Recycling and sharing method, system and equipment of garbage recycling and sharing equipment and medium

Abstract

The invention relates to the technical field of recycling and sharing, and discloses a recycling and sharing method, system, equipment and medium for garbage recycling and sharing equipment, and the method comprises the steps: collecting a garbage throwing comparison image and gravity sensing data, and extracting the brightness signal-to-noise ratio feature of the garbage throwing comparison image; performing brightness contrast enhancement on the garbage throwing contrast image according to the brightness signal-to-noise ratio feature to obtain an enhanced contrast image; identifying a garbage target area in the enhanced comparison image, and identifying a garbage throwing category according to the garbage target area; and garbage recycling data and shared recycling income are calculated according to the garbage throwing type and the gravity sensing data. Through the implementation of the invention, the image definition of the garbage throwing comparison image can be improved, the details are clearer, the interference of the existing garbage on the garbage throwing category can be eliminated through the garbage target area, and the garbage throwing category can be identified more accurately, so that the utilization rate and the accuracy of garbage recycling equipment are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of recycling and sharing technology, and in particular to a recycling and sharing method, system, equipment and medium for waste recycling and sharing equipment. Background Technology

[0002] As people's awareness of environmental protection and resource recycling continues to increase, their acceptance and willingness to use shared waste recycling equipment are also growing. More and more people are willing to actively participate in waste sorting and resource recycling, providing a good social foundation for the promotion and application of shared waste recycling equipment. For example, with the continuous expansion of the sharing economy model, the innovative application of shared trash cans is gradually being integrated into daily life. By introducing the sharing model into the field of waste sorting, shared trash cans achieve efficient sorting and resource utilization of waste through intelligent waste sorting technology.

[0003] While existing shared recycling equipment has made some progress, its accuracy in identifying certain types of waste remains poor, especially in complex environments or when dealing with specific types. For example, it may be unable to accurately classify mixed-package, irregularly shaped, or stained waste, thus affecting the efficiency and accuracy of waste sorting and recycling by the shared recycling equipment.

[0004] In summary, improving the efficiency and accuracy of shared recycling equipment for shared waste collection has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a recycling and sharing method, system, equipment, and medium for waste recycling and sharing equipment, the main purpose of which is to solve the problems of poor efficiency and accuracy of shared waste recycling.

[0006] To achieve the above objectives, the present invention provides a recycling sharing method for a waste recycling sharing device, comprising: acquiring a user recycling request received by the waste recycling device; collecting a waste disposal comparison image and gravity sensing data according to the user recycling request, and extracting the brightness signal-to-noise ratio (BNR) features of the waste disposal comparison image; enhancing the brightness contrast of the waste disposal comparison image according to the BNR features to obtain an enhanced comparison image; identifying the waste target area in the enhanced comparison image, and identifying the waste disposal category corresponding to the waste disposal comparison image according to the waste target area; and calculating waste recycling data and shared recycling revenue according to the waste disposal category and gravity sensing data.

[0007] This invention also provides a recycling sharing system for a shared waste recycling device. The system includes: a data acquisition module for acquiring user recycling requests received by the waste recycling device, acquiring waste disposal comparison images and gravity sensing data based on the user recycling requests, and extracting the brightness signal-to-noise ratio features of the waste disposal comparison images; a brightness contrast enhancement module for enhancing the brightness contrast of the waste disposal comparison images based on the brightness signal-to-noise ratio features to obtain an enhanced comparison image; a waste disposal category identification module for identifying target waste areas in the enhanced comparison images and identifying the corresponding waste disposal category based on the target waste areas; and a recycling revenue calculation module for calculating waste recycling data and shared recycling revenue based on the waste disposal category and gravity sensing data.

[0008] The present invention also provides an electronic device, comprising: a memory communicatively connected to at least one processor; wherein the processor is configured to execute a computer program stored in the memory; the memory stores a computer program executable by at least one processor, the computer program being executed by at least one processor to enable at least one processor to execute the above-described recycling and sharing method of a waste recycling and sharing device.

[0009] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the recycling and sharing method of the waste recycling and sharing device described above.

[0010] This invention, by extracting the brightness signal-to-noise ratio (BNR) features from waste disposal comparison images, simultaneously considers the brightness and texture structure information within the image details. This improves image clarity and enables more accurate waste disposal category identification. By enhancing the brightness contrast of the comparison images based on the BNR features, an enhanced comparison image is obtained, making details clearer and more accurately identifying the specific type and state of waste. Identifying the target waste region in the enhanced comparison image eliminates interference from existing waste, further refining waste disposal category identification. Furthermore, by calculating waste recycling data and shared recycling revenue based on waste disposal category and gravity sensor data, the shared recycling status of each waste recycling device can be analyzed, allowing for planned adjustments to the waste recycling device layout and effectively improving the utilization rate and rationality of the waste recycling equipment. Therefore, the waste recycling sharing method, system, equipment, and medium proposed in this invention can solve the problem of poor efficiency and accuracy in shared waste recycling using existing waste recycling equipment. Attached Figure Description

[0011] Figure 1 This is a schematic flowchart of a waste recycling and sharing method provided by an embodiment of the present invention;

[0012] Figure 2 This is a schematic diagram illustrating the process of enhancing the brightness contrast of a waste disposal comparison image according to an embodiment of the present invention;

[0013] Figure 3 This is a schematic diagram of a process for identifying garbage target regions in an enhanced contrast image according to an embodiment of the present invention;

[0014] Figure 4 This is a functional block diagram of a waste recycling sharing system provided in an embodiment of the present invention;

[0015] Figure 5 This is a schematic diagram of the structure of an electronic device for implementing a recycling and sharing method for waste recycling sharing equipment, as provided in an embodiment of the present invention.

[0016] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] This application provides a recycling and sharing method for a waste recycling sharing device. The executing entity of this recycling and sharing method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the recycling and sharing method can be executed by software or hardware installed on a terminal device or a server device; the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0019] Reference Figure 1 The diagram shown is a flowchart illustrating a recycling and sharing method for a waste recycling sharing device according to an embodiment of the present invention. In this embodiment, the recycling and sharing method for the waste recycling sharing device includes:

[0020] S1. Obtain the user recycling request received by the waste recycling equipment, collect waste disposal comparison images and gravity sensor data according to the user recycling request, and extract the brightness signal-to-noise ratio features of the waste disposal comparison images.

[0021] In this embodiment of the invention, the waste recycling equipment is a type of equipment in which residents or users put recyclable waste into the equipment, and the equipment operator returns a portion of the revenue to the user in the form of cash, points, or other forms after recycling and processing the waste. Specifically, after users put in recyclables, they receive corresponding revenue according to a preset recycling price. For example, putting plastic bottles into the waste recycling equipment will result in corresponding revenue being returned to the user.

[0022] Among them, the user recycling request is a garbage recycling request sent by the user to the garbage recycling equipment by scanning a QR code on the recycling interface of the garbage recycling equipment through a mini program or through an application. After receiving the user recycling request, the garbage recycling equipment will open the disposal port, close it after the user has disposed of the garbage, and use the camera equipment set in the garbage recycling equipment to take pictures of the user before and after disposal, so as to obtain a comparison image of garbage disposal.

[0023] For example, the waste disposal comparison images include images of the storage area in the waste recycling equipment before the user disposes of the waste, such as focusing on the disposal port or temporary storage area of ​​the waste recycling equipment and capturing the state of various types of waste that have been piled up and compressed; it also includes the state of the storage area in the waste recycling equipment after the user disposes of the waste, such as the state of paper, plastic bottles, metal cans, glass bottles, etc., piled up randomly without being compressed or sorted. By using the waste disposal comparison images, it is possible to compare the waste before and after waste recycling, remove the interference of previously disposed waste, and more accurately identify the waste currently disposed of.

[0024] Among them, gravity sensing data refers to the gravity change data monitored by the gravity sensing device installed in the waste recycling equipment, as well as the weight of the items thrown in by the user. The data can be reset to zero after each recycling is completed, so that gravity sensing data can be collected when a new user recycling request is received.

[0025] Specifically, the brightness signal-to-noise ratio (SNR) features of the waste disposal comparison images are extracted, including: performing multi-layer convolution processing on the waste disposal comparison images to obtain multi-layer convolution features; performing residual connections on the multi-layer convolution features to obtain brightness distribution features; enhancing the feature dimension of the brightness distribution features to obtain a brightness feature map; performing grayscale conversion and mean filtering on the waste disposal comparison images to obtain filtered images; generating a noise image based on the waste disposal comparison images and the filtered image, and generating an SNR feature map based on the filtered image and the noise image; and fusing the brightness feature map and the SNR feature map to obtain the brightness SNR features.

[0026] In this embodiment of the invention, multi-layer convolution processing of the garbage disposal comparison image is performed using multiple convolutional layers with the same kernel size. This allows for more detailed extraction of feature information and amplification of local brightness details in the image. Residual connections are then used to pass the output and input of each layer as the input to the next layer for further convolution. Residual connections on the multi-layer convolutional features directly pass the input of each layer to the subsequent layers (skipping one or more layers), and perform addition operations with the features after convolution. Residual connections further enhance the expressive power of convolution processing, thereby extracting brightness distribution features.

[0027] Furthermore, by performing multi-layer convolution processing on the brightness distribution features, the brightness information in the brightness distribution features is converted into a brightness feature map. Then, feature mapping is performed through an activation function, which can transform the low-dimensional brightness distribution features into a higher-dimensional feature to capture more complex features and obtain a brightness feature map with richer image brightness information.

[0028] In this embodiment of the invention, grayscale conversion of the waste disposal comparison image involves converting the pixel values ​​in the waste disposal comparison image into grayscale values ​​representing brightness. This conversion can be performed based on the values ​​of the three color channels (Red (R), Green (G), and Blue (B)) and a preset conversion formula to obtain a grayscale image. Then, mean filtering is applied to the grayscale image to obtain a noise-free filtered image. Mean filtering involves moving a sliding window (usually a square or circular template) across the grayscale image corresponding to the waste disposal comparison image, calculating the mean of all pixel values ​​within the window, and using this mean as the new value for the center pixel of the window to obtain the filtered image. This results in a denoised filtered image that can more accurately capture key features of the waste, such as shape, color, and texture. For example, when identifying paper waste, the filtered image can more clearly present the fiber texture and edge shape of the paper, reducing the possibility of misidentification as other waste of similar color but different texture (such as plastic film), providing a foundation for subsequent image enhancement based on brightness signal-to-noise ratio characteristics.

[0029] Furthermore, by subtracting the pixel values ​​of the garbage disposal comparison image from the corresponding filtered image and taking the absolute value, a noisy image is obtained. The pixel values ​​of the filtered image and the noisy image are then divided to obtain the signal-to-noise ratio feature map.

[0030] In this embodiment of the invention, the brightness signal-to-noise ratio feature can simultaneously take into account the brightness and texture structure information in the details of the waste disposal comparison image, which is beneficial to improve the image clarity of the waste disposal comparison image and thus more accurately identify the waste disposal category.

[0031] S2. Enhance the brightness contrast of the garbage disposal comparison image based on the brightness signal-to-noise ratio characteristics to obtain an enhanced comparison image.

[0032] In this embodiment of the invention, since the garbage may be obscured or the camera equipment may not be able to cover the whole area when it is dumped, the brightness of the garbage dumping comparison image may be weak, resulting in the loss of some feature information. Therefore, brightness enhancement is required. Brightness contrast enhancement is to enhance the darker areas in the garbage dumping comparison image where the brightness information is missing based on the brightness signal-to-noise ratio characteristics.

[0033] Specifically, see Figure 2 As shown, brightness contrast enhancement is performed on the garbage disposal comparison image based on the brightness signal-to-noise ratio characteristics to obtain an enhanced contrast image, including:

[0034] S21. Perform shallow feature extraction on the garbage disposal comparison image to obtain a shallow feature map, and calculate the short-distance feature map corresponding to the garbage disposal comparison image based on the shallow feature map.

[0035] S22. Based on the brightness signal-to-noise ratio characteristics, perform long-distance feature extraction on the shallow feature map to obtain the long-distance feature map;

[0036] S23. Use the brightness signal-to-noise ratio feature to fuse the short-range feature map and the long-range feature map to obtain the enhanced feature;

[0037] S24. Perform feature decoding on the enhanced features to obtain an enhanced comparison image of the garbage disposal comparison image.

[0038] In detail, shallow feature extraction utilizes the first few convolutional layers in the preset feature extraction module to extract shallow feature maps representing information such as edges and textures in the garbage disposal comparison image. The shallow feature maps are then subjected to deep feature extraction through multiple convolutional layers. Next, multiple convolutional residual blocks without batch normalization are used to further extract features, which can enhance the ability to preserve details. Finally, a convolutional layer is used to convolve the output of the residual convolutional blocks to obtain the short-range feature map of the garbage disposal comparison image.

[0039] For example, short-range features can capture detailed information such as edges, textures, and corners, which are helpful in identifying the shape and material of garbage in garbage disposal comparison images. Long-range features can provide global information such as the overall position of garbage in garbage disposal comparison images and its relative position with other objects, which helps to determine the approximate range and type of garbage.

[0040] Furthermore, long-range feature extraction is performed on the shallow feature map based on the brightness signal-to-noise ratio (SNR) characteristics to obtain a long-range feature map. This includes: segmenting the shallow feature map to obtain feature map blocks; calculating the mask value matrix of the feature map blocks using the brightness SNR characteristics; performing self-attention calculation on the feature map blocks based on the mask value matrix to obtain attention block features; and concatenating the attention block features to obtain a long-range feature map.

[0041] In detail, feature map segmentation is performed on a shallow feature map of size H×W×C with a preset segment size of D×D. The shallow feature map is then divided into m = (H / D)×(W / D) uniform feature map segments. The luminance signal-to-noise ratio (BNR) feature is adjusted to match the size of the shallow feature map. The BNR feature of the same size is then segmented according to the feature map segments. The average value of the feature values ​​in each feature map segment is calculated. The segmentation of each BNR feature is binarized based on the average value to obtain the mask value of the feature map segment. The mask value is used as a mask during self-attention calculation to prevent feature information in dark areas with missing information from participating in the attention calculation. Specifically, the segmentation mask value of the BNR feature is used to construct a one-dimensional vector, and the one-dimensional vector is copied into an m×m mask value matrix.

[0042] Specifically, the self-attention weights are calculated using the following formula:

[0043]

[0044] Among them, S i The self-attention weights of the i-th feature map block are represented by Q, where softmax represents the softmax activation function. i , V i Let d represent the query vector, the transpose of the key-value vector, and the value vector corresponding to the i-th feature map block, respectively. k Represents the key-value vector K i The dimension is L, which represents the mask value matrix, and σ represents the preset negative scalar parameter.

[0045] Specifically, the self-attention weight of each feature map block is multiplied by the feature map block to obtain the attention block features, and then the attention block features are concatenated to obtain the long-distance feature map.

[0046] In this embodiment of the invention, short-range feature maps and long-range feature maps can be used to focus on different feature contents in the waste disposal comparison image, thereby achieving complementary brightness information. For example, for areas with normal brightness and sufficient local information, the weight of short-range features is increased to achieve information complementarity; for extremely dark areas with severely missing information, the visibility of adjacent areas is also very low and noise is severe, the weight of long-range features is increased to achieve complementarity, thereby improving the accuracy of subsequent feature fusion and further enabling precise identification of waste disposal categories.

[0047] Furthermore, the luminance signal-to-noise ratio (SNR) features are used to fuse the short-range and long-range feature maps to obtain enhanced features. This includes: performing an image inversion transformation on the luminance feature map and the SNR feature map corresponding to the luminance SNR features to obtain inverted feature maps corresponding to the luminance feature map and the SNR feature map; performing a weighted summation on the luminance feature map and the SNR feature map to obtain a first weighted feature map, and performing a weighted summation on the inverted feature map to obtain a second feature map; multiplying the first feature map with the short-range feature map to obtain a first fused feature map, and multiplying the second feature map with the long-range feature map to obtain a second fused feature map; and adding the pixel values ​​of the first fused feature map and the second fused feature map to obtain the enhanced features.

[0048] In this embodiment of the invention, the image inversion transformation involves inverting the pixel value in both the brightness feature map and the signal-to-noise ratio (SNR) feature map, i.e., subtracting the original pixel value from 1. This highlights the originally darker areas in both the brightness and SNR feature maps, making them brighter and thus enhancing contrast. The brightness feature map and the SNR feature map are obtained by fusing the aforementioned features.

[0049] Furthermore, by using four different preset weights to perform weighted summation, a first weighted feature map and a second weighted feature map are obtained, thereby constructing an enhanced feature with richer feature information.

[0050] Specifically, by enhancing features, both detailed and global features can be taken into account, resulting in a more comprehensive and accurate understanding of waste disposal comparison images. For example, in waste disposal comparison images, the waste to be identified may be occluded, deformed, or intertwined with other waste. The fused features can grasp the overall scene structure through long-range features and capture the detailed features of target objects using short-range features, thereby more accurately detecting and locating the target waste area.

[0051] In this embodiment of the invention, feature decoding is to restore the enhanced features to an image, and an enhanced contrast image after brightness and contrast enhancement.

[0052] Specifically, feature decoding is performed on the enhanced features to obtain an enhanced comparison image of the garbage disposal comparison image, including: performing channel feature convolution on the enhanced features to obtain channel convolution features; performing pointwise convolution on the channel convolution features to obtain target features; and performing feature activation mapping on the target features to obtain the enhanced comparison image.

[0053] In this embodiment of the invention, feature convolution is performed by using a 3×3 convolution kernel to perform convolution operation on each channel of the enhanced feature, with each channel using an independent convolution kernel, which can extract spatial features; pointwise convolution is a 1×1 convolution operation used to fuse the channel convolution features between channels after depthwise convolution, extract the target features, and then use a preset activation function to map the features to a preset feature space, reconstructing the target features into an enhanced contrast image.

[0054] In detail, enhancing the contrast of the image can help restore details in lower areas and improve image clarity. Furthermore, by capturing more local features and spatial information through depth and pointwise convolution, details can be made clearer and the specific type and state of the trash can be identified more accurately. At the same time, it provides the overall position and layout of the trash in the image, which can accurately identify trash that is occluded or located in a complex background.

[0055] S3. Identify the target waste region in the enhanced contrast image, and identify the waste disposal category corresponding to the waste disposal contrast image based on the target waste region.

[0056] In this embodiment of the invention, the target waste area is the area of ​​the waste corresponding to the user's recycling request in the enhanced comparison image. The enhanced comparison image includes images before the user's recycling request and images after the waste disposal is completed. Therefore, by comparing the images between the enhanced comparison images, the changes between the enhanced comparison images can be distinguished, the area where the disposed waste is located can be identified, and thus the waste disposal category can be identified more accurately.

[0057] For example, by capturing consecutive images before and after a user requests recycling, and comparing the subsequent images with the previous ones when recycling waste is put into the recycling equipment, the grayscale value of the image in the area where the recycling waste is put in will change, thus obtaining the target area of ​​the waste. This allows for the localization of the put-in waste, thereby eliminating the interference of existing waste in the recycling equipment before the user puts in the recycling waste, and enabling more accurate identification of the waste disposal category.

[0058] In the embodiments of the present invention, see Figure 3 As shown, identifying garbage target regions in enhanced contrast images includes:

[0059] S31. Perform grayscale processing on the enhanced contrast image to obtain a grayscale contrast image;

[0060] S32. Perform image difference calculation on the grayscale contrast image to obtain the difference grayscale image;

[0061] S33. Perform morphological operations on the difference image to obtain the target difference image;

[0062] S34. Extract the garbage target region from the enhanced contrast image based on the target difference image.

[0063] In this embodiment of the invention, image difference calculation is to calculate the difference in grayscale values ​​of the same pixel in a grayscale contrast image, compare the difference with a preset threshold, and generate a difference grayscale image that represents the difference between the grayscale contrast images. In the difference grayscale image, pixels with large differences are marked as change points, usually represented by white or a specific color, while pixels with small differences or no differences are marked as background, represented by black or transparent.

[0064] In detail, the OTSU method can be used to calculate the preset threshold, and the segmentation threshold can be automatically determined based on the grayscale characteristics of the image, thereby improving the recognition efficiency of garbage target areas.

[0065] Furthermore, morphological operations utilize small matrices of structuring elements (usually squares or circles) to perform image erosion and dilation operations on the differential grayscale image. This can remove small noise points or connect adjacent regions of change, further analyze structural features, and obtain a more accurate target differential image.

[0066] In this embodiment of the invention, by identifying the areas of significant difference in the target differential image, matching these areas against the image after the user's recycling request and the completed waste disposal in the enhanced contrast image, the target waste area is extracted from the enhanced contrast image. This allows for the identification of the type of waste disposed of by the user based on the target waste area.

[0067] In detail, by extracting the target area of ​​the waste, we can analyze the comparison before and after the user's recycling request, thereby determining the image area where waste disposal category identification is required, effectively improving the accuracy of subsequent waste disposal category identification.

[0068] In this embodiment of the invention, identifying the waste disposal category corresponding to the waste disposal comparison image based on the waste target area includes: performing color space conversion on the waste target area to obtain a color space region; calculating the color distribution features of each waste target area based on the color space region; calculating the local binary pattern histogram of each waste target area to obtain local texture features; combining the color distribution features and local texture features to obtain multi-dimensional local features; performing feature linear fusion of the global color features and global texture features to obtain image recognition features; and classifying the waste target area according to the image recognition features to obtain the waste disposal category.

[0069] In detail, color space conversion involves converting each target area of ​​waste to the HSV color space (Hue, Saturation, and Value), extracting the hue information contained in the H channel from the HSV color space, calculating the histogram of the H channel using a histogram function, and counting the frequency of each hue value to obtain the color distribution characteristics.

[0070] Furthermore, the Local Binary Pattern Histogram (LBP) extracts the texture features of each garbage target region using the Local Binary Pattern (LBP). Specifically, for each pixel in the garbage target region, it is taken as the center pixel, and its surrounding neighboring pixels (usually a 3×3 neighborhood) are taken. The gray values ​​of the neighboring pixels are compared with the gray value of the center pixel. If the gray value of the neighboring pixels is greater than or equal to the gray value of the center pixel, it is recorded as 1; otherwise, it is recorded as 0. The binary number formed by the comparison result is then converted into a decimal number as the LBP feature value of the center pixel. The frequency of occurrence of different LBP feature values ​​is counted to form an LBP histogram, thus obtaining local texture features used to describe the texture features of the image.

[0071] For example, since recyclable waste such as plastic bottles, cardboard, and books have different colors and shapes, the waste disposal category can be identified based on multi-dimensional local features.

[0072] In this embodiment of the invention, feature splicing involves splicing the color distribution features and local texture features from the multi-dimensional local features to obtain global color features and global texture features. Then, the global color feature vector and global texture feature vector are spliced ​​into a unified feature vector and linearly weighted and fused to obtain image recognition features.

[0073] In detail, a pre-trained multi-classification model can be used to calculate the probability of each image recognition feature being classified into a preset waste disposal category, and the maximum probability can be selected as the corresponding waste disposal category.

[0074] In this embodiment of the invention, identifying waste disposal categories through multi-dimensional local features can take into account the color and texture differences between different waste disposal categories. For example, plastic and cardboard may have similar colors, but cardboard and plastic are made of different materials, resulting in fundamental differences in texture features. Therefore, by using multi-dimensional local features and considering the similarity of spatial features in local areas, accurate waste disposal category identification can be achieved.

[0075] S4. Calculate waste recycling data and share recycling revenue based on waste disposal category and gravity sensor data.

[0076] In this embodiment of the invention, the waste recycling data refers to the category and weight data of the waste to be recycled in this user recycling request, and the shared recycling revenue refers to the revenue that the user can obtain from this recycling.

[0077] Specifically, waste recycling data and shared recycling revenue are calculated based on waste disposal categories and gravity sensor data, including: performing recycling calibration using waste disposal categories and gravity sensor data to obtain calibration results; matching recycling rules based on calibration results and gravity sensor data, and calculating shared recycling revenue using recycling rules; and collecting waste disposal categories and gravity sensor data to obtain waste recycling data.

[0078] In this embodiment of the invention, recycling calibration is to determine whether the type of waste disposed of by the user and the weight obtained from the gravity sensor data are consistent with the norm. For example, if the waste disposal type is cardboard and books, but the gravity sensor data is much greater than the normal weight, then there may be a situation where illegal disposal occurs and waste is mixed together, which requires corresponding processing and recycling using different recycling rules.

[0079] For example, a tiered revenue calculation rule can be set based on the magnitude of gravity sensor data. For instance, when the gravity sensor data is less than a first threshold, recycling is carried out at a rate of A yuan per kilogram; when the gravity sensor data is between the first and second thresholds, recycling is carried out at a rate of B yuan per kilogram, where B is greater than A. This tiered revenue calculation can activate users' enthusiasm for shared recycling and increase the utilization rate of waste sharing and recycling equipment.

[0080] In detail, waste recycling equipment can only recycle one type of waste, such as metal, plastic, or cardboard. Mixed recycling may lead to inconsistent recycling benefits and unsuccessful recycling. Therefore, recycling calibration is necessary.

[0081] For example, when the calibration results show that the waste disposal category and the gravity sensor data are consistent, the shared recycling revenue is obtained by multiplying the preset price of the waste disposal category with the gravity sensor data. When they are inconsistent, the shared recycling revenue is obtained by using the corresponding recycling rules.

[0082] In detail, by summarizing the waste disposal category and gravity sensor data corresponding to each user recycling request, waste recycling data can be obtained. This allows analysis of the waste sharing and recycling status of each waste recycling device, such as whether the waste recycling device is full and can no longer recycle, requiring the emptying of recyclable items. At the same time, the average time required for each waste recycling device to reach full capacity can be determined, thereby allowing for planned adjustments to the placement layout of waste recycling devices and improving their utilization rate and rationality.

[0083] Furthermore, after calculating waste recycling data and shared recycling revenue based on waste disposal category and gravity sensor data, the present invention may further include: feeding back the shared recycling revenue to the user corresponding to the recycling request, receiving feedback information corresponding to the user's recycling request; parsing the feedback information to parse the payment method for the shared recycling revenue; calling the available payment channels of the waste recycling equipment according to the payment method; and paying the shared recycling revenue to the user based on the payment method using the available payment area.

[0084] Furthermore, the shared recycling revenue is fed back to the corresponding user through the user's recycling request. For example, if a user sends a user recycling request by scanning a QR code through a mini-program, the shared recycling revenue will be fed back to the user's mini-program interface, and the user will be asked whether they accept the shared recycling revenue. Feedback information will be obtained after the user submits their feedback.

[0085] In detail, when the feedback information is "accepted," the system analyzes the payment method for shared recycling revenue in the user's feedback information, such as payment amount, points, or equivalent items. Based on the user's needs, the corresponding payment method is determined. The client of the waste recycling device then retrieves the available savings in the user's account that support that payment method and pays the shared recycling revenue to the user. For example, if the user selects WeChat Mini Program as the payment method, the waste recycling device will use channels that can pay revenue to WeChat Mini Programs as available payment channels. Specifically, it can prioritize the channel with the largest available amount among those supporting WeChat Mini Program payments.

[0086] Furthermore, if the feedback is "unacceptable," the garbage sharing and recycling of this user's recycling request can be stopped, and the revenue can be recalculated, which can improve the success rate of garbage sharing and recycling.

[0087] Preferably, since the types and quantities of waste generated vary greatly among different areas such as residential areas, commercial areas, and industrial areas, as well as population density and population flow, for example, densely populated areas such as city centers and large communities have relatively high waste generation and require more waste recycling equipment to meet residents' shared waste recycling needs, it is possible to analyze the waste recycling situation in different areas based on waste recycling data, rationally deploy waste recycling equipment, ensure that the equipment can cover the main waste-generating areas and match the amount of waste generated, improve the utilization efficiency of waste recycling equipment, and reduce operating costs.

[0088] Furthermore, after calculating waste recycling data and shared recycling revenue based on waste disposal categories and gravity sensing data, the present invention may further include: dividing waste recycling equipment into regions to obtain equipment regions; collecting recycling data sequences for each equipment region based on waste recycling data; performing data interpolation processing on the recycling data sequences to obtain smooth data sequences for each equipment region, and constructing data sequence features for the smooth data sequences; acquiring regional information for each equipment region, and constructing influence features for each equipment region based on the regional information; performing feature fusion on the data sequence features and influence features to obtain target region features; calculating the equipment demand quantity for each equipment region based on the target region features; and optimizing the layout of waste recycling equipment in each equipment region using the equipment demand quantity to obtain an optimized layout.

[0089] Specifically, waste recycling equipment can be divided into areas based on neighborhoods, streets, business districts, or a predetermined center distance to obtain equipment areas. Each equipment area may contain multiple waste recycling devices. The sum of waste recycling data within a predetermined time interval is collected from each equipment area and sorted according to time to obtain a recycling data sequence. For example, the sum of waste recycling data can be collected every 6 hours, 12 hours, daily, every two days, or daily. The data collected within the predetermined time period constitutes the recycling data sequence, which can yield the total amount of waste recycling data collected in the equipment area within a month. This allows for the analysis of the trend of the total amount of waste recycling data in the equipment area over time.

[0090] Furthermore, since the collection time intervals may differ, the amount of data in the recycling data sequence varies across different equipment areas, resulting in poor smoothness of the recycling data sequence. Therefore, cubic spline interpolation can be used to interpolate the recycling data sequence, making the data points in the interpolated data sequence smoother. This allows the original trend to be maintained even as the amount of data increases, facilitating the accurate extraction of data sequence features. For example, if the recycling data sequence consists of the sum of data collected once a day, cubic spline interpolation can be used to smooth the time interval in the data sequence to be every 6 hours.

[0091] In this embodiment of the invention, the regional information of the equipment area includes the geographical location, population density, and category of each equipment area. For example, the equipment area may be located in the city center or suburbs; the population density and the category of the equipment area, such as commercial area, industrial area, development zone, or residential area, can be obtained using publicly available information. Then, features of each piece of information in the regional information are constructed to obtain the influencing features. Specifically, the information can be converted into feature vectors to obtain the influencing features.

[0092] Furthermore, the smoothed data sequence can be input into a pre-trained long short-term memory neural network to obtain data sequence features. Then, the data sequence features are concatenated with each feature vector in the influence features to obtain the target region features. The target region features are then predicted through the fully connected layer following the long short-term memory neural network to obtain the required number of devices for each region.

[0093] Specifically, the core of a Long Short-Term Memory (LSTM) neural network is the memory cell, which stores and updates information. The memory cell controls the inflow and outflow of information through a gating mechanism, which includes three gate structures: an input gate, a forget gate, and an output gate. At each time step, the LSM receives the current input and the hidden state from the previous time step, and updates the information in the memory cell through the gating mechanism. This effectively captures long-term dependencies in compressed resolution sequences, improving the accuracy of predictive retrieval data computation.

[0094] Furthermore, the layout can be optimized based on the required number of devices. For example, if the area is a residential area and the required number of devices is 5, then 5 waste recycling devices need to be set up in the area. Specifically, they can be evenly distributed in the area to meet the needs of each user as much as possible, thereby improving the utilization rate of the waste recycling devices.

[0095] like Figure 4 The diagram shown is a functional block diagram of a waste recycling sharing system provided in an embodiment of the present invention.

[0096] The recycling sharing system 400 of the waste recycling sharing equipment of the present invention can be installed in an electronic device. Depending on the functions implemented, the recycling sharing system 400 may include a data acquisition module 401, a brightness contrast enhancement module 402, a waste disposal category identification module 403, and a recycling revenue calculation module 404. A module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0097] In this embodiment, the functions of each module / unit are as follows:

[0098] The data acquisition module 401 is used to acquire user recycling requests received by the waste recycling equipment, acquire waste disposal comparison images and gravity sensing data according to the user recycling requests, and extract the brightness signal-to-noise ratio features of the waste disposal comparison images.

[0099] The brightness contrast enhancement module 402 is used to enhance the brightness contrast of the garbage disposal comparison image based on the brightness signal-to-noise ratio characteristics to obtain an enhanced contrast image.

[0100] The waste disposal category recognition module 403 is used to identify the target area of ​​waste in the enhanced contrast image and identify the waste disposal category corresponding to the waste disposal contrast image based on the target area of ​​waste.

[0101] The recycling revenue calculation module 404 is used to calculate waste recycling data and share recycling revenue based on waste disposal category and gravity sensor data.

[0102] In detail, each module in the recycling and sharing system 400 of the waste recycling sharing equipment in this embodiment of the invention adopts the same characteristics as described above during use. Figures 1 to 3 The recycling and sharing methods of the waste recycling and sharing equipment are the same as those used in China, and can produce the same technical effects, so they will not be elaborated here.

[0103] like Figure 5 The diagram shown is a structural schematic of an electronic device for implementing a recycling and sharing method for a waste recycling and sharing device according to an embodiment of the present invention.

[0104] The electronic device 500 may include a processor 501, a memory 502, a communication bus 503, and a communication interface 504. It may also include a computer program stored in the memory and capable of running on the processor, such as a recycling and sharing method program for a waste recycling and sharing device.

[0105] In some embodiments, the processor 501 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips.

[0106] The memory 502 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 502 may be an internal storage unit of an electronic device, such as the portable hard drive of the electronic device.

[0107] The communication bus 503 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 502 and at least one processor 501.

[0108] Communication interface 504 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface.

[0109] Figure 5 The image only shows electronic devices with components; it will be understood by those skilled in the art that... Figure 5 The structure shown does not constitute a limitation on the electronic device 500, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0110] Specifically, the processor's implementation method for the above instructions can be found in the description of the relevant steps in the corresponding embodiments in the accompanying drawings, and will not be repeated here.

[0111] In the several embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0112] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0113] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0114] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0115] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0116] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0117] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim may also be implemented by a single unit or system through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A recycling and sharing method for a waste recycling sharing device, characterized in that, The method includes: The system acquires user recycling requests received by the waste recycling equipment, collects waste disposal comparison images and gravity sensor data based on the user recycling requests, and extracts the brightness signal-to-noise ratio features of the waste disposal comparison images. The brightness contrast of the waste disposal comparison image is enhanced based on the brightness signal-to-noise ratio characteristics to obtain an enhanced comparison image. Identify the target waste region in the enhanced contrast image, and identify the waste disposal category corresponding to the waste disposal contrast image based on the target waste region; Waste recycling data and shared recycling revenue are calculated based on the waste disposal category and the gravity sensor data.

2. The recycling and sharing method of the waste recycling sharing equipment as described in claim 1, characterized in that, The step of extracting the brightness signal-to-noise ratio features of the waste disposal comparison image includes: The waste disposal comparison images are subjected to multi-layer convolution processing to obtain multi-layer convolution features; The multi-layer convolutional features are residually connected to obtain brightness distribution features. The brightness distribution features are then augmented to obtain a brightness feature map. The waste disposal comparison images are respectively subjected to grayscale conversion and mean filtering to obtain filtered images; A noisy image is generated based on the waste disposal comparison image and the filtered image, and a signal-to-noise ratio feature map is generated based on the filtered image and the noisy image; The brightness feature map and the signal-to-noise ratio feature map are fused to obtain the brightness signal-to-noise ratio feature.

3. The recycling and sharing method of the waste recycling sharing equipment as described in claim 1, characterized in that, The step of enhancing the brightness contrast of the waste disposal comparison image based on the brightness signal-to-noise ratio features to obtain an enhanced comparison image includes: Shallow feature extraction is performed on the waste disposal comparison image to obtain a shallow feature map, and a short-range feature map corresponding to the waste disposal comparison image is calculated based on the shallow feature map; Based on the brightness signal-to-noise ratio characteristics, long-range features are extracted from the shallow feature map to obtain a long-range feature map. The brightness signal-to-noise ratio feature is used to fuse the short-range feature map and the long-range feature map to obtain enhanced features; The enhanced features are decoded to obtain the enhanced comparison image of the waste disposal comparison image.

4. The recycling and sharing method of the waste recycling sharing equipment as described in claim 3, characterized in that, The step of extracting long-range features from the shallow feature map based on the brightness signal-to-noise ratio features to obtain a long-range feature map includes: The shallow feature map is segmented to obtain feature map blocks; The mask value matrix of the feature map block is calculated using the brightness signal-to-noise ratio feature; Self-attention calculation is performed on the feature map blocks based on the mask value matrix to obtain attention block features; The attention-block features are concatenated to obtain a long-distance feature map.

5. The recycling and sharing method of the waste recycling sharing equipment as described in claim 3, characterized in that, The step of fusing the short-range feature map and the long-range feature map using the brightness signal-to-noise ratio feature to obtain enhanced features includes: The brightness feature map and the signal-to-noise ratio feature map corresponding to the brightness signal-to-noise ratio feature are subjected to image inversion transformation to obtain the inverted feature map corresponding to the brightness feature map and the signal-to-noise ratio feature map; The brightness feature map and the signal-to-noise ratio feature map are weighted and summed to obtain a first weighted feature map, and the inverted feature map is weighted and summed to obtain a second feature map; Multiply the first feature map with the short-range feature map to obtain the first fused feature map, and multiply the second feature map with the long-range feature map to obtain the second fused feature map; The pixel values ​​of the first fused feature map and the second fused feature map are added together to obtain the enhanced feature.

6. The recycling and sharing method of the waste recycling sharing equipment as described in claim 3, characterized in that, The step of decoding the enhanced features to obtain the enhanced comparison image of the waste disposal comparison image includes: The enhanced features are convolved with channel features to obtain channel convolution features; The target features are obtained by performing point-by-point convolution on the channel convolution features; Feature activation mapping is performed on the target features to obtain an enhanced contrast image.

7. The recycling and sharing method of the waste recycling sharing equipment as described in claim 1, characterized in that, The identification of the garbage target region in the enhanced contrast image includes: The enhanced contrast image is converted to grayscale to obtain a grayscale contrast image; Image difference calculation is performed on the grayscale contrast image to obtain a difference grayscale image; Perform morphological operations on the difference image to obtain the target difference image; The garbage target region is extracted from the enhanced contrast image based on the target difference image.

8. The recycling and sharing method of the waste recycling sharing equipment as described in claim 1, characterized in that, The step of identifying the waste disposal category corresponding to the waste disposal comparison image based on the waste target area includes: The target area of ​​the waste is converted to a color space to obtain a color space region; Calculate the color distribution characteristics of each of the waste target areas based on the color space regions; Calculate the local binary pattern histogram for each of the garbage target regions to obtain local texture features; By combining the color distribution features and the local texture features, multi-dimensional local features are obtained; The global color features and the global texture features are linearly fused to obtain image recognition features; The waste target area is classified according to the image recognition features to obtain the waste disposal category.

9. The recycling and sharing method of the waste recycling sharing equipment as described in claim 1, characterized in that, The calculation of waste recycling data and shared recycling revenue based on the waste disposal category and the gravity sensor data includes: The recycling calibration is performed using the waste disposal category and the gravity sensor data to obtain the calibration results; Based on the calibration results and the gravity sensor data, a recycling rule is matched, and the shared recycling revenue is calculated using the recycling rule. By combining the waste disposal categories and the gravity sensor data, waste recycling data is obtained.

10. A recycling and sharing system for waste recycling equipment, characterized in that, The system includes: The data acquisition module is used to acquire user recycling requests received by the waste recycling equipment, acquire waste disposal comparison images and gravity sensing data according to the user recycling requests, and extract the brightness signal-to-noise ratio features of the waste disposal comparison images. A brightness contrast enhancement module is used to enhance the brightness contrast of the waste disposal contrast image based on the brightness signal-to-noise ratio characteristics to obtain an enhanced contrast image. The waste disposal category identification module is used to identify the waste target area in the enhanced contrast image and identify the waste disposal category corresponding to the waste disposal contrast image based on the waste target area; The recycling revenue calculation module is used to calculate waste recycling data and share recycling revenue based on the waste disposal category and the gravity sensor data.

11. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The processor is used to execute computer programs stored in the memory; The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the recycling and sharing method of the waste recycling sharing device as described in any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the recycling and sharing method of the waste recycling sharing device as described in any one of claims 1 to 9.

Images