A dynamic garbage classification, collection, transfer and processing system and method

Abstract

The present disclosure provides a dynamic garbage classification, collection, transfer and processing system and method. The present disclosure utilizes a file reading and processing module to not only update the processing parameters of the garbage processing station, but also to form a sample data set adapted to the current scenario based on the latest garbage classification instruction file. Using this data set to train a verification model can improve the accuracy of garbage classification quality monitoring, which is conducive to improving the effectiveness of garbage classification processing. At the same time, the scheduling module combines the updated processing parameters of the garbage processing station for scheduling, realizing the scheduling of garbage vehicles based on the current performance of each garbage processing station. This not only effectively improves the efficiency of garbage classification and transfer, but also can maximize the dual improvement of environmental and economic benefits, and realizes the flexible configuration of classification and transfer plans according to scenario requirements, improving the scenario adaptability of the plan.

Description

Technical Field

[0001] The present disclosure relates to the field of dynamic garbage disposal, and in particular to a dynamic garbage classification, collection, transfer and disposal system and method. Background Art

[0002] Dynamic garbage classification, collection, transfer and treatment is a systematic and complex process that involves multiple links and the participation of multiple parties. It aims to achieve effective classification, efficient collection, safe transfer and harmless treatment of garbage.

[0003] At present, the more prominent problems in dynamic garbage classification, collection, transfer and treatment are: low classification and transfer efficiency; low flexibility, and the classification and transfer plan cannot be flexibly configured according to scene requirements, resulting in poor scene adaptability; transfer scheduling cannot be carried out according to the specific conditions of each garbage treatment station, and it is impossible to achieve dual guarantees of efficiency and benefits; the quality of garbage classification is poor, which affects the garbage treatment effect. Summary of the Invention

[0004] The present disclosure at least provides a dynamic garbage classification, collection, transfer and processing system and method to solve at least one of the above technical problems.

[0005] According to one aspect of the present disclosure, a dynamic garbage classification, collection, transfer and processing system is provided, comprising:

[0006] The file reading and processing module is used to import a new file and identify the file name. When the identification result indicates that the new file is a processing performance file of a garbage processing station, the file content is read and identified, and the processing parameters of the garbage processing station are extracted and stored. The processing parameters include: the processing efficiency of the garbage processing station for various types of garbage, the weight of various types of garbage to be processed, the unit processing cost of processing various types of garbage, the environmental pollution value generated by processing various types of garbage, the unit benefit generated by processing various types of garbage, and the location of the garbage processing station. When the identification result indicates that the new file is a garbage classification instruction file, , comparing the new garbage classification index file with the stored historical garbage classification index file to obtain a difference text; identifying the difference text, and when the difference text indicates that a new category has been added to a garbage category, obtaining a picture of the new category from the Internet, and rotating and / or scaling the obtained picture; using the picture obtained from the Internet and the rotated and / or scaled picture as an initial sample training set and storing the picture; sending an instruction message to a display module so that the display module displays the added new category and information forming the initial sample training set, and allowing a user to train a corresponding verification model based on the initial sample training set;

[0007] A classification verification module is used to obtain a video of a garbage truck collecting garbage, extract type positioning key frames and classification verification key frames from the video file, wherein the type positioning key frames include at least two frames, and the classification verification key frames include multiple key frames randomly selected from frames after a predetermined number of frames after the type positioning key frame in the video; input the type positioning key frames into a trained classification model, use the classification model to determine the garbage category corresponding to each type positioning key frame, and when the garbage category corresponding to each type positioning key frame is the same, use the garbage category determined by the classification model as the target garbage category; determine a target verification model that matches the target garbage category, and input the classification verification key frames into the trained target verification model, use the target verification model to determine the proportion of garbage belonging to the target garbage type in each key frame; calculate the average of the proportions corresponding to each key frame, and when the average is greater than a preset threshold, determine that the currently collected garbage classification is qualified; wherein different categories of garbage correspond to different verification models;

[0008] A weight assessment module is configured to, if the garbage classification is qualified, obtain images of the garbage collectors of each category on the garbage truck, input the images corresponding to the garbage collectors of each category into the corresponding weight assessment model, process the received images using the weight assessment model to obtain a weight assessment value for each category of garbage, and input the weight assessment value corresponding to each category of garbage into the scheduling module and the early warning interaction module if the weight assessment value of each category of garbage is greater than a first preset weight; wherein different weight assessment models correspond to different categories of garbage;

[0009] An early warning interaction module is configured to store the total weight of each type of garbage collected by the garbage truck during each time period, and to generate and display statistical charts based on the stored total weight of each type of garbage collected and the time period; and, if the total weight collected during N consecutive time periods exceeds a second preset weight for the corresponding type of garbage collected, display and send an early warning message to the control terminal; the early warning message includes the type of excess garbage collected and the weight of the garbage collected exceeding the corresponding second preset weight; wherein N is a positive integer;

[0010] The scheduling module is used to obtain the processing parameters of each garbage treatment station, and determine the transportation cost and transportation time of each garbage treatment station according to the location of each garbage treatment station; combine the weight evaluation value corresponding to each category of garbage, the processing efficiency of each category of garbage at each garbage treatment station and the weight of each category of garbage to be processed, and the transportation time of each garbage treatment station to determine the timeliness index of each garbage treatment station in processing the garbage on the garbage truck; combine the weight evaluation value corresponding to each category of garbage, the unit processing cost of each garbage treatment station for processing each category of garbage, the transportation cost of each garbage treatment station, and the unit benefit generated by each garbage treatment station for processing each category of garbage, to determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck; combine the weight evaluation value corresponding to each category of garbage, the unit processing cost of each garbage treatment station for processing each category of garbage, the transportation cost of each garbage treatment station, and the unit benefit generated by each garbage treatment station for processing each category of garbage The corresponding weight assessment value and the environmental pollution index generated by each garbage treatment station in treating various types of garbage are used to determine the environmental benefits of each garbage treatment station in treating the garbage on the garbage vehicle; the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit are obtained respectively, and the scheduling priority value of each garbage treatment station in treating the garbage on the garbage vehicle is determined by using the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit and the timeliness index, economic benefit and environmental benefit corresponding to each garbage treatment station, and the garbage treatment station with the highest scheduling priority value is used as the target treatment station; the navigation route corresponding to the target treatment station is determined and sent to the garbage vehicle, so that the garbage vehicle transports the garbage to the target treatment station according to the navigation route.

[0011] In a possible implementation, when identifying a file name, the file guide processing module is specifically configured to:

[0012] Get the file name;

[0013] Perform word segmentation on the file name to obtain multiple words;

[0014] Extract keywords from the multiple words to obtain multiple keywords;

[0015] The extracted keywords are matched with the vocabulary corresponding to each preset recognition result, and the preset recognition result with the highest matching degree is used as the recognition result of the new file.

[0016] In a possible implementation, when determining the navigation route corresponding to the target processing station, the scheduling module is specifically configured to:

[0017] Obtaining a first current location of the garbage truck and a second location of the target processing station;

[0018] Get pre-made maps;

[0019] A navigation route corresponding to a target processing station is generated according to the first location, the second location, and the prefabricated map.

[0020] In a possible implementation, when acquiring a video of a garbage truck collecting garbage, the classification verification module is specifically configured to:

[0021] When the garbage truck lifts the garbage can containing garbage, the video collection starts; and when the garbage truck puts down the garbage can, the video collection stops;

[0022] The type positioning key frames are two frames in the first M frames of the video; wherein M is a positive integer.

[0023] In one possible implementation, the weight assessment model determines the weight assessment value according to the height of the garbage in the garbage collector.

[0024] In a possible implementation, the early warning interaction module is further configured to:

[0025] When the total weight in P consecutive time periods is less than the third preset weight of the corresponding garbage category, a praise message is displayed and sent to the management and control end; the praise message includes the category of garbage and the weight of garbage lower than the corresponding third preset weight; wherein P is a positive integer.

[0026] In a possible implementation, the scheduling module is further configured to:

[0027] Get the processing parameters input by the user;

[0028] Stores processing parameters entered by the user.

[0029] According to another aspect of the present disclosure, a dynamic garbage classification, collection, transfer and processing method is provided, comprising:

[0030] Importing a new file and identifying the file name; if the identification result indicates that the new file is a processing performance file for a waste treatment station, reading and identifying the read file content, extracting and storing the processing parameters of the waste treatment station; wherein the processing parameters include: the waste treatment station's processing efficiency for each type of waste, the weight of each type of waste to be processed, the unit processing cost of processing each type of waste, the environmental pollution value generated by processing each type of waste, the unit benefit generated by processing each type of waste, and the location of the waste treatment station; if the identification result indicates that the new file is a waste classification instruction file, comparing the new waste classification indicator file with the stored historical waste classification indicator file to obtain difference text; identifying the difference text, and if the difference text indicates that a new category has been added to a waste category, obtaining an image of the new category from the Internet, rotating and / or scaling the obtained image; using the image obtained from the Internet and the rotated and / or scaled image as an initial sample training set and storing the image; sending instruction information to a display module so that the display module displays the added new category and information forming the initial sample training set, and allowing a user to train a target verification model based on the initial sample training set;

[0031] Obtain a video of a garbage truck collecting garbage, extract type positioning key frames and classification verification key frames from the video file, wherein the type positioning key frames include at least two frames, and the classification verification key frames include multiple key frames randomly selected from frames after a predetermined number of frames after the type positioning key frame in the video; input the type positioning key frames into a trained classification model, use the classification model to determine the garbage category corresponding to each type positioning key frame, and when the garbage category corresponding to each type positioning key frame is the same, use the garbage category determined by the classification model as the target garbage category; determine a target verification model that matches the target garbage category, and input the classification verification key frames into the trained target verification model, and use the target verification model to determine the proportion of garbage belonging to the target garbage type in each key frame; calculate the average of the proportions corresponding to each key frame, and when the average is greater than a preset threshold, determine that the currently collected garbage classification is qualified; wherein different categories of garbage correspond to different verification models;

[0032] If the garbage classification is qualified, images of garbage collectors of each category on the garbage truck are obtained, and the images corresponding to the garbage collectors of each category are respectively input into the corresponding weight assessment model, and the received images are processed using the weight assessment model to obtain a weight assessment value of each category of garbage. If the weight assessment value of each category of garbage is greater than a first preset weight, the weight assessment value corresponding to each category of garbage is input into the scheduling module and the early warning interaction module; wherein different categories of garbage correspond to different weight assessment models;

[0033] The system stores the total weight of each type of garbage collected by the garbage truck during each time period, and generates and displays a statistical chart based on the stored total weight of each type of garbage and each time period. Furthermore, if the total weight during N consecutive time periods exceeds a second preset weight for the corresponding garbage category, the system displays and sends an early warning message to the control terminal. The early warning message includes the category of excess garbage and the weight of the garbage exceeding the corresponding second preset weight. N is a positive integer.

[0034] Obtain the processing parameters of each garbage treatment station, and determine the transportation cost and transportation time of each garbage treatment station according to the location of each garbage treatment station; determine the timeliness index of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the processing efficiency of each category of garbage at each garbage treatment station, the weight of each category of garbage to be processed, and the transportation time of each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the unit processing cost of each category of garbage at each garbage treatment station, the transportation cost of each category of garbage at each garbage treatment station, and the unit benefit generated by each category of garbage at each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the unit processing cost of each category of garbage at each garbage treatment station, the transportation cost of each category of garbage at each garbage treatment station, and the unit benefit generated by each category of garbage at each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage The weight assessment value and the environmental pollution index generated by each garbage treatment station in treating various types of garbage are used to determine the environmental benefits of each garbage treatment station in treating the garbage on the garbage vehicle; the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit are obtained respectively, and the scheduling priority value of each garbage treatment station in treating the garbage on the garbage vehicle is determined respectively using the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit and the timeliness index, economic benefit and environmental benefit corresponding to each garbage treatment station, and the garbage treatment station with the highest scheduling priority value is used as the target treatment station; the navigation route corresponding to the target treatment station is determined and sent to the garbage vehicle, so that the garbage vehicle transports the garbage to the target treatment station according to the navigation route.

[0035] The dynamic garbage classification, collection, and transportation processing system and method disclosed herein utilizes a file reading processing module to not only update the processing parameters of the garbage processing station, but also to form a sample data set adapted to the current scenario based on the latest garbage classification instruction file. Using this data set to train a verification model can improve the accuracy of garbage classification quality monitoring, which is beneficial to improving the effectiveness of garbage classification processing. At the same time, the scheduling module performs scheduling based on the updated processing parameters of the garbage processing station, scheduling garbage vehicles based on the current performance of each garbage processing station. This not only effectively improves the efficiency of garbage classification and transportation, but also maximizes the dual improvement of environmental and economic benefits. It also enables flexible configuration of classification and transportation plans based on scenario requirements, improving the scenario adaptability of the plan. The classification verification module disclosed herein extracts type positioning keyframes and classification verification keyframes, and utilizes a classification model to process the type positioning keyframes to identify garbage categories. Based on the identification, a verification model matching the garbage category is enabled to process the classification verification keyframes, enabling monitoring of garbage classification quality. The keyframes and deep learning methods are used here to effectively improve the efficiency and accuracy of garbage classification quality monitoring, providing strong support for subsequent effective garbage processing. The weight assessment module of the present disclosure uses images from the garbage collector to quickly and accurately determine the weight of each category of garbage on the garbage truck. Once the weight of each category of garbage reaches a predetermined value, it sends information to the scheduling module and the early warning interaction module for garbage truck scheduling and statistical chart display. This effectively avoids vehicle scheduling when garbage trucks are not fully loaded, saving garbage transfer and processing costs. The early warning interaction module of the present disclosure can not only display statistical charts of the total weight of each type of garbage in each time period, but also issue an early warning if the garbage weight exceeds the specified value for multiple consecutive time periods. This allows relevant departments or staff to quickly and accurately observe the changing trend of garbage weight and control the generation of garbage at the source.

[0036] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0038] Figure 1 It is a structural diagram of the dynamic garbage classification, collection, transfer and processing system according to the present disclosure;

[0039] Figure 2 It is a flow chart of the dynamic garbage classification, collection, transfer and processing method disclosed in the present invention. DETAILED DESCRIPTION

[0040] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0041] The present disclosure is based on the defects of the current dynamic garbage classification, collection, transfer and treatment scheme, such as low classification and transfer efficiency; low flexibility, inability to flexibly configure the classification and transfer scheme according to the scene requirements, resulting in poor scene adaptability; the transfer scheduling cannot be carried out according to the specific conditions of each garbage treatment station, and the inability to achieve dual guarantees of efficiency and benefits; poor garbage classification quality, which affects the garbage treatment effect. A dynamic garbage classification, collection, transfer and treatment system and method are provided. The present disclosure utilizes a file reading processing module to not only update the processing parameters of the garbage treatment station, but also to form a sample data set adapted to the current scene based on the latest garbage classification instruction file. The verification model is trained using the data set, which can improve the accuracy of garbage classification quality monitoring and is conducive to improving the effect of garbage classification treatment. At the same time, the scheduling module performs scheduling in combination with the updated processing parameters of the garbage treatment station, and realizes the scheduling of garbage vehicles according to the current performance of each garbage treatment station, which not only effectively improves the efficiency of garbage classification and transfer, but also can maximize the dual improvement of environmental benefits and economic benefits, and realizes the flexible configuration of classification and transfer schemes according to scene requirements, thereby improving the scene adaptability of the scheme. The classification verification module of the present disclosure extracts type positioning keyframes and classification verification keyframes, and uses a classification model to process the type positioning keyframes to achieve garbage category identification; based on the identification, the verification model matching the garbage category is activated to process the classification verification keyframes, realizing garbage classification quality monitoring. The use of keyframes and deep learning methods here effectively improves the efficiency and accuracy of garbage classification quality monitoring, providing strong support for subsequent effective garbage disposal. The weight assessment module of the present disclosure uses images from the garbage collector to quickly and accurately determine the weight of each category of garbage on the garbage truck. When the weight of each category of garbage reaches a predetermined value, it sends information to the scheduling module and the early warning interaction module to schedule garbage trucks and display statistical charts. This effectively avoids vehicle scheduling when the garbage truck is not full, saving garbage transfer and processing costs. The early warning interaction module of the present disclosure can not only display statistical charts of the total weight of each type of garbage in each time period, but also issue an early warning if the garbage weight exceeds the specified value for multiple consecutive time periods, so that relevant departments or staff can quickly and accurately observe the changing trend of garbage weight and control garbage generation from the source.

[0042] The technical solution of the present disclosure is described below through specific embodiments.

[0043] like Figure 1 As shown, it is a structural diagram of the dynamic garbage classification, collection, transfer and processing system of this embodiment. Specifically, the dynamic garbage classification, collection, transfer and processing system of this embodiment includes a file reading and processing module 101, a classification verification module 102, a weight assessment module 103, an early warning interaction module 104, and a scheduling module 105.

[0044] The file reading and processing module 101 is used to import a new file and identify the file name. When the identification result indicates that the new file is a processing performance file of a garbage processing station, the file content is read and identified, and the processing parameters of the garbage processing station are extracted and stored. The processing parameters include: the processing efficiency of the garbage processing station for each type of garbage, the weight of each type of garbage to be processed, the unit processing cost of processing each type of garbage, the environmental pollution value generated by processing each type of garbage, the unit benefit generated by processing each type of garbage, and the location of the garbage processing station. When the identification result indicates that the new file is a garbage classification instruction file, the processing parameters are extracted and stored. In this case, the new garbage classification index file is compared with the stored historical garbage classification index file to obtain a difference text; the difference text is identified, and when the difference text represents that a new category has been added to a garbage category, a picture of the new category is obtained from the Internet, and the obtained picture is rotated and / or scaled; the picture obtained from the Internet and the rotated and / or scaled picture are used as an initial sample training set and stored; an instruction information is sent to a display module to enable the display module to display the added new category and the information forming the initial sample training set, and to enable the user to train the target verification model according to the initial sample training set.

[0045] When identifying a file name, the file reading processing module 101 is specifically used to: obtain the file name; perform word segmentation processing on the file name to obtain multiple words; extract keywords from the multiple words to obtain multiple keywords; match the extracted keywords with the vocabulary corresponding to each preset recognition result, and use the preset recognition result with the highest matching degree as the recognition result of the new file.

[0046] The above-mentioned word libraries corresponding to the respective preset recognition results are pre-set. The above-mentioned garbage classification instruction file may be an official document.

[0047] In some embodiments, the user labels the initial sample training set and adds some interference pictures to form a final sample training set, and then uses the final sample training set to train the verification model, which can effectively improve the accuracy of model recognition.

[0048] The file reading processing module 101 can specifically implement the above functions by using machine learning, deep learning and other methods.

[0049] The classification verification module 102 is used to obtain a video of a garbage truck collecting garbage, extract type positioning key frames and classification verification key frames from the video file, wherein the type positioning key frames include at least two frames, and the classification verification key frames include multiple key frames randomly selected from the frames after a predetermined number of frames after the type positioning key frame in the video; input the type positioning key frames into a trained classification model, use the classification model to determine the garbage category corresponding to each type positioning key frame, and when the garbage category corresponding to each type positioning key frame is the same, use the garbage category determined by the classification model as the target garbage category; determine a target verification model that matches the target garbage category, and input the classification verification key frames into the trained target verification model, use the target verification model to determine the proportion of garbage belonging to the target garbage type in each key frame; calculate the average of the proportions corresponding to each key frame, and when the average is greater than a preset threshold, determine that the currently collected garbage classification is qualified; wherein different categories of garbage correspond to different verification models.

[0050] When obtaining a video of a garbage truck collecting garbage, the classification verification module 102 is specifically used to: start collecting video when the garbage truck lifts a garbage can containing garbage; and stop collecting video when the garbage truck puts down the garbage can; the type positioning key frames are two frames in the first M frames of the video; where M is a positive integer.

[0051] The above-mentioned type of positioning key frame is an image of a trash can containing trash. The classification model uses the identification information on the trash can, or can determine the type of trash based on the trash can.

[0052] The aforementioned classification verification keyframes are images captured as garbage is being dumped from a trash can into the garbage truck's garbage collector. The greater the number of classification verification keyframes, the higher the verification accuracy. The number of classification verification keyframes can be determined based on actual circumstances. For example, the number of classification verification keyframes can be half the total number of frames in the captured video.

[0053] The classification model was trained using sample data from trash bins containing different types of garbage. The verification model is tailored to the garbage category, meaning different types of garbage are verified using different verification models. This design takes into account the significant differences in appearance and other aspects of different types of garbage. Using matching verification models effectively ensures accuracy. The training process also uses sample images of matching garbage types.

[0054] The weight assessment module 103 is used to obtain images of garbage collectors of various categories on the garbage truck when the garbage classification is qualified, and input the images corresponding to the garbage collectors of various categories into the corresponding weight assessment models respectively, and use the weight assessment models to process the received images to obtain the weight assessment value of each category of garbage. When the weight assessment value of each category of garbage is greater than a first preset weight, the weight assessment value corresponding to each category of garbage is input into the scheduling module and the early warning interaction module; wherein, different categories of garbage correspond to different weight assessment models.

[0055] The weight assessment model determines the weight of the garbage based on its height in the garbage collector. In addition to height, the weight assessment model can also combine information such as density and moisture content of different types of garbage to determine the weight assessment.

[0056] The weight estimation model is trained using sample images of garbage collectors containing garbage of varying heights and low levels.

[0057] The early warning interaction module 104 is used to store the total weight of each type of garbage collected by the garbage truck in each time period, and to generate and display statistical charts based on the stored total weight of each type of garbage and each time period; and, if the total weight in N consecutive time periods is greater than the second preset weight of the corresponding garbage category, to display and send an early warning message to the management and control end; the early warning message includes the category of excess garbage and the weight of the garbage exceeding the corresponding second preset weight; wherein N is a positive integer.

[0058] The early warning interaction module 104 is also used to: when the total weight in P consecutive time periods is less than the third preset weight of the corresponding garbage category, display and send a praise message to the management and control end; the praise message includes the category of garbage and the weight of garbage lower than the corresponding third preset weight; where P is a positive integer.

[0059] Statistical charts can be used to intuitively and quickly observe the changing trends in the weight of various types of garbage in different time periods, which is beneficial for relevant departments to carry out management and control, such as through bonuses or fines.

[0060] The scheduling module 105 is used to obtain the processing parameters of each garbage treatment station, and determine the transportation cost and transportation time of each garbage treatment station according to the location of each garbage treatment station; determine the timeliness index of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each type of garbage, the processing efficiency of each type of garbage at each garbage treatment station, the weight of each type of garbage to be processed, and the transportation time of each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each type of garbage, the unit processing cost of each garbage treatment station for processing each type of garbage, the transportation cost of each garbage treatment station, and the unit benefit generated by each garbage treatment station for processing each type of garbage; and determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each type of garbage, the unit processing cost of each garbage treatment station for processing each type of garbage, the transportation cost of each garbage treatment station, and the unit benefit generated by each garbage treatment station for processing each type of garbage. The weight assessment value corresponding to the garbage and the environmental pollution index generated by each garbage treatment station in treating each type of garbage are used to determine the environmental benefits of each garbage treatment station in treating the garbage on the garbage vehicle; the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit are obtained respectively, and the scheduling priority value of each garbage treatment station in treating the garbage on the garbage vehicle is determined respectively using the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit and the timeliness index, economic benefit and environmental benefit corresponding to each garbage treatment station, and the garbage treatment station with the highest scheduling priority value is used as the target treatment station; the navigation route corresponding to the target treatment station is determined and sent to the garbage vehicle, so that the garbage vehicle transports the garbage to the target treatment station according to the navigation route.

[0061] When determining the navigation route corresponding to the target processing station, the scheduling module 105 is specifically used to: obtain the current first position of the garbage truck and the second position of the target processing station; obtain a prefabricated map; and generate the navigation route corresponding to the target processing station based on the first position, the second position and the prefabricated map.

[0062] The scheduling module 105 is further used to: obtain the processing parameters input by the user through the interactive port; and store the processing parameters input by the user. Another solution for updating the processing parameters is provided here.

[0063] During the scheduling process, the scheduling module 105 utilizes factors such as the processing efficiency of each garbage treatment station for each type of garbage, the weight of each type of garbage to be processed, the unit processing cost of processing each type of garbage, the environmental pollution value generated by processing each type of garbage, the unit benefit generated by processing each type of garbage, and the location of the garbage treatment station. It not only achieves scheduling and allocation that takes into account both environmental and economic benefits, but also effectively guarantees the efficiency of garbage treatment.

[0064] Based on the same inventive concept, the present disclosure provides a flow chart of a dynamic garbage classification, collection, transfer and processing method. The steps performed by the method are the same or similar to those of the above system, so similar parts are not repeated here. Figure 2 As shown, the dynamic garbage classification, collection, transfer and processing method of this embodiment includes:

[0065] S210, intelligently process various files to update or store the processing parameters of the garbage treatment station, or form an initial sample training set for training and verification models: import a new file and identify the file name. When the identification result indicates that the new file is a processing performance file of the garbage treatment station, read the file content, identify the read file content, extract and store the processing parameters of the garbage treatment station; wherein the processing parameters include: the processing efficiency of the garbage treatment station for various types of garbage, the weight of various types of garbage to be processed, the unit processing cost of processing various types of garbage, the environmental pollution value generated by processing various types of garbage, the unit benefit generated by processing various types of garbage, and the location of the garbage treatment station; in the identification result, In the case where the new file is characterized as a garbage classification indication file, the new garbage classification index file is compared with the stored historical garbage classification index file to obtain a difference text; the difference text is identified, and in the case where the difference text represents that a new category has been added to a garbage category, a picture of the new category is obtained from the Internet, and the obtained picture is rotated and / or scaled; the picture obtained from the Internet, the rotated and / or scaled picture is used as an initial sample training set and stored; an indication information is sent to the display module to enable the display module to display the added new category and the information forming the initial sample training set, and to enable the user to train the corresponding verification model according to the initial sample training set.

[0066] S220, determining the type of garbage and conducting garbage classification quality verification: obtaining a video of a garbage truck collecting garbage, extracting type positioning keyframes and classification verification keyframes from the video file, wherein the type positioning keyframes include at least two frames, and the classification verification keyframes include multiple keyframes randomly selected from frames after a predetermined number of frames after the type positioning keyframe in the video; inputting the type positioning keyframes into a trained classification model, using the classification model to determine the garbage category corresponding to each type positioning keyframe, and when the garbage categories corresponding to each type positioning keyframe are the same, using the garbage category determined by the classification model as the target garbage category; determining a target verification model that matches the target garbage category, and inputting the classification verification keyframes into the trained target verification model, using the target verification model to determine the proportion of garbage belonging to the target garbage type in each keyframe; calculating the average of the proportions corresponding to each keyframe, and when the average is greater than a preset threshold, determining that the currently collected garbage classification is qualified; wherein different categories of garbage correspond to different verification models;

[0067] S230, garbage weight assessment and garbage classification processing scheduling: If the garbage classification is qualified, obtain images of the garbage collectors of each category on the garbage truck, and input the images corresponding to the garbage collectors of each category into the corresponding weight assessment model. Use the weight assessment model to process the received images to obtain the weight assessment value of each category of garbage. If the weight assessment value of each category of garbage is greater than a first preset weight, execute the following steps:

[0068] The system stores the total weight of each type of garbage collected by the garbage truck during each time period, and generates and displays a statistical chart based on the stored total weight of each type of garbage and each time period. Furthermore, if the total weight during N consecutive time periods exceeds a second preset weight for the corresponding garbage category, the system displays and sends an early warning message to the control terminal. The early warning message includes the category of excess garbage and the weight of the garbage exceeding the corresponding second preset weight. N is a positive integer.

[0069] Obtain the processing parameters of each garbage treatment station, and determine the transportation cost and transportation time of each garbage treatment station according to the location of each garbage treatment station; determine the timeliness index of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the processing efficiency of each category of garbage at each garbage treatment station, the weight of each category of garbage to be processed, and the transportation time of each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the unit processing cost of each category of garbage at each garbage treatment station, the transportation cost of each category of garbage at each garbage treatment station, and the unit benefit generated by each category of garbage at each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the unit processing cost of each category of garbage at each garbage treatment station, the transportation cost of each category of garbage at each garbage treatment station, and the unit benefit generated by each category of garbage at each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage The weight assessment value and the environmental pollution index generated by each garbage treatment station in treating various types of garbage are used to determine the environmental benefits of each garbage treatment station in treating the garbage on the garbage vehicle; the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit are obtained respectively, and the scheduling priority value of each garbage treatment station in treating the garbage on the garbage vehicle is determined respectively using the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit and the timeliness index, economic benefit and environmental benefit corresponding to each garbage treatment station, and the garbage treatment station with the highest scheduling priority value is used as the target treatment station; the navigation route corresponding to the target treatment station is determined and sent to the garbage vehicle, so that the garbage vehicle transports the garbage to the target treatment station according to the navigation route.

[0070] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0071] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0072] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0073] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0074] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0075] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0076] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0077] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A dynamic garbage classification, collection, transfer and processing system, characterized in that: include: The file reading and processing module is used to import a new file and identify the file name. When the identification result indicates that the new file is a processing performance file of a garbage processing station, the file content is read and identified, and the processing parameters of the garbage processing station are extracted and stored. The processing parameters include: the processing efficiency of the garbage processing station for various types of garbage, the weight of various types of garbage to be processed, the unit processing cost of processing various types of garbage, the environmental pollution value generated by processing various types of garbage, the unit benefit generated by processing various types of garbage, and the location of the garbage processing station. When the identification result indicates that the new file is a garbage classification instruction file, , comparing the new garbage classification index file with the stored historical garbage classification index file to obtain a difference text; identifying the difference text, and when the difference text indicates that a new category has been added to a garbage category, obtaining a picture of the new category from the Internet, and rotating and / or scaling the obtained picture; using the picture obtained from the Internet and the rotated and / or scaled picture as an initial sample training set and storing the picture; sending an instruction message to a display module so that the display module displays the added new category and information forming the initial sample training set, and allowing a user to train a corresponding verification model based on the initial sample training set; A classification verification module is used to obtain a video of a garbage truck collecting garbage, extract type positioning key frames and classification verification key frames from the video file, wherein the type positioning key frames include at least two frames, and the classification verification key frames include multiple key frames randomly selected from frames after a predetermined number of frames after the type positioning key frame in the video; input the type positioning key frames into a trained classification model, use the classification model to determine the garbage category corresponding to each type positioning key frame, and when the garbage category corresponding to each type positioning key frame is the same, use the garbage category determined by the classification model as the target garbage category; determine a target verification model that matches the target garbage category, and input the classification verification key frames into the trained target verification model, use the target verification model to determine the proportion of garbage belonging to the target garbage type in each key frame; calculate the average of the proportions corresponding to each key frame, and when the average is greater than a preset threshold, determine that the currently collected garbage classification is qualified; wherein different categories of garbage correspond to different verification models; A weight assessment module is configured to, if the garbage classification is qualified, obtain images of the garbage collectors of each category on the garbage truck, input the images corresponding to the garbage collectors of each category into the corresponding weight assessment model, process the received images using the weight assessment model to obtain a weight assessment value for each category of garbage, and input the weight assessment value corresponding to each category of garbage into the scheduling module and the early warning interaction module if the weight assessment value of each category of garbage is greater than a first preset weight; wherein different weight assessment models correspond to different categories of garbage; An early warning interaction module is configured to store the total weight of each type of garbage collected by the garbage truck during each time period, and to generate and display statistical charts based on the stored total weight of each type of garbage collected and the time period; and, if the total weight collected during N consecutive time periods exceeds a second preset weight for the corresponding type of garbage collected, display and send an early warning message to the control terminal; the early warning message includes the type of excess garbage collected and the weight of the garbage collected exceeding the corresponding second preset weight; wherein N is a positive integer; The scheduling module is used to obtain the processing parameters of each garbage treatment station, and determine the transportation cost and transportation time of each garbage treatment station according to the location of each garbage treatment station; combine the weight evaluation value corresponding to each category of garbage, the processing efficiency of each category of garbage at each garbage treatment station and the weight of each category of garbage to be processed, and the transportation time of each garbage treatment station to determine the timeliness index of each garbage treatment station in processing the garbage on the garbage truck; combine the weight evaluation value corresponding to each category of garbage, the unit processing cost of each garbage treatment station for processing each category of garbage, the transportation cost of each garbage treatment station, and the unit benefit generated by each garbage treatment station for processing each category of garbage, to determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck; combine the weight evaluation value corresponding to each category of garbage, the unit processing cost of each garbage treatment station for processing each category of garbage, the transportation cost of each garbage treatment station, and the unit benefit generated by each garbage treatment station for processing each category of garbage The corresponding weight assessment value and the environmental pollution index generated by each garbage treatment station in treating various types of garbage are used to determine the environmental benefits of each garbage treatment station in treating the garbage on the garbage vehicle; the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit are obtained respectively, and the scheduling priority value of each garbage treatment station in treating the garbage on the garbage vehicle is determined by using the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit and the timeliness index, economic benefit and environmental benefit corresponding to each garbage treatment station, and the garbage treatment station with the highest scheduling priority value is used as the target treatment station; the navigation route corresponding to the target treatment station is determined and sent to the garbage vehicle, so that the garbage vehicle transports the garbage to the target treatment station according to the navigation route.

2. The system according to claim 1, wherein: When identifying the file name, the file reading processing module is specifically used to: Get the file name; Perform word segmentation on the file name to obtain multiple words; Extract keywords from the multiple words to obtain multiple keywords; The extracted keywords are matched with the vocabulary corresponding to each preset recognition result, and the preset recognition result with the highest matching degree is used as the recognition result of the new file.

3. The system according to claim 1, wherein: When determining the navigation route corresponding to the target processing station, the scheduling module is specifically used to: Obtaining a first current location of the garbage truck and a second location of the target processing station; Get pre-made maps; A navigation route corresponding to a target processing station is generated according to the first location, the second location, and the prefabricated map.

4. The system according to claim 1, wherein: When obtaining a video of a garbage truck collecting garbage, the classification verification module is specifically used to: When the garbage truck lifts the garbage can containing garbage, the video collection starts; and when the garbage truck puts down the garbage can, the video collection stops; The type positioning key frames are two frames in the first M frames of the video; wherein M is a positive integer.

5. The system according to claim 1, wherein: The weight estimation model determines a weight estimation value based on the height of the garbage in the garbage collector.

6. The system according to claim 1, wherein: The early warning interaction module is also used for: When the total weight in P consecutive time periods is less than the third preset weight of the corresponding garbage category, a praise message is displayed and sent to the management and control end; the praise message includes the category of garbage and the weight of garbage lower than the corresponding third preset weight; wherein P is a positive integer.

7. The system according to claim 1, wherein: The scheduling module is also used to: Get the processing parameters input by the user; Stores processing parameters entered by the user.

8. A dynamic garbage classification, collection, transfer and processing method, characterized in that: include: Importing a new file and identifying the file name; if the identification result indicates that the new file is a processing performance file of a waste treatment station, reading and identifying the read file content, extracting and storing the processing parameters of the waste treatment station; wherein the processing parameters include: the processing efficiency of the waste treatment station for each type of waste, the weight of each type of waste to be processed, the unit processing cost of processing each type of waste, the environmental pollution value generated by processing each type of waste, the unit benefit generated by processing each type of waste, and the location of the waste treatment station; if the identification result indicates that the new file is a waste classification instruction file, comparing the new waste classification indicator file with the stored historical waste classification indicator file to obtain difference text; identifying the difference text, if the difference text indicates that a new category has been added to a waste category, obtaining an image of the new category from the Internet, rotating and / or scaling the obtained image; using the image obtained from the Internet and the rotated and / or scaled image as an initial sample training set and storing it; sending instruction information to a display module so that the display module displays the added new category and information forming the initial sample training set, and allowing the user to train the corresponding verification model based on the initial sample training set; Obtain a video of a garbage truck collecting garbage, extract type positioning key frames and classification verification key frames from the video file, wherein the type positioning key frames include at least two frames, and the classification verification key frames include multiple key frames randomly selected from frames after a predetermined number of frames after the type positioning key frames in the video; input the type positioning key frames into a trained classification model, use the classification model to determine the garbage category corresponding to each type positioning key frame, and when the garbage category corresponding to each type positioning key frame is the same, use the garbage category determined by the classification model as the target garbage category; determine a target verification model that matches the target garbage category, and input the classification verification key frames into the trained target verification model, use the target verification model to determine the proportion of garbage belonging to the target garbage type in each key frame; calculate the average of the proportions corresponding to each key frame, and when the average is greater than a preset threshold, determine that the currently collected garbage classification is qualified; wherein different categories of garbage correspond to different verification models; If the garbage classification is qualified, images of garbage collectors of each category on the garbage truck are obtained, and the images corresponding to the garbage collectors of each category are respectively input into the corresponding weight estimation model. The received images are processed by the weight estimation model to obtain the weight estimation value of each category of garbage. If the weight estimation value of each category of garbage is greater than a first preset weight, the following steps are performed: The system stores the total weight of each type of garbage collected by the garbage truck during each time period, and generates and displays a statistical chart based on the stored total weight of each type of garbage and each time period. Furthermore, if the total weight during N consecutive time periods exceeds a second preset weight for the corresponding garbage category, the system displays and sends an early warning message to the control terminal. The early warning message includes the category of excess garbage and the weight of the garbage exceeding the corresponding second preset weight. N is a positive integer. Obtain the processing parameters of each garbage treatment station, and determine the transportation cost and transportation time of each garbage treatment station according to the location of each garbage treatment station; determine the timeliness index of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the processing efficiency of each category of garbage at each garbage treatment station, the weight of each category of garbage to be processed, and the transportation time of each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the unit processing cost of each category of garbage at each garbage treatment station, the transportation cost of each category of garbage at each garbage treatment station, and the unit benefit generated by each category of garbage at each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage, the unit processing cost of each category of garbage at each garbage treatment station, the transportation cost of each category of garbage at each garbage treatment station, and the unit benefit generated by each category of garbage at each garbage treatment station; determine the economic benefit of each garbage treatment station in processing the garbage on the garbage truck by combining the weight evaluation value corresponding to each category of garbage The weight assessment value and the environmental pollution index generated by each garbage treatment station in treating various types of garbage are used to determine the environmental benefits of each garbage treatment station in treating the garbage on the garbage vehicle; the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit are obtained respectively, and the scheduling priority value of each garbage treatment station in treating the garbage on the garbage vehicle is determined respectively using the weight values ​​corresponding to the timeliness index, economic benefit and environmental benefit and the timeliness index, economic benefit and environmental benefit corresponding to each garbage treatment station, and the garbage treatment station with the highest scheduling priority value is used as the target treatment station; the navigation route corresponding to the target treatment station is determined and sent to the garbage vehicle, so that the garbage vehicle transports the garbage to the target treatment station according to the navigation route.

Images