UAV dispatching method, device, computer equipment and storage medium

Abstract

This application discloses a drone scheduling method, apparatus, computer device, and storage medium. The method implementation includes: obtaining data to be predicted, performing feature extraction on the data to be predicted to obtain features to be predicted; based on the features to be predicted, predicting user demand vectors for different demand locations; constructing an objective function and constraints for a preset equipment scheduling target based on the user demand vectors; based on the objective function, calculating a first objective function value for each equipment location solution that satisfies the constraints, and determining an optimal equipment location solution based on the first objective function value; and based on the objective function and the optimal equipment location solution, calculating a second objective function value for each path planning solution that satisfies the constraints, and determining an optimal path planning solution based on the second objective function value. This method can better cope with the complex demands in logistics and distribution, and improve the resource utilization and overall efficiency of drones.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a drone scheduling method, apparatus, computer equipment, and storage medium. Background Art

[0002] Drone logistics and delivery have experienced rapid growth in recent years, demonstrating significant potential, particularly in inaccessible areas and for emergency delivery scenarios. Drones' efficiency and flexibility have led to their continued expansion in industries such as e-commerce, healthcare, and emergency rescue. However, as demand grows, the challenges of site selection and route planning for drone delivery networks have become increasingly complex. Rationally allocating resources and optimizing delivery routes have become pressing challenges.

[0003] Currently, traditional delivery planning methods rely heavily on static demand assumptions, failing to fully consider the dynamic and complex nature of customer demand and overlooking the impact of market conditions, seasonal factors, and unexpected events on demand. This static forecasting approach cannot accurately respond to fluctuating demand, resulting in poor site selection and route planning adapting to actual demand, leading to wasted delivery resources and delays. This makes it difficult for dispatch systems to cope with high-frequency demand fluctuations and hinders the full potential of drone delivery. Summary of the Invention

[0004] Based on this, it is necessary to provide a drone scheduling method, device, computer equipment and storage medium to address the above technical problems, so as to solve at least one problem existing in the above-mentioned prior art.

[0005] In a first aspect, the embodiment of the present application is implemented as follows: a method for dispatching a drone is provided, comprising the following steps:

[0006] Acquiring data to be predicted, and performing feature extraction on the data to be predicted to obtain features to be predicted;

[0007] Based on the features to be predicted, predict user demand vectors at different demand locations;

[0008] Based on the user demand vector, construct an objective function and constraint conditions for a preset equipment scheduling target;

[0009] Calculating, based on the objective function, a first objective function value of each device site selection scheme that satisfies the constraint condition, so as to determine an optimal device site selection scheme based on the first objective function value;

[0010] Based on the objective function and the optimal equipment location scheme, a second objective function value of each path planning scheme that meets the constraint condition is calculated to determine the optimal path planning scheme based on the second objective function value.

[0011] In one embodiment, calculating, based on the objective function, a first objective function value of each device site selection solution that satisfies the constraint condition, so as to determine an optimal device site selection solution based on the first objective function value, includes:

[0012] Constructing a set of equipment site selection solutions, wherein the set of equipment site selection solutions includes a plurality of initial equipment site selection solutions;

[0013] Performing an iterative search on each initial equipment location plan, and obtaining a local optimal equipment location plan for this iterative process based on the first objective function value;

[0014] The optimal solution among all the local optimal equipment location solutions is selected as the global optimal equipment location solution.

[0015] In one embodiment, the iterative search for each initial equipment site selection plan and obtaining a local optimal equipment site selection plan for this iteration based on the first objective function value includes:

[0016] Performing a neighborhood search on the initial equipment location plan to obtain a neighborhood solution;

[0017] Based on the objective function, calculating the objective function value of the neighborhood solution;

[0018] The objective function value of the neighborhood solution is compared with the objective function value of the initial equipment location scheme. If the neighborhood solution is better, the neighborhood solution is used as the local optimal equipment location scheme for this iterative process. Otherwise, the simulated annealing strategy is used to determine whether the neighborhood solution is used as the local optimal equipment location scheme for this iterative process.

[0019] In one embodiment, selecting the optimal solution from all the locally optimal device location solutions as the global optimal device location solution includes:

[0020] Compare the local equipment location solution obtained in each iteration process with the local optimal equipment location solution obtained in the previous iteration process to obtain the current local optimal equipment location solution, and save it to the optimal solution set, while deleting the local optimal equipment location solution generated in the previous iteration process saved in the optimal solution set;

[0021] When the iteration is completed, the local optimal equipment location solution retained in the optimal solution set is used as the global optimal equipment location solution.

[0022] In one embodiment, the calculating, based on the objective function and the optimal equipment location solution, a second objective function value of each path planning solution that satisfies the constraint condition, so as to determine the optimal path planning solution based on the second objective function value, includes:

[0023] Determining an initial path planning solution based on the optimal equipment site selection solution;

[0024] Iteratively searching the initial path planning solution and obtaining a local optimal path planning solution of this iterative process based on the second objective function value;

[0025] The best solution among all the local optimal path planning solutions is selected as the global optimal path planning solution.

[0026] In one embodiment, the step of predicting user demand vectors at different demand locations based on the features to be predicted includes:

[0027] Inputting the to-be-predicted features into a pre-trained prediction model, wherein the prediction model includes a plurality of decision trees;

[0028] Each decision tree predicts the feature to be predicted respectively to obtain multiple prediction results;

[0029] All the prediction results are aggregated to obtain user demand vectors of the different demand locations.

[0030] In one embodiment, the trained prediction model is calculated as follows:

[0031] Acquiring historical order data, performing feature extraction on the historical order data, and establishing a training feature set based on the extracted features, wherein the training feature set includes a plurality of training feature subsets;

[0032] recursively constructing a prediction model using Gini impurity or information gain as a splitting criterion, the prediction model comprising a plurality of decision trees;

[0033] Each decision tree is independently iteratively trained on the training feature subset until a preset convergence condition is met, thereby obtaining the trained prediction model.

[0034] In a second aspect, a drone dispatching device is provided, comprising:

[0035] A feature acquisition unit to be predicted, used to acquire data to be predicted and perform feature extraction on the data to be predicted to obtain features to be predicted;

[0036] A user demand vector prediction unit, configured to predict user demand vectors at different demand locations based on the features to be predicted;

[0037] An objective function construction unit, configured to construct an objective function and constraint conditions for a preset equipment scheduling objective based on the user demand vector;

[0038] an optimal equipment site selection scheme determining unit, configured to calculate, based on the objective function, a first objective function value of each equipment site selection scheme satisfying the constraint condition, so as to determine an optimal equipment site selection scheme based on the first objective function value;

[0039] The optimal path optimization scheme determination unit is used to calculate the second objective function value of each path planning scheme that meets the constraint conditions based on the objective function and the optimal equipment site selection scheme, so as to determine the optimal path planning scheme based on the second objective function value.

[0040] In a third aspect, a computer device is provided, comprising a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, wherein the processor implements the drone scheduling method as described above when executing the computer-readable instructions.

[0041] In a fourth aspect, a readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the drone scheduling method as described above is implemented.

[0042] The drone scheduling method, apparatus, computer device, and storage medium described above include: obtaining data to be predicted, performing feature extraction on the data to be predicted to obtain features to be predicted; predicting user demand vectors for different demand locations based on the features to be predicted; constructing an objective function and constraints for a preset equipment scheduling objective based on the user demand vectors; calculating a first objective function value for each equipment location solution that satisfies the constraints based on the objective function, and determining an optimal equipment location solution based on the first objective function value; and calculating a second objective function value for each path planning solution that satisfies the constraints based on the objective function and the optimal equipment location solution, and determining an optimal path planning solution based on the second objective function value. In embodiments of the present application, accurate user demand prediction can identify distribution hotspots in advance and rationally allocate drone and facility locations, thereby improving the efficiency and service quality of logistics distribution. The prediction model not only helps cope with demand changes but also provides real-time updated data support for the scheduling system, thereby optimizing distribution routes, reducing empty flights, and improving drone resource utilization. This can better cope with the complex demands of logistics distribution and improve the overall efficiency of drone logistics. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 This is a flow chart of a method for dispatching a drone in one embodiment of the present application;

[0045] Figure 2 This is a structural diagram of a drone dispatching device in one embodiment of the present application;

[0046] Figure 3 Schematic diagram of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] In one embodiment, if Figure 1 As shown, a drone scheduling method is provided, comprising the following steps:

[0049] In step S110, data to be predicted is obtained, and feature extraction is performed on the data to be predicted to obtain features to be predicted;

[0050] In embodiments of the present application, the data to be predicted may include order data, which may include information such as the location of demand, order time, and order quantity. Feature engineering can be used to extract features from the data to be predicted, such as time features, such as hour and day of the week, and location features, such as latitude and longitude, region type, and region name. It should be noted that the acquired data to be predicted may first be cleaned, for example, to remove null values ​​and outliers.

[0051] In step S120, based on the features to be predicted, user demand vectors of different demand locations are predicted;

[0052] In an embodiment of the present application, a user demand prediction model can be constructed and trained using a training data set to obtain a trained user demand prediction model. The features to be predicted are input into the user demand prediction model for prediction processing to obtain user demand vectors for different demand locations. It should be noted that different demand locations refer to different business districts, regions, locations, etc. with service demands, such as demand locations for drone delivery. The user demand vector refers to all users with service demands within a certain range of different demand locations, such as drone delivery service demands.

[0053] Optionally, the user demand prediction model may be a random forest model, a neural network model, etc. Taking the random forest model as an example, it may include multiple decision trees, each of which can predict a result, so the user demand vector output by the prediction is It can be represented as the aggregation of all decision tree prediction results. The user demand forecasting model can accurately predict user demand at different demand locations, providing key input for equipment site selection and route planning, thereby optimizing the efficiency and responsiveness of delivery services.

[0054] In step S130, based on the user demand vector, an objective function and constraint conditions of a preset equipment scheduling target are constructed;

[0055] For example, if there are 100 users in business district A, it is predicted that 70 of them will have delivery needs, while the remaining 30 will not. By establishing a user demand prediction model to predict user demand, we can eliminate interference factors and prioritize drone site selection and route planning in locations with a high concentration of demanding users, thereby improving service coverage and maximizing revenue. The preset equipment scheduling objectives can be maximizing total revenue or maximizing service coverage, among other goals.

[0056] The decision variables can be obtained first, the value range of each element in the decision variables can be determined, and the objective function and constraint conditions of the preset equipment scheduling target can be constructed based on the decision variables. For example, the decision variables may include , indicating that if the drone In the itinerary Zhongcong Facilities Service Request , if there is a service demand, it is 1, otherwise it is 0. , indicating that if the facility 1 if established, 0 otherwise. It means that if the drone Assigned to a facility , then it is 1, otherwise it is 0.

[0057] The objective function can be specifically shown in the following formula (1), and the constraint conditions can be shown in the following formulas (2)-(14):

[0058]

[0059] Wherein, formula (1) is the objective function to maximize total revenue. Constraint (2) ensures that each demand is served at most once. Constraint (3) ensures that each drone trip is served only once. The number of facilities is limited by constraint (4). Constraint (5) enforces the drone capacity constraint. The capacity of each facility and the total number of assigned drones are subject to constraints (6) and (7). Constraints (8) and (9) ensure that each drone is assigned to a facility at most one location. In constraint (10), a drone can only serve a demand in a trip assigned to a facility if the drone is assigned to the facility. Constraint (11) ensures that a demand must be satisfied before the latest delivery time. In constraints (12) and (13), consecutive deliveries need to start later and cannot overlap. Constraint (14) defines the variables.

[0060] in, : The set of all required locations. : The set of all potential facility locations. : The collection of all drones. : The set of itineraries for each drone. :Service demand location Revenue from customers. :From the demand position To potential facilities travel distance. :From the demand position To potential facilities travel time. : Maximum number of facilities. :need The latest delivery time. :facility capacity (maximum number of drones that can be assigned). : Drone exist As needed during the trip Time of service. : The travel distance limit of the drone.

[0061] Based on the above objective function, the maximum number of flights for each drone can be calculated as follows:

[0062] ;

[0063] in, The calculation formula is as follows: For each potential facility, sort it from largest to smallest according to the distance to the facility, and then accumulate the previous distances to customers until the sum of their distances is greater than ,therefore, .

[0064] By obtaining the maximum number of flights, the number of flights of the UAV can be limited when solving the objective function to reduce the solution space and improve the search efficiency and algorithm efficiency.

[0065] It should be noted that the above objective function can be solved by the adaptive large neighborhood search algorithm (ALNS), or by other heuristic or meta-heuristic algorithms to obtain an approximate optimal solution.

[0066] In step S140, based on the objective function, a first objective function value of each equipment site selection scheme that meets the constraint condition is calculated to determine an optimal equipment site selection scheme based on the first objective function value;

[0067] In an embodiment of the present application, the objective function can be solved by an adaptive large neighborhood search algorithm (ALNS), or by other heuristic or meta-heuristic algorithms to obtain an approximate optimal solution. Taking the adaptive large neighborhood search algorithm (ALNS) as an example, the solution process is described. For example, a greedy algorithm can be used to construct an initial device location solution, or an initial device location solution can be constructed based on a heuristic approach, and a neighborhood search can be performed to obtain a neighborhood solution, and the objective function value of the neighborhood solution can be calculated and compared with the objective function value of the initial device location solution. If the neighborhood solution is better, it is used as the latest current solution. Otherwise, a simulated annealing method can be used to determine whether to accept it as the latest current solution, and the latest current solution obtained is used as the optimal solution for this iteration. Repeat the above process until the optimal device location solution is obtained.

[0068] In step S150, based on the objective function and the optimal equipment location scheme, a second objective function value of each path planning scheme that meets the constraint condition is calculated to determine the optimal path planning scheme based on the second objective function value.

[0069] In an embodiment of the present application, according to the determined optimal equipment site selection plan, all flight points of the UAV can be determined, and then based on the flight points, path planning can be further performed. Specifically, the solution can be obtained by the adaptive large neighborhood search algorithm (ALNS), or the above-mentioned objective function can be solved by other heuristic or meta-heuristic algorithms to obtain an approximate optimal solution as a path planning solution. Taking the adaptive large neighborhood search algorithm (ALNS) as an example, the solution process is described. Exemplarily, a greedy algorithm can be used to construct an initial path planning solution, or all initial path planning solutions can be constructed in a heuristic manner, and a neighborhood search is performed to obtain a neighborhood solution, and the objective function value of the neighborhood solution is calculated and compared with the objective function value of the initial path planning solution. If the neighborhood solution is better, it is used as the latest current solution. Otherwise, a simulated annealing method can be used to determine whether to accept it as the latest current solution, and the latest current solution obtained is used as the optimal solution for this iteration. Repeat the above process until the optimal path planning solution is obtained.

[0070] In an embodiment of the present application, the optimal equipment site selection plan and the optimal path planning plan can be displayed through a user interface to present to the user, enable user interaction, and enhance user participation and experience. Specifically, the user interface may include a data view that can be used to display historical order data and extracted feature sets. The prediction result view can display the user demand predicted for each demand location in the form of a chart. The real-time site selection view is used to display the optimized facility location and drone coverage on a map. The path planning view is used to display the optimal path and estimated delivery time of the drone. The control panel of the control center can also allow users to start the prediction, optimization and path planning processes, and monitor the system status in real time.

[0071] The drone scheduling method includes: obtaining data to be predicted, performing feature extraction on the data to be predicted to obtain features to be predicted; predicting user demand vectors for different demand locations based on the features to be predicted; constructing an objective function and constraints for a preset equipment scheduling objective based on the user demand vectors; calculating a first objective function value for each equipment location solution that satisfies the constraints based on the objective function, and determining an optimal equipment location solution based on the first objective function value; and calculating a second objective function value for each path planning solution that satisfies the constraints based on the objective function and the optimal equipment location solution, and determining an optimal path planning solution based on the second objective function value. In embodiments of the present application, accurate user demand prediction can identify distribution hotspots in advance and rationally allocate drone and facility locations, thereby improving the efficiency and service quality of logistics distribution. The prediction model not only helps cope with demand changes but also provides real-time updated data support to the scheduling system, thereby optimizing distribution routes, reducing empty flights, and improving drone resource utilization. This can better cope with the complex demands of logistics distribution and improve the overall efficiency of drone logistics.

[0072] In one embodiment of the present application, calculating, based on the objective function, a first objective function value of each device site selection scheme that satisfies the constraint condition, so as to determine an optimal device site selection scheme based on the first objective function value, includes:

[0073] Construct an initial equipment siting plan;

[0074] Iteratively searching the initial equipment site selection plan, and obtaining a local optimal equipment site selection plan for this iterative process based on the first objective function value;

[0075] The optimal solution among all the local optimal equipment location solutions is selected as the global optimal equipment location solution.

[0076] Optionally, a greedy algorithm can be used to construct an initial path planning solution, or all initial equipment location solutions can be constructed based on a heuristic approach. Define a neighborhood structure, for example, select a location and change its establishment state from 0 to 1, or from 1 to 0. The objective function can be solved using an adaptive large neighborhood search algorithm (ALNS), or other heuristic or meta-heuristic algorithms. A local optimal solution can be obtained during each iteration. Based on the objective function value of the local optimal solution, a global optimal solution can be selected. For example, the larger the objective function value, the more preferentially it is selected as the global optimal solution. This global optimal solution can be used as the global optimal equipment location solution.

[0077] It should be noted that for the globally optimal equipment location solution, heuristic rules can be applied, such as giving priority to facility locations with high demand or favorable geographical locations, such as business districts, residential areas, and other locations where users are concentrated and demand is high.

[0078] In one embodiment of the present application, the iterative search for each initial device site selection plan and obtaining a local optimal device site selection plan for this iterative process based on the first objective function value includes:

[0079] Performing a neighborhood search on the initial equipment location plan to obtain a neighborhood solution;

[0080] Based on the objective function, calculating the objective function value of the neighborhood solution;

[0081] The objective function value of the neighborhood solution is compared with the objective function value of the initial equipment location scheme. If the neighborhood solution is better, the neighborhood solution is used as the local optimal equipment location scheme for this iterative process. Otherwise, the simulated annealing strategy is used to determine whether the neighborhood solution is used as the local optimal equipment location scheme for this iterative process.

[0082] Optionally, a neighborhood search can be performed on the initial device location solution to obtain a neighborhood solution. The objective function value of the neighborhood solution is calculated and compared with the objective function value of the initial device location solution. If the neighborhood solution is superior, it is used as the latest current solution. Otherwise, a simulated annealing method can be used to determine whether to accept it as the latest current solution. The latest current solution obtained is then used as the optimal solution for this iteration. This process is then repeated for the device location solution of the next iteration until the iteration is complete and the optimal device location solution is obtained.

[0083] The specific implementation of the neighborhood search is as follows: A user-greedy search strategy is performed, replacing the user with the lowest benefit from the solution with the user with the highest benefit from the unserved users. A facility-greedy search strategy is performed, replacing the facility with the lowest customer coverage income from the solution with the remaining unselected facility with the one that covers the most customers or has the highest customer coverage income, and then reassigning customers. A greedy-random search strategy is used: users or facilities are sorted from low to high by income, and a random user is selected from the top K (K = 3, 4, 5, etc.) of these users. Then, both the user-greedy and facility-greedy strategies are applied.

[0084] In one embodiment of the present application, selecting the optimal solution from all the locally optimal device location solutions as the global optimal device location solution includes:

[0085] Compare the local equipment location solution obtained in each iteration process with the local optimal equipment location solution obtained in the previous iteration process to obtain the current local optimal equipment location solution, and save it to the optimal solution set, while deleting the local optimal equipment location solution generated in the previous iteration process saved in the optimal solution set;

[0086] When the iteration is completed, the local optimal equipment location solution retained in the optimal solution set is used as the global optimal equipment location solution.

[0087] Optionally, the local device location scheme obtained in each iteration is compared with the local optimal device location scheme obtained in the previous iteration to obtain the current local optimal device location scheme, which is saved in the optimal solution set. At the same time, the local optimal device location scheme generated in the previous iteration saved in the optimal solution set is deleted, so that the optimal solution set only retains one current local optimal device location scheme in each iteration. When the iteration is completed, the local optimal device location scheme retained in the optimal solution set is used as the global optimal device location scheme.

[0088] In one embodiment of the present application, the calculating, based on the objective function and the optimal equipment site selection plan, a second objective function value of each path planning plan that satisfies the constraint condition, so as to determine the optimal path planning plan based on the second objective function value, includes:

[0089] Determining an initial path planning solution based on the optimal equipment site selection solution;

[0090] Iteratively searching the initial path planning solution and obtaining a local optimal path planning solution of this iterative process based on the second objective function value;

[0091] The best solution among all the local optimal path planning solutions is selected as the global optimal path planning solution.

[0092] Optionally, based on the determined optimal equipment site selection plan, all flight points of the UAV can be determined, and then based on the flight points, path planning can be further performed. For example, a greedy algorithm can be used to construct an initial path planning solution, or all initial path planning solutions can be constructed based on a heuristic approach, and a neighborhood search can be performed to obtain a neighborhood solution. The objective function value of the neighborhood solution is calculated and compared with the objective function value of the initial path planning solution. If the neighborhood solution is better, it is used as the latest current solution. Otherwise, a simulated annealing method can be used to determine whether to accept it as the latest current solution, and the latest current solution obtained is used as the optimal solution for this iteration. Repeat the above process until the optimal path planning solution is obtained.

[0093] In an embodiment of the present application, predicting user demand vectors at different demand locations based on the features to be predicted includes:

[0094] Inputting the to-be-predicted features into a pre-trained prediction model, wherein the prediction model includes a plurality of decision trees;

[0095] Each decision tree predicts the feature to be predicted respectively to obtain multiple prediction results;

[0096] All the prediction results are aggregated to obtain user demand vectors of the different demand locations.

[0097] Optionally, historical order data can be collected to establish a historical order data set, and feature extraction can be performed on the historical order data in the historical order data set, such as time features, regional features, etc., to establish feature set X, and use the prediction model Each tree in the required position The feature set Make predictions, calculate the aggregate value of the prediction results of each decision tree, and obtain the predicted user needs , aggregate the prediction results of all trees to obtain the final predicted customer demand vector .

[0098] In the embodiment of the present application, the trained prediction model is calculated as follows:

[0099] Acquiring historical order data, performing feature extraction on the historical order data, and establishing a training feature set based on the extracted features, wherein the training feature set includes a plurality of training feature subsets;

[0100] recursively constructing a prediction model using Gini impurity or information gain as a splitting criterion, the prediction model comprising a plurality of decision trees;

[0101] Each decision tree is independently iteratively trained on the training feature subset until a preset convergence condition is met, thereby obtaining the trained prediction model.

[0102] Optionally, historical order data can be collected as training sample data, which may specifically include the location of demand, order time, order quantity, etc. Feature engineering is used to extract features from the historical order data, such as time features and location features, to construct a training feature set. This is used to iteratively train the prediction model until preset convergence conditions are met, such as a loss value less than a preset threshold or the number of iterations reaches a preset number. A trained prediction model is then obtained.

[0103] It should be noted that the prediction model can be composed of T decision trees. Specifically, the decision trees can be recursively constructed using Gini impurity or information gain as the splitting criterion. The training feature set can then be divided into multiple subsets. Each decision tree t can then be independently trained on a randomly selected subset. A loss function (such as mean square error (MSE) or coefficient of determination (R²)) can be used to calculate the loss of the model's prediction results. If the loss value is greater than or equal to a preset threshold, iterative training is repeated until the loss value falls below the preset threshold, resulting in a fully trained prediction model.

[0104] It is understandable that the decision tree may include multiple nodes, and the best splitting feature is found at each node. and split point , to minimize the impurity of the node. The best split feature and split point The search can be done as follows. For continuous features, all possible split points can be traversed and the point with the largest Gini impurity or information gain can be used as the split point. For discrete features, each feature value is considered as a potential split point, and the best split feature and split point are selected. The above process is recursively applied to the left and right child nodes formed after the split until the stopping condition is met, such as the number of samples in the node is less than the preset threshold or the maximum tree depth is reached. A decision tree is then obtained and added to the random forest model. Make predictions in .

[0105] For each demand location ∈ , using the model Make forecasts and get predicted customer demand , The prediction results It can be expressed as the aggregation of all decision tree predictions:

[0106] ;

[0107] in, It is Trees on demand location The predicted value of Represents the required location set The predicted customer demand vector on . :Model The number of decision trees in . Indicates the required location Forecast customer demand. Indicates the Trees on demand location The predicted value of .

[0108] In the embodiments of this application, accurate user demand forecasting enables early identification of delivery hotspots and the rational allocation of drone and facility locations, thereby improving the efficiency and service quality of logistics delivery. The forecasting model not only helps respond to changes in demand but also provides real-time data support for the scheduling system, thereby optimizing delivery routes, reducing empty flights, and improving drone resource utilization. This allows for better response to the complex demands of logistics delivery, finding the optimal path for each drone and ensuring efficient delivery. Through this approach, the facility layout and route planning of drone delivery services are significantly optimized, improving service efficiency and customer satisfaction, and enhancing the overall effectiveness of drone logistics.

[0109] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0110] In one embodiment, a drone scheduling device is provided, which corresponds one-to-one to the drone scheduling method in the above embodiment. Figure 2 As shown, the UAV scheduling device includes a feature acquisition unit 10 for prediction, a user demand vector prediction unit 20, an objective function construction unit 30, an optimal equipment location solution determination unit 40, and an optimal path optimization solution determination unit 50. Each functional module is described in detail as follows:

[0111] The feature acquisition unit 10 is used to acquire data to be predicted and perform feature extraction on the data to be predicted to obtain features to be predicted;

[0112] A user demand vector prediction unit 20 is configured to predict user demand vectors at different demand locations based on the features to be predicted;

[0113] An objective function construction unit 30 is configured to construct an objective function and constraint conditions for a preset equipment scheduling objective based on the user demand vector;

[0114] an optimal equipment site selection scheme determining unit 40, configured to calculate, based on the objective function, a first objective function value of each equipment site selection scheme satisfying the constraint condition, so as to determine an optimal equipment site selection scheme based on the first objective function value;

[0115] The optimal path optimization solution determination unit 50 is used to calculate the second objective function value of each path planning solution that meets the constraint conditions based on the objective function and the optimal equipment site selection solution, so as to determine the optimal path planning solution based on the second objective function value.

[0116] In one embodiment of the present application, the optimal equipment site selection solution determining unit 40 is further configured to:

[0117] Construct an initial equipment siting plan;

[0118] Iteratively searching the initial equipment site selection plan, and obtaining a local optimal equipment site selection plan for this iterative process based on the first objective function value;

[0119] The optimal solution among all the local optimal equipment location solutions is selected as the global optimal equipment location solution.

[0120] In one embodiment of the present application, the optimal equipment site selection solution determining unit 40 is further configured to:

[0121] Performing a neighborhood search on the initial equipment location plan to obtain a neighborhood solution;

[0122] Based on the objective function, calculating the objective function value of the neighborhood solution;

[0123] The objective function value of the neighborhood solution is compared with the objective function value of the initial equipment location scheme. If the neighborhood solution is better, the neighborhood solution is used as the local optimal equipment location scheme for this iterative process. Otherwise, the simulated annealing strategy is used to determine whether the neighborhood solution is used as the local optimal equipment location scheme for this iterative process.

[0124] In one embodiment of the present application, the optimal equipment site selection solution determining unit 40 is further configured to:

[0125] Compare the local equipment location solution obtained in each iteration process with the local optimal equipment location solution obtained in the previous iteration process to obtain the current local optimal equipment location solution, and save it to the optimal solution set, while deleting the local optimal equipment location solution generated in the previous iteration process saved in the optimal solution set;

[0126] When the iteration is completed, the local optimal equipment location solution retained in the optimal solution set is used as the global optimal equipment location solution.

[0127] In one embodiment of the present application, the optimal path planning solution determining unit 50 is further configured to:

[0128] Determining an initial path planning solution based on the optimal equipment site selection solution;

[0129] Iteratively searching the initial path planning solution and obtaining a local optimal path planning solution of this iterative process based on the second objective function value;

[0130] The best solution among all the local optimal path planning solutions is selected as the global optimal path planning solution.

[0131] In one embodiment of the present application, the user demand vector prediction unit 20 is further configured to:

[0132] Inputting the to-be-predicted features into a pre-trained prediction model, wherein the prediction model includes a plurality of decision trees;

[0133] Each decision tree predicts the feature to be predicted respectively to obtain multiple prediction results;

[0134] All the prediction results are aggregated to obtain user demand vectors of the different demand locations.

[0135] In one embodiment of the present application, the optimal path planning solution determining unit 50 is further configured to:

[0136] Acquiring historical order data, performing feature extraction on the historical order data, and establishing a training feature set based on the extracted features, wherein the training feature set includes a plurality of training feature subsets;

[0137] recursively constructing a prediction model using Gini impurity or information gain as a splitting criterion, the prediction model comprising a plurality of decision trees;

[0138] Each decision tree is independently iteratively trained on the training feature subset until a preset convergence condition is met, thereby obtaining the trained prediction model.

[0139] In the embodiments of this application, accurate user demand forecasting enables early identification of delivery hotspots and the rational allocation of drone and facility locations, thereby improving the efficiency and service quality of logistics delivery. The forecasting model not only helps respond to changes in demand but also provides real-time data support for the scheduling system, thereby optimizing delivery routes, reducing empty flights, and improving drone resource utilization. This allows for better response to the complex demands of logistics delivery, finding the optimal path for each drone and ensuring efficient delivery. Through this approach, the facility layout and route planning of drone delivery services are significantly optimized, improving service efficiency and customer satisfaction, and enhancing the overall effectiveness of drone logistics.

[0140] The specific definition of the drone scheduling device can be found in the definition of the drone scheduling method above and will not be repeated here. The various modules in the above-mentioned drone scheduling device can be implemented in whole or in part by software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0141] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal via a network connection. When executed by the processor, the computer-readable instructions implement a method for dispatching a drone. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0142] In an embodiment of the present application, a computer device is provided, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the drone scheduling method described above are implemented.

[0143] In an embodiment of the application, a readable storage medium is provided, which stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the steps of the drone scheduling method as described above are implemented.

[0144] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0145] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0146] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A drone scheduling method, characterized in that: The method comprises: Acquiring data to be predicted, and performing feature extraction on the data to be predicted to obtain features to be predicted; The feature to be predicted is input into a pre-trained prediction model, which includes multiple decision trees; each decision tree predicts the feature to be predicted separately to obtain multiple prediction results; all the prediction results are aggregated to obtain user demand vectors for different demand locations. The user demand vectors refer to all users with service needs within a certain range of different demand locations. User demand is predicted by establishing a user demand prediction model, eliminating interference items, and prioritizing drone site selection and path planning for locations with a large number of demand users and a relatively high density of demand users; Based on the user demand vector, construct an objective function and constraint conditions for a preset equipment scheduling target; Obtain decision variables, determine the value range of each element in the decision variables, and construct the objective function and constraint conditions of the preset equipment scheduling target based on the decision variables. For example, the decision variables may include , indicating that if the drone In the itinerary Zhongcong Facilities Service Request , if there is a service demand, it is 1, otherwise it is 0, , indicating that if the facility If established, it is 1, otherwise it is 0. It means that if the drone Assigned to a facility , then it is 1, otherwise it is 0; The objective function is specifically shown in the following formula (1), and the constraints are shown in the following formulas (2)-(14): Wherein, formula (1) is the objective function to maximize total revenue, constraint (2) ensures that each demand is served at most once, constraint (3) ensures that each drone trip is served only once, the number of facilities is limited by constraint (4), constraint (5) enforces the drone capacity constraint, the capacity of each facility and the total number of assigned drones are subject to constraints (6) and (7), constraints (8) and (9) ensure that each drone is assigned to a facility at most, in constraint (10), a drone can only serve a demand in a trip assigned to a facility if it is assigned to the facility, constraint (11) ensures that the demand must be met before the latest delivery time, in constraints (12) and (13), consecutive deliveries need to start later and cannot overlap, and constraint (14) defines the variables; in, : the set of all required locations, : the set of all potential facility locations, : The collection of all drones, : The itinerary set of each drone, :Service demand location Revenue from customers :From the demand position To potential facilities travel distance, :From the demand position To potential facilities travel time, : Maximum number of facilities, :need The latest delivery time, :facility The capacity of the facility The capacity represents the maximum number of drones that can be allocated. : Drone exist As needed during the trip Time of service, : Drone travel distance limit; Based on the above objective function, the maximum number of flights for each drone can be calculated as follows: ； in, The calculation formula is as follows: For each potential facility, sort it from largest to smallest according to the distance to the facility, and then accumulate the previous distances to customers until the sum of their distances is greater than ,therefore, ; By obtaining the maximum number of flights, the number of flights of the UAV can be limited when solving the objective function to reduce the solution space; Based on the objective function, a first objective function value of each device location solution that meets the constraint condition is calculated to determine the optimal device location solution based on the first objective function value, and an initial device location solution is constructed using a greedy algorithm, or an initial device location solution is constructed based on a heuristic approach, and a neighborhood search is performed to obtain a neighborhood solution, and the objective function value of the neighborhood solution is calculated and compared with the objective function value of the initial device location solution. If the neighborhood solution is better, it is used as the latest current solution. Otherwise, a simulated annealing method can be used to determine whether to accept it as the latest current solution, and the latest current solution obtained is used as the optimal solution for this iteration; Based on the objective function and the optimal equipment site selection plan, a second objective function value of each path planning plan that meets the constraint conditions is calculated to determine the optimal path planning plan based on the second objective function value. According to the determined optimal equipment site selection plan, all flight points of the UAV can be determined, and then based on the flight points, an initial path planning solution is constructed using a greedy algorithm, or all initial path planning solutions are constructed based on a heuristic approach, and a neighborhood search is performed to obtain a neighborhood solution, and the objective function value of the neighborhood solution is calculated and compared with the objective function value of the initial path planning solution. If the neighborhood solution is better, it is used as the latest current solution. Otherwise, a simulated annealing method can be used to determine whether to accept it as the latest current solution, and the latest current solution obtained is used as the optimal solution of this iteration until the optimal path planning plan is obtained; The pre-trained prediction model is calculated as follows: Acquiring historical order data, performing feature extraction on the historical order data, and establishing a training feature set based on the extracted features, wherein the training feature set includes a plurality of training feature subsets; recursively constructing a prediction model using Gini impurity or information gain as a splitting criterion, the prediction model comprising a plurality of decision trees; Each decision tree is independently iteratively trained on the training feature subset until a preset convergence condition is met, thereby obtaining the trained prediction model; Among them, the optimal equipment site selection plan and the optimal path planning plan are displayed through the user interface. The user interface may specifically include a data view, which can be used to display historical order data and extracted feature sets; a prediction result view, which can display the user demand predicted for each demand location in the form of a chart; a real-time site selection view, which is used to display the optimized facility location and drone coverage on the map; a path planning view, which is used to display the optimal path and estimated delivery time of the drone; through the control panel of the control center, users can start the prediction, optimization and path planning processes, and monitor the system status in real time.

2. The drone dispatching method according to claim 1, wherein: The step of calculating, based on the objective function, a first objective function value of each device site selection scheme that satisfies the constraint condition, so as to determine an optimal device site selection scheme based on the first objective function value, includes: Construct an initial equipment siting plan; Iteratively searching the initial equipment site selection plan, and obtaining a local optimal equipment site selection plan for this iterative process based on the first objective function value; The optimal solution among all the local optimal equipment location solutions is selected as the global optimal equipment location solution.

3. The drone dispatching method according to claim 2, wherein: The iterative search of the initial equipment site selection plan and obtaining a local optimal equipment site selection plan of this iterative process based on the first objective function value includes: Performing a neighborhood search on the initial equipment location plan to obtain a neighborhood solution; Based on the objective function, calculating the objective function value of the neighborhood solution; The objective function value of the neighborhood solution is compared with the objective function value of the initial equipment location scheme. If the neighborhood solution is better, the neighborhood solution is used as the local optimal equipment location scheme for this iterative process. Otherwise, the simulated annealing strategy is used to determine whether the neighborhood solution is used as the local optimal equipment location scheme for this iterative process.

4. The drone dispatching method according to claim 2, wherein: The selecting the optimal solution from all the locally optimal equipment location solutions as the global optimal equipment location solution includes: Compare the local equipment location solution obtained in each iteration process with the local optimal equipment location solution obtained in the previous iteration process to obtain the current local optimal equipment location solution, and save it to the optimal solution set, while deleting the local optimal equipment location solution generated in the previous iteration process saved in the optimal solution set; When the iteration is completed, the local optimal equipment location solution retained in the optimal solution set is used as the global optimal equipment location solution.

5. The drone dispatching method according to claim 1, wherein: The calculating, based on the objective function and the optimal equipment location scheme, a second objective function value of each path planning scheme that satisfies the constraint condition, so as to determine the optimal path planning scheme based on the second objective function value, includes: Determining an initial path planning solution based on the optimal equipment site selection solution; Iteratively searching the initial path planning solution and obtaining a local optimal path planning solution of this iterative process based on the second objective function value; The best solution among all the local optimal path planning solutions is selected as the global optimal path planning solution.

6. A drone dispatching device, characterized in that: The device comprises: A feature acquisition unit for obtaining data to be predicted, configured to obtain data to be predicted and perform feature extraction on the data to be predicted to obtain features to be predicted; A user demand vector prediction unit is configured to input the feature to be predicted into a pre-trained prediction model, wherein the prediction model includes multiple decision trees; each decision tree predicts the feature to be predicted and obtains multiple prediction results; all the prediction results are aggregated to obtain user demand vectors for different demand locations. The user demand vectors refer to all users with service needs within a certain range of different demand locations. User demand is predicted by establishing a user demand prediction model, eliminating interference items, and prioritizing drone site selection and path planning for locations with a large number of demand users and a relatively high density of demand users; An objective function construction unit, configured to construct an objective function and constraint conditions for a preset equipment scheduling objective based on the user demand vector; Obtain decision variables, determine the value range of each element in the decision variables, and construct the objective function and constraint conditions of the preset equipment scheduling target based on the decision variables. For example, the decision variables may include , indicating that if the drone In the itinerary Zhongcong Facilities Service Request , if there is a service demand, it is 1, otherwise it is 0, , indicating that if the facility If established, it is 1, otherwise it is 0. It means that if the drone Assigned to a facility , then it is 1, otherwise it is 0; The objective function is specifically shown in the following formula (1), and the constraints are shown in the following formulas (2)-(14): Wherein, formula (1) is the objective function to maximize total revenue, constraint (2) ensures that each demand is served at most once, constraint (3) ensures that each drone trip is served only once, the number of facilities is limited by constraint (4), constraint (5) enforces the drone capacity constraint, the capacity of each facility and the total number of assigned drones are subject to constraints (6) and (7), constraints (8) and (9) ensure that each drone is assigned to a facility at most, in constraint (10), a drone can only serve a demand in a trip assigned to a facility if it is assigned to the facility, constraint (11) ensures that the demand must be met before the latest delivery time, in constraints (12) and (13), consecutive deliveries need to start later and cannot overlap, and constraint (14) defines the variables; in, : the set of all required locations, : the set of all potential facility locations, : The collection of all drones, : The itinerary set of each drone, :Service demand location Revenue from customers :From the demand position To potential facilities travel distance, :From the demand position To potential facilities travel time, : Maximum number of facilities, :need The latest delivery time, :facility The capacity of the facility The capacity represents the maximum number of drones that can be allocated. : Drone exist As needed during the trip Time of service, : Drone travel distance limit; Based on the above objective function, the maximum number of flights for each drone can be calculated as follows: ； in, The calculation formula is as follows: For each potential facility, sort it from largest to smallest according to the distance to the facility, and then accumulate the previous distances to customers until the sum of their distances is greater than ,therefore, ; an optimal equipment location solution determination unit, configured to calculate, based on the objective function, a first objective function value of each equipment location solution that satisfies the constraint conditions, so as to determine the optimal equipment location solution based on the first objective function value, construct an initial equipment location solution using a greedy algorithm, or construct an initial equipment location solution based on a heuristic approach, and perform a neighborhood search to obtain a neighborhood solution, calculate the objective function value of the neighborhood solution, and compare it with the objective function value of the initial equipment location solution; if the neighborhood solution is better, take it as the latest current solution; otherwise, use a simulated annealing method to determine whether to accept it as the latest current solution, and take the obtained latest current solution as the optimal solution for this iteration; An optimal path optimization solution determination unit is configured to calculate, based on the objective function and the optimal equipment siting solution, a second objective function value of each path planning solution that satisfies the constraint conditions, so as to determine the optimal path planning solution based on the second objective function value. According to the determined optimal equipment siting solution, all flight points of the UAV can be determined, and then based on the flight points, an initial path planning solution is constructed using a greedy algorithm, or all initial path planning solutions are constructed based on a heuristic method, and a neighborhood search is performed to obtain a neighborhood solution, and the objective function value of the neighborhood solution is calculated, and compared with the objective function value of the initial path planning solution. If the neighborhood solution is better, it is used as the latest current solution. Otherwise, a simulated annealing method can be used to determine whether to accept it as the latest current solution, and the latest current solution obtained is used as the optimal solution of this iteration until the optimal path planning solution is obtained; The pre-trained prediction model is calculated as follows: Acquiring historical order data, performing feature extraction on the historical order data, and establishing a training feature set based on the extracted features, wherein the training feature set includes a plurality of training feature subsets; recursively constructing a prediction model using Gini impurity or information gain as a splitting criterion, the prediction model comprising a plurality of decision trees; Each decision tree is independently iteratively trained on the training feature subset until a preset convergence condition is met, thereby obtaining the trained prediction model; Among them, the optimal equipment site selection plan and the optimal path planning plan are displayed through the user interface. The user interface may specifically include a data view, which can be used to display historical order data and extracted feature sets; a prediction result view, which can display the user demand predicted for each demand location in the form of a chart; a real-time site selection view, which is used to display the optimized facility location and drone coverage on the map; a path planning view, which is used to display the optimal path and estimated delivery time of the drone; through the control panel of the control center, users can start the prediction, optimization and path planning processes, and monitor the system status in real time.

7. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, wherein: When the processor executes the computer-readable instructions, the drone scheduling method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the drone scheduling method according to any one of claims 1 to 5 is implemented.

Images