback includes an evaluation of the character shape and handwriting, and the appropriateness of the stroke order. For example, specific comments such as "Excellent!" or "Needs improvement" are added. This feedback is saved in text format and is reflected in the user's past feedback history.

[1326] Sending and Viewing Feedback

[1327] The server then sends the generated feedback back to the device. It is serialized in JSON format and sent back as an HTTP response. The device then deserializes the received feedback and displays it to the user using a UI framework (e.g., React Native or Flutter).

[1328] Track progress and generate study plans

[1329] The server tracks the user's progress and generates a personalized learning plan based on past feedback. For example, if a specific character or stroke order needs continuous improvement, a practice menu will be generated accordingly. This learning plan is presented to the user upon login and periodically to support efficient learning.

[1330] Specific examples

[1331] For example, consider the case where a child writes the character "thank you" and the user captures it with the device's camera. At this time, the device sends the image data to the server, which analyzes the image data and recognizes the word "thank you." The handwriting, shape, and stroke order of each character are evaluated, and since the shape of "a" is correct but "ri" is somewhat distorted, feedback "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. Based on this feedback, the user can instruct the child to practice writing "ri" again.

[1332] Prompt Sentence Examples

[1333] A camera captures a child writing "thank you." Analyze the image to assess the correctness of each character's handwriting, shape, and stroke order, and provide feedback.

[1334] The above is an embodiment of the present invention. The user can receive objective and specific feedback on the child's character practice, enabling the child to progress in learning effectively.

[1335] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1336] Step 1:

[1337] The user uses the device's camera to capture an image of the child's writing. Specifically, the user opens the camera app, frames the appropriate part of the writing, and presses the shutter button. The captured image data is saved in the device's internal memory in an appropriate resolution, such as JPEG format. The input in this step is the child's writing, and the output is the captured image data.

[1338] Step 2:

[1339] The device uses its Internet connection to send the stored image data to the server. The image data is encoded in Base64 format and sent to the server as an HTTP POST request. Specifically, the following request is generated:

[1340] POST / upload HTTP / 1.1

[1341] Host: example.com

[1342] Content-Type: application / json

[1343] {

[1344] "imageData": "base64_encoded_image_data"

[1345] }

[1346] The input is the captured image data (a file in memory) and the output is an HTTP request to the server.

[1347] Step 3:

[1348] The server analyzes the received HTTP POST request and extracts the image data from the request body. Specifically, it decodes the Base64 format data and saves it as an image file. For example, the following process is performed:

[1349] decoded_image_data = base64.b64decode(request.json['imageData'])

[1350] with open("path / to / save / image.jpg", "wb") as f:

[1351] f.write(decoded_image_data)

[1352] The input is the HTTP request data, and the output is an image file in the server storage.

[1353] Step 4:

[1354] The server reads the saved image file and performs analysis. It uses a deep learning model (e.g., a CNN model using TensorFlow or PyTorch) to detect character regions, identify characters, and evaluate handwriting, shape, and stroke order. Specific processing examples are as follows:

[1355] image = load_image("path / to / save / image.jpg")

[1356] bounding_boxes = detect_text_regions(image)

[1357] for box in bounding_boxes:

[1358] character_image = crop_image(image, box)

[1359] recognized_character = recognizer_model.predict(character_image)

[1360] evaluate_characteristics(recognized_character)

[1361] The input is an image file stored in the server, and the output is the analysis results (character identification and characteristic evaluation).

[1362] Step 5:

[1363] The server generates feedback based on the analysis results. The feedback generation algorithm compiles the evaluation results of the handwriting and shape of each character and generates a comment to be provided to the user. For example, feedback such as "Excellent!" or "Needs improvement" is generated. The generated feedback is converted into text format and saved as follows:

[1364] feedback = {

[1365] "character": "ri",

[1366] "evaluation": "Needs improvement",

[1367] "comment": "The shape is out of order and needs to be rewritten."

[1368] }

[1369] The input is the analysis results and the output is the generated feedback data.

[1370] Step 6:

[1371] The server returns the generated feedback to the device by serializing the feedback data in JSON format and sending it to the device via an HTTP response. Specifically, the following response is returned:

[1372] HTTP / 1.1 200 OK

[1373] Content-Type: application / json

[1374] {

[1375] "feedback": {

[1376] "character": "ri",

[1377] "evaluation": "Needs improvement",

[1378] "comment": "The shape is out of order and needs to be rewritten."

[1379] }

[1380] }

[1381] The input is the generated feedback data, and the output is the HTTP response to the terminal.

[1382] Step 7:

[1383] The device deserializes the received feedback and displays it to the user, using a UI framework (e.g., React Native or Flutter) to display a message like this:

[1384] "Evaluation result: The shape of the 'ri' character is broken, so practice 'ri' again."

[1385] The input is the received feedback data and the output is the feedback message that is displayed to the user.

[1386] (Application example 1)

[1387] 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."

[1388] Conventional product quality inspection systems often require manual inspection or complex, specialized equipment, which can be inefficient and costly. Furthermore, detailed analysis, such as evaluating handwriting, shape, and stroke order, requires specialized knowledge, making it difficult to provide accurate feedback. Furthermore, generating a personalized learning plan based on feedback is not easy. To address these challenges, a more efficient and versatile system is needed.

[1389] 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.

[1390] In this invention, the server includes an analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, and a factory robot control means for inspecting the quality of the product. This improves the efficiency of product quality inspection, particularly enabling accurate confirmation of the marking of product lot numbers and quality control symbols. It also makes it possible to provide highly accurate feedback based on detailed analysis such as handwriting evaluation.

[1391] "Capture means" refers to a device or method for capturing an image of an object or scene, such as a digital camera or a smartphone camera.

[1392] A "transmission mechanism" is a system or protocol for sending data from one device to another, such as an HTTP POST request over the Internet.

[1393] A "server means" is a computer system that receives a request and executes a specific process. Examples include a web server and a database server.

[1394] "Analysis means" refers to a method or device that analyzes input data and extracts useful information. Examples of this include image processing algorithms and deep learning models.

[1395] The "feedback generation means" refers to a method or device for creating feedback to be provided to a user based on the analysis results. For example, this includes software that generates evaluation comments or recommendations.

[1396] A "return mechanism" is a system or protocol for returning the generated feedback to the sending device, such as an HTTP response from the server to the client.

[1397] "Display means" refers to a device or method for displaying the received feedback in a form that can be confirmed by the user. Examples include a monitor or a smartphone display.

[1398] "Factory robot control means" refers to a system that controls the robots used in factories and performs operations such as product quality inspections and line changes. Specifically, this refers to the software and hardware that controls the operation of the robot arm.

[1399] The present invention relates to a system for automating product quality inspections by factory robots and providing efficient feedback. The system includes an image capturing unit, a transmission unit, a server unit, an analysis unit, a feedback generating unit, a return unit, a display unit, and a factory robot control unit.

[1400] Recording method and image transmission

[1401] First, the factory robot uses its on-board camera to capture images of lot numbers and quality control symbols engraved on products. This camera has high resolution and can accurately capture even small markings. The captured image is then sent to a server via the Internet using a transmission method. To ensure security, the image data is converted to Base64 format and encrypted and sent via an HTTP POST request.

[1402] Image analysis on the server

[1403] The server receives the transmitted images and analyzes the image data using analytical methods, including the latest AI models and deep learning algorithms. This analysis process involves detecting character regions, recognizing characters, and evaluating handwriting and shape. Specifically, OpenCV is used for image processing, and character recognition is performed using a generative AI model such as TensorFlow.

[1404] Generate and return feedback

[1405] Based on the analysis results, the feedback generation means generates appropriate feedback. The feedback includes evaluations such as "Excellent!" or "Needs improvement," and if a defective product is detected, special instructions are generated. The generated feedback is then sent back to the terminal using the transmission means.

[1406] Feedback display and robot control

[1407] The terminal displays the received feedback using a display means. The user can check this feedback and understand the quality status of the product. The factory robot control means automatically controls the operation based on the feedback. If a defective product is detected, the robot is operated to send the product to another line.

[1408] Specific examples

[1409] For example, when checking the lot number "1234" engraved on a product manufactured in a factory, the system works as follows: First, the factory robot's camera captures an image of the product with the lot number "1234" engraved on it and sends the image to the server. The server analyzes the image, generates feedback, and returns a "Needs improvement" rating. The user confirms this feedback, and the robot automatically sends the product to another line.

[1410] Prompt Sentence Examples

[1411] Capture an image of the lot number "1234" stamped on the product, send it to the server, and get the analysis results. Based on the feedback, you can decide whether to send it to the defective line.

[1412] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1413] Step 1:

[1414] Image capture by device

[1415] The terminal uses a camera mounted on the factory robot to capture images of lot numbers and quality control symbols engraved on products. In this step, a high-resolution camera is used to accurately capture even the finest markings.

[1416] Input: Physical product

[1417] Output: High-resolution image of the product

[1418] Step 2:

[1419] Sending images

[1420] The device then sends the captured image to a server over the Internet, where it is converted to Base64 format and encrypted via an HTTP POST request to ensure secure communication.

[1421] Input: High-resolution image of product

[1422] Output: Encrypted image data in Base64 format

[1423] Step 3:

[1424] Image reception on the server

[1425] The server receives the transmitted image data, decodes it from Base64 format, and saves it as an image file, which allows subsequent analysis.

[1426] Input: Encrypted Base64 image data

[1427] Output: Decoded image file

[1428] Step 4:

[1429] Image analysis

[1430] The server analyzes the received image using an analysis method. In this step, image processing algorithms and generative AI models are used to detect character regions, recognize characters, and evaluate handwriting and shape. For example, character regions are extracted using OpenCV, and character recognition is performed using TensorFlow or similar.

[1431] Input: Decoded image file

[1432] Output: Character area coordinates and character recognition results

[1433] Step 5:

[1434] Feedback Generation

[1435] The server generates feedback based on the results of image analysis, including an assessment of the product's quality and whether it is defective. Specifically, the server generates assessments such as "Excellent!" or "Needs improvement."

[1436] Input: Character recognition result

[1437] Output: Feedback text

[1438] Step 6:

[1439] Sending feedback

[1440] The server sends the generated feedback to the device using a standard data format such as JSON.

[1441] Input: Feedback text

[1442] Output: Feedback data in JSON format

[1443] Step 7:

[1444] View Feedback

[1445] The device displays the received feedback for the user to review. The display is done on the device's screen or display. Based on this feedback, the user can judge the quality of the product.

[1446] Input: Feedback data in JSON format

[1447] Output: The displayed feedback text

[1448] Step 8:

[1449] Robot Control

[1450] Based on the feedback, the factory robot control system automatically controls its operation. If a defective product is detected, the robot will take action such as sending the product to another line.

[1451] Input: Feedback text

[1452] Output: Robot operation instructions (e.g., move to defective product line)

[1453] Through the above processing steps, a product quality inspection system using a factory robot is realized.

[1454] 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.

[1455] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[1456] User inputs image of text

[1457] The user uses the device's camera to capture an image of the child's writing, which the device stores in memory and then transmits to a server, where the image is captured at an appropriate resolution and may be compressed or optimized.

[1458] The device sends the image to the server

[1459] The device uses a transmission means via the Internet to send the captured image to the server. The image data is converted into a format such as Base64 and sent to the server using an HTTP POST request. The sent data is encrypted to ensure secure communication.

[1460] The server receives the image

[1461] The server receives the HTTP POST request and retrieves the image data. The retrieved image data is decoded and saved as a file. The saved image is used for subsequent processing.

[1462] The server analyzes the image

[1463] The server uses an AI model to analyze the stored image data. Specifically, it detects character regions, identifies characters, and evaluates handwriting, shape, and stroke order. Image processing algorithms and deep learning techniques are used to detect character regions. Character recognition is then performed on the detected character regions, and evaluation is performed based on the recognized characters.

[1464] Feedback Generation

[1465] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, the correctness of the stroke order, etc. Specifically, it generates feedback such as "Excellent!" or "Needs improvement." This feedback is saved in text format and is reflected in the user's past feedback history.

[1466] Emotion recognition by emotion engine

[1467] The server is equipped with an emotion engine that analyzes the emotion data (e.g., facial expression data, voice data) sent by the user. The emotion engine identifies the user's emotion and adjusts the content and tone of the feedback based on that emotion. For example, if the user is feeling discouraged, a message of encouragement and motivation will be generated.

[1468] Sending and Viewing Feedback

[1469] The server then sends the generated feedback back to the device, which then displays the received feedback for the user to review. Based on this feedback, the user can continue practicing their child's handwriting and identify areas for improvement.

[1470] Track progress and generate study plans

[1471] The server tracks the user's progress and generates a personalized learning plan based on past feedback, providing an efficient and personalized learning experience. For example, if a specific character or stroke order needs continuous improvement, a corresponding practice plan will be presented.

[1472] Specific examples

[1473] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to the server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, the shape of "a" is correct, but "ri" is somewhat awkward, so feedback such as "Needs improvement" is generated. This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion engine will generate an encouraging message such as "Good job! Just keep practicing and you'll improve your 'ri' in no time!". The user can see this feedback and encouraging message and instruct the child to practice writing "ri" again.

[1474] The above is an embodiment of the present invention. The present invention allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively.

[1475] The processing flow will be explained below.

[1476] Step 1:

[1477] The user uses the device's camera to capture an image of the child's writing. The device then activates the camera and captures the image of the writing. The device then saves the image at the appropriate resolution.

[1478] Step 2:

[1479] The device sends the captured image to the server. The image data is converted to Base64 format and sent to the server using an HTTP POST request. The data is encrypted to ensure security.

[1480] Step 3:

[1481] The server receives the HTTP POST request and retrieves the image data. The server decodes the Base64 data and saves it as an image file for further analysis.

[1482] Step 4:

[1483] The server reads the saved image file and uses the AI ​​model to detect text areas within the image, then performs character recognition on the detected text areas, using deep learning technology.

[1484] Step 5:

[1485] Based on the results of character recognition, the server evaluates the user's handwriting, shape, and stroke order, for example, determining whether the characters are written in the correct shape and stroke order.

[1486] Step 6:

[1487] The server generates feedback based on the analysis results. The feedback includes the quality of the handwriting and shape, and the correctness of the stroke order. Specific examples of feedback include "Excellent!" and "Needs improvement."

[1488] Step 7:

[1489] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes facial expression and voice data sent from the device to identify the user's emotions. The emotion data is used to adjust the feedback.

[1490] Step 8:

[1491] The server takes emotional data into account and adjusts the content and tone of the feedback, for example, if the user is feeling discouraged it might include an encouraging message like "Great effort! Keep it up!"

[1492] Step 9:

[1493] The server returns the generated feedback to the device. The feedback is sent to the device as an HTTP response. The feedback data is also encrypted before being sent.

[1494] Step 10:

[1495] The device decodes the received feedback and displays it to the user in a visually friendly format. The user can review the feedback and use it to improve their next practice.

[1496] Step 11:

[1497] The server tracks the user's progress and generates a personalized learning plan based on past feedback, suggesting the best practice method and order for practicing characters.

[1498] Step 12:

[1499] The device displays a personalized learning plan to the user, allowing the user to effectively practice writing with their child based on this plan.

[1500] The above are the specific processing steps for implementing the present invention. This system allows users to receive objective and specific feedback on their children's character practice, enabling parents and children to enjoy learning together effectively. Furthermore, by combining it with an emotion engine, flexible feedback is provided that responds to the user's emotions.

[1501] Example 2

[1502] 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."

[1503] Previous character learning systems were unable to objectively evaluate a child's handwriting and provide specific feedback. They also lacked an effective way to maintain user motivation, as they were unable to analyze the user's emotions and adjust the content and tone of the feedback. Furthermore, their ability to generate and provide individual learning plans to users was limited, making it difficult to provide an efficient and personalized learning experience.

[1504] 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.

[1505] In this invention, the server includes an image analysis means, a feedback generation means, and an emotion recognition means. This allows the server to analyze image data to evaluate the handwriting, shape, and stroke order of characters, and to analyze the user's emotions to adjust the tone of the feedback. It also tracks the user's progress and generates a personalized learning plan, providing an efficient and individualized learning experience.

[1506] "Image acquisition means" is a function that allows the terminal to capture a character image of the user.

[1507] The "data transmission means" is a function for transmitting the captured character image to the server.

[1508] The "receiving means" is a function that allows the server to receive a character image sent from a user.

[1509] The "image analysis means" is a function for analyzing received character images and evaluating the handwriting, shape, and stroke order.

[1510] The "feedback generation means" is a function for generating feedback to be provided to the user based on the results of image analysis.

[1511] The "data return means" is a function for returning the generated feedback to the terminal.

[1512] The "display means" is a function for displaying the feedback received by the terminal to the user.

[1513] The "emotion recognition means" is a function for analyzing the user's emotional data and adjusting the tone of the feedback.

[1514] The "study plan generator" is a function for tracking a user's progress and generating a personalized study plan based on past feedback history.

[1515] The present invention relates to a system that analyzes images of characters written by a child, recognizes the user's emotions, and provides feedback, and includes a terminal, a server, a transmission means, an analysis means, a feedback generation means, a display means, and an emotion engine.

[1516] Hardware and software used

[1517] The user uses a device as image acquisition means, such as a smartphone or tablet, to capture an image of the characters written by the child. The captured image is sent to a server via the Internet via the device's data transmission means. The server receives the image data using the data receiving means and then analyzes the image using the analysis means. Image processing algorithms and deep learning techniques are used for this analysis. Feedback is generated by the feedback generation means based on the analysis results, and the generated feedback is sent back to the device via the data return means. Furthermore, the emotion recognition means analyzes the user's emotion data and adjusts the tone of the feedback. A personalized learning plan based on the user's progress is generated by the study plan generation means.

[1518] A specific example is the following flow.

[1519] First, the user uses the device's camera to capture an image of the character "Thank you" written by the child. The image is temporarily saved on the device and then sent to the server using the data transmission means. Communication is performed using a secure protocol (e.g., SSL / TLS). The server receives the image using the receiving means, detects character regions using the analysis means, and evaluates the handwriting, shape, and stroke order of each character. For example, the server may use a deep learning model (e.g., YOLOv3) to detect character regions, and then use the Tesseract OCR engine to perform character recognition. Based on the analysis results, the feedback generation means generates feedback such as, "The character 'あ' is well-formed. 'り' needs improvement."

[1520] Next, the emotion recognition means analyzes the user's facial expression data, and if it is determined that the user is depressed, it generates feedback including an encouraging tone such as "Don't worry! You're doing great!" The generated feedback is returned to the terminal through the data return means and displayed to the user by the display means. Furthermore, the learning plan generation means generates a practice plan for writing the character "ri" based on the past feedback history and proposes it to the user.

[1521] Prompt Sentence Examples

[1522] "Please explain in detail the process flow of a system that analyzes images of children's handwriting captured by a camera and generates feedback using an AI model."

[1523] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1524] Step 1:

[1525] User inputs image of text

[1526] The user uses the device's camera to capture an image of the child's writing.

[1527] Specific behavior:

[1528] The user launches the camera app and takes a picture of the characters written by the child (for example, "aiueo").

[1529] Input: Child's writing

[1530] Output: Image file saved on device

[1531] Step 2:

[1532] The device sends the image to the server

[1533] The device uses a transmission means over the Internet to send the captured image to the server, where the image data is encoded in Base64 format and sent to the server using an HTTP POST request.

[1534] Specific behavior:

[1535] The terminal performs an encoding process and converts the image data into Base64 format.

[1536] Use an HTTP client library to create a POST request containing the encoded image data.

[1537] Input: Captured character image

[1538] Output: Encoded image data sent to the server

[1539] Step 3:

[1540] The server receives the image

[1541] The server receives the HTTP POST request, obtains the image data contained therein, decodes the image data, and saves it as a file.

[1542] Specific behavior:

[1543] The server decodes the encoded image data and returns it to the original JPEG image format.

[1544] Save the image to a file path such as " / uploads / unique_id.jpg".

[1545] Input: POST request with encoded image data

[1546] Output: Decoded JPEG image file

[1547] Step 4:

[1548] The server analyzes the image

[1549] The server uses AI models to analyze the stored image data, detecting character regions, identifying characters, and evaluating handwriting, shape, and stroke order.

[1550] Specific behavior:

[1551] Use a deep learning model (e.g., YOLOv3) to detect character regions in an image.

[1552] The detected character area is input to an OCR engine (e.g., Tesseract) for character recognition.

[1553] Input: Saved image file

[1554] Output: Analysis results of handwriting, shape, and stroke order of characters

[1555] Step 5:

[1556] Server generates feedback

[1557] The server generates feedback based on the analysis results, including the quality of the handwriting, shape, and the correctness of the stroke order.

[1558] Specific behavior:

[1559] Based on the analysis results, a feedback message is created. For example, a message such as "The character 'あ' is well-formed. 'り' needs improvement." is generated.

[1560] Input: Character analysis result

[1561] Output: Textual feedback message

[1562] Step 6:

[1563] Emotion recognition by emotion engine

[1564] The server is equipped with an emotion engine that analyzes the emotional data (facial expression data, voice data) sent by the user and adjusts the content and tone of the feedback.

[1565] Specific behavior:

[1566] The server analyzes facial expression and voice data to identify emotions.

[1567] Adjust the tone and message of your feedback based on the emotion, for example, "Don't worry! You're doing great!"

[1568] Input: User emotion data

[1569] Output: Adjusted feedback message

[1570] Step 7:

[1571] Server sends feedback

[1572] The server transmits the generated feedback back to the terminal, and the terminal displays the received feedback so that the user can confirm it.

[1573] Specific behavior:

[1574] The server generates an HTTP response including a feedback message and sends it to the terminal.

[1575] The terminal receives the response and displays a feedback message on the screen.

[1576] Input: Feedback message

[1577] Output: Feedback message displayed on the terminal

[1578] Step 8:

[1579] Track progress and generate study plans

[1580] The server tracks the user's progress and generates a personalized learning plan based on past feedback history.

[1581] Specific behavior:

[1582] The server consults a database of user feedback history and determines whether specific characters or stroke orders require ongoing improvement.

[1583] It generates and suggests to the user practice plans for characters that require continuous improvement.

[1584] Input: User feedback history data

[1585] Output: Personalized study plan

[1586] (Application example 2)

[1587] 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."

[1588] Modern educational settings require rapid and specific feedback on children's character practice. However, it is difficult for parents and teachers to provide appropriate guidance on the spot, and in many cases, children continue practicing on their own. Furthermore, to increase children's motivation to learn, encouragement and advice that takes into account their emotional state is necessary. However, recognizing emotions and generating feedback based on them requires advanced technology, which has been difficult to achieve with conventional systems.

[1589] 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 an optical sensor means for the terminal to capture a character image of the user, a data transmission means for transmitting the captured image to the server, a data receiving means for receiving the image, a data analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order, a feedback generation means for generating individual feedback based on the analysis results, a data return means for returning the feedback to the terminal, a display means for displaying the feedback, an emotion analysis means for analyzing the user's facial expressions and voice to recognize emotions, and a feedback adjustment means for adjusting the feedback content based on the emotions. This makes it possible to provide quick and specific feedback to a child's writing practice and to generate encouragement and advice according to the emotional state of the user (child or parent).

[1590] "Optical sensor means" refers to equipment and technology that uses light to capture images of objects.

[1591] "Data transmission means" refers to a function or method for transmitting acquired data to another device or system.

[1592] "Data receiving means" refers to equipment or technology that receives data sent from outside.

[1593] "Data analysis means" refers to algorithms or software that analyzes received data and evaluates the characteristics of the target object.

[1594] "Feedback generation means" refers to a system or technology that automatically generates feedback for subjects based on the results of data analysis.

[1595] The "data return means" is a function for returning the generated feedback to the original destination.

[1596] "Display means" refers to a device or technology that displays the received feedback in a form that can be confirmed by the user.

[1597] "Emotion analysis means" refers to technology or algorithms that analyze a user's facial expressions and voice data and identify their emotions.

[1598] "Feedback adjustment means" refers to a system or technology for adjusting the content of feedback based on the results of emotion analysis.

[1599] System Program

[1600] This invention is a system for providing feedback to children's writing practice, and uses the following means:

[1601] 1. Terminal hardware and software:

[1602] Optical sensor means: Uses the camera built into a smartphone or tablet to capture an image of the letters written by the child.

[1603] Data transmission means: A network communication function for transmitting captured images to a server. The image data is encoded in Base64 format or other appropriate format.

[1604] Data receiving means: A function for receiving feedback data returned from the server.

[1605] 2. Server-side hardware and software:

[1606] Data receiving means: A function that receives image data sent from a terminal. Protocols such as HTTP POST are used.

[1607] Data analysis method: An algorithm that analyzes received image data and evaluates character recognition, handwriting, shape, and stroke order. It uses AI models and image processing technology.

[1608] Feedback generator: An algorithm that generates personalized feedback based on the analysis results, including specific suggestions for improvement.

[1609] Emotion analysis means: Analyzes the user's facial expressions and voice data to recognize emotions. For example, facial expression recognition technology and voice analysis technology are used.

[1610] Feedback adjustment measures: Based on the results of sentiment analysis, the content of the feedback is adjusted, for example, by adding encouraging words or changing the tone to a gentler one.

[1611] 3. Display means: A function to display feedback on the device's display, including text and images.

[1612] Natural language explanation of the process

[1613] The device uses the camera built into the smartphone or tablet to capture an image of the characters written by the child. The captured image is then sent to a server via the Internet using a data transmission means. At this time, the image data is encoded in a compressed format such as Base64 format and sent using an HTTP POST request.

[1614] The server decodes the received image data and detects character regions within the image using a data analysis means. The server then uses a character recognition algorithm to identify characters within the detected character regions and evaluates their handwriting, shape, and stroke order. Based on the evaluation results, a feedback generation means generates individual feedback.

[1615] Next, the emotion analysis means analyzes the user's facial expression data and voice data to identify the user's emotions (e.g., joy, sadness, lack of motivation, etc.). The feedback adjustment means adjusts the feedback content based on the identified emotions. For example, if the user is feeling down, an encouraging message such as "Great progress! You'll get even better if you practice more!" is added.

[1616] Finally, the generated feedback is sent to the terminal using the data return means and visually displayed to the user through the display means, allowing the user to support the child's practice based on this feedback.

[1617] Examples of concrete examples and prompts

[1618] Examples:

[1619] For example, suppose a child writes the character "thank you" and captures it with the device's camera. The device sends the image to a server, which analyzes the image to recognize the word "thank you" and evaluates the handwriting, shape, and stroke order of each character. Based on the analysis results, feedback is generated, such as "the shape of the character "a" is accurate, but the character "ri" is a little awkward, so it's "inaccurate." This feedback is sent back to the device and displayed to the user. If the user is feeling depressed at this time, the emotion analysis engine generates an encouraging message such as "Great progress! You can do better next time!" The user can see this feedback and encouraging message and instruct the child to practice writing the character "ri" again.

[1620] Example prompt sentence:

[1621] 1. Take a picture of the letters your child has written with your camera.

[1622] 2. Send the captured image for analysis within the app.

[1623] 3. Emotional feedback for the child will also be displayed along with the analysis results.

[1624] example:

[1625] Photo taken: "Thank you.jpg"

[1626] Submitted response: "Feedback: The shape is accurate, but the stroke order needs improvement. Great progress! More practice will help you improve even more!"

[1627] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1628] Step 1:

[1629] The user uses the camera on their smartphone or tablet to capture an image of the letters written by the child. Specifically, the user launches the camera app, adjusts the exposure so that the letters are clearly visible, and presses the shutter. The input is the "letters written by the child," and the output is a "letter image file."

[1630] Step 2:

[1631] The terminal sends the captured text image to the server using a data transmission means. At this time, the image data is encoded in a format such as Base64, encrypted, and sent using an HTTP POST request. The input is a "text image file," and the output is "request data sent to the server."

[1632] Step 3:

[1633] The server receives the HTTP POST request and obtains the image data using the data receiving means. Specifically, the server decodes the Base64-encoded image data from the request and saves it as a file. The input is the "request data" and the output is the "decoded image file."

[1634] Step 4:

[1635] The server analyzes the stored image data using data analysis means. First, it uses an image processing algorithm to detect character regions, then performs character recognition using an AI model. It then evaluates the handwriting, shape, and stroke order. The input is the "decoded image file," and the output is the "character recognition and evaluation results."

[1636] Step 5:

[1637] The server generates feedback based on the analysis results using a feedback generation means. Specifically, it generates feedback in text format based on the evaluation results, including suggestions for improvement and encouraging messages. The input is "character recognition and evaluation results," and the output is "feedback text."

[1638] Step 6:

[1639] The server analyzes the user's facial expression data and voice data using emotion analysis means. The server uses an AI model to identify emotions from facial expressions and voice. The input is the user's facial expression data and voice data, and the output is the emotion identification result.

[1640] Step 7:

[1641] The server adjusts the feedback content using a feedback adjustment means based on the emotion analysis results. Specifically, it adds encouraging or advice messages to the feedback according to the emotion. The input is the "feedback text" and the "emotion identification result," and the output is the "adjusted feedback text."

[1642] Step 8:

[1643] The server sends the generated adjusted feedback to the terminal using the data return means, where the input is the "adjusted feedback text" and the output is the "feedback data to be sent to the terminal".

[1644] Step 9:

[1645] The terminal displays the received feedback using a display means. Specifically, the received feedback text is displayed on the screen so that the user can easily check it. The input is "feedback data" and the output is "feedback displayed on the terminal display."

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1651] 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.

[1652] 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).

[1653] 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.

[1654] 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."

[1655] 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.

[1656] 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).

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] The following is further disclosed regarding the above embodiment.

[1668] (Claim 1)

[1669] camera means for the terminal to capture a character image of the user;

[1670] a transmitting means for transmitting the captured image to a server;

[1671] server means for receiving said images;

[1672] analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order;

[1673] feedback generation means for generating individual feedback based on the analysis results;

[1674] a returning means for returning the feedback to the terminal;

[1675] display means for displaying said feedback;

[1676] A system including:

[1677] (Claim 2)

[1678] 2. The system according to claim 1, wherein the analyzing means includes means for detecting a character area from the character image and performing character recognition on the detected character area.

[1679] (Claim 3)

[1680] 2. The system of claim 1, wherein the feedback generating means includes means for generating a personalized study plan based on the user's past feedback history.

[1681] "Example 1"

[1682] (Claim 1)

[1683] a capturing means for a user to capture a character image;

[1684] a transmitting means for transmitting the captured image data to a server via the Internet;

[1685] a server device for receiving the transmitted image data;

[1686] analysis means for analyzing the received image data and evaluating character identification, handwriting, shape, and stroke order;

[1687] a feedback generating means for generating feedback based on the analysis result;

[1688] a returning means for returning the generated feedback to the terminal;

[1689] display means for displaying said feedback;

[1690] A system including:

[1691] (Claim 2)

[1692] 2. The system according to claim 1, wherein the analyzing means includes means for detecting a character area from the character image and performing character recognition on the detected character area.

[1693] (Claim 3)

[1694] 2. The system of claim 1, wherein the feedback generating means includes means for generating a personalized study plan based on the user's past feedback history.

[1695] "Application Example 1"

[1696] (Claim 1)

[1697] an image capturing means for the terminal to capture a character image of the user;

[1698] a transmitting means for transmitting the captured image to a server;

[1699] server means for receiving said images;

[1700] analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order;

[1701] feedback generation means for generating individual feedback based on the analysis results;

[1702] a returning means for returning the feedback to the terminal;

[1703] display means for displaying said feedback;

[1704] a factory robot control means for inspecting the quality of the product;

[1705] A system including:

[1706] (Claim 2)

[1707] 2. The system according to claim 1, wherein the analyzing means includes means for detecting a character area from the character image and performing character recognition on the detected character area.

[1708] (Claim 3)

[1709] 2. The system of claim 1, wherein the feedback generating means includes means for generating a personalized study plan based on the user's past feedback history.

[1710] "Example 2: Combining Emotion Engines"

[1711] (Claim 1)

[1712] image capture means for the terminal to capture a character image of the user;

[1713] data transmission means for transmitting the captured image to a server;

[1714] receiving means for receiving the image;

[1715] image analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order;

[1716] feedback generation means for generating individual feedback based on the analysis results;

[1717] data return means for returning the feedback to the terminal;

[1718] display means for displaying said feedback;

[1719] emotion recognition means for analyzing the user's emotion data and adjusting the tone of the feedback;

[1720] a learning plan generator for tracking a user's progress and generating a personalized learning plan;

[1721] A system including:

[1722] (Claim 2)

[1723] 2. The system according to claim 1, wherein the image analysis means includes means for detecting a character area from the character image and performing character recognition on the detected character area.

[1724] (Claim 3)

[1725] 2. The system of claim 1, wherein the feedback generating means includes means for generating a personalized study plan based on the user's past feedback history.

[1726] "Application example 2 when combining emotion engines"

[1727] (Claim 1)

[1728] an optical sensor means for the terminal to capture a character image of the user;

[1729] data transmission means for transmitting the captured image to a server;

[1730] data receiving means for receiving the image;

[1731] data analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order;

[1732] feedback generation means for generating individual feedback based on the analysis results;

[1733] data return means for returning the feedback to the terminal;

[1734] display means for displaying said feedback;

[1735] emotion analysis means for recognizing emotions by analyzing facial expressions and voice of a user;

[1736] a feedback adjusting means for adjusting the feedback content based on the emotion;

[1737] A system including:

[1738] (Claim 2)

[1739] 2. The system according to claim 1, wherein the data analysis means includes an algorithm for detecting a character region from the character image and performing character recognition on the detected character region.

[1740] (Claim 3)

[1741] 10. The system of claim 1, wherein the feedback generating means includes an algorithm that generates a personalized study plan based on the user's past feedback history. [Explanation of symbols]

[1742] 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. camera means for the terminal to capture a character image of the user; a transmitting means for transmitting the captured image to a server; server means for receiving said images; analysis means for analyzing the received image and evaluating the handwriting, shape, and stroke order; feedback generation means for generating individual feedback based on the analysis results; a returning means for returning the feedback to the terminal; display means for displaying said feedback; A system including:

2. 2. The system according to claim 1, wherein said analyzing means includes means for detecting a character area from said character image and performing character recognition on said detected character area.

3. 2. The system of claim 1, wherein the feedback generating means includes means for generating a personalized study plan based on the user's past feedback history.

Images