A smart city garbage disposal equipment management method and an internet of things system

Abstract

The embodiment of the present specification provides a smart city garbage treatment equipment management method and an Internet of Things system. The method is executed based on a management platform of a smart city garbage treatment equipment management Internet of Things system. The method comprises the following steps: acquiring a garbage accumulation condition in a target area; determining at least one sub-area in the target area as at least one garbage point to be treated based on the garbage accumulation condition; and determining a garbage truck scheduling scheme of the target area based on the at least one garbage point to be treated. The garbage truck scheduling scheme comprises the type of at least one garbage truck to be scheduled and the departure time of the at least one garbage truck.

Description

Technical Field

[0001] This manual relates to the field of intelligent management of waste treatment equipment, and in particular to a smart city waste treatment equipment management method and Internet of Things system. Background Technology

[0002] With the large influx of people into cities, the amount of garbage generated in cities is also increasing. There are often cases of excessive garbage accumulation at garbage collection points in communities and streets. This not only affects the appearance of the city, but also may breed bacteria and affect people's health if the garbage is left to accumulate for too long.

[0003] Therefore, it is hoped that a smart city waste disposal equipment management method and Internet of Things system can be provided to determine the garbage truck dispatching plan based on the garbage accumulation situation in the target area, so as to dispatch garbage trucks in a timely and flexible manner. This can not only achieve timely cleaning of garbage points in various areas of the city, but also save management costs. Summary of the Invention

[0004] One embodiment of this specification provides a method for managing smart city waste disposal equipment, executed on a management platform of a smart city waste disposal equipment management Internet of Things system. The method includes: acquiring the waste accumulation situation within a target area; based on the waste accumulation situation, identifying at least one sub-area within the target area as at least one waste point to be processed; and based on the at least one waste point to be processed, determining a garbage truck dispatching scheme for the target area. The garbage truck dispatching scheme includes: the type of at least one garbage truck to be dispatched and the departure time of at least one garbage truck.

[0005] One embodiment of this specification provides an IoT system for managing smart city waste disposal equipment, including a user platform, a service platform, a management platform, a sensor network platform, and an object platform. The object platform is used to acquire information on waste accumulation within a target area. The sensor network platform is used to transmit the information on waste accumulation within the target area acquired by the object platform to the management platform. The management platform is used to: determine at least one sub-area within the target area as at least one waste point to be processed based on the waste accumulation information; and determine a garbage truck dispatching plan for the target area based on the at least one waste point to be processed. The garbage truck dispatching plan includes: the type of at least one garbage truck to be dispatched and the departure time of at least one garbage truck. The service platform is used to feed back the garbage truck dispatching plan to the user through the user platform.

[0006] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the aforementioned smart city waste disposal equipment management method. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 This is a diagram of an IoT system for managing smart city waste disposal equipment, based on some embodiments of this specification.

[0009] Figure 2 This is an exemplary flowchart of a smart city waste disposal equipment management method according to some embodiments of this specification;

[0010] Figure 3 This is an exemplary flowchart of a method for determining at least one waste point to be treated, according to some embodiments of this specification;

[0011] Figure 4 This is an exemplary flowchart of a method for determining a garbage truck dispatching scheme for a target area, according to some embodiments of this specification;

[0012] Figure 5 This is an exemplary flowchart of another method for determining a garbage truck dispatch scheme for a target area, as shown in some embodiments of this specification. Detailed Implementation

[0013] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0014] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0015] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0017] Figure 1 This is a diagram of an IoT system for managing smart city waste disposal equipment, based on some embodiments of this specification.

[0018] like Figure 1 As shown, the smart city waste disposal equipment management IoT system 100 may include a user platform 110, a service platform 120, a management platform 130, a sensor network platform 140, and an object platform 150.

[0019] User platform 110 can refer to a user-centric platform that includes acquiring user needs and providing information feedback to users. In some embodiments, user platform 110 can be configured as a terminal device, such as a desktop computer, tablet computer, laptop computer, mobile phone, or other intelligent electronic device that performs data processing and data communication.

[0020] In some embodiments, the user platform 110 can be used to receive garbage truck dispatch plans for various urban areas (e.g., garbage truck type, garbage truck departure time, etc.) sent by the service platform 120, and to send garbage truck dispatch plan query instructions for various urban areas to the service platform 120.

[0021] Service platform 120 can be a platform for receiving and transmitting data and / or information. For example, service platform 120 can be used to receive garbage truck dispatch plans for various urban areas uploaded to the overall database of management platform 130, and to send the garbage truck dispatch plans for various urban areas to user platform 110. In some embodiments, service platform 120 can also be used to receive garbage truck dispatch plan query instructions for various urban areas issued by user platform 110, and to transmit the garbage truck dispatch plan query instructions to the overall database of management platform 130.

[0022] In some embodiments, the service platform 120 may include multiple service sub-platforms, each corresponding to a management sub-platform, wherein the service sub-platforms may be divided based on city regions (e.g., region A, region B, etc.).

[0023] The management platform 130 can refer to a platform that coordinates and integrates the connections and collaborations between various functional platforms, gathers all the information of the Internet of Things (IoT), and provides sensing, management, and control functions for the IoT operating system. For example, the management platform 130 can be used to receive garbage monitoring data (such as garbage accumulation status) uploaded by the sensor network platform 140 from various areas of the city, and then process the garbage monitoring data to determine the garbage truck dispatching plan for each area of ​​the city.

[0024] In some embodiments, the management platform 130 may include a master database and multiple management sub-platforms, with each management sub-platform corresponding to a sensor network sub-platform, wherein the management sub-platforms may be divided based on urban areas.

[0025] In some embodiments, the management sub-platform can receive and process waste monitoring data from various urban areas uploaded by the sensor network sub-platform. After processing, the management sub-platform sends the data to the central database for aggregation and storage. The central database then sends the data to the corresponding service sub-platforms for each area, and the data is transmitted to the user platform 110 via each service sub-platform. In some embodiments, the central database can receive waste truck dispatch plan query instructions from the service sub-platforms for various urban areas and send them to the corresponding management sub-platforms. After receiving the waste truck dispatch plan query instructions, the management sub-platform generates corresponding waste monitoring data query instructions and sends them to the corresponding sensor network sub-platforms.

[0026] The sensor network platform 140 can refer to a platform for processing, storing, and transmitting data and / or information. For example, the sensor network platform 140 can be used to receive waste monitoring data related to various areas of a city acquired by the object platform 150 and upload it to the management platform 130. In some embodiments, the sensor network platform 140 can be configured as a communication network and a gateway.

[0027] In some embodiments, the sensor network platform 140 may include multiple sensor network sub-platforms, each corresponding to a specific object sub-platform, wherein the sensor network sub-platforms may be divided based on urban areas. In some embodiments, each sensor network sub-platform may be configured with an independent gateway.

[0028] In some embodiments, the sensor network sub-platform can be used to receive garbage monitoring-related data from various areas of the city uploaded by the object sub-platform and transmit it to the corresponding management sub-platform; the sensor network sub-platform can also be used to receive the above-mentioned garbage monitoring-related data query instructions issued by the management sub-platform and send them to the corresponding object sub-platform.

[0029] The object platform 150 can be a functional platform for acquiring data and / or information. For example, the object platform can be used to acquire waste monitoring-related data in various areas of a city and transmit it to the management platform 130 via the sensor network platform 140. In some embodiments, the object platform 150 can be configured as a monitoring device (e.g., a camera device), which can be deployed in communities in various areas of the city.

[0030] In some embodiments, the object platform 150 may include multiple object sub-platforms, which may be divided based on urban areas. In some embodiments, the object sub-platform may be used to receive waste monitoring related data query instructions issued by the sensor network sub-platform for various areas of the city, and after obtaining the corresponding waste monitoring related data, upload it to the corresponding management sub-platform via the corresponding sensor network sub-platform.

[0031] In some embodiments of this specification, a smart city waste disposal equipment management IoT system is built based on a five-platform architecture. The architecture design based on each platform can ensure the independence between different types of data, ensure data classification and transmission, traceability, and the classification, issuance, and processing of instructions, making the IoT structure and data processing clear and controllable, and facilitating IoT management and data processing.

[0032] It should be noted that the above description of the IoT system and its modules for managing smart city waste disposal equipment is for convenience only and should not be construed as limiting this specification to the embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. In some embodiments, Figure 1 The user platform, service platform, management platform, sensor network platform, and object platform disclosed herein can be different modules within a single system, or a single module can implement the functions of two or more of the aforementioned modules. For example, modules can share a single storage module, or each module can have its own separate storage module. Such variations are all within the scope of protection of this specification.

[0033] Figure 2 This is an exemplary flowchart illustrating a smart city waste disposal equipment management method according to some embodiments of this specification.

[0034] In some embodiments, process 200 may be executed by management platform 130. For example... Figure 2 As shown, process 200 may include the following steps:

[0035] Step 210: Obtain information on garbage accumulation within the target area.

[0036] The target area can refer to any area within a city. For example, the target area could be a specific community or street within the city. Alternatively, if a city has three areas: Area A, Area B, and Area C, then all three areas can be considered target areas.

[0037] The target area can be determined in various ways, such as random determination. In some embodiments, the target area can be determined based on preset rules, such as using the first letter of the name of each district in a city, and selecting each district as the target area in alphabetical order (a, b, c, etc.). The preset rules can be pre-defined rules and can be determined based on historical experience, algorithms, and other methods.

[0038] Waste accumulation can refer to the amount of waste accumulated. In some embodiments, the management sub-platform can obtain waste accumulation information for various areas of the city based on the object sub-platform. The object sub-platform can be configured as a monitoring device (e.g., a camera device) in a community in various areas of the city to obtain waste accumulation information for each area of ​​the city.

[0039] In some embodiments, the waste accumulation status may further include the historical waste volume of each sub-area within the target area at multiple historical moments. In some embodiments, the target area may be further divided into multiple sub-areas, wherein each sub-area may include one or more waste collection points, waste bins, etc. Further explanation regarding sub-area division can be found at [link to relevant documentation]. Figure 5 And related descriptions. Multiple historical moments can refer to multiple moments prior to this one. Historical garbage volume can refer to the corresponding garbage accumulation volume at multiple historical moments.

[0040] Step 220: Based on the garbage accumulation situation, at least one sub-region within the target area is identified as at least one garbage point to be processed.

[0041] A waste disposal point can refer to a sub-area that requires waste disposal.

[0042] There are several ways to determine the waste disposal sites. In some embodiments, based on the waste accumulation situation, a sub-region where the waste accumulation exceeds a certain threshold can be identified as a waste disposal site. For example, for sub-region A1 in region A, the set accumulation threshold is 2m. 3 However, the actual amount of garbage accumulated in sub-area A1 is 2.5m³. 3 This means that sub-region A1 can be considered a waste collection point to be processed. The accumulation threshold can be a pre-set value, which can be determined based on actual circumstances.

[0043] In some embodiments, the increase in waste in each sub-region at future times can be predicted based on the historical waste volume of each sub-region at multiple historical moments within the target region. Then, based on the historical waste volume and waste increase of each sub-region, at least one waste point to be processed can be determined. For details on how to predict the waste increase based on the historical waste volume of each sub-region and then determine the waste point to be processed based on the historical waste volume and waste increase, please refer to [link to relevant documentation]. Figure 3 And its related descriptions.

[0044] Step 230: Determine the garbage truck dispatching plan for the target area based on at least one garbage collection point.

[0045] A garbage truck dispatching plan refers to relevant schemes for dispatching garbage trucks, including but not limited to the truck's route and dispatch cycle. For example, if a sudden increase in garbage volume is detected at at least one pending garbage collection point, the garbage truck dispatching plan could be a new plan derived from the original plan, such as changing the truck's route or shortening the dispatch time for trucks to the collection points with increased garbage volume. Here, "garbage volume increase" refers to the amount of garbage growth over a period of time, and can be used to reflect the garbage growth situation.

[0046] In some embodiments, a garbage truck dispatching scheme may include: the type of at least one garbage truck to be dispatched, and the departure time of at least one garbage truck.

[0047] In some embodiments, the type of garbage truck can be classified according to its capacity. For example, when 1m 3 <Garbage truck capacity ≤ 3m 3 At that time, the garbage truck type was a small garbage truck; when 3m 3 <Garbage truck capacity ≤ 5m 3 At that time, the garbage truck type is a medium-sized garbage truck; when the garbage truck capacity is >5m³ 3 At that time, the garbage truck was classified as a large garbage truck. Garbage trucks can also be classified in other ways, such as based on their function, but this manual does not limit this classification.

[0048] The departure time of a garbage truck can refer to the time when the truck departs. The departure time of a garbage truck can be determined in various ways, such as based on historical experience.

[0049] In some embodiments, the departure time of the garbage truck can be determined based on the garbage accumulation at the designated garbage collection point. For example, the larger the garbage accumulation at a collection point or the faster the rate of increase in garbage volume, the earlier the garbage truck will depart. Specifically, when it is found that the rate of increase in garbage volume at at least one collection point exceeds a growth rate threshold, the departure time of the garbage truck can be advanced. The growth rate threshold can be determined based on historical experience or other methods.

[0050] In some embodiments, the management platform 130 can determine the garbage truck dispatching scheme in multiple ways. For example, the management sub-platform of the management platform 130 can match garbage monitoring-related data (e.g., garbage accumulation status) of the target area with historical garbage monitoring-related data, then use the historical garbage monitoring-related data with the highest similarity as reference data, and use the historical reference garbage truck dispatching scheme corresponding to the reference data as the garbage truck dispatching scheme for the target area. Here, historical garbage monitoring-related data can refer to a collection of historical garbage monitoring-related data from various areas of the city; reference data can refer to the data in the historical data that has the highest similarity to the garbage monitoring-related data of the target area; and the historical reference garbage truck dispatching scheme can refer to the garbage truck dispatching scheme adopted when the target area is in the reference data state.

[0051] In some embodiments, a waste disposal map corresponding to the target area can be constructed based on at least one waste disposal point, a garbage truck departure point, and road network information of the target area. Then, a garbage truck dispatching scheme for the target area can be determined based on the waste disposal map. For details on how to construct the waste disposal map corresponding to the target area and how to determine the garbage truck dispatching scheme based on the waste disposal map, please refer to [link to relevant documentation]. Figure 4 And its related descriptions.

[0052] In some embodiments, at least one waste management sub-map can be determined based on the waste management map. Each sub-map includes at least one dispatch node. Then, based on the sub-map, a waste truck dispatching scheme for the dispatch nodes is determined, along with the corresponding waste truck dispatching scheme for each sub-map. Finally, based on the dispatching schemes for each sub-map, a waste truck dispatching scheme for the target area is determined. For details on how to determine at least one waste management sub-map based on the waste management map, then determine the corresponding waste truck dispatching scheme, and finally determine the target area's waste truck dispatching scheme, please refer to [link to relevant documentation]. Figure 5 And its related descriptions.

[0053] In some embodiments, process 200 may further include the following steps:

[0054] Step 240: Feed back the garbage truck dispatch plan for the target area to the user.

[0055] In some embodiments, after the management sub-platform of the management platform 130 determines the garbage truck dispatch plan for the target area, it can transmit the garbage truck dispatch plan to the corresponding service sub-platform through the main database. The service sub-platform then sends the garbage truck dispatch plan to the user platform 110. Users can obtain the garbage truck dispatch plan for the target area on the user platform 110.

[0056] In some embodiments of this specification, the IoT system for managing smart city waste disposal equipment enables the determination and transmission of garbage truck dispatching plans for target areas. This facilitates timely and flexible dispatching of garbage trucks based on the garbage accumulation situation within the target area, ensuring urban cleanliness while reducing management costs.

[0057] Figure 3 This is an exemplary flowchart illustrating a method for determining at least one waste point to be treated, according to some embodiments of this specification.

[0058] In some embodiments, process 300 can be executed by management platform 130. For example... Figure 3 As shown, process 300 may include the following steps:

[0059] Step 310: Based on the historical garbage amount of each sub-region in the target region at multiple historical moments, predict the garbage increment of each sub-region at future moments.

[0060] Garbage increment can refer to the increase in garbage amount in a sub-region of a target region at a certain time compared to the garbage amount at the previous time. For example, if the garbage amount at a certain time t1 is V1 and the garbage amount at the next time t2 is V2, the garbage increment ΔV = V2 - V1. In some embodiments, garbage increment can be the increase in garbage amount in each sub-region of the target region at a future time (e.g., one hour in the future) compared to the garbage amount at the current time.

[0061] In some embodiments, the management platform 130 can determine the future garbage increment for each sub-region within the target region based on the historical garbage volume of each sub-region at multiple historical moments. For details regarding historical garbage volume, please refer to [link / reference]. Figure 2 And its description.

[0062] In some embodiments, the management platform 130 can predict the garbage increment of each sub-region in the target area at future times based on a predictive model.

[0063] A predictive model can refer to a model used to predict the increase in garbage. In some embodiments, the predictive model can be a trained machine learning model. For example, the predictive model can include any one or a combination of Deep Neural Networks (DNN) models, Recurrent Neural Networks (RNN) models, Long Short-Term Memory (LSTM) models, or other custom model structures.

[0064] In some embodiments, the input to the prediction model includes the amount of garbage at multiple historical moments and one or more future moments. By processing the garbage amounts at multiple historical moments and one or more future moments, the prediction model outputs the increment of garbage at one or more future moments.

[0065] It should be noted that multiple historical moments, as well as one or more future moments, can be a continuous time series based on a preset time step. For example, a time step of 2 hours can be preset, and a time point is obtained after every 2 hours. Accordingly, the amount of garbage at multiple historical moments can be determined based on the amount of garbage corresponding to each historical time point. Since multiple historical moments can include the current moment, the amount of garbage at multiple historical moments can also include the amount of garbage at the current moment.

[0066] In some embodiments, the prediction model can be trained using the amount of garbage at multiple labeled historical sample moments and one or more future sample moments. The amount of garbage at multiple historical sample moments can be historical garbage data from the past day or the past week. For example, the garbage amounts at 0:00, 2:00, 4:00…16:00 of the past day can be considered as a set of garbage amounts for historical sample moments. Correspondingly, one or more moments from the aforementioned 18:00, 20:00, 22:00, etc., of the past day can be considered as one or more future sample moments corresponding to the multiple historical sample moments. The label can be the increment of garbage amount corresponding to the set of one or more future sample moments (e.g., one or more moments from the aforementioned 18:00, 20:00, 22:00). The labels can be generated manually or through other methods.

[0067] During the initial training of the prediction model, the management platform 130 can input the historical garbage amount of each sample group into the prediction model. Through processing by the prediction model, it outputs the garbage amount increments for multiple future time periods. The management platform 130 can construct a loss function based on the label of the historical garbage amount of each sample group and the output of the prediction model, and iteratively update the parameters of the prediction model based on the loss function until preset conditions are met, resulting in a trained prediction model. These preset conditions can be that the loss function is less than a threshold, convergence, or the training period reaches a threshold.

[0068] In some embodiments, the management platform 130 can also predict the increase in garbage in each sub-region of the target area at future times based on the historical garbage volume and historical pedestrian flow sequence of each sub-region in the target area at multiple historical times.

[0069] Historical pedestrian flow sequences can refer to pedestrian flow at multiple consecutive points in history based on a preset time step. For example, a historical pedestrian flow sequence can be a sequence of pedestrian flow at 0:00, 2:00, 4:00...16:00 on a past day with a time step of 2 hours. In some embodiments, the management platform 130 can determine the historical pedestrian flow sequence based on the historical pedestrian flow data of each sub-area in the target area.

[0070] In some embodiments, the input to the prediction model also includes historical pedestrian flow sequences. The prediction model processes the amount of garbage at multiple historical moments, the historical pedestrian flow sequences, and one or more future moments to output the increase in the amount of garbage at one or more future moments.

[0071] In some embodiments, when training the initial prediction model, the first training samples of the prediction model include the amount of garbage at multiple historical time points, one or more future time points, and a historical pedestrian flow sequence. The amount of garbage at multiple historical time points and the historical pedestrian flow sequence can correspond to the same time series. The first label can be the garbage increment corresponding to one or more future time points. The management platform 130 can input the amount of garbage at multiple historical time points, one or more future time points, and the historical pedestrian flow sequence into the prediction model, and after processing by the prediction model, output the garbage increment for one or more future time points. For details on training the prediction model, please refer to the previous description of the prediction model; it will not be repeated here.

[0072] Some embodiments in this specification demonstrate that predictive models can quickly and efficiently determine the increase in garbage at multiple future time points. Furthermore, incorporating historical pedestrian flow sequences helps to make the results of determining the increase in garbage at multiple future time points more accurate.

[0073] Step 320: Based on the historical waste volume and waste increment of each sub-region, identify at least one waste point to be processed.

[0074] In some embodiments, the management platform 130 can determine the current and / or future waste accumulation amount of each sub-region based on the historical waste amount and waste increment of each sub-region, and identify sub-regions where the waste accumulation amount exceeds the accumulation amount threshold as waste points to be processed. For more information on waste points to be processed, please refer to [link / reference]. Figure 2 And its description.

[0075] In some embodiments, the management platform 130 can determine the processing demand of each sub-region based on the historical waste volume and waste increment of each sub-region, and determine at least one waste point to be processed based on the processing demand of each sub-region.

[0076] The processing demand level refers to the degree to which a sub-area needs garbage collection. The processing demand can be represented by a numerical value, such as 5, 8.5, etc. The higher the value, the higher the processing demand level of the sub-area, and the more garbage collection is needed in that sub-area. The processing demand level can be determined based on a preset algorithm or formula. For example, the processing demand level can be determined based on the following formula (1):

[0077] F= k1*V1 + k2*V2 (1)

[0078] In formula (1), F represents the processing demand, V1 represents the current amount of garbage in the target sub-region, and V2 represents the garbage increment in the target sub-region at future times (e.g., 1 hour or 2 hours in the future). k1 and k2 are preset weight coefficients, which can be preset values, such as k1 = 0.6 and k2 = 0.4.

[0079] In some embodiments, the management platform 130 may identify sub-regions with a processing demand level higher than a preset demand level threshold as waste collection points to be processed. The preset demand level threshold may be determined based on experience or other methods, and is not limited here. For example, the preset demand level threshold may be 5, 10, etc.

[0080] Some embodiments in this specification determine the garbage collection points by processing demand, which helps to better reflect the actual situation when determining whether a target sub-area needs garbage collection.

[0081] In some embodiments, the processing demand threshold is related to the average of the subgraph load values ​​of multiple subgraphs after subgraph partitioning. Each subgraph includes at least one unprocessed garbage point. A higher subgraph load value indicates more complex road conditions and a greater number of unprocessed garbage points within the area corresponding to the subgraph. It is understood that if the subgraph load value of each subgraph is higher, the average subgraph load value of the multiple subgraphs will be higher, resulting in a greater workload or pressure for garbage trucks during garbage collection. For further explanation of subgraphs and subgraph load, see [link to relevant documentation]. Figure 4 And its description.

[0082] In some embodiments, when the average value of the subgraph load is higher, the management platform 130 can reduce the number of unprocessed garbage points corresponding to each subgraph by increasing the processing demand threshold. For example, if the average value of the subgraph load of multiple garbage processing subgraphs is large, the current processing demand threshold can be increased multiple times (e.g., gradually increased to 8, 9, 10, etc.) to gradually reduce the number of unprocessed garbage points in each garbage processing subgraph, thereby gradually reducing the subgraph load value of each garbage processing subgraph. When the average value of the subgraph load of all garbage processing subgraphs decreases to a preset average load threshold, the increase in the processing demand threshold is stopped. At this point, the subgraph load of each garbage processing subgraph in the multiple garbage processing subgraphs reaches the expected value.

[0083] In some embodiments of this specification, when dividing a waste processing subgraph, combining the processing demand threshold with the average value of the subgraph load value of each waste processing subgraph helps to make the subgraph load values ​​of the multiple waste processing subgraphs after division more balanced. This can effectively adjust the number of waste points to be processed in each waste processing subgraph, reduce the waste collection pressure on subsequent garbage trucks, and improve the level of humanization.

[0084] Some embodiments in this specification determine the waste points to be treated by predicting the waste increment of each sub-region at future times, which can make the determination of waste points to be treated more efficient and reduce the human and material costs of manual observation.

[0085] Figure 4 This is an exemplary flowchart of a method for determining a garbage truck dispatching scheme for a target area, according to some embodiments of this specification.

[0086] In some embodiments, process 400 can be executed by management platform 130. For example... Figure 4 As shown, process 400 may include the following steps:

[0087] Step 410: Based on at least one garbage collection point to be processed, garbage truck departure point and road network information of the target area, construct a garbage processing map corresponding to the target area.

[0088] A waste management map can refer to a knowledge graph of the distribution of waste collection points in a target area. It can represent information such as the number of waste collection points in the target area and the distance between them. In some embodiments, the management platform 130 can construct a waste management map corresponding to the target area based on at least one waste collection point, garbage truck departure point, and road network information of the target area.

[0089] like Figure 4 The image shows a waste treatment map 414 constructed by the management platform 130 based on at least one waste disposal point 411, a waste truck departure point 412, and road network information 413 of the target area.

[0090] A waste management map may include multiple nodes. In some embodiments, the nodes of a waste management map include waste dispatch point nodes and intersection nodes.

[0091] Dispatch nodes can be used to characterize garbage truck dispatch points in a target area. Dispatch node nodes can be determined based on information such as the number and location of dispatch points. In some embodiments, such as... Figure 4 As shown, the management platform 130 can determine the departure node based on the garbage truck departure point 412. The departure nodes in the garbage disposal map 414 include: node n1, node n9, and node n12 (e.g., gray solid nodes).

[0092] The characteristics of a vehicle dispatch node include whether it is a garbage collection point, its historical garbage volume, and the expected future garbage volume. Other information may also be included. For example, the characteristics of a dispatch node may include the type, capacity, and number of garbage trucks, as well as the location of the garbage truck dispatch point.

[0093] Intersection nodes can be used to represent street intersections within a target area. Intersection nodes can be determined based on road network information. In some embodiments, such as... Figure 4 As shown, the management platform 130 can determine intersection nodes based on the road network information 413 of the target area. The intersection nodes in the waste disposal map 414 include: node n2, node n4, node n6, etc. (e.g., white hollow nodes).

[0094] The characteristics of an intersection node can include whether it is a waste collection point, its historical waste volume, and the expected increase in waste at future times. Intersection node characteristics can also include other information. For example, intersection node characteristics can include the intersection's location, name, current traffic flow, and whether it is congested.

[0095] A waste management map can include multiple edges. The edges of the waste management map can be used to represent traversable streets in the road network. They can be determined based on actual street information in the road network. In some embodiments, such as... Figure 4 As shown, the management platform 130 can determine multiple edges of the waste disposal map based on the road network information 413 of the target area. The edges in the waste disposal map 414 include: edge A, edge B, edge C, etc.

[0096] The characteristics of edges in a waste management graph can include whether they are waste collection points, historical waste volume, and future waste increments. Other information can also be included. For example, edge characteristics might include length (e.g., L = 100m) and width (e.g., W = 3m). It's important to note that the streets corresponding to edges in the waste management graph can include multiple waste collection areas (e.g., public trash cans). When the current waste volume in a street (e.g., the total waste volume across multiple collection areas) reaches a preset condition for a waste collection point (e.g., the current waste volume reaches a threshold), the street becomes a waste collection point. Correspondingly, the edge corresponding to this street is designated as a waste collection point node, and the characteristic value for whether the edge is a waste collection point is set to 1.

[0097] In some embodiments, when the feature value of whether a given node or edge is a waste point to be processed is 1, the edge or node will be set as a waste point to be processed node, such as nodes n3, n5, n8, and n13 in the waste processing graph. Waste point to be processed nodes can be used to represent at least one waste point to be processed in the target area. Waste point to be processed nodes can be determined based on information such as the number and location of waste points to be processed within the target area.

[0098] The management platform 130 can dynamically adjust the nodes of waste to be processed based on the characteristics of each node and edge in the waste processing graph. The adjustment method can be determined according to the current amount of waste and the waste increment at future time for each node and edge. For example, when the current amount of waste of a node does not meet the conditions for a waste to be processed node (e.g., the current amount of waste is lower than the accumulation threshold), the node is not a waste to be processed node; when the amount of waste of the node at a future time meets the conditions for a waste to be processed node, and the current time reaches the aforementioned future time, then the node can be adjusted to become a waste to be processed node. At this time, the management platform 130 can set the value of whether the node is a waste to be processed in the node characteristics to 1.

[0099] The characteristics of a pending waste collection point node can include various information. For example, the characteristics of a pending waste collection point can include waste quantity information, such as the current waste quantity and the expected increase in waste quantity at future times. The characteristics of a pending waste collection point can also include regional information, such as the region to which the pending waste collection point belongs and its location information. It should be noted that when the current waste quantity of a pending waste collection point decreases below the accumulation threshold, the pending waste collection point is adjusted to a non-pending waste collection point. A non-pending waste collection point can be an intersection node or edge in the corresponding waste processing graph 414. Similarly, if the current waste quantity of an intersection node or edge in the waste processing graph 414 exceeds the accumulation threshold, then that node or edge needs to be adjusted to a pending waste collection point node.

[0100] It should be noted that when an edge in the waste management graph 414 is adjusted to become a waste node to be processed, this waste node can be set as the midpoint of the edge. The characteristics of this waste node can be set according to the characteristics of the original edge. For example, the current waste amount and the future waste increment in the characteristics of the waste node to be processed can be set to the current waste amount and the future waste increment of the original edge. In addition, the original edge is divided into two new edges (for example, each half of the original edge). The characteristics of these two new edges are also adjusted accordingly. For example, the current waste amount and the future waste increment in the characteristics of each of the two new edges can be adjusted to half of the original edge. Other information is also adjusted accordingly. For example, the edge length feature value is adjusted to half of the original edge.

[0101] It should be noted that nodes (e.g., intersection nodes) and nodes of waste to be processed, as well as edges and nodes of waste to be processed, in the waste management graph can transform into each other over time. The management platform 130 adjusts these relationships by setting the value (1 or 0) of the feature of whether a node or edge is a node to be processed.

[0102] In some embodiments, after the waste dispatching scheme is completed (e.g., after the daily waste collection by garbage trucks), the management platform 130 can regenerate a new waste disposal map based on at least one waste disposal point, a waste dispatch point, and road network information of the target area. The management platform 130 can also update the features of nodes (such as dispatch nodes and intersection nodes) and edges in the waste map, and based on the updated waste disposal map, regenerate the waste disposal sub-graph corresponding to the target area (see...). Figure 5 ).

[0103] Step 420: Based on the waste disposal map, determine the waste truck dispatching plan for the target area.

[0104] In some embodiments, the management platform 130 can determine a garbage truck dispatching plan for a target area based on the garbage disposal map 414. For details regarding garbage truck dispatching plans, please refer to [link / reference needed]. Figure 2 And its description.

[0105] In some embodiments, the management platform 130 may determine the garbage truck scheduling scheme based on the scheduling scheme determination model.

[0106] The scheduling scheme determination model can refer to a model used to determine garbage truck scheduling schemes. In some embodiments, the scheduling scheme determination model can be a trained machine learning model. For example, the scheduling scheme determination model can include any one or a combination of recurrent neural network models, convolutional neural networks, or other custom model structures.

[0107] In some embodiments, the scheduling scheme determination model may include a trained graph neural network model. The management platform 130 can input the waste disposal map into the scheduling scheme determination model, process the waste disposal map through the scheduling scheme determination model, and output a waste scheduling scheme from the vehicle dispatch point node.

[0108] In some embodiments, the scheduling scheme determination model can be obtained by training multiple labeled sample waste disposal maps. These sample waste disposal maps can be multiple historical waste disposal maps, and the labels can be determined based on the waste truck scheduling schemes corresponding to the sample waste disposal maps. For example, labels may include the departure point, type, and departure time of the waste trucks, based on the distribution, quantity, and amount of waste to be processed in the sample waste disposal maps. Labels can be added manually or through other methods.

[0109] During the initial training of the scheduling scheme determination model, the management platform 130 can input each sample waste disposal map into the model and output a waste truck scheduling scheme based on the model's processing. The management platform 130 can construct a loss function based on the label of each sample waste disposal map and the output of the scheduling scheme determination model. The parameters of the scheduling scheme determination model are iteratively updated based on the loss function until preset conditions are met, resulting in a trained scheduling scheme determination model. These preset conditions can include the loss function being less than a threshold, convergence, or the training period reaching a threshold.

[0110] Some embodiments in this specification demonstrate that determining waste disposal scheduling schemes through waste disposal maps can make the determination of waste disposal scheduling schemes faster and more efficient.

[0111] Figure 5 This is an exemplary flowchart of another method for determining a garbage truck dispatch scheme for a target area, as shown in some embodiments of this specification.

[0112] In some embodiments, process 500 can be executed by management platform 130. For example... Figure 5 As shown, process 500 may include the following steps:

[0113] Step 510: Based on the waste management map, determine at least one waste management sub-map; each waste management sub-map includes at least one vehicle dispatch node.

[0114] A waste management subgraph can refer to a graph consisting of at least some of the nodes and / or edges of a waste management graph.

[0115] In some embodiments, the management platform 130 can determine at least one waste management sub-map of the waste management map based on urban road network information, physical planning, or administrative planning. For example, if a city includes areas A, B, and C, the management platform 130 can correspondingly divide the waste management map into three waste management sub-maps: one for area A, one for area B, and one for area C.

[0116] In this process, each waste management subgraph in at least one waste management subgraph includes at least one vehicle dispatch node. The vehicle dispatch node can be determined based on the preset waste truck dispatch points (e.g., waste truck parking points, waste management stations) in the urban area corresponding to each waste management subgraph.

[0117] In some embodiments, the management platform 130 may segment the waste treatment map based on a preset sub-graph segmentation method to determine at least one waste treatment sub-graph.

[0118] In some embodiments, the management platform 130 can perform multiple rounds of iterative segmentation of the waste management map based on a preset subgraph segmentation method, and ultimately determine at least one waste management subgraph. For example... Figure 5 As shown, at least one waste treatment sub-graph that is finally determined based on the waste treatment map 511 can be waste treatment sub-graph 512, waste treatment sub-graph 513, or waste treatment sub-graph 514.

[0119] The preset subgraph segmentation method performs multiple rounds of iterative segmentation of the waste management map. Each round of iterative processing may include the following steps S1 to S5:

[0120] Step S1: Based on the vehicle dispatch nodes of the waste processing map, determine at least one initial waste processing sub-map; each initial waste processing sub-map contains one vehicle dispatch node.

[0121] The initial waste management subgraph can refer to the waste management subgraph obtained when the waste management graph is segmented in each iteration. In some embodiments, the management platform 130 can use each of the at least one garbage truck departure points as the starting node or reference node of the corresponding at least one initial waste management subgraph.

[0122] like Figure 5As shown, the vehicle dispatch nodes in the waste processing graph 511 include nodes n1, n9, and n12, which determines three initial waste processing subgraphs. Each initial waste processing subgraph contains at least its corresponding vehicle dispatch node; for example, initial waste processing subgraph 512 includes vehicle dispatch node n9. It can be understood that the number of vehicle dispatch nodes determines the number of initial waste processing subgraphs. For example, the aforementioned three vehicle dispatch nodes determine that the number of initial waste processing subgraphs will be three.

[0123] Step S2: Select the intersection nodes (including intersection nodes that are converted into waste disposal points) in the waste disposal map as nodes to be assigned, and select a target node from the nodes to be assigned based on the preset filtering method;

[0124] A node to be assigned can refer to a node in the waste management graph that has not yet been assigned to the initial waste management subgraph.

[0125] The target node can refer to the node selected from the nodes to be assigned in this round to determine the initial waste processing subgraph to which it belongs.

[0126] In some embodiments, the management platform 130 may select at least one node as the target node from the nodes to be assigned based on a preset strategy. For example, it may select several nodes to be assigned near a certain departure node (e.g., less than a preset distance threshold) as the target node based on a random selection strategy.

[0127] In some embodiments, the management platform 130 may select at least one target node from the nodes to be assigned based on a preset filtering method.

[0128] The preset filtering method can be to select a target node based on the current preferred value of the node to be assigned. The current preferred value is related to the first distance between the node and the initial waste processing subgraph with the smallest current subgraph load value, and the second distance between the previous target node and the node.

[0129] The preference value can be used to determine the probability that a node to be assigned will be selected as a target node. The preference value can be a value in the range [0, 1], such as 0.8. The higher the preference value of a node to be assigned, the higher the priority of that node. The preference value can also be other representations, such as level 1, level 2, level 3, etc. In some embodiments, the management platform 130 can determine the preference value of each node to be assigned based on a first distance between the node to be assigned and the garbage disposal subgraph with the smallest current subgraph load value, and a second distance between the previous target node and the node.

[0130] The subgraph load value refers to the stress load of the current initial waste processing subgraph. It can characterize the complexity of the initial waste processing subgraph and the pressure on the garbage truck's garbage collection work. The subgraph load value can be a single numerical value, such as 4 or 10. The larger the value, the higher the subgraph load value of the corresponding initial waste processing subgraph. The subgraph load value can be determined based on the number of nodes and edges in the current initial waste processing subgraph. As an example only, the subgraph load value can be equal to the sum of the number of unprocessed garbage nodes and edges in a certain initial waste processing subgraph.

[0131] In some embodiments, the subgraph load value may include a first load value and a second load value.

[0132] The first load value can represent the number of unprocessed garbage nodes in the initial garbage processing subgraph, and it can be a numerical value, such as 8. The more unprocessed garbage nodes there are in the initial garbage processing subgraph, the larger the first load value will be. In some embodiments, the first load value can be equal to the number of unprocessed garbage nodes in the initial garbage processing subgraph.

[0133] The second load value can characterize the number of nodes and edges in the initial garbage processing subgraph, and it can be a numerical value, such as 10. The more nodes and edges in the initial garbage processing subgraph, the larger the second load value. In some embodiments, the second load value can be equal to the sum of the number of nodes and edges in the initial garbage processing subgraph.

[0134] In some embodiments, the subgraph load value can be determined based on a first load value and a second load value. For example, the subgraph load value can be determined based on the following formula (2):

[0135] P = k3 * P1 + k4 * P2 (2)

[0136] In formula (2), P represents the subgraph load value of the initial waste treatment subgraph, P1 represents the first load value of the initial waste treatment subgraph, and P2 represents the second load value of the initial waste treatment subgraph; k3 and k4 are preset weight coefficients, for example, k3 = 0.7 and k4 = 0.5.

[0137] In some embodiments, the first distance can be determined based on the distance between the current node to be assigned and the reference node of the initial waste processing subgraph (i.e., the vehicle departure point node of the initial waste processing subgraph). For example, it can be determined based on the sum of the lengths of the edges corresponding to the shortest path connecting the current node to be assigned and the reference node.

[0138] like Figure 5As shown, for the waste processing subgraph 512, the first distance between the node to be assigned n5 and the reference node n9 of the waste processing subgraph 512 can be determined based on the sum of the lengths of edge G and edge N. The length of edge M can be determined by the length feature value (e.g., 200m) in the characteristics of edge M, and the same applies to edge F.

[0139] In some embodiments, the second distance can be determined based on the sum of the lengths of the edges corresponding to the shortest path connecting the current node to be assigned and the previous target node. The previous target node can be the last target node assigned to the initial garbage processing subgraph in the previous round of subgraph partitioning.

[0140] In some embodiments, the management platform 130 further determines the initial waste treatment subgraph with the smallest subgraph load value based on the subgraph load values ​​of each initial waste treatment subgraph, and determines the preferred value of each node to be assigned based on a first distance and a second distance. The smaller the first distance, the larger the preferred value; the larger the second distance, the larger the preferred value. In some embodiments, the management platform 130 can determine a first preferred value based on the first distance of the node to be assigned, determine a second preferred value based on the second distance of the node to be assigned, and then determine the final preferred value of the node to be assigned based on the average of the first and second preferred values.

[0141] In some embodiments, the management platform 130 may sort the preferred values ​​of each node to be assigned (e.g., in descending order) and select the node with the largest preferred value as the target node.

[0142] Some embodiments in this specification, through a preset screening method, can help balance the load of each initial waste treatment subgraph and prevent size imbalances between the initial waste treatment subgraphs.

[0143] Step S3: Determine the initial waste processing subgraph to which the target node belongs based on the objective function value of the target node relative to each initial waste processing subgraph.

[0144] The objective function value can be used to determine the probability that the target node selected in step S2 will ultimately be assigned to one of the initial waste processing subgraphs. The objective function value can be related to the subgraph load value of the initial waste processing subgraph and the first distance between the target node and the initial waste processing subgraph. The smaller the objective function value of the target node relative to an initial waste processing subgraph, the greater the probability that the target node will be assigned to that initial waste processing subgraph.

[0145] In some embodiments, the objective function value is determined based on the subgraph load value and the proximity value. For example, the objective function may be a predefined algorithm or formula. For instance, the objective function may be formula (3) as shown below:

[0146] F = k5*P + k6*d (3)

[0147] The objective function value can be determined based on formula (3). In formula (3), F represents the objective function value, P represents the subgraph load value of the initial waste management subgraph to which the target node is to be assigned, k5 and k6 are preset weight coefficients, which can be preset values. For example, k5 = 0.5, k6 = 0.3; d represents the proximity value, which can be the first distance between the target node and the initial waste management subgraph to which the target node is to be assigned.

[0148] In some embodiments, the management platform 130 can determine the objective function value of the target node when it is assigned to each initial waste treatment subgraph based on formula (3), and assign the target node to the initial waste treatment subgraph corresponding to the smallest objective function value F.

[0149] In some embodiments, the objective function value is also related to the similarity between the future garbage increment of the garbage point to be processed in the initial garbage processing subgraph and the future garbage increment of the target node.

[0150] The similarity of garbage increments can be used to characterize the degree of similarity between the garbage increments of the target node and the garbage points to be processed in the initial garbage processing subgraph. The similarity of garbage increments can be a value in the range [0, 1], and the larger the value, the greater the similarity.

[0151] In some embodiments, the management platform 130 can obtain the garbage increment of each garbage point to be processed in each initial garbage processing subgraph at a future time (e.g., in the next hour), and determine the average value of the garbage increment of all garbage points to be processed in each initial garbage processing subgraph. Then, based on the difference between this average value and the garbage increment of the node to be assigned at a future time (e.g., also in the next hour), the similarity of the garbage increments is determined. The smaller the difference, the greater the similarity of the garbage increments.

[0152] In some embodiments, the management platform 130 may introduce a calculation term for incremental garbage similarity based on the above formula (3) to determine the objective function value. For example, the objective function value may be determined based on the following formula (4):

[0153] F= k5*P +k6*d+k7*(1 / S) (4)

[0154] In formula (4), F represents the objective function value, S represents the similarity between the future garbage increment of the target node and the future garbage increment of the unprocessed garbage point in the initial garbage processing subgraph to which the target node is to be assigned, k7 is a preset weight coefficient, which can be a preset value, for example, k7 = 0.2. k5, P, k6, and d in formula (4) are the same as the corresponding calculation terms in formula (3), and will not be repeated here.

[0155] In some embodiments of this specification, when determining the initial waste processing subgraph to which the target node belongs, the introduction of subgraph load value and proximity value can make the load of multiple waste subgraphs to be processed after segmentation more balanced. In addition, the introduction of waste increment similarity can group nodes with similar waste increments into the same waste processing subgraph as much as possible, which is convenient for the unified scheduling of garbage trucks in the future.

[0156] Step S4: Determine the new target node and repeat the above operation until all nodes to be assigned have determined their initial waste processing subgraph.

[0157] The new target node can refer to the node to be assigned in the current iteration of subgraph segmentation after the previous round of subgraph segmentation. The selection of new target nodes is the same as in step S2.

[0158] In some embodiments, the management platform 130 may repeat the operations of steps S2 and S3 in each iteration, gradually assigning unassigned nodes and edges in the waste processing graph to the target initial waste processing subgraph, until all unassigned nodes in the waste processing graph are assigned to their respective initial waste processing subgraphs, at which point the iteration terminates.

[0159] It should be noted that when a certain edge of the waste management graph (such as...) Figure 5 The two nodes to be assigned connected by edge D) (e.g. Figure 5 Nodes n5 and n2 are assigned to two different garbage processing subgraphs (e.g., ... Figure 5 When considering waste management subgraphs 512 and 513, the management platform 130 can base its decisions on the midpoint of that edge (e.g., midpoint P). m Divide the edge into two segments (e.g., n5-P). m and P m -n2), and divide the two segments into the two waste management subgraphs (e.g., ... Figure 5 Waste processing subgraphs 512 and 513). In this case, if the edge is a waste point to be processed, the waste processing work of the waste point to be processed can belong to the waste processing subgraphs of the two segments of the edge respectively (e.g., Figure 5(Waste disposal sub-graphs 512 and 513) Accordingly, the garbage cleaning work of the streets corresponding to the two segments of this side can be handled by the garbage trucks of the sub-area corresponding to waste disposal sub-graph 512 and the sub-area corresponding to waste disposal sub-graph 513 respectively.

[0160] Step S5: The initial waste processing subgraphs after the aforementioned operations are completed are used as the final waste processing subgraphs.

[0161] like Figure 5 As shown, when the iteration terminates, all nodes and edges in the waste processing graph are divided, thereby determining the nodes and edges contained in the final three waste processing subgraphs, such as waste processing subgraph 512, waste processing subgraph 513 and waste processing subgraph 514.

[0162] It should be noted that the preset subgraph segmentation methods can include segmentation by nodes or segmentation by edges, etc. The preset subgraph segmentation method described above, which uses segmentation by nodes, is only an example and is not intended to limit the scope of the problem.

[0163] Some embodiments in this specification use a preset subgraph segmentation method to automatically segment the waste treatment map, which can improve the efficiency of segmenting waste treatment subgraphs. At the same time, it takes into account the subgraph load during the division of waste treatment subgraphs, which helps to make the divided waste treatment subgraphs more balanced and facilitates a more balanced determination of the waste cleaning workload.

[0164] Step 520: Based on the waste processing subgraph, determine the waste truck dispatching scheme for the waste truck dispatching point corresponding to the dispatching node in the waste processing subgraph, and determine the waste truck dispatching scheme corresponding to the waste processing subgraph.

[0165] The garbage truck dispatch plan at the garbage truck departure point refers to the garbage truck dispatch plan that involves collecting garbage from the departure point. For example... Figure 5 As shown in the waste management sub-graph 512, the waste truck scheduling scheme includes a waste truck scheduling scheme starting from the departure node n9. This waste truck scheduling scheme may include the type, capacity, and departure time of the waste trucks at the waste truck departure point corresponding to the departure node n9.

[0166] In some embodiments, the management platform 130 can determine the garbage truck scheduling scheme corresponding to each garbage processing sub-graph based on information such as the number of garbage truck departure points, the number of garbage points to be processed, the current amount of garbage at each garbage point to be processed, and the distance between multiple garbage points to be processed in at least one garbage processing sub-graph.

[0167] In some embodiments, the garbage truck scheduling scheme further includes garbage truck travel routes. The management platform 130 can determine that the route from the vehicle departure node of the garbage processing sub-map to the garbage points to be processed in the area corresponding to the garbage processing sub-map is the garbage truck travel route; and based on the garbage truck travel route, determine the garbage truck scheduling scheme corresponding to the garbage processing sub-map.

[0168] A garbage truck's route can refer to the path a garbage truck takes from its departure point to at least one waste disposal site. The garbage truck's route can be a sequence of nodes and edges in a waste management subgraph. For example... Figure 5 As shown in the waste treatment sub-graph 512, the garbage truck's route can be n9-n10-n8-n7-n5, etc.

[0169] The route of the garbage truck can be determined based on preset rules. For example, it can be determined according to the pre-set garbage truck routes of the areas corresponding to the garbage treatment sub-map. In some embodiments, the management platform 130 can determine the route based on the shortest path of the garbage truck through all untreated garbage points in the areas corresponding to the garbage treatment sub-map.

[0170] In some embodiments, based on the region corresponding to the waste processing subgraph, the management platform 130 can use the vehicle departure node of the waste processing subgraph as the starting point and perform multiple rounds of traversal operations from this starting point. Each round of traversal includes obtaining all unprocessed waste nodes in the waste processing subgraph, and determining the next unprocessed waste node to be processed based on the current amount of waste, the waste increment at multiple future times, and the distance to the current node for each unprocessed waste node. After this round of traversal is completed, the management platform 130 can use the aforementioned next unprocessed waste node as a new starting point to perform the next round of traversal operations until the order of all unprocessed waste nodes is determined, thus obtaining the garbage truck route.

[0171] In some embodiments, the intersection nodes of the waste treatment subgraph have processing priority values, and the garbage truck travel route can be determined based on the processing priority value of each intersection node, wherein the processing priority value of an intersection node can be determined based on the peak value of the path from the current node to that intersection node.

[0172] The processing priority value of an intersection node can be used to characterize the priority of a garbage truck going to the intersection corresponding to that intersection node. The processing priority value can be a value in the range [0, 1], such as 0.3 or 0.8. The larger the processing priority value of an intersection node, the higher the priority of the garbage truck going to the intersection corresponding to that intersection node.

[0173] In some embodiments, the processing priority of intersection nodes can be preset. For example, the management platform 130 can preset the priority based on information such as the location (e.g., downtown area, suburbs) of each intersection in the target area corresponding to each waste treatment sub-map, road condition information (e.g., busy road section, length, width), and distance from the garbage truck departure point.

[0174] Peak values ​​for a path at an intersection node can be used to characterize traffic flow, the presence of congestion, and the duration of congestion. Peak values ​​can be determined based on historical traffic data from different time periods for that path. For example, management platform 130 can statistically analyze traffic flow (vehicle and pedestrian traffic) at different times of day (e.g., morning, noon, afternoon) over a past period (e.g., six months, one month) and determine peak values ​​based on this traffic flow. It should be noted that peak values ​​can include multiple different values; for example, a peak value could be 0.8 for 8:00-9:00 AM and 0.3 for 12:00-13:00 PM.

[0175] In some embodiments, the management platform 130 can determine the processing priority of the corresponding intersection node based on the peak value of each intersection. The higher the peak value of the path, the lower the processing priority of the intersection node.

[0176] In some embodiments, after determining the processing priority value of each intersection node in the waste disposal subgraph, the management platform 130 can determine the garbage truck's route based on the processing priority value of each intersection node. For example, the management platform 130 can sort the processing priority values ​​of all intersection nodes in the waste disposal subgraph in descending order, and then use the order of the intersection nodes as the order in which the garbage trucks travel, thereby determining the garbage truck's route.

[0177] In some embodiments of this specification, the processing priority value of intersection nodes is determined by the peak value of road traffic. By introducing traffic congestion, the subsequent determination of garbage truck routes can more effectively avoid traffic congestion.

[0178] In some embodiments, the peak value of the path can be correlated with the pedestrian flow sequence.

[0179] Understandably, the greater the pedestrian traffic along a route, the higher the probability of traffic congestion. Furthermore, pedestrian traffic varies at different times of day, and consequently, the probability of traffic congestion also varies at different times of day. In some embodiments, the management platform 130 can determine the peak traffic volume of the route based on a peak traffic prediction model.

[0180] In some embodiments, the peak prediction model can be a trained machine learning model. For example, the prediction model can include any one or a combination of deep neural network models, recurrent neural networks, long short-term memory neural network models, or other custom model structures.

[0181] In some embodiments, the peak traffic prediction model takes as input a sequence of pedestrian flow data from multiple historical moments up to the current moment, and one or more future moments. The peak traffic prediction model processes the pedestrian flow data and the multiple future moments to output the peak traffic values ​​for the paths at those future moments. See also the section on pedestrian flow data from historical moments. Figure 3 And its description.

[0182] In some embodiments, the peak traffic prediction model can be trained using multiple labeled historical pedestrian flow sequences and one or more future sample times. The historical pedestrian flow sequences can be sequences from the past day or the past week. For example, a pedestrian flow sequence constructed from pedestrian flow at 0:00, 2:00, 4:00…16:00 of the past day can be used as the sample pedestrian flow sequence, and 18:00, 20:00, and 22:00 of the past day can be used as one or more future sample times. The label can be the peak value corresponding to one or more future sample times (e.g., 18:00, 20:00, and 22:00 of the past day), where the peak value can be a [0, 1] value determined based on path congestion; for example, a label of 1 indicates congestion, and a label of 0 indicates no congestion. The label can also be determined based on the duration of congestion. For example, a label of 0 indicates no congestion; a label of 1 indicates congestion lasting more than 10 minutes, and the label decreases according to a preset ratio (e.g., decreasing by 0.1 for every minute less congestion), such as a label of 0.5 for 5 minutes of congestion, and so on. Labels can be created manually or through other methods.

[0183] When training the initial peak traffic prediction model, the management platform 130 can input the historical traffic flow sequence of each sample and multiple future time points of the sample into the peak traffic prediction model. Through processing by the peak traffic prediction model, the peak traffic values ​​for the sample at multiple future time points are output. The management platform 130 can construct a loss function based on the label of each sample's historical traffic flow sequence and the output of the peak traffic prediction model, and iteratively update the parameters of the peak traffic prediction model based on the loss function until preset conditions are met and training is complete, resulting in a trained peak traffic prediction model. These preset conditions can be that the loss function is less than a threshold, convergence, or the training period reaches a threshold.

[0184] Some embodiments in this specification use peak prediction models to predict peak values ​​of paths based on pedestrian flow sequences, which can obtain path peak values ​​more quickly and efficiently.

[0185] In some embodiments, in the garbage truck scheduling scheme of each garbage disposal subgraph, the garbage truck departure time is related to the garbage truck's travel route.

[0186] In the garbage truck dispatching plan for each garbage disposal sub-map, the departure time of the garbage truck can be determined based on the total length of the garbage truck's route, the traffic flow and congestion conditions of each road segment it passes through, etc. For example, the longer the total length of the garbage truck's route, the earlier the garbage truck can depart.

[0187] In some embodiments, the management platform 130 can determine the garbage truck departure time in the garbage truck scheduling scheme based on the current garbage volume and garbage increment at each garbage collection point along the garbage truck's travel route. For example, the management platform 130 can obtain the current garbage volume and garbage increment at one or more future times at each garbage collection point along the garbage truck's travel route. If the sum of the current garbage volume at all garbage collection points is larger, the garbage truck departure time can be earlier; conversely, if the sum of the garbage increment at one or more future times at all garbage collection points is larger, the garbage truck departure time can also be earlier.

[0188] In some embodiments of this specification, the departure time of the garbage truck is determined based on the current amount of garbage and the increase in garbage at each garbage collection point along the truck's route, which makes the departure time more targeted.

[0189] Step 530: Based on the garbage truck scheduling scheme corresponding to each garbage disposal sub-map, determine the garbage truck scheduling scheme for the target area.

[0190] In some embodiments, the management platform 130 can determine the garbage dispatching scheme for the sub-regions corresponding to the target area of ​​each garbage disposal sub-map based on the garbage truck dispatching scheme corresponding to each garbage disposal sub-map, and further generate the garbage truck dispatching scheme for the target area. The garbage truck dispatching scheme for the target area may include the garbage truck departure time, garbage truck type, number, and garbage truck route of each sub-region's garbage dispatching scheme. In some embodiments, the management platform 130 can also perform garbage truck allocation based on the garbage disposal progress and garbage disposal time length of each sub-region's garbage dispatching scheme, thereby determining the garbage truck dispatching scheme for the target area. This specification does not limit this aspect.

[0191] Some embodiments in this specification, by segmenting the waste treatment map and determining the garbage truck dispatching scheme for the target area corresponding to the segmented waste treatment sub-map, help to make more detailed arrangements for the garbage truck dispatching scheme of the target area, while also reducing the workload of waste cleaning, making the garbage truck dispatching scheme more reasonable and effective.

[0192] It should be noted that the descriptions of processes 200, 300, 400, and 500 above are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the processes under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0193] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0194] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0195] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0196] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0197] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0198] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0199] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for managing smart city waste disposal equipment, executed on a management platform of a smart city waste disposal equipment management Internet of Things (IoT) system; the method includes: Obtain information on garbage accumulation within the target area; Based on the garbage accumulation situation, at least one sub-region within the target area is identified as at least one garbage point to be processed; Based on the at least one unprocessed waste point, a waste truck dispatching plan for the target area is determined, including: Based on the at least one garbage collection point to be processed, the garbage truck departure point, and the road network information of the target area, a garbage processing map corresponding to the target area is constructed. The nodes of the waste disposal map include vehicle departure nodes and intersection nodes; the vehicle departure node corresponds to the waste truck departure point, and the intersection node corresponds to the street intersection within the target area; The edges of the waste disposal map correspond to the streets within the target area; The node characteristics and edge characteristics of the node include: whether it is a garbage point to be processed, the historical amount of garbage, and the garbage increment at future time. Based on the waste management map, at least one waste management sub-map is determined, including: Based on the vehicle departure node, at least one initial waste processing sub-graph is determined; The intersection node is taken as the node to be assigned. A target node is selected from the nodes to be assigned based on the current preferred value of the node to be assigned. The current preferred value is related to the first distance between the node to be assigned and the initial waste disposal subgraph with the smallest current subgraph load value, and the second distance between the previous target node and the node to be assigned. Based on the objective function value of the target node relative to each of the initial waste processing subgraphs, the initial waste processing subgraph to which the target node belongs is determined. The objective function value is related to the subgraph load value of the initial waste processing subgraph and the first distance between the target node and the initial waste processing subgraph. The subgraph load value is used to characterize the complexity of the initial waste processing subgraph and the pressure of the garbage truck's waste collection work. Each of the at least one waste processing subgraph includes at least one vehicle dispatch node. Based on the waste treatment subgraph, determine the waste truck dispatching scheme for the waste truck dispatching point corresponding to the dispatching node in the waste treatment subgraph, and determine the waste truck dispatching scheme corresponding to the waste treatment subgraph; Based on the garbage truck scheduling scheme corresponding to each of the garbage disposal sub-graphs, the garbage truck scheduling scheme for the target area is determined; the garbage truck scheduling scheme includes: the type of at least one garbage truck to be scheduled, and the departure time of the at least one garbage truck.

2. The method according to claim 1, wherein the garbage accumulation situation includes the historical garbage volume of each sub-region in the target area at multiple historical moments; The step of identifying at least one sub-region within the target area as at least one waste point to be processed based on the waste accumulation situation includes: Based on the historical garbage volume of each sub-region in the target region at multiple historical moments, predict the garbage increment of each sub-region at future moments; Determining at least one waste point to be processed based on the historical waste volume and waste increment of each sub-region includes: determining the processing demand degree of each sub-region based on the historical waste volume and waste increment of each sub-region; identifying the sub-regions whose processing demand degree is greater than a demand degree threshold as waste points to be processed; the demand degree threshold is related to the average value of the subgraph load values ​​of multiple waste processing subgraphs after the subgraph is divided.

3. The method according to claim 2, wherein predicting the garbage increment of each sub-region at future times based on the historical garbage amount of each sub-region in the target region at multiple historical moments comprises: Based on the historical garbage volume and historical pedestrian flow sequence of each sub-region at multiple historical moments, predict the garbage increment of each sub-region at future moments; The historical pedestrian flow sequence is determined based on the pedestrian flow of the sub-region at the corresponding historical times.

4. The method according to claim 1, wherein the scheduling scheme further comprises: Garbage truck route; The process of determining the garbage truck dispatching scheme corresponding to the garbage disposal sub-graph includes: The garbage truck's route is determined by traversing the garbage points to be processed within the region corresponding to the garbage processing subgraph, starting from the vehicle departure node of the garbage processing subgraph. This includes: determining the processing priority value of each garbage point to be processed in the garbage processing subgraph, and determining the garbage truck's route based on the processing priority value of each garbage point to be processed; the processing priority value is determined based on the peak value of the path from the current node to the garbage point to be processed; the peak value is related to the pedestrian flow sequence. Based on the garbage truck's travel route, a garbage truck scheduling scheme corresponding to the garbage disposal sub-graph is determined.

5. The method according to claim 1, further comprising: The garbage truck dispatch plan for the target area will be fed back to the user.

6. The method according to claim 5, wherein the smart city waste disposal equipment management IoT system further comprises a user platform, a service platform, a sensor network platform, and an object platform; The object platform is used to obtain the garbage accumulation situation; The sensor network platform is used to transmit the waste accumulation information to the management platform; the sensor network platform includes several sensor network sub-platforms; The management platform includes a main database and several sub-platforms. The service platform is used to feed back the garbage truck dispatch plan to the user through the user platform; the service platform includes several service sub-platforms. Each of the plurality of sensor network sub-platforms, each of the plurality of management sub-platforms, and each of the plurality of service sub-platforms corresponds to one of the target areas; The management platform's main database communicates with the corresponding sensor network sub-platforms through the several management sub-platforms.

7. A smart city waste disposal equipment management Internet of Things system, comprising a user platform, a service platform, a management platform, a sensor network platform, and an object platform; The object platform is used to obtain information on garbage accumulation within the target area; The sensor network platform is used to transmit the garbage accumulation situation in the target area obtained by the object platform to the management platform; The management platform is used for: Based on the garbage accumulation situation, at least one sub-region within the target area is identified as at least one garbage point to be processed; Based on the at least one unprocessed waste point, a waste truck dispatching plan for the target area is determined, and the management platform is further used for: Based on the at least one garbage collection point to be processed, the garbage truck departure point, and the road network information of the target area, a garbage processing map corresponding to the target area is constructed. The nodes of the waste disposal map include vehicle departure nodes and intersection nodes; the vehicle departure node corresponds to the waste truck departure point, and the intersection node corresponds to the street intersection within the target area; The edges of the waste disposal map correspond to the streets within the target area; The node characteristics and edge characteristics of the node include: whether it is a garbage point to be processed, the historical amount of garbage, and the garbage increment at future time. Based on the waste management map, at least one waste management sub-map is determined, including: Based on the vehicle departure node, at least one initial waste processing sub-graph is determined; The intersection node is taken as the node to be assigned. A target node is selected from the nodes to be assigned based on the current preferred value of the node to be assigned. The current preferred value is related to the first distance between the node to be assigned and the initial waste disposal subgraph with the smallest current subgraph load value, and the second distance between the previous target node and the node to be assigned. Based on the objective function value of the target node relative to each of the initial waste processing subgraphs, the initial waste processing subgraph to which the target node belongs is determined. The objective function value is related to the subgraph load value of the initial waste processing subgraph and the first distance between the target node and the initial waste processing subgraph. The subgraph load value is used to characterize the complexity of the initial waste processing subgraph and the pressure of the garbage truck's waste collection work. Each of the at least one waste processing subgraph includes at least one vehicle dispatch node. Based on the waste treatment subgraph, determine the waste truck dispatching scheme for the waste truck dispatching point corresponding to the dispatching node in the waste treatment subgraph, and determine the waste truck dispatching scheme corresponding to the waste treatment subgraph; Based on the garbage truck dispatching scheme corresponding to each of the garbage disposal sub-maps, the garbage truck dispatching scheme for the target area is determined; the garbage truck dispatching scheme includes: the type of at least one garbage truck to be dispatched, and the departure time of at least one garbage truck; The service platform is used to feed back the garbage truck dispatch plan to the user through the user platform.

8. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the smart city waste disposal equipment management method as described in any one of claims 1-6.

Images