A multi-circular-ward vehicle area collaborative operation path planning method and system

Abstract

This invention proposes a method and system for collaborative route planning of multiple sanitation vehicles in a region, relating to the field of sanitation operation planning technology. The method involves acquiring a cleaning area map corresponding to the target area to be cleaned by the sanitation vehicles, wherein the cleaning area map includes multiple sanitation operation areas; discretizing each sanitation operation area into multiple cleaning nodes, and constructing a cleaning path network based on all cleaning nodes; constructing a path planning model based on the cleaning node transition probability function and the cleaning path network, and constructing an initial cleaning path for each sanitation vehicle according to the path planning model; inputting a collaborative path optimization function and the initial cleaning path into the path planning model for iterative processing, and when the iteration termination condition is reached, the path planning model outputs the optimized cleaning path corresponding to each sanitation vehicle. This application helps improve the timeliness and efficiency of sanitation vehicle operations.

Description

Technical Field

[0001] This invention relates to the field of sanitation operation planning technology, and in particular to a method and system for planning the collaborative operation routes of multiple sanitation vehicles in a region. Background Technology

[0002] As cities develop, people's demands for the environment are increasing. Traditional sanitation management methods can no longer meet the information processing needs of sanitation management. Managers cannot grasp relevant information in real time and dynamically, and cannot quickly dispatch personnel in the event of emergencies. Sanitation departments have increasingly higher requirements for cost control, and the standards for urban environmental sanitation are also getting higher and higher. The sanitation management system is also becoming more refined.

[0003] Chinese patent CN117436662A discloses an intelligent optimization and guidance system for sanitation vehicle operation routes. This system calculates the priority coefficient of cleaning operations by comprehensively considering the urgency label, time limit, and distance to the sanitation vehicle. Based on the priority coefficient, it generates an operation sorting table and plans the operation routes of sanitation vehicles according to the order of the sorting table. It can prioritize more urgent cleaning operations. When a sanitation vehicle begins a cleaning operation, it monitors the time limit; if the time limit is less than a set threshold, the urgency label of the corresponding cleaning operation is raised by one level. However, the above solution requires drawing operation routes on an electronic map and lacks data support. It also cannot adjust the cleaning path according to real-time data and dynamic changes, making it difficult to guarantee the operational efficiency of sanitation vehicles. Therefore, it is essential to provide a method and system for container truck route planning in container factory areas based on BeiDou positioning to improve the timeliness and efficiency of sanitation vehicle operations. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for collaborative operation path planning of multiple sanitation vehicles in a region. By acquiring a map of the cleaning area, discretizing each sanitation operation area into multiple cleaning nodes, assigning an initial cleaning path to each sanitation vehicle, and adjusting the cleaning path according to real-time data and dynamic changes, the timeliness and efficiency of sanitation vehicle operations are significantly improved.

[0005] This invention provides a method for planning routes for collaborative operations of multiple sanitation vehicles in a region, the method comprising:

[0006] Obtain a cleaning area map corresponding to the target area to be cleaned by sanitation vehicles, wherein the cleaning area map includes multiple sanitation operation areas;

[0007] Each sanitation operation area is discretized into multiple cleaning nodes, and a cleaning path network is constructed based on all the cleaning nodes;

[0008] Based on the cleaning node transfer probability function and the cleaning path network, a path planning model is constructed, and an initial cleaning path is constructed for each sanitation vehicle according to the path planning model.

[0009] The collaborative path optimization function and the initial cleaning path are input into the path planning model for successive iterations. When the iteration termination condition is reached, the path planning model outputs the optimized cleaning path corresponding to each sanitation vehicle.

[0010] Based on the above technical solutions, preferably, the step of discretizing each sanitation operation area into multiple cleaning nodes and constructing a cleaning path network based on all cleaning nodes specifically includes:

[0011] Each sanitation operation area is divided into multiple sanitation operation sub-areas according to a predetermined spatial resolution, wherein each sanitation operation sub-area includes one or more cleaning nodes;

[0012] Based on the geographical distance between any two cleaning nodes, the traffic attributes between any two cleaning nodes, and the operation attribute information corresponding to the cleaning nodes, determine the connection relationship between any two cleaning nodes and the path weight between any two cleaning nodes.

[0013] Generate the adjacency matrix for each clean node based on the connection relationship and path weight between any two clean nodes;

[0014] Based on the adjacency matrix and the cleaning nodes corresponding to the sanitation operation sub-areas, a cleaning path network is constructed.

[0015] Based on the above technical solutions, preferably, the operation attribute information includes one or more of the following: the geographical coordinates of the cleaning node, the garbage density of the cleaning node, the operation time window requirement of the cleaning node, the estimated workload of the cleaning node, and the node priority.

[0016] More preferably, the step of constructing a corresponding initial cleaning path for each sanitation vehicle based on the path planning model specifically includes:

[0017] Collect basic work information for each sanitation vehicle, including available time windows for work capacity and historical work data.

[0018] Based on the cleaning node transition probability function and the cleaning path network, a corresponding cleaning node sequence is assigned to each sanitation vehicle. The cleaning nodes in the cleaning node sequence are then connected sequentially according to time sequence requirements to obtain an initial cleaning path.

[0019] More preferably, the sequence of cleaning nodes assigned to each sanitation vehicle based on the cleaning node transition probability function and the cleaning path network specifically includes:

[0020] Calculate the transition probability between any two cleaning nodes based on the cleaning node transition probability function.

[0021] Based on the ant colony optimization algorithm and the transition probability between any two cleaning nodes, a corresponding cleaning node sequence is assigned to each sanitation vehicle.

[0022] More preferably, the specific expression of the cleaning node transition probability function is:

[0023]

[0024] Among them, P ij This represents the transition probability function for cleaning nodes. The pheromone concentration on the edge connecting cleaning node i and cleaning node j is represented by λ1, which represents the first importance parameter, and η is the pheromone concentration on the edge connecting cleaning node i and cleaning node j. ij The parameters represent the heuristic information parameters between cleaning node i and cleaning node j, λ2 represents the second importance parameter, k represents all feasible neighbor nodes of cleaning node i, and O i Let S represent the set of neighboring nodes of cleaning node i, λ3 represent the third importance parameter, and S ij ω1 represents the spatial similarity factor between cleaning node i and cleaning node j in the cleaning path network, ω1 represents the weight coefficient corresponding to geographical distance, and d ij ω2 represents the Euclidean distance between cleaning node i and cleaning node j in the cleaning path network, ρ represents the weight coefficient corresponding to the region density, and ρ represents the distance between cleaning node i and cleaning node j in the network. i ρ represents the region density of cleaning node i. j ω represents the region density of cleaning node j, ω3 represents the weight coefficient corresponding to the time window, OL() represents the overlap length function of the time window, and T i T represents the job time window for cleaning node i. j The time window for cleaning node j is represented by Span(), which is the time span function between the time window for cleaning node i and the time window for cleaning node j.

[0025] More preferably, the specific expression of the cooperative path optimization function is:

[0026]

[0027] Where F represents the cooperative path optimization function, α represents the weight coefficient corresponding to the topology term, u represents the total number of edges in the sweep path network, and N ijk represents the edge connecting cleaning node i and cleaning node j in the cleaning path network. i k represents the cleaning workload at cleaning node i. j G represents the cleaning workload at cleaning node j. i Indicates the sanitation operation area number to which cleaning node i belongs, g j Indicates the sanitation operation area number to which cleaning node j belongs, Γ(g i ,g j ) represents the sanitation operation area judgment function, β represents the weight coefficient corresponding to the spatial similarity function, and S ij Let represent the spatial similarity function between cleaning node i and cleaning node j in the cleaning path network, γ represent the weight coefficient corresponding to the load balancing factor, μ represent the average workload of all sanitation vehicles, and σ represent the standard deviation of the workload of all sanitation vehicles.

[0028] More preferably, the iteration termination condition includes:

[0029] The iteration process of the path planning model stops when the preset maximum number of iterations is reached; or the iteration process of the path planning model stops when the difference between the output values ​​of the collaborative path optimization function in two consecutive iterations is lower than a preset optimization threshold.

[0030] A second aspect of this application provides a multi-sanitation vehicle regional collaborative operation route planning system, which includes a network construction module, a route construction module, and a route optimization module, wherein...

[0031] The network construction module is used to obtain a cleaning area map corresponding to the target area to be cleaned by the sanitation vehicle. The cleaning area map includes multiple sanitation operation areas, each sanitation operation area is discretized into multiple cleaning nodes, and a cleaning path network is constructed based on all the cleaning nodes.

[0032] The path construction module is used to construct a path planning model based on the sweeping node transfer probability function and the sweeping path network, and to construct a corresponding initial cleaning path for each sanitation vehicle according to the path planning model.

[0033] The path optimization module is used to input the collaborative path optimization function and the initial cleaning path into the path planning model for successive iterations. When the iteration termination condition is reached, the path planning model outputs the optimized cleaning path corresponding to each sanitation vehicle.

[0034] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.

[0035] The method and system for regional collaborative operation path planning of multiple sanitation vehicles provided by this invention have the following advantages over the prior art:

[0036] (1) By acquiring a map of the cleaning area and discretizing each sanitation operation area into multiple cleaning nodes, it is ensured that all cleaning areas are fully covered, reducing the omission of operations. Based on the cleaning node transfer probability function and path planning model, an initial cleaning path is assigned to each sanitation vehicle to ensure that the workload of each vehicle is balanced, thereby improving the overall resource utilization and comprehensiveness. The path planning model can adjust the cleaning path according to real-time data and dynamic changes through iterative optimization, ensuring that each cleaning node completes its work within the specified time window, significantly improving the timeliness and efficiency of sanitation vehicle operations. The collaborative path optimization process considers the coordination between multiple vehicles to avoid path conflicts and resource competition, thereby improving the stability and reliability of sanitation vehicle operation.

[0037] (2) By subdividing the sanitation operation area into multiple sanitation operation sub-areas, and each sanitation operation sub-area contains one or more cleaning nodes, the comprehensiveness and detail of the operation coverage are ensured, important areas are avoided, and the accuracy of path planning is improved. At the same time, by generating an adjacency matrix and constructing a cleaning path network, structured data support is provided for the path optimization algorithm, enabling sanitation vehicles to operate efficiently in the optimized path network, reducing repetitive operations and empty runs, improving resource utilization and operation efficiency. Furthermore, the path weight calculation model takes into account dynamic traffic conditions and operation priorities, and can adjust the path planning according to real-time changes, ensuring that sanitation operations can quickly respond to environmental changes, further improving operation efficiency and the flexibility of resource allocation. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A flowchart illustrating a method for regional collaborative operation path planning of multiple sanitation vehicles provided by the present invention;

[0040] Figure 2This is a schematic diagram of the multi-sanitation vehicle regional collaborative operation path planning system provided by the present invention.

[0041] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0042] Explanation of reference numerals in the attached diagram: 1. Multi-sanitation vehicle regional collaborative operation route planning system; 11. Network construction module; 12. Route construction module; 13. Route optimization module; 2. Electronic equipment; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. Detailed Implementation

[0043] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0044] This invention discloses a method for regional collaborative operation path planning of multiple sanitation vehicles, with reference to... Figure 1 The steps of this method include S1 to S4.

[0045] Step S1: Obtain a cleaning area map corresponding to the target area to be cleaned by the sanitation vehicle. The cleaning area map includes multiple sanitation operation areas.

[0046] In this step, geographic information data can be obtained by contacting local municipal departments or relevant government agencies to request the latest geographic information data, including road networks, building distribution, green spaces, parks, public facilities, etc. This includes obtaining vector data (such as Shapefiles), raster data (such as satellite imagery), and DEMs (Digital Elevation Models). Alternatively, basic geographic data can be obtained using open platforms such as Amap, Baidu Maps, and OpenStreetMap, through API interfaces or download tools to acquire map data for the required area, including roads, landmarks, public facilities, etc. High-resolution aerial photography using drones or purchasing the latest satellite imagery from commercial satellite imagery providers can also be used to obtain the latest terrain and geomorphological information, identifying real-time dynamics such as road changes and construction areas. Sanitation operation data can be obtained from data provided by sanitation departments, including cleaning routes, operation frequency, operation schedules, and historical operation records.

[0047] Furthermore, GIS software (such as ArcGIS and QGIS) is used to convert data from different sources into a unified format, such as GeoJSON and Shapefile. Duplicate or irrelevant data points are removed to ensure data uniqueness and relevance, and geographic coordinate errors are corrected and missing data attributes are supplemented. The projection coordinate system, units of measurement, and naming conventions of the data are standardized to ensure consistency between different datasets. Different types of geographic data (roads, buildings, green spaces, etc.) are overlaid to form a comprehensive geographic information layer. Based on sanitation operation requirements, the entire target area is divided into multiple work zones, each containing specific cleaning tasks and areas. Sanitation operation data is then associated with geographic information data, such as attaching attributes like cleaning frequency and operation time to corresponding geographic areas or nodes.

[0048] In one example, the criteria for delineating sanitation operation areas include geographical boundary criteria and operational demand criteria. Geographical boundary criteria include dividing operation areas based on natural geographical features (such as river or park boundaries) or administrative divisions (such as streets or communities). Operational demand criteria include dividing different operation areas based on factors such as cleaning frequency, waste generation, and traffic flow. GIS tools are used to draw the boundaries of each sanitation operation area, ensuring that the coverage of each area is reasonable and non-overlapping. Within each operation area, key cleaning nodes are identified, such as the location of trash cans, major intersections, and in front of important buildings. Geographic coordinates, cleaning frequency, priority, and other attribute information for each cleaning node are recorded. The cleaning nodes are connected according to the road network to form potential routes, and each route is weighted according to factors such as road type, traffic flow, and cleaning difficulty. The route weight reflects the route's quality. Accurate geographic coordinates (longitude and latitude) are assigned to each cleaning node to ensure the accuracy of route planning.

[0049] Step S2: Discretize each sanitation operation area into multiple cleaning nodes, and construct a cleaning path network based on all cleaning nodes.

[0050] This step also includes steps S21 to S24.

[0051] Step S21: Divide each sanitation operation area into multiple sanitation operation sub-areas according to a predetermined spatial resolution, wherein each sanitation operation sub-area includes one or more cleaning nodes.

[0052] In this step, detailed geographic information of the sanitation operation area is obtained, including road networks, building distribution, and green areas. A regular grid is overlaid in the GIS, dividing the entire operation area into equally sized grid cells, each representing a sanitation operation sub-region. Depending on actual conditions such as population density and traffic flow, irregular or adaptive zoning methods can be used to make the sanitation operation sub-regions more aligned with actual needs. Based on the location of cleaning nodes within each sub-region, nodes are assigned to the corresponding sub-regions, ensuring that each sub-region contains one or more cleaning nodes to optimize operational efficiency.

[0053] Furthermore, based on the operational capabilities and characteristics of sanitation vehicles (such as sweeping width and turning radius), a suitable spatial resolution is determined (e.g., each sub-area has a side length of 50 meters). Detailed map data of the sanitation operation area is acquired, including road networks, street layouts, and terrain features. The acquired map data is cleaned and formatted, redundant information is removed, and data consistency and usability are ensured. The boundary information of the operation area is extracted as the basis for sub-area division. A Cartesian coordinate system is established within the operation area, and the origin position is determined to provide a reference framework for grid division. Based on the predetermined spatial resolution (ΔX, ΔY), equally spaced grids are generated within the operation area, with each grid cell representing a potential sanitation operation sub-area. Boundary grid cells of the sanitation operation area are identified, and cases where the boundary does not completely coincide with the overall area are handled. The shape of the boundary grid is adjusted to ensure the continuity and integrity of the sub-areas, avoiding sub-area shapes that cross physical obstacles or are unreasonable. Grid cells located near the boundary are refined to adapt to actual road and terrain features, ensuring the practicality and operability of the sub-areas. Set a minimum area threshold for each sub-region to avoid sub-regions that are too small or cannot be operated independently. For sub-regions with an area below the minimum threshold, merge them according to preset rules (such as merging with the nearest sub-region) to ensure that the merged sub-regions still meet the predetermined spatial resolution requirements while maintaining the regularity and continuity of the sub-regions. Within each sanitation operation sub-region, allocate one or more cleaning nodes based on actual operational needs and cleaning priorities. Ensure that each cleaning node covers the specific work points within the sub-region to meet the actual needs of sanitation operations. Assign a unique identifier to each sub-region and record its geographic coordinate range, area, included cleaning nodes, and other attribute information. Store the sub-region division results in a standard Geographic Information System (GIS) format for easy subsequent route planning and management.

[0054] Step S22: Determine the connection relationship between any two cleaning nodes and the path weight between any two cleaning nodes based on the geographical distance between any two cleaning nodes, the traffic attributes between any two cleaning nodes, and the operation attribute information corresponding to the cleaning nodes.

[0055] Furthermore, the operation attribute information includes one or more of the following: the geographical coordinates of the cleaning node, the garbage density of the cleaning node, the operation time window requirement of the cleaning node, the estimated workload of the cleaning node, and the node priority.

[0056] In this step, traffic attributes include road type, traffic conditions, and road status. Road types include arterial roads, secondary roads, and local roads, each with different capacity and speed limits. Traffic conditions include congestion levels, speed limits, and the number and distribution of traffic lights. Road status includes factors such as one-way streets, two-way streets, road maintenance status, and construction zones. Operational attributes include cleaning task priority, time window, and operational complexity. Different cleaning nodes have different task priorities, such as garbage collection and street sweeping. Some cleaning nodes may have specific time requirements and must be completed within a specified time. Operational complexity includes the difficulty of the cleaning task and the required resources (such as manpower and equipment).

[0057] Determining whether a connection should be established between any two cleaning nodes based on traffic attributes, geographical distance, and operational attributes mainly includes the following steps:

[0058] Calculate the straight-line distance and actual travel distance between two cleaning nodes using Geographic Information System (GIS) tools or geographic coordinates. Analyze the road type and traffic conditions connecting the two cleaning nodes to determine road capacity and possible travel time. Check the job priorities and time windows of the two cleaning nodes to ensure that the connecting path meets the job time requirements. Based on geographic distance and traffic attributes, select feasible connecting paths to ensure that there is at least one feasible path connecting each pair of cleaning nodes; for example, exclude paths that are impassable due to road construction or traffic restrictions.

[0059] Furthermore, by utilizing road network data, ensuring that connections follow actual road alignments and traffic rules, nodes (intersections) and edges (roads) in the road network are identified, and the road network topology is constructed. Priority is given to connecting geographically proximate clean nodes to reduce unnecessary long-distance travel and to ensure feasible road paths exist between two nodes, taking into account road type and traffic restrictions. All possible connection pairs between clean nodes are generated, and infeasible or excessively costly connection pairs are eliminated based on the road network and traffic constraints. Path weights are defined based on the total time required from the origin to the destination, the total path length, and a comprehensive score combining time, distance, and other factors.

[0060] Understandably, the process involves collecting and organizing the geographical location and operational attribute information of all cleaning nodes, and obtaining traffic attribute data for the relevant road network, including road type, traffic congestion, and speed limits. For each pair of cleaning nodes, the actual travel distance and time are calculated. Based on the road network and traffic attributes, it is determined whether feasible connection paths exist. Feasible connections are established, forming a preliminary set of candidate paths. For each candidate path, path weights are calculated based on geographical distance, traffic attributes, and operational attributes. Standardization and weighted models are applied. All cleaning nodes, their connection relationships, and corresponding path weights are integrated to form a complete cleaning path network. The connectivity of the generated path network is checked to ensure that all necessary nodes are connected by feasible paths. The rationality of the path weights is evaluated to ensure that the weights reflect actual operational needs and traffic conditions. Simulation tests are conducted to verify the effectiveness and optimization potential of the path network in practical applications.

[0061] In one example, assuming there are two cleaning nodes A and B, the process of determining the connection relationship and path weights between them is as follows:

[0062] Distance calculation: The actual driving distance between cleaning node A and cleaning node B is 2 kilometers.

[0063] Traffic attributes assessment: The main road between clean node A and clean node B is a secondary arterial road with a speed limit of 50 km / h and a current traffic congestion index of 0.3.

[0064] Considering the job attributes: Cleaning node A has a high job priority, cleaning node B has a medium job priority, and the job time window is from 8:00 AM to 10:00 AM.

[0065] Calculate path weights (assuming the maximum distance is 10 kilometers): Standardized distance: Distance weight = 2 / 10 = 0.2 Distance weight = 2 / 10 = 0.2.

[0066] Standardized traffic congestion index: Traffic weight = 0.3 / 1 = 0.3.

[0067] Task priority inverse ratio (high priority is 1, medium priority is 0.8): Task weight = (1 + 0.8) / 2 = 0.9.

[0068] Overall weighting (assuming weighting coefficients α = 0.5, β = 0.3, γ = 0.2):

[0069] Overall weight = 0.5×0.2+0.3×0.3+0.2×0.9=0.1+0.09+0.18=0.37

[0070] In the cleaning path network, a connection path with a weight of 0.37 is established between cleaning node A and cleaning node B.

[0071] In this embodiment, by systematically analyzing and integrating geographical distance, traffic attributes, and operational attributes, the connection relationship and path weight between any two cleaning nodes can be effectively determined. This not only ensures the scientific and rational nature of the path network but also provides a solid foundation for subsequent path optimization and operational scheduling. Reasonable connection relationships and accurate path weight calculations can significantly improve the efficiency and effectiveness of collaborative operations among multiple sanitation vehicles, achieving efficient resource utilization and comprehensive operational coverage.

[0072] Step S23: Generate the adjacency matrix of each clean node based on the connection relationship and path weight between any two clean nodes.

[0073] In this step, a unique number is assigned to each cleaned node (e.g., node 1, node 2, ..., node N). Each node number is mapped to a row and column index in the adjacency matrix. Typically, there is a one-to-one correspondence between node numbers and matrix indices. First, an N×N matrix A is initialized, where N is the total number of cleaned nodes. For all paths i = 1 to N and j = 1 to N, if i = j, A is typically set to... ij =0, indicating that the distance from the node to itself is zero. Otherwise, set A... ij =∞ or other special values ​​that represent "no connection".

[0074] For each pair of clean nodes (i,j) in the path planning model, if there is a connection between clean node i and clean node j, then the path weight is assigned to the adjacency matrix A. ij If no connection exists, then keep A. ij This is the initial "no connection" value.

[0075] Step S24: Construct a cleaning path network based on the adjacency matrix and the cleaning nodes corresponding to the sanitation operation sub-areas.

[0076] In this embodiment, by subdividing the sanitation operation area into multiple sanitation operation sub-areas, and each sanitation operation sub-area containing one or more cleaning nodes, the comprehensiveness and detail of the operation coverage are ensured, avoiding omission of important areas and improving the accuracy of path planning. At the same time, by generating an adjacency matrix and constructing a cleaning path network, structured data support is provided for the path optimization algorithm, enabling sanitation vehicles to operate efficiently in the optimized path network, reducing repetitive work and empty runs, improving resource utilization and operation efficiency. Furthermore, the path weight calculation model considers dynamic traffic conditions and operation priorities, and can adjust path planning according to real-time changes, ensuring that sanitation operations can quickly respond to environmental changes, further improving operation efficiency and the flexibility of resource allocation.

[0077] Step S3: Based on the cleaning node transfer probability function and the cleaning path network, construct a path planning model, and construct a corresponding initial cleaning path for each sanitation vehicle according to the path planning model.

[0078] This step also includes steps S31 to S32.

[0079] Step S31: Collect basic work information for each sanitation vehicle, including available time windows for work capacity and historical work data.

[0080] In this step, the collection of operational capacity information includes entering basic information such as the specifications of the sweeping equipment and the capacity of the garbage containers for each vehicle into the system, and monitoring the working status of the sweeping equipment in real time through IoT sensors, recording equipment usage. The collection of available time windows includes setting and adjusting the work schedule for each vehicle in the vehicle management system, including daily working hours, rest periods, and maintenance times. The collection of historical operation data includes the system automatically recording the start and end times, location, route, and workload of each operation, allowing drivers to manually input or confirm operation information to supplement details not automatically collected by the system.

[0081] Step S32: Based on the cleaning node transition probability function and the cleaning path network, assign a corresponding cleaning node sequence to each sanitation vehicle, and connect the cleaning nodes in the cleaning node sequence sequentially according to the time sequence requirements to obtain the initial cleaning path.

[0082] In this step, the starting cleaning node for each sanitation vehicle is determined, typically its current location or base node. Based on the transition probability function, the next cleaning node is selected from the current node, and this process is repeated until all assigned cleaning nodes are included in the sequence. Cleaning nodes are arranged in a suitable order according to their time window and job priority. High-priority or urgent job nodes are prioritized at the beginning of the sequence to ensure timely completion. Adjacent node pairs in the cleaning node sequence are traversed, and the adjacency matrix in the cleaning path network is used to find the optimal path (e.g., shortest path or minimum weight path) from node A to node B. The travel time and estimated job time from node A to node B are calculated, ensuring that the arrival time at node B is within its time window. If this is not met, the node sequence or path needs to be adjusted. If time verification fails, the following strategies are applied: adjusting the position of node B in the sequence so that it executes at an earlier or later time period, or selecting an alternative connection path, which may sacrifice travel distance but save time, or, within the possible, extending or shortening the job time to meet the time window.

[0083] In one example, suppose a sanitation vehicle is assigned the following sequence of cleaning nodes: node A, node B, node C, and node D, and each node has a specific time window.

[0084] Based on the transition probability function, the sequence is determined to be A→B→C→D.

[0085] Find the optimal path from A to B, calculate the required time, and ensure that the arrival time at B is within its time window. Find the optimal path from B to C, calculate the required time, and ensure that the arrival time at C is within its time window. If a conflict is found, such as an arrival time at C earlier than its start time, adjust the sequence or select an alternative path. Similarly, find paths and verify times, making adjustments if necessary. Confirm the optimized path is A→B→C→D; the path has been optimized and verified, meeting all job requirements.

[0086] Based on the cleaning node transition probability function and cleaning path network, a cleaning node sequence is generated for each sanitation vehicle, and these nodes are connected sequentially to obtain the initial cleaning path. This can effectively optimize the path planning of sanitation operations, not only improving the accuracy and rationality of the path, but also increasing operational efficiency and resource utilization, ensuring that each vehicle can complete the cleaning task within the specified time.

[0087] In this embodiment, the transition probability between any two cleaning nodes is calculated based on the cleaning node transition probability function; and a corresponding cleaning node sequence is assigned to each sanitation vehicle based on the ant colony optimization algorithm and the transition probability between any two cleaning nodes.

[0088] The specific expression for the transition probability function of the cleanup node is:

[0089]

[0090] Among them, P ij This represents the transition probability function for cleaning nodes. The pheromone concentration on the edge connecting cleaning node i and cleaning node j is represented by λ1, which represents the first importance parameter, and η is the pheromone concentration on the edge connecting cleaning node i and cleaning node j. ij The parameters represent the heuristic information parameters between cleaning node i and cleaning node j, λ2 represents the second importance parameter, k represents all feasible neighbor nodes of cleaning node i, and O i Let S represent the set of neighboring nodes of cleaning node i, λ3 represent the third importance parameter, and S ij ω1 represents the spatial similarity factor between cleaning node i and cleaning node j in the cleaning path network, ω1 represents the weight coefficient corresponding to geographical distance, and d ij ρ represents the Euclidean distance between cleaning node i and cleaning node j in the cleaning path network, ω2 represents the weight coefficient corresponding to the region density, and ρ represents the distance between cleaning node i and cleaning node j in the Euclidean distance network. i ρ represents the region density of cleaning node i.j ω represents the region density of cleaning node j, ω3 represents the weight coefficient corresponding to the time window, OL() represents the overlap length function of the time window, and T i T represents the job time window for cleaning node i. j The time window for cleaning node j is represented by Span(), which is the time span function between the time window for cleaning node i and the time window for cleaning node j.

[0091] Furthermore, the heuristic information parameters for cleaning node i and cleaning node j can be the actual travel distance d from cleaning node i to cleaning node j. ij The reciprocal of the heuristic. That is, the greater the heuristic information, the shorter the actual travel distance from cleaning node i to cleaning node j, and the higher the probability of achieving the transfer.

[0092] The specific expression for the cooperative path optimization function is:

[0093]

[0094] Where F represents the cooperative path optimization function, α represents the weight coefficient corresponding to the topology term, u represents the total number of edges in the sweep path network, and N ij Let k represent the edge connecting cleaning node i and cleaning node j in the cleaning path network. i k represents the cleaning workload of cleaning node i. j G represents the cleaning workload at cleaning node j. i Indicates the sanitation operation area number to which cleaning node i belongs, g j Indicates the sanitation operation area number to which cleaning node j belongs, Γ(g i ,g j ) represents the sanitation operation area judgment function, β represents the weight coefficient corresponding to the spatial similarity function, and S ij Let represent the spatial similarity function between cleaning node i and cleaning node j in the cleaning path network, γ represent the weight coefficient corresponding to the load balancing factor, μ represent the average workload of all sanitation vehicles, and σ represent the standard deviation of the workload of all sanitation vehicles.

[0095] All paths constructed by ants are evaluated, and the path quality is calculated based on path length, time cost, and synergy.

[0096] Adjust pheromone concentration based on path quality:

[0097]

[0098] in, Let ε represent the pheromone concentration on the edge connecting cleaning node i and cleaning node j, and let ε represent the pheromone evaporation rate. The value represents the change in pheromone concentration on the edge connecting cleaning node i and cleaning node j, m represents the number of paths, and L represents the path length.

[0099] Step S4 involves iterating the collaborative path optimization function and the initial cleaning path into the path planning model. When the iteration termination condition is met, the path planning model outputs the optimized cleaning path for each sanitation vehicle.

[0100] In this embodiment, the initial cleaning path of each sanitation vehicle is input into the path planning model as the starting point for optimization. The cleaning node sequence and initial path of each vehicle are input into the path planning model. The total cost of the initial path (e.g., total distance, total time) is calculated. Minor adjustments are made to the current initial cleaning path, such as node swapping, insertion, or deletion, to generate new candidate paths. Path adjustments are performed among multiple sanitation vehicles to optimize resource allocation and job coverage. The performance of each candidate path on the collaborative path optimization function is evaluated, ensuring that the candidate paths meet constraints such as job capacity and time window. The candidate solution with the optimal objective function value and satisfying all constraints is selected. Once the termination condition is met, the path planning model outputs the optimized cleaning path for each sanitation vehicle, updating the current path to the selected optimal candidate path.

[0101] In one example, suppose there are two sanitation vehicles (vehicle 1 and vehicle 2), and their initial cleaning paths are as follows:

[0102] Car 1: Node A → Node B → Node C.

[0103] Car 2: Node D → Node E → Node F.

[0104] The optimized path planning is achieved through a collaborative path optimization function and a successive iterative process, as follows:

[0105] First iteration: Car 1 attempts to swap nodes B and D, generating a new path A→D→C. Car 2 adjusts its path to node B→node E→node F. The improved path is evaluated, and the total distance is reduced.

[0106] Second iteration:

[0107] Car 1 swaps nodes C and E, generating the path A→D→E. Car 2 is then adjusted to node B→node C→node F. The total time is further optimized.

[0108] The third iteration found that further exchanges did not provide significant improvement, so the iteration was terminated.

[0109] Final optimization path:

[0110] Car 1: Node A → Node D → Node E.

[0111] Car 2: Node B → Node C → Node F.

[0112] The iteration process of the path planning model stops when it reaches the preset maximum number of iterations; or the iteration process of the path planning model stops when the difference between the output values ​​of the collaborative path optimization function in two consecutive iterations is lower than the preset optimization threshold.

[0113] In this embodiment, by acquiring a cleaning area map and discretizing each sanitation operation area into multiple cleaning nodes, all cleaning areas are fully covered, reducing omissions. Based on the cleaning node transfer probability function and path planning model, an initial cleaning path is assigned to each sanitation vehicle, ensuring balanced workload across vehicles and improving overall resource utilization and comprehensiveness. The path planning model, through iterative optimization, can adjust the cleaning path according to real-time data and dynamic changes, ensuring that each cleaning node completes its work within a specified time window, significantly improving the timeliness and efficiency of sanitation vehicle operations. The collaborative path optimization process considers coordination among multiple vehicles, avoiding path conflicts and resource competition, and improving the stability and reliability of sanitation vehicle operation.

[0114] Based on the above method, a multi-sanitation vehicle regional collaborative operation path planning system is proposed, referencing... Figure 2 The multi-sanitation vehicle regional collaborative operation route planning system 1 includes a network construction module 11, a route construction module 12, and a route optimization module 13, wherein...

[0115] The network construction module 11 is used to obtain a cleaning area map corresponding to the target area to be cleaned by the sanitation vehicle. The cleaning area map includes multiple sanitation operation areas, each sanitation operation area is discretized into multiple cleaning nodes, and a cleaning path network is constructed based on all the cleaning nodes.

[0116] The path construction module 12 is used to construct a path planning model based on the sweeping node transfer probability function and the sweeping path network, and to construct a corresponding initial cleaning path for each sanitation vehicle according to the path planning model.

[0117] The path optimization module 13 is used to iterate the collaborative path optimization function and the initial cleaning path into the path planning model. When the iteration termination condition is reached, the path planning model outputs the optimized cleaning path corresponding to each sanitation vehicle.

[0118] In one example, the network construction module 11 is used to divide each sanitation operation area into multiple sanitation operation sub-regions according to a predetermined spatial resolution, wherein each sanitation operation sub-region includes one or more cleaning nodes; based on the geographical distance between any two cleaning nodes, the traffic attributes between any two cleaning nodes, and the operation attribute information corresponding to the cleaning nodes, the connection relationship and path weight between any two cleaning nodes are determined; based on the connection relationship and path weight between any two cleaning nodes, an adjacency matrix for each cleaning node is generated; and based on the adjacency matrix and the cleaning nodes corresponding to the sanitation operation sub-regions, a cleaning path network is constructed.

[0119] In one example, job attribute information includes one or more of the following: the geographic coordinates of the cleaning node, the garbage density of the cleaning node, the job time window requirement of the cleaning node, the estimated job workload of the cleaning node, and the node priority.

[0120] In one example, the path construction module 12 is used to collect basic work information of each sanitation vehicle, including the available time window of work capacity and historical work data; based on the cleaning node transfer probability function and the cleaning path network, a corresponding cleaning node sequence is assigned to each sanitation vehicle, and the cleaning nodes in the cleaning node sequence are connected sequentially according to the time sequence requirements to obtain the initial cleaning path.

[0121] In one example, the path building module 12 is used to calculate the transition probability between any two cleaning nodes based on the cleaning node transition probability function; and to assign a corresponding cleaning node sequence to each sanitation vehicle based on the ant colony optimization algorithm and the transition probability between any two cleaning nodes.

[0122] In one example, the specific expression for the sweep node transition probability function is:

[0123]

[0124] Among them, P ij This represents the transition probability function for cleaning nodes. The pheromone concentration on the edge connecting cleaning node i and cleaning node j is represented by λ1, which represents the first importance parameter, and η is the pheromone concentration on the edge connecting cleaning node i and cleaning node j. ij The parameters represent the heuristic information parameters between cleaning node i and cleaning node j, λ2 represents the second importance parameter, k represents all feasible neighbor nodes of cleaning node i, and O i Let S represent the set of neighboring nodes of cleaning node i, λ3 represent the third importance parameter, and S ij ω1 represents the spatial similarity factor between cleaning node i and cleaning node j in the cleaning path network, ω1 represents the weight coefficient corresponding to geographical distance, and d ijρ represents the Euclidean distance between cleaning node i and cleaning node j in the cleaning path network, ω2 represents the weight coefficient corresponding to the region density, and ρ represents the distance between cleaning node i and cleaning node j in the Euclidean distance network. i ρ represents the region density of cleaning node i. j ω represents the region density of cleaning node j, ω3 represents the weight coefficient corresponding to the time window, OL() represents the overlap length function of the time window, and T i T represents the job time window for cleaning node i. j The time window for cleaning node j is represented by Span(), which is the time span function between the time window for cleaning node i and the time window for cleaning node j.

[0125] In one example, the specific expression for the cooperative path optimization function is:

[0126]

[0127] Where F represents the cooperative path optimization function, α represents the weight coefficient corresponding to the topology term, u represents the total number of edges in the sweep path network, and N ij Let k represent the edge connecting cleaning node i and cleaning node j in the cleaning path network. i k represents the cleaning workload of cleaning node i. j G represents the cleaning workload at cleaning node j. i Indicates the sanitation operation area number to which cleaning node i belongs, g j Indicates the sanitation operation area number to which cleaning node j belongs, Γ(g i ,g j ) represents the sanitation operation area judgment function, β represents the weight coefficient corresponding to the spatial similarity function, and S ij Let represent the spatial similarity function between cleaning node i and cleaning node j in the cleaning path network, γ represent the weight coefficient corresponding to the load balancing factor, μ represent the average workload of all sanitation vehicles, and σ represent the standard deviation of the workload of all sanitation vehicles.

[0128] In one example, the iteration termination conditions include: the path planning model reaching a preset maximum number of iterations, stopping the iteration process of the path planning model; or the difference between the output values ​​of two consecutive collaborative path optimization functions being lower than a preset optimization threshold in two consecutive iterations, stopping the iteration process of the path planning model.

[0129] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 2 may include: at least one processor 21, at least one network interface 24, user interface 23, memory 25, and at least one communication bus 22.

[0130] The communication bus 22 is used to enable communication between these components.

[0131] The user interface 23 may include a display screen and a camera. Optionally, the user interface 23 may also include a standard wired interface and a wireless interface.

[0132] The network interface 24 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0133] The processor 21 may include one or more processing cores. The processor 21 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 25, and by calling data stored in the memory 25. Optionally, the processor 21 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 21.

[0134] The memory 25 may include random access memory (RAM) or read-only memory. Optionally, the memory 25 may include non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 25 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 25 may also be at least one storage device located remotely from the aforementioned processor 21. Figure 3 As shown, the memory 25, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a multi-sanitation vehicle regional collaborative operation path planning method.

[0135] exist Figure 3 In the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and obtain the user input data; while the processor 21 can be used to call the application program of a multi-sanitation vehicle regional collaborative operation path planning method stored in the memory 25. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0136] A computer-readable storage medium storing instructions that, when executed by one or more processors, cause a computer to perform one or more methods as described in the embodiments above.

[0137] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0138] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0140] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0142] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0143] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truths. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure.

[0144] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for planning the collaborative operation path of multiple sanitation vehicles in a region, characterized in that, The method includes: Obtain a cleaning area map corresponding to the target area to be cleaned by sanitation vehicles, wherein the cleaning area map includes multiple sanitation operation areas; Each sanitation operation area is discretized into multiple cleaning nodes, and a cleaning path network is constructed based on all the cleaning nodes; The process of discretizing each sanitation operation area into multiple cleaning nodes and constructing a cleaning path network based on all cleaning nodes specifically includes: Each sanitation operation area is divided into multiple sanitation operation sub-areas according to a predetermined spatial resolution, wherein each sanitation operation sub-area includes one or more cleaning nodes; Based on the geographical distance between any two cleaning nodes, the traffic attributes between any two cleaning nodes, and the operation attribute information corresponding to the cleaning nodes, determine the connection relationship between any two cleaning nodes and the path weight between any two cleaning nodes. Generate the adjacency matrix for each clean node based on the connection relationship and path weight between any two clean nodes; Based on the adjacency matrix and the cleaning nodes corresponding to the sanitation operation sub-areas, a cleaning path network is constructed; Based on the cleaning node transfer probability function and the cleaning path network, a path planning model is constructed, and an initial cleaning path is constructed for each sanitation vehicle according to the path planning model. The specific expression for the cleaning node transition probability function is as follows: ； ； in, P ij This represents the transition probability function for cleaning nodes. φ ij Indicates cleaning node i With cleaning nodes j The pheromone concentration on the connecting edge, λ 1 indicates the parameter of first importance. η ij Indicates cleaning node i With cleaning nodes j Heuristic information parameters, λ 2 indicates the second most important parameter. k Indicates cleaning node i All feasible neighbor nodes, O i Indicates cleaning node i The set of neighboring nodes, λ 3 indicates the third most important parameter. S ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j Spatial similarity factor, ω 1 represents the weighting coefficient corresponding to geographical distance. d ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j Euclidean distance, ω 2 represents the weighting coefficient corresponding to the region density. ρ i Indicates cleaning node i regional density, ρ j Indicates cleaning node j regional density, ω 3 represents the weighting coefficient corresponding to the time window, and OL() represents the overlap length function of the time window. T i Indicates cleaning node i The task time window, T j Indicates cleaning node j The operation time window, Span() represents the cleaning node. i Operation time window and cleaning nodes j The time span function of the task time window; The collaborative path optimization function and the initial cleaning path are input into the path planning model for successive iterations. When the iteration termination condition is reached, the path planning model outputs the optimized cleaning path corresponding to each sanitation vehicle. The specific expression for the cooperative path optimization function is as follows: ； in, F Represents the cooperative path optimization function. α This represents the weight coefficient corresponding to the topology term. u This represents the total number of edges in the clean path network. N ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j The connecting edges, f i Indicates cleaning node i The amount of cleaning work, f j Indicates cleaning node j The amount of cleaning work, g i Indicates cleaning node i The sanitation operation area number to which it belongs. g j Indicates cleaning node j The sanitation operation area number to which it belongs, Γ( g i , g j ) represents the function for determining sanitation work areas. β The weight coefficients represent the spatial similarity function. S ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j Spatial similarity function, γ This represents the weighting coefficient corresponding to the load balancing factor. μ This represents the average workload of all sanitation vehicles. σ This represents the standard deviation of the workload of all sanitation vehicles.

2. The multi-sanitation vehicle regional collaborative operation route planning method as described in claim 1, characterized in that, The operation attribute information includes one or more of the following: the geographical coordinates of the cleaning node, the garbage density of the cleaning node, the operation time window requirement of the cleaning node, the estimated workload of the cleaning node, and the node priority.

3. The multi-sanitation vehicle regional collaborative operation route planning method as described in claim 1, characterized in that, The step of constructing an initial cleaning path for each sanitation vehicle based on the path planning model specifically includes: Collect basic work information for each sanitation vehicle, including available time windows for work capacity and historical work data. Based on the cleaning node transition probability function and the cleaning path network, a corresponding cleaning node sequence is assigned to each sanitation vehicle. The cleaning nodes in the cleaning node sequence are then connected sequentially according to time sequence requirements to obtain an initial cleaning path.

4. The multi-sanitation vehicle regional collaborative operation route planning method as described in claim 3, characterized in that, The sequence of cleaning nodes assigned to each sanitation vehicle based on the cleaning node transition probability function and the cleaning path network specifically includes: Calculate the transition probability between any two cleaning nodes based on the cleaning node transition probability function. Based on the ant colony optimization algorithm and the transition probability between any two cleaning nodes, a corresponding cleaning node sequence is assigned to each sanitation vehicle.

5. The method for regional collaborative operation path planning of multiple sanitation vehicles as described in claim 1, characterized in that, The iteration termination conditions include: The iteration process of the path planning model stops when the preset maximum number of iterations is reached; or the iteration process of the path planning model stops when the difference between the output values ​​of the collaborative path optimization function in two consecutive iterations is lower than a preset optimization threshold.

6. A multi-sanitation vehicle regional collaborative operation route planning system, characterized in that, The multi-sanitation vehicle regional collaborative operation route planning system (1) includes a network construction module (11), a route construction module (12), and a route optimization module (13), wherein, The network construction module (11) is used to obtain a cleaning area map corresponding to the target area to be cleaned by the sanitation vehicle. The cleaning area map includes multiple sanitation operation areas, each sanitation operation area is discretized into multiple cleaning nodes, and a cleaning path network is constructed based on all the cleaning nodes. The process of discretizing each sanitation operation area into multiple cleaning nodes and constructing a cleaning path network based on all cleaning nodes specifically includes: Each sanitation operation area is divided into multiple sanitation operation sub-areas according to a predetermined spatial resolution, wherein each sanitation operation sub-area includes one or more cleaning nodes; Based on the geographical distance between any two cleaning nodes, the traffic attributes between any two cleaning nodes, and the operation attribute information corresponding to the cleaning nodes, determine the connection relationship between any two cleaning nodes and the path weight between any two cleaning nodes. Generate the adjacency matrix for each clean node based on the connection relationship and path weight between any two clean nodes; Based on the adjacency matrix and the cleaning nodes corresponding to the sanitation operation sub-areas, a cleaning path network is constructed; The path construction module (12) is used to construct a path planning model based on the sweeping node transfer probability function and the sweeping path network, and to construct a corresponding initial cleaning path for each sanitation vehicle according to the path planning model. The specific expression for the cleaning node transition probability function is as follows: ； ； in, P ij This represents the transition probability function for cleaning nodes. φ ij Indicates cleaning node i With cleaning nodes j The pheromone concentration on the connecting edge, λ 1 indicates the parameter of first importance. η ij Indicates cleaning node i With cleaning nodes j Heuristic information parameters, λ 2 indicates the second most important parameter. k Indicates cleaning node i All feasible neighbor nodes, O i Indicates cleaning node i The set of neighboring nodes, λ 3 indicates the third most important parameter. S ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j Spatial similarity factor, ω 1 represents the weighting coefficient corresponding to geographical distance. d ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j Euclidean distance, ω 2 represents the weighting coefficient corresponding to the region density. ρ i Indicates cleaning node i regional density, ρ j Indicates cleaning node j regional density, ω 3 represents the weighting coefficient corresponding to the time window, and OL() represents the overlap length function of the time window. T i Indicates cleaning node i The task time window, T j Indicates cleaning node j The operation time window, Span() represents the cleaning node. i Operation time window and cleaning nodes j The time span function of the task time window; The path optimization module (13) is used to input the collaborative path optimization function and the initial cleaning path into the path planning model for iterative processing. When the iteration termination condition is reached, the path planning model outputs the optimized cleaning path corresponding to each sanitation vehicle. The specific expression for the cooperative path optimization function is as follows: ； in, F Represents the cooperative path optimization function. α This represents the weight coefficient corresponding to the topology term. u This represents the total number of edges in the clean path network. N ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j The connecting edges, f i Indicates cleaning node i The amount of cleaning work, f j Indicates cleaning node j The amount of cleaning work, g i Indicates cleaning node i The sanitation operation area number to which it belongs. g j Indicates cleaning node j The sanitation operation area number to which it belongs, Γ( g i , g j ) represents the function for determining sanitation work areas. β The weight coefficients represent the spatial similarity function. S ij This represents the cleaning nodes in the cleaning path network. i With cleaning nodes j Spatial similarity function, γ This represents the weighting coefficient corresponding to the load balancing factor. μ This represents the average workload of all sanitation vehicles. σ This represents the standard deviation of the workload of all sanitation vehicles.

7. An electronic device, characterized in that, The device includes a processor (21), a memory (25), a user interface (23), and a network interface (24). The memory (25) is used to store instructions. The user interface (23) and the network interface (24) are used to communicate with other devices. The processor (21) is used to execute the instructions stored in the memory (25) to cause the electronic device (2) to perform the method as described in any one of claims 1-5.

Images