Intelligent classification control system and method for urban garbage recovery

Abstract

The invention discloses an intelligent classification control system and an intelligent classification control method for urban garbage recovery, and belongs to the field of garbage recovery. The method comprises the steps of performing classification error garbage weight distribution, performing classification effect analysis according to a classification error garbage weight distribution result, classification data of garbage classification and classification accuracy condition data, and performing classification abnormity early warning according to an obtained classification effect analysis result. The abnormal classification condition is accurately identified, so that the influence of an image identification factor on the judgment accuracy of the abnormal classification condition is avoided, and the identification accuracy and efficiency of the abnormal classification condition are improved.

Description

Technical Field

[0001] The present application belongs to the field of garbage recycling, and specifically to an intelligent classification control system and method for urban garbage recycling. Background Art

[0002] The automatic garbage sorting system first uses recognition technology to distinguish different types of garbage, which usually includes image recognition, infrared recognition, sensor technology, etc. For example, the image recognition system can capture images of garbage through a camera and use image processing algorithms to identify its type. Once the garbage is identified, the sorting mechanism will separate it according to the type of garbage. This may include robotic arms, pneumatic sorting devices, vibrating conveyor belts, etc. For example, the robotic arm can grab a specific type of garbage according to instructions and put it into the corresponding recycling bin. The automatic garbage sorting system usually integrates artificial intelligence algorithms such as deep learning, machine learning, etc. to continuously improve the accuracy and efficiency of classification. The algorithm can be used from a large amount of data. Learning from the process, so as to better identify and classify garbage. The principle of automatic garbage classification is to reduce manual intervention, improve the efficiency and accuracy of garbage classification, reduce environmental pollution, and promote resource recycling and reuse. In the process of garbage classification, classification errors often occur. The most common cause of classification errors is the failure of the classification module, and a small part of the cause is the accuracy of the image recognition algorithm. In the process of identifying abnormal classification, it is impossible to quickly analyze whether it is the factor of the accuracy of the image recognition algorithm or the failure of the classification module, resulting in low recognition accuracy and efficiency for abnormal classification. Most of the existing technologies have the above problems.

[0003] In order to improve the recognition accuracy and efficiency of classification anomalies, the present application designs an intelligent classification control system and method for urban waste recycling. Summary of the invention

[0004] In order to address the deficiencies in the prior art mentioned in the background technology, the present application proposes an intelligent classification control system and method for urban waste recycling. The present application assigns weights to misclassified waste based on the error analysis results of the misclassified waste, performs classification effect analysis based on the weight assignment results of the misclassified waste, classification data of the waste classification, and classification accuracy data, and performs classification anomaly warning based on the obtained classification effect analysis results. The present application conducts comprehensive data analysis on classification errors in the waste classification process, accurately identifies classification anomalies, avoids the influence of image recognition factors on the accuracy of judging classification anomalies, and improves the recognition accuracy and efficiency of classification anomalies.

[0005] To achieve the above objectives, the present application provides the following technical solutions: In the first aspect, the present application provides an intelligent classification control method for urban waste recycling, which includes the following specific steps:

[0006] Step 1, obtaining classification data of garbage classification by garbage classification equipment;

[0007] Step 2: performing error spam error analysis based on the misclassified spam information, and assigning misclassified spam weights according to the error spam error analysis results;

[0008] Step 3: Analyze the classification effect based on the weight distribution results of misclassified garbage, the classification data of garbage classification, and the classification accuracy data;

[0009] Step 4: Perform classification anomaly warning based on the classification effect analysis results.

[0010] Preferably, the specific content of the classification data of the garbage classification of the garbage classification equipment is:

[0011] Step 11: Obtain the successfully classified items during the operation of the garbage classification device, and store the obtained data;

[0012] Step 12: Obtain images and size data of classified items that fail to be classified during the operation of the garbage sorting equipment, obtain images and size data of corresponding items in the database, and simultaneously obtain images and size data of corresponding items in the database of classified items that fail to be classified, and store the acquired data.

[0013] Preferably, the performing error spam error analysis based on misclassified spam information comprises the following specific steps:

[0014] Step 21, obtaining images and size data of the classified items that failed to be classified, and obtaining images and size data of the corresponding items in the database of the corresponding classified items, and obtaining images and size data of the corresponding items in the database of the classified items that failed to be classified;

[0015] Step 22: obtaining the classified product image similarity based on the image of the classified object that failed to be classified and the image of the corresponding object in the database. The classified product image similarity here can be one of the image similarity calculation formulas such as cosine similarity, and obtaining the maximum classified product image similarity corresponding to the classified object;

[0016] Step 23, based on the image of the classified object that failed to be classified and the image of the corresponding object in the database of the classified object that failed to be classified, the similarity of the classified garbage image is obtained. It should be noted that the similarity calculation formula of the classified garbage image is the same as that of the classified product image, and the maximum similarity of the classified garbage image corresponding to the classified object is obtained;

[0017] Step 24, obtain the calculated maximum classified product image similarity corresponding to the classified item and the maximum classified error garbage image similarity corresponding to the classified item, and import them into the error garbage error value calculation formula to calculate the error garbage error value, wherein the error garbage error value is used to reflect the degree of influence of the classification error on the image recognition, wherein the error garbage error value calculation formula of the i-th classified error garbage is: , where exp() is the power of the natural constant e, Si is the maximum similarity of the misclassified garbage image corresponding to the i-th misclassified garbage, and Mi is the maximum similarity of the classified product image corresponding to the i-th misclassified garbage.

[0018] Preferably, the step of allocating weights of classified erroneous garbage according to the erroneous garbage error analysis result comprises the following specific steps:

[0019] Step 25, obtain the calculated error garbage error values ​​of all misclassified garbage, and import the obtained error garbage error values ​​of all misclassified garbage into the misclassified garbage weight calculation formula to calculate the misclassified garbage weight, wherein the i-th misclassified garbage weight calculation formula is: , where the formula weights the error calculation by the error difficulty of classifying the wrong garbage.

[0020] Preferably, the classification effect analysis includes the following specific contents: Step 31, obtaining the number of correct classifications, the number of incorrect classifications and the weight allocation results of incorrectly classified garbage in the previous cycle, and obtaining classification accuracy data at the same time, and weighting the number of incorrectly classified garbage sites according to the weight allocation results of incorrectly classified garbage;

[0021] Step 32: The number of correct classifications of garbage in the previous cycle, the number of incorrect classifications, the weight distribution results of the incorrectly classified garbage sites, and the classification accuracy data are obtained to perform classification effect analysis. The classification effect is proportional to the number of correct classifications of garbage and the classification accuracy data, and the classification effect is inversely proportional to the number of incorrect classifications and the weight distribution results of the incorrectly classified garbage sites. The classification effect calculation formula is: , where g is the classification accuracy data, zq is the number of garbage classifications that are correct, and m is the number of classification errors. is the classification error influence coefficient, which is used to reflect the impact of classification error on the classification effect.

[0022] Preferably, the classification abnormality warning based on the obtained classification effect analysis results includes the following specific contents: obtaining the classification effect of the previous period and comparing it with the set classification effect threshold. If the classification effect is less than the set classification effect threshold, it means that the classification is abnormal and the classification module of the equipment needs to be maintained, and the maintenance personnel are warned. If the classification effect is greater than or equal to the set classification effect threshold, it means that the classification is normal.

[0023] It should be noted that the value determination method of the setting parameters of the present application is obtained by technicians in this field through historical data experiments.

[0024] In the second aspect, the present application provides an intelligent classification control system for urban waste recycling, which is implemented based on the above-mentioned intelligent classification control method for urban waste recycling, and specifically includes an acquisition unit, an error analysis unit, a classification effect analysis unit, a classification abnormality warning unit and a control unit; wherein the acquisition unit is used to obtain classification data of garbage classification of the garbage classification equipment; the error analysis unit performs error analysis of erroneous garbage based on the information of misclassified garbage, and assigns weights of classified erroneous garbage according to the error analysis results; the classification effect analysis unit performs classification effect analysis according to the weight assignment results of classified erroneous garbage, classification data of garbage classification and classification accuracy data; the classification abnormality warning unit is used for the classification abnormality warning unit, and the control unit is used to control the operation of the acquisition unit, the error analysis unit, the classification effect analysis unit and the classification abnormality warning unit.

[0025] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0026] The processor executes the above-mentioned intelligent classification control method for urban waste recycling by calling the computer program stored in the memory.

[0027] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute an intelligent classification control method for urban waste recycling as described above.

[0028] At the same time, compared with the prior art, the technical effects and advantages of the present application are: the present application performs error analysis on misclassified garbage information, and assigns weights to misclassified garbage based on the error analysis results, performs classification effect analysis based on the weight assignment results of misclassified garbage, classification data of garbage classification and classification accuracy data, and performs classification anomaly warning based on the obtained classification effect analysis results. The present application performs comprehensive data analysis on misclassification situations in the garbage classification process, accurately identifies classification anomalies, avoids the influence of image recognition factors on the accuracy of judging classification anomalies, and improves the recognition accuracy and efficiency of classification anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 This is a schematic diagram of the overall process of the embodiment of the present application method;

[0031] Figure 2 This is a specific flow chart of step 2 of the embodiment of the method of this application;

[0032] Figure 3 This is a specific flow chart of step 4 of the embodiment of the method of this application;

[0033] Figure 4 It is a schematic diagram of the overall framework of an embodiment of the system of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use.

[0035] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0036] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0037] Example 1

[0038] In order to solve the technical problems raised in the background technology, the present application provides a preferred embodiment: Figure 1-Figure 3 As shown, a method for intelligent classification control of urban garbage recycling includes the following specific steps:

[0039] Step 1, obtaining classification data of garbage classification by garbage classification equipment;

[0040] In this embodiment, the specific content of the classification data of the garbage classification device is:

[0041] Step 11, obtaining successfully classified objects during the operation of the garbage classification device. For example, if the input garbage is a glass, and the identified garbage is also a glass, then the classification is successful, and the obtained data is stored;

[0042] Step 12, obtaining the image and size data of the classified items that failed to be classified during the operation of the garbage classification device. For example, if the garbage thrown in is a glass, and the identified garbage is a kettle, this will cause classification failure. The image and size data of the corresponding classified items in the database, that is, the image and size data of the glass in the database, are obtained. At the same time, the image and size data of the corresponding classified items in the database that failed to be classified, that is, the image and size data of the kettle in the database, are obtained, and the obtained data are stored; the image and size data here are obtained through the sensors configured in the system;

[0043] Step 2: performing error spam error analysis based on the misclassified spam information, and assigning misclassified spam weights according to the error spam error analysis results;

[0044] In this embodiment, performing error spam error analysis based on misclassified spam information includes the following specific steps:

[0045] Step 21, obtaining images and size data of the classified items that failed to be classified, and obtaining images and size data of the corresponding items in the database of the corresponding classified items, and obtaining images and size data of the corresponding items in the database of the classified items that failed to be classified;

[0046] Step 22: obtaining the classified product image similarity based on the image of the classified object that failed to be classified and the image of the corresponding object in the database. The classified product image similarity here can be one of the image similarity calculation formulas such as cosine similarity, and obtaining the maximum classified product image similarity corresponding to the classified object;

[0047] Image similarity calculation is used to measure the similarity between two images in terms of content, color, shape, etc. For example: Histogram comparison: Color histogram comparison: Determine the similarity of two images by comparing their color histograms. Common methods include: Chi-square test, cross entropy, etc. Texture histogram comparison: Analyze image texture features, such as using local binary patterns (LBP); Feature point matching: SIFT (Scale Invariant Feature Transform): Extract key points and describe features, and then calculate similarity by the distance between feature points; SURF (Speeded Up Robust Features): Similar to SIFT, but faster to calculate and suitable for real-time applications; ORB (Oriented FAST and Rotated BRIEF): It is an efficient and high-performance feature point detection and description algorithm; Structural Similarity Metric (SSIM): The SSIM index is a measure of the similarity between two images, taking into account changes in brightness, contrast, and structure; Template Matching: Template matching is a method of finding a small image in a large image, usually using correlation coefficients or other similarity metrics as matching criteria; Convolutional Neural Networks (CNNs) are used to extract high-level features of images, and then the similarity between feature vectors is calculated, such as using cosine similarity, Euclidean distance, etc.;

[0048] Step 23, based on the image of the classified object that failed to be classified and the image of the corresponding object in the database of the classified object that failed to be classified, the similarity of the classified garbage image is obtained. It should be noted that the similarity calculation formula of the classified garbage image is the same as that of the classified product image, and the maximum similarity of the classified garbage image corresponding to the classified object is obtained;

[0049] Step 24, obtain the calculated maximum classified product image similarity corresponding to the classified item and the maximum classified error garbage image similarity corresponding to the classified item, and import them into the error garbage error value calculation formula to calculate the error garbage error value, wherein the error garbage error value is used to reflect the degree of influence of the classification error on the image recognition, wherein the error garbage error value calculation formula of the i-th classified error garbage is: , where exp() is the power of the natural constant e, Si is the maximum similarity of the image of the misclassified garbage corresponding to the i-th misclassified garbage, and Mi is the maximum similarity of the classified product image corresponding to the i-th misclassified garbage; at the same time, the weight allocation of misclassified garbage according to the error analysis result of the misclassified garbage includes the following specific steps:

[0050] Step 25, obtain the calculated error garbage error values ​​of all misclassified garbage, and import the obtained error garbage error values ​​of all misclassified garbage into the misclassified garbage weight calculation formula to calculate the misclassified garbage weight, wherein the i-th misclassified garbage weight calculation formula is: , where the formula weights the error calculation by the error difficulty of classifying the wrong garbage;

[0051] Step 3: Analyze the classification effect based on the weight distribution results of misclassified garbage, the classification data of garbage classification, and the classification accuracy data;

[0052] In this embodiment, the classification effect analysis includes the following specific contents: Step 31, obtaining the number of correct classifications, the number of incorrect classifications and the weight allocation results of incorrectly classified garbage in the previous cycle, and obtaining the classification accuracy data at the same time, and weighting the number of incorrectly classified garbage sites according to the weight allocation results of incorrectly classified garbage;

[0053] Step 32: The number of correct classifications of garbage in the previous cycle, the number of incorrect classifications, the weight distribution results of the incorrectly classified garbage sites, and the classification accuracy data are obtained to perform classification effect analysis. The classification effect is proportional to the number of correct classifications of garbage and the classification accuracy data, and the classification effect is inversely proportional to the number of incorrect classifications and the weight distribution results of the incorrectly classified garbage sites. The classification effect calculation formula is: , where g is the classification accuracy data, zq is the number of garbage classifications that are correct, and m is the number of classification errors. is the classification error influence coefficient, which is used to reflect the impact of classification error on classification effect;

[0054] Step 4: Perform classification abnormality warning based on the obtained classification effect analysis results;

[0055] In this embodiment, classification abnormality warning based on the obtained classification effect analysis results includes the following specific contents: obtaining the classification effect of the previous period and comparing it with the set classification effect threshold. If the classification effect is less than the set classification effect threshold, it means that the classification is abnormal and the classification module of the equipment needs to be maintained, and the maintenance personnel are warned. If the classification effect is greater than or equal to the set classification effect threshold, it means that the classification is normal.

[0056] Secondly, it should be noted that in this embodiment, the value-taking method of the setting parameters in this embodiment is obtained by technical personnel in this field through historical data experiments. Herein, one of the acquisition methods is as follows: obtain the classification data and classification abnormality cause data of historical garbage classification equipment, substitute them into the steps of this embodiment and finally substitute them into the classification effect calculation formula to calculate the classification effect, substitute the classification abnormality cause judgment result and the classification effect calculation result into the fitting software (such as matlab or python) to obtain the value of the relevant setting parameters that meet the maximum judgment accuracy.

[0057] Finally, the benefits of this embodiment are explained here. This embodiment conducts comprehensive data analysis on classification errors in the garbage classification process, accurately identifies classification abnormalities, avoids the influence of image recognition factors on the accuracy of judging classification abnormalities, and improves the recognition accuracy and efficiency of classification abnormalities.

[0058] Example 2

[0059] like Figure 4 As shown, this embodiment provides an intelligent classification control system for urban waste recycling, which is implemented based on the above-mentioned intelligent classification control method for urban waste recycling, and specifically includes an acquisition unit, an error analysis unit, a classification effect analysis unit, a classification abnormality warning unit and a control unit; wherein the acquisition unit is used to obtain classification data of garbage classification of the garbage classification equipment; the error analysis unit performs error analysis of erroneous garbage based on the information of erroneous garbage classified, and assigns weights of erroneous garbage classified according to the error analysis results of the erroneous garbage; the classification effect analysis unit performs classification effect analysis according to the weight assignment results of erroneous garbage classified, the classification data of garbage classification and the classification accuracy data; the classification abnormality warning unit is used for the classification abnormality warning unit, and the control unit is used to control the operation of the acquisition unit, the error analysis unit, the classification effect analysis unit and the classification abnormality warning unit. At the same time, it should be noted that Figure 4 The direction of the arrow in the figure represents the direction of control signal transmission. The control unit controls the operation of other units through control systems such as PLC.

[0060] Example 3

[0061] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0062] The processor executes the above-mentioned intelligent classification control method for urban garbage recycling by calling the computer program stored in the memory.

[0063] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a method for intelligent classification control of urban garbage recycling provided by the above method embodiment. The electronic device may also include other components for implementing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface to input and output data. This embodiment will not be described in detail here.

[0064] Example 4

[0065] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0066] When the computer program runs on a computer device, the computer device executes the above-mentioned intelligent classification control method for urban garbage recycling.

[0067] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0068] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0069] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0070] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0071] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent classification control method for urban garbage recycling, characterized in that: It includes the following specific steps: Obtaining classification data of garbage classification by garbage classification equipment; Performing error spam error analysis based on misclassified spam information, and assigning misclassified spam weights based on the error spam error analysis results; Analyze the classification effect based on the weight distribution results of misclassified garbage, the classification data of garbage classification, and the classification accuracy data; According to the obtained classification effect analysis results, classification abnormality warning is issued.

2. The intelligent classification control method for urban waste recycling according to claim 1, characterized in that: The error spam error analysis based on misclassified spam information comprises the following specific steps: Acquire the image and size data of the classified object that failed to be classified, and at the same time acquire the image and size data of the corresponding object in the database of the corresponding classified object, and at the same time acquire the image and size data of the corresponding object in the database of the classified object that failed to be classified; Based on the image of the classified object that failed to be classified and the image of the corresponding object in the database, the classified product image similarity is obtained to obtain the maximum classified product image similarity corresponding to the classified object; Based on the image of the classified object that failed to be classified and the image of the corresponding object in the database of the classified object that failed to be classified, the similarity of the classified error garbage image is obtained to obtain the maximum similarity of the classified error garbage image corresponding to the classified object; The calculated maximum classified product image similarity corresponding to the classified items and the maximum classified error garbage image similarity corresponding to the classified items are obtained, and the error garbage error value calculation formula is imported to calculate the error garbage error value.

3. The intelligent classification control method for urban waste recycling according to claim 1, characterized in that: The method of allocating weights of classified error garbage according to the error garbage error analysis result comprises the following specific steps: The calculated wrong garbage error values ​​of all wrongly classified garbage are obtained, and the obtained wrong garbage error values ​​of all wrongly classified garbage are imported into the wrongly classified garbage weight calculation formula to calculate the wrongly classified garbage weight.

4. The intelligent classification control method for urban waste recycling as claimed in claim 3, characterized in that: The classification effect analysis includes the following specific contents: obtaining the number of correct classifications, the number of incorrect classifications and the weight allocation results of incorrectly classified garbage in the previous cycle, and obtaining the classification accuracy data at the same time, and weighting the number of incorrectly classified garbage sites according to the weight allocation results of incorrectly classified garbage; The number of correct classifications of garbage in the previous cycle, the number of incorrect classifications, the weight allocation results of the incorrectly classified garbage sites and the classification accuracy data are obtained to analyze the classification effect. The classification effect is directly proportional to the number of correct classifications of garbage and the classification accuracy data, and the classification effect is inversely proportional to the number of incorrect classifications and the weight allocation results of the incorrectly classified garbage sites.

5. The intelligent classification control method for urban waste recycling as claimed in claim 4, characterized in that: The classification abnormality warning based on the obtained classification effect analysis results includes the following specific contents: obtaining the classification effect of the previous period and comparing it with the set classification effect threshold. If the classification effect is less than the set classification effect threshold, it means that the classification is abnormal, and the classification module of the equipment needs to be maintained, and the maintenance personnel are warned. If the classification effect is greater than or equal to the set classification effect threshold, it means that the classification is normal.

6. The intelligent classification control method for urban waste recycling as claimed in claim 5, characterized in that: The specific content of the classification data of the garbage classification equipment is: Obtaining successfully classified items during the operation of the garbage classification equipment, and storing the acquired data; Acquire the image and size data of the classified items that failed to be classified during the operation of the garbage sorting equipment, acquire the image and size data of the corresponding items in the database, and at the same time acquire the image and size data of the corresponding items in the database of the classified items that failed to be classified, and store the acquired data.

7. The intelligent classification control method for urban waste recycling as claimed in claim 2, characterized in that: The calculation method of the classified product image similarity is one of the image similarity calculation formulas, and the classification error garbage image similarity calculation formula is the same as the classified product image similarity.

8. An intelligent classification control system for urban waste recycling, which is implemented based on the intelligent classification control method for urban waste recycling as claimed in any one of claims 1 to 7, characterized in that: It specifically includes an acquisition unit, an error analysis unit, a classification effect analysis unit, a classification abnormality warning unit and a control unit; wherein the acquisition unit is used to acquire classification data of garbage classification of the garbage classification equipment; the error analysis unit performs error analysis of erroneous garbage based on the information of misclassified garbage, and assigns weights of classified erroneous garbage according to the error analysis results; the classification effect analysis unit performs classification effect analysis according to the weight assignment results of misclassified garbage, classification data of garbage classification and classification accuracy data; the classification abnormality warning unit is used for the classification abnormality warning unit, and the control unit is used to control the operation of the acquisition unit, the error analysis unit, the classification effect analysis unit and the classification abnormality warning unit.

9. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the intelligent classification control method for urban waste recycling as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

Images