A mathematical element interactive control method

Abstract

This application discloses a method for interactive control of mathematical elements, allowing users to upload images. The system uses a CNN convolutional neural network and Face++ API to identify, classify, and count objects in the images, mapping the results to preset calculation areas in the form of mathematical elements. Users can learn by manipulating these mathematical elements. Furthermore, uploaded images can be segmented. A U-Net model is used to divide fruits and other shapes in uploaded images into multiple parts, which users can then piece together to form new shapes and name them. The color and shape of the new shapes are automatically generated based on the characteristics of the original segments. This feature not only enhances the fun and interactivity of mathematical learning but also helps users better understand mathematical concepts such as proportion and geometric combinations through hands-on practice. The app's design seamlessly connects mathematical learning with the real world, making the learning process more intuitive, engaging, and challenging.

Description

Technical Field

[0001] This invention relates to the field of online teaching technology, and in particular to a method for interactive control of mathematical elements. Background Technology

[0002] With the rapid development of mobile internet technology and the increasing penetration rate of smartphones, mobile applications have become an indispensable part of people's daily lives. Image recognition technology, as an important branch of artificial intelligence, has been widely used in mobile applications in recent years. Through image recognition technology, mobile applications can automatically analyze and process user-uploaded images, greatly enhancing user experience and application value.

[0003] However, while numerous mobile applications integrate image recognition capabilities, most remain at the level of simple object identification or classification, failing to deeply integrate the recognition results with specific application scenarios. Particularly in the education sector, how to effectively utilize image recognition technology to assist mathematics teaching and improve students' learning interest and efficiency remains a pressing issue.

[0004] On the other hand, mathematics teaching often involves the display and interaction of various mathematical elements. Traditional mobile applications often use static charts or text to display mathematical elements, lacking interactivity and fun, and failing to stimulate students' learning interest. Therefore, developing a mobile application that can dynamically display mathematical elements and allow users to interact with them is of great significance for improving the effectiveness of mathematics teaching. Summary of the Invention

[0005] This application addresses the aforementioned problems by providing a mathematical element interactive control method, offering a mobile application that combines image recognition technology with interactive display functions of mathematical elements. By integrating a convolutional neural network (CNN) and the Face++ image recognition API, this invention can automatically recognize, classify, and count user-uploaded images, dynamically displaying the recognition results as mathematical elements within a preset calculation area. Furthermore, this invention provides rich interactive functions, allowing users to select and move the displayed mathematical elements, segment uploaded graphics, and recombine them into user-preferred patterns, helping users better understand mathematical operations and thus enhancing the application's interactivity and engagement.

[0006] This application provides a method for interactive control of mathematical elements, including:

[0007] S101, Add an image upload button and a recognition result display area to the APP interface;

[0008] S102 integrates image recognition technology into the APP;

[0009] S103, When entering the interactive page, initialize the preset calculation area;

[0010] S104, perform meshing on the preset computational region;

[0011] S105, map the identified object types and quantities to a preset calculation area;

[0012] S106, detect input operations within the preset calculation area, select the target mathematical element based on the input, and display its coordinate position in real time;

[0013] S107, determine whether there is overlap based on the real-time coordinates of the first mathematical element and the second mathematical element;

[0014] S108, if there is regional overlap, the final result will be displayed in the recognition result display area.

[0015] Preferably, step S102 integrates image recognition technology into the APP, including:

[0016] We chose CNN (Convolutional Neural Network) as the image recognition technology and integrated the Face++ image recognition API.

[0017] Preferably, S102 includes:

[0018] S201 uses a graphic segmentation algorithm to divide the graphic in the uploaded image into multiple parts;

[0019] S202 integrates the image segmentation algorithm into the APP;

[0020] S203, Add a graphic segmentation button and a segmentation result display area to the APP;

[0021] S204 maps each segmented block to a mathematical element and allows users to perform mathematical operations on these elements.

[0022] Preferably, S201 includes:

[0023] We chose U-Net, a deep learning-based image segmentation algorithm;

[0024] U-Net uses a CNN (Convolutional Neural Network) to extract features and classify images;

[0025] Set the input image size to 512x512 pixels and train the U-Net model until the IoU (Intersection over Union) ratio reaches a segmentation accuracy of 0.8 or higher;

[0026] Based on user needs, different shapes or regions in the image are defined as different parts.

[0027] Preferably, S203 includes:

[0028] In the app's UI design, add a button to trigger graphic segmentation and create an area to display the segmentation results;

[0029] When a user clicks the segment button, the app calls the graphics segmentation module to process the data and displays the result in the specified area.

[0030] Preferably, S204 includes:

[0031] From uploading the image to completing the image segmentation, the segmentation process must be completed within 2 seconds.

[0032] Preferably, S204 further includes:

[0033] Contour extraction and shape recognition are performed on each segmented part;

[0034] Each segment after division can be regarded as a different mathematical element, and the number of segments can be directly used for addition and subtraction operations.

[0035] Preferably, S204 further includes:

[0036] S301, splice together different fruit segments and process the characteristics of the spliced ​​fruit;

[0037] S302, add a naming input box to the APP to allow users to enter a custom name for new combinations of fruits;

[0038] S303, calculate the average value of the RGB parameters of two or more fruit colors as the color of the new combination of fruits;

[0039] S304, Based on the proportion of each fruit segment to the original fruit and the shape characteristics of the original fruit, generate the shape of the new combined fruit.

[0040] Preferably, S303 includes:

[0041] Extract the RGB color parameters of each fruit segment;

[0042] The RGB color model is described here, where R represents red, G represents green, and B represents blue, with each color value ranging from 0 to 255.

[0043] Calculate the average value of the RGB parameters for the colors of two or more fruits.

[0044] Preferably, S304 includes:

[0045] Calculate the proportion of each type of fruit slice relative to the original fruit;

[0046] Extract the shape characteristics of the original fruit;

[0047] Based on the proportion of each fruit segment and the shape characteristics of the original fruit, generate the shape of the new combined fruit.

[0048] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0049] 1. By adding an image upload button, users can easily upload real-life images to the app, seamlessly connecting math learning with the real world. This feature makes math learning more practical and improves the software's usability. After users upload images, the app can immediately recognize them and display the results; this timely feedback mechanism greatly enhances the software's interactivity. Users can adjust their learning content based on the recognition results in real time, achieving a more personalized learning experience.

[0050] 2. Utilizing Convolutional Neural Networks (CNNs) and the Face++ image recognition API, the app can accurately identify, classify, and count objects in images. This advanced technology makes math learning more fun and challenging, capturing users' attention. The identified object types and quantities are mapped to preset calculation areas and presented to the user as mathematical elements. This innovative presentation method makes math learning no longer tedious but full of fun and exploration.

[0051] 3. This solution employs the U-Net deep learning-based image segmentation algorithm, utilizing a convolutional neural network (CNN) for feature extraction and classification, achieving efficient and accurate image segmentation. The input image size is set to 512x512 pixels, and the U-Net model is trained to achieve an IoU (Intersection over Union) ratio of over 0.8 to ensure the accuracy of the segmentation results. Simultaneously, the uploaded images undergo preprocessing such as resizing and normalization to adapt to the model's input requirements, further improving segmentation accuracy. This key technical feature enables the entire process from image upload to segmentation completion to be completed within 2 seconds, significantly improving segmentation efficiency and providing users with a fast and accurate segmentation experience.

[0052] 4. The app's UI design includes buttons to trigger graphic segmentation and areas to display the results. Users can easily segment graphics and view the results with simple clicks. Simultaneously, each segmented part undergoes contour extraction and shape recognition, mapping it to different mathematical elements, allowing users to perform mathematical operations on these elements. By allowing users to drag segmented graphic pieces to preset calculation areas and complete calculations by piecing them together, this technical feature not only enhances user engagement but also makes the learning process more intuitive and engaging, helping users better understand and master mathematical knowledge.

[0053] 5. Precise stitching and feature processing of fruit segments greatly enhance user experience and visual effects. By using the U-Net model to precisely segment uploaded images, users can easily obtain segments of different fruits. On the app interface, users can freely combine these segments into new fruit shapes by dragging or clicking. After stitching, the app automatically smooths the edges and applies color transitions to the newly combined fruit, ensuring that the stitched fruit looks natural, aesthetically pleasing, and without obvious stitching marks. This precise stitching and feature processing technology not only meets users' personalized needs for innovative fruit shapes but also enhances the visual appeal of the newly combined fruit, providing users with a better experience during operation.

[0054] 6. The custom naming and color / shape generation features for new fruit combinations further enhance user engagement and creativity. After assembling the fruit, users can enter a custom name for the new combination using the naming input box on the app interface. This name will be saved by the app and associated with the image data of the new combination, facilitating later retrieval or recall. Simultaneously, the app will generate the shape of the new combination based on the proportion of each fruit segment to the original fruit and the shape characteristics of the original fruit. This custom naming and shape generation feature allows users to create unique fruit images, fully satisfying their creative and personalized needs. Furthermore, the app will calculate the average RGB parameters of two or more fruit colors as the color of the new combination. This color fusion technology ensures that the new combination retains the characteristics of the original fruit colors while also possessing a degree of innovation, further enhancing the user's visual experience. Attached Figure Description

[0055] Figure 1 This is a flowchart illustrating a mathematical element interaction control method according to an embodiment of the present invention. Detailed Implementation

[0056] To facilitate understanding of the present invention, a more complete description of this application will be given below with reference to the accompanying drawings, which illustrate preferred embodiments of the invention. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to enable a more thorough and complete understanding of the disclosure of the present invention.

[0057] It should be noted that the terms "vertical," "horizontal," "up," "down," "left," "right," and similar expressions used in this article are for illustrative purposes only and do not represent the only possible implementation.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention; the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0059] Figure 1 This is a flowchart illustrating a mathematical element interaction control method according to an embodiment of the present invention.

[0060] like Figure 1 As shown, a method for interactive control of mathematical elements includes the following steps:

[0061] S101, add an image upload button and a recognition result display area to the APP interface.

[0062] S102 integrates image recognition technology into the APP, enabling image uploading, recognition, classification, and counting functions through API interfaces.

[0063] Specifically, Convolutional Neural Networks (CNNs) were chosen as the image recognition technique, and the Face++ image recognition API was integrated. CNNs can automatically and accurately extract image features from raw pixels, and through training, CNNs can learn to recognize specific objects.

[0064] Within the app, users can upload images by clicking a button or selecting a file. Uploading an image sends a request to the API via an HTTP POST request. Once the API receives the image, it returns a confirmation response indicating successful reception. After receiving the image, the API processes it using a CNN image recognition algorithm. The recognition process includes feature extraction, object detection, and classification. After recognition, the API returns a response containing the recognition results, typically in JSON or other structured data formats. Based on the recognition results, the API can classify the objects in the image. Classification can be based on predefined categories, such as animals, plants, and buildings, or it can be a custom category. The classification result is returned to the app along with the recognition result. If the image contains multiple identical objects, the API can also count them. This counting function is typically based on the object detection and classification results of the recognition algorithm. The counting result is also returned to the app in structured data format.

[0065] S103, When entering the interactive page, initialize the preset calculation area.

[0066] Specifically, when a page containing a preset calculation area is opened, the area is immediately initialized, and all mathematical elements in the current area are cleared.

[0067] S104, perform meshing on the preset computational region.

[0068] Specifically, before or after displaying mathematical elements (depending on specific needs), the preset calculation area is divided into multiple rectangular grids using alternating horizontal and vertical grid lines.

[0069] S105, map the identified object types and quantities to a preset calculation area.

[0070] Specifically, based on the image recognition results, the corresponding mathematical elements are displayed within a preset calculation area.

[0071] S106, detect input operations within the preset calculation area, select the target mathematical element based on the input, and display its coordinate position in real time.

[0072] The target mathematical element is either the first mathematical element or the second mathematical element. Both the first and second mathematical elements can be numerical or graphical representations.

[0073] S107, determine whether there is overlap based on the real-time coordinates of the first mathematical element and the second mathematical element.

[0074] S108, if there is regional overlap, the final result will be displayed in the recognition result display area.

[0075] Specifically, if overlapping areas occur, the numerical and graphical information from the first and second overlapping mathematical elements are retrieved, and these two mathematical elements are converted into a graphical folder at the overlapping area. This graphical folder contains the same number of icons as the numerical information and the same graphics as the graphical information.

[0076] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages:

[0077] 1. By adding an image upload button, users can easily upload real-life images to the app, seamlessly connecting math learning with the real world. This feature makes math learning more practical and improves the software's usability. After users upload images, the app can immediately recognize them and display the results; this timely feedback mechanism greatly enhances the software's interactivity. Users can adjust their learning content based on the recognition results in real time, achieving a more personalized learning experience.

[0078] 2. Utilizing Convolutional Neural Networks (CNNs) and the Face++ image recognition API, the app can accurately identify, classify, and count objects in images. This advanced technology makes math learning more fun and challenging, capturing users' attention. The identified object types and quantities are mapped to preset calculation areas and presented to the user as mathematical elements. This innovative presentation method makes math learning no longer tedious but full of fun and exploration.

[0079] Example 2: Following Example 1, by adding an image upload button and utilizing Convolutional Neural Networks (CNN) and the Face++ image recognition API, the app can accurately identify, classify, and count objects in images, making math learning more interesting and challenging. To further enhance the intuitiveness and ease of understanding of abstract mathematical concepts, Example 1 is further improved by adding an image segmentation function, such as dividing an apple into multiple pieces, to assist users in understanding and interacting with addition and subtraction operations. The improvement is based on step S102 of Example 1, specifically as follows:

[0080] S201 uses a graphic segmentation algorithm to divide the graphic in the uploaded image into multiple parts.

[0081] Specifically, the U-Net deep learning-based image segmentation algorithm was chosen. U-Net uses a convolutional neural network (CNN) to extract features and classify images. The input image size was set to 512x512 pixels, and the U-Net model was trained until the IoU (Intersection over Union) ratio reached a segmentation accuracy of 0.8 or higher. Different shapes or regions in the image were defined as different parts according to user needs.

[0082] For example, in an image containing multiple geometric shapes, each shape is treated as an independent part. After preprocessing the uploaded image, such as resizing and normalizing, the preprocessed image is input into the U-Net model for segmentation. The model outputs a segmentation mask with the same size as the input image, where the value of each pixel corresponds to its respective part. Based on the segmentation mask, the original image is segmented into multiple parts.

[0083] S202 integrates the image segmentation algorithm into the APP.

[0084] S203, add a graphic segmentation button and a segmentation result display area to the APP.

[0085] Specifically, in the app's UI design, add a button to trigger image segmentation and create an area (which can be an image view or a canvas) to display the segmentation results. When the user clicks the segmentation button, the app calls the image segmentation module to process the data and displays the results in the designated area.

[0086] S204 maps each segmented block to a mathematical element and allows users to perform mathematical operations on these elements.

[0087] Specifically, contour extraction and shape recognition are performed on each part of the segmented image. Each segmented block can be considered a different mathematical element, and the number of segments can be directly used for addition and subtraction operations. For example, an apple can be divided into 3 pieces and 2 pieces, and then addition can be performed to obtain the total.

[0088] It should be noted that in the contour extraction and shape recognition of each part of the segmented image, the OpenCV functions cv::findContours() are used to extract the contour, cv::contourArea() are used to calculate the area of ​​the contour, and cv::arcLength() are used to calculate the perimeter of the contour. The above functions are existing technologies and will not be elaborated on in this article.

[0089] The process of segmenting an uploaded image must be completed within 2 seconds, from uploading the image to its segmentation. For the selected images to be segmented, those with a complete outline and shape are preferred.

[0090] For example, upload an image containing an apple, an orange, and a watermelon. The app automatically preprocesses the image and uses the U-Net model for segmentation. The segmentation result display area shows three independent shapes: apple, orange, and watermelon, each segmented into smaller shapes—apple into 3 segments, orange into 2 segments, and watermelon into 5 segments. Drag the segments to the preset calculation area to assemble them into a complete shape, and the final calculated number will be displayed in the result display area. For example, dragging the three apple segments sequentially to the preset calculation area will display the number 3 in the result display area.

[0091] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages:

[0092] 1. This solution employs the U-Net deep learning-based image segmentation algorithm, utilizing a convolutional neural network (CNN) for feature extraction and classification, achieving efficient and accurate image segmentation. The input image size is set to 512x512 pixels, and the U-Net model is trained to achieve an IoU (Intersection over Union) ratio of over 0.8 to ensure the accuracy of the segmentation results. Simultaneously, the uploaded images undergo preprocessing such as resizing and normalization to adapt to the model's input requirements, further improving segmentation accuracy. This key technical feature enables the entire process from image upload to segmentation completion to be completed within 2 seconds, significantly improving segmentation efficiency and providing users with a fast and accurate segmentation experience.

[0093] 2. The app's UI design includes buttons to trigger graphic segmentation and areas to display the segmentation results. Users can easily segment graphics and view the results with simple clicks. Simultaneously, each segmented part undergoes contour extraction and shape recognition, mapping it to different mathematical elements, allowing users to perform mathematical operations on these elements. By allowing users to drag segmented graphic pieces to preset calculation areas and complete calculations by piecing together the graphics, this technical feature not only enhances user engagement but also makes the learning process more intuitive and engaging, helping users better understand and master mathematical knowledge.

[0094] Example 3: Example 2 above adds a graphic segmentation function, such as dividing an apple into multiple pieces, to aid in understanding and interaction of addition and subtraction operations. To enhance understanding of mathematical operations, proportions, and graphic combinations, a function for piecing together and naming segmented fruits can be added. Users can combine different types of fruit pieces to form new "fruits" and output their color, shape, and other characteristics, further improving the interactivity and fun of the math teaching software, enabling users to understand mathematical concepts such as proportions and graphic combinations through practical operation. Further improvements are made based on step S204 of Example 2, specifically:

[0095] S301, splice together different fruit segments and process the characteristics of the spliced ​​fruit.

[0096] Specifically, firstly, the uploaded image is segmented using the previously mentioned U-Net model to obtain segments of different fruits; then, users can select the fruit segments they want to stitch together on the app interface, and combine these segments into a new fruit shape by dragging or clicking; finally, after stitching is completed, the app will perform feature processing on the newly combined fruit, which may include edge smoothing, color transition, etc., to ensure that the stitched fruit looks natural and beautiful.

[0097] S302 adds a naming input box to the app, allowing users to enter custom names for new combinations of fruits.

[0098] Specifically, the UI design of the app should include a naming input box, which is usually located below or next to the display area of ​​the new combination of fruits. Users can enter a custom name for the new combination of fruits using the keyboard or handwriting input. The name entered by the user will be saved by the app and associated with the image or data of the new combination of fruits so that users can later retrieve or call the new combination of fruits by name.

[0099] S303 calculates the average value of the RGB parameters of two or more fruit colors to determine the color of the new combination of fruits.

[0100] Specifically, first, the RGB color parameters of each fruit segment are extracted. RGB is a color model where R represents red, G represents green, and B represents blue, with each color value ranging from 0 to 255. Then, the average of the RGB parameters of two or more fruit colors is calculated. Assuming there are two fruits, A and B, with RGB parameters (Ra, Ga, Ba) and (Rb, Gb, Bb) respectively, the RGB parameters of the new combined fruit can be calculated using the following formulas: R_new = (Ra + Rb) / 2, G_new = (Ga + Gb) / 2, B_new = (Ba + Bb) / 2. Here, Ra, Ga, Ba, etc., represent the RGB parameter values ​​of fruit A, Rb, Gb, Bb, etc., represent the RGB parameter values ​​of fruit B, and R_new, G_new, B_new represent the RGB parameter values ​​of the new combined fruit. RGB parameters are the specific numerical values ​​of the colors and are the basis for calculating the color of the new combined fruit. By calculating the average, the colors of two or more fruits can be blended together to obtain a new color. This color retains the characteristics of the original fruit color while also being innovative.

[0101] S304, Based on the proportion of each fruit segment to the original fruit and the shape characteristics of the original fruit, generate the shape of the new combined fruit.

[0102] Specifically, the process begins by calculating the proportion of each fruit segment relative to the original fruit, followed by extracting the shape features of the original fruit. Finally, based on the proportion of each fruit segment and the shape features of the original fruit, the shape of the new combined fruit is generated.

[0103] For example, the app first uses its upload function to upload images of apples, bananas, and oranges to the system. The app then uses the U-Net model to accurately segment these three images, obtaining segmented blocks for apples, bananas, and oranges.

[0104] On the app's interface, users can combine the top half of an apple, the middle half of a banana, and the bottom half of an orange by dragging and clicking to create a new fruit shape.

[0105] The app automatically smooths the edges and color transitions of the newly combined fruits, ensuring the finished product looks natural and aesthetically pleasing. Once completed, a naming input box appears below the display area of ​​the new fruit combination. The user enters "Fruit World Heroes" as the name for this combination, which the app saves and associates with the image data of the new fruit combination.

[0106] The app extracted the RGB color parameters of apples, bananas, and oranges from the segmented blocks (assuming the RGB parameters of apples are (255,0,0), bananas are (255,255,0), and oranges are (255,128,0)). It then calculated the RGB parameters of the new combination of fruits according to the formula (R_new=(255+255+255) / 3≈255, G_new=(0+255+128) / 3≈128, B_new=(0+0+0) / 3=0).

[0107] Therefore, the color of the new fruit combination "Fruit Heroes" is (255, 128, 0), which is a new color between red, yellow, and orange. The app also calculated the proportion of each fruit segment relative to the original fruit (30% for the upper half of the apple, 40% for the middle half of the banana, and 30% for the lower half of the orange) and extracted the shape features of the original fruit (such as the roundness of the apple, the curvature of the banana, and the spherical shape of the orange).

[0108] Finally, based on these proportions and shape characteristics, the app generated a new combination of fruits called "Fruit Heroes": the upper part is the circle of an apple, the middle part is the curve of a banana, and the lower part is the sphere of an orange, but the overall shape looks more harmonious and unified.

[0109] By adding the functions of assembling and naming fruit pieces, the interactivity and fun of the math teaching software have been further improved, enabling users to understand mathematical concepts such as proportion and graphic combination through practical operation.

[0110] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages:

[0111] 1. Precise stitching and feature processing of fruit segments greatly enhance user experience and visual effects. By using the U-Net model to accurately segment uploaded images, users can easily obtain segments of different fruits. On the app interface, users can freely combine these segments into new fruit shapes by dragging or clicking. After stitching, the app automatically smooths the edges and applies color transitions to the newly combined fruit, ensuring that the stitched fruit looks natural, aesthetically pleasing, and without obvious stitching marks. This precise stitching and feature processing technology not only meets users' personalized needs for innovative fruit shapes but also enhances the visual appeal of the newly combined fruit, providing users with a better experience during operation.

[0112] 2. The custom naming and color / shape generation features for new fruit combinations further enhance user engagement and creativity. After assembling the fruit, users can enter a custom name for the new combination using the naming input box on the app interface. This name will be saved by the app and associated with the image data of the new combination, facilitating later retrieval or recall. Simultaneously, the app will generate the shape of the new combination based on the proportion of each fruit segment to the original fruit and the shape characteristics of the original fruit. This custom naming and shape generation feature allows users to create unique fruit images, fully satisfying their creative and personalized needs. Furthermore, the app will calculate the average RGB parameters of two or more fruit colors as the color of the new combination. This color fusion technology ensures that the new combination retains the characteristics of the original fruit colors while also possessing a degree of innovation, further enhancing the user's visual experience.

[0113] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for interactive control of mathematical elements, characterized in that, include: S101, Add an image upload button and a recognition result display area to the APP interface; S102, integrate image recognition technology into the APP; specifically, select CNN convolutional neural network as the image recognition technology and integrate Face++ image recognition API; adopt the U-Net deep learning-based image segmentation algorithm to segment the image on the uploaded image into multiple parts, and integrate the image segmentation algorithm into the APP; add an image segmentation button and a segmentation result display area to the APP; map each segmented block to a mathematical element and allow users to perform mathematical operations on these elements; stitch together different fruit segmented blocks and process the features of the stitched fruit; add a naming input box to the APP so that users can... Enter a custom name for the new fruit combination; calculate the average RGB parameters of various fruit colors and use this as the color of the new fruit combination; calculate the proportion of each fruit segment to the original fruit, extract the shape features of the original fruit, and then generate the shape of the new fruit combination based on the proportion of each fruit segment to the original fruit and the shape features of the original fruit; add a naming input box to the APP's UI design, which is set below or next to the display area of ​​the new fruit combination; users can enter a custom name for the new fruit combination using different input methods; the APP saves the user-inputted name and associates it with the image or data of the new fruit combination. S103, When entering the interactive page, initialize the preset calculation area; S104, perform meshing on the preset computational region; S105, map the identified object types and quantities to a preset calculation area; S106, detect input operations within the preset calculation area, select the target mathematical element based on the input, and display its coordinate position in real time; S107, determine whether there is overlap based on the real-time coordinates of the first mathematical element and the second mathematical element; S108, if there is regional overlap, the final result will be displayed in the recognition result display area.

2. The mathematical element interaction control method as described in claim 1, characterized in that, The image segmentation algorithm U-Net, based on deep learning, is used to segment the image in the uploaded image into multiple parts, including: The image segmentation algorithm U-Net, based on deep learning, is used, while CNN convolutional neural networks are used for image feature extraction and classification. Set the input image size to 512x512 pixels and train the U-Net model until the IoU (Intersection over Union) ratio reaches a segmentation accuracy of 0.8 or higher; Based on user needs, different shapes or regions in the image are defined as different parts.

3. The mathematical element interaction control method as described in claim 1, characterized in that, The addition of a graphic segmentation button and a segmentation result display area to the APP includes: In the app's UI design, add a button to trigger graphic segmentation and create an area to display the segmentation results; When a user clicks the segment button, the app calls the graphics segmentation module to process the data and displays the result in the specified area.

4. The mathematical element interaction control method as described in claim 1, characterized in that, The process of mapping each segmented block to a mathematical element includes: From uploading the image to completing the image segmentation, the segmentation process must be completed within 2 seconds.

5. The mathematical element interaction control method as described in claim 1, characterized in that, Also includes: Contour extraction and shape recognition are performed on each segmented part; Each segment after division is regarded as a different mathematical element, and the number of segments is directly used for addition and subtraction operations.

6. The mathematical element interaction control method as described in claim 1, characterized in that, The calculation of the average RGB parameters of multiple fruit colors as the color of the new combination of fruits includes: Extract the RGB color parameters of each fruit segment; The RGB color model is described here, where R represents red, G represents green, and B represents blue, with each color value ranging from 0 to 255. Calculate the average value of the RGB parameters for the colors of various fruits.

Images