A smart scheduling-based transportation optimization method and system

Abstract

The application discloses a kind of transport optimization method and system based on intelligent scheduling, it is related to wisdom logistics technical field.The method is first to collect the task information of multiple transport tasks and obtain the resource information of all logistics resources currently available and including unmanned aerial vehicle and rider, then based on this information, construct the man-machine collaborative transport network containing multiple nodes and multiple edges, the transport decision matrix of each transport task and multiple constraint conditions, and with the maximum goal of global logistics resource effective utilization time length ratio, the optimal transport decision matrix of each transport task under multiple constraint conditions is obtained by optimization, finally according to the optimization result, generate and output the transport optimization scheme for scheduling all logistics resources to complete multiple transport tasks, whereby by intelligently coordinating and optimizing scheduling unmanned aerial vehicle and rider two kinds of heterogeneous resources, multiple transport tasks with the same delivery time window requirement can be completed while maximizing the utilization rate of logistics resources.

Description

Technical Field

[0001] This invention belongs to the field of smart logistics technology, specifically relating to a transportation optimization method and system based on intelligent scheduling. Background Technology

[0002] With the rapid development of e-commerce and on-demand delivery, urban logistics faces the challenges of high costs, low efficiency, and stringent timeliness requirements in "last-mile" delivery. Currently, the mainstream delivery model relies on riders (such as food delivery workers and couriers), but this is susceptible to traffic congestion, has limited delivery capacity per trip, and suffers from bottlenecks in resource utilization. Drone delivery has advantages such as straight-line flight, high speed, and independence from ground traffic, but it also has problems such as limited range, small payload, and restrictions on takeoff and landing in densely populated areas. Existing technologies include either simple drone delivery solutions or rider delivery solutions, but they fail to fully consider the deep integration and complementary advantages of these two logistics resources (i.e., drones and riders). Although some preliminary collaborative solutions exist, most have simple scheduling strategies (e.g., drones are only responsible for the transfer from the station to the rider), failing to dynamically and intelligently allocate appropriate execution entities (drones, riders, or a combination of both) and optimal routes for each task from a global optimization perspective. As a result, they cannot maximize the utilization of overall resources (i.e., drone swarms and rider swarms) while meeting strict timeliness requirements. Therefore, there is an urgent need for an innovative intelligent scheduling solution for logistics resources that can deeply integrate the transportation capacity of drones and riders, and solve the above-mentioned technical challenges through global optimization. Summary of the Invention

[0003] The purpose of this invention is to provide a transportation optimization method, system, computer equipment, computer-readable storage medium, and computer program product based on intelligent scheduling, in order to solve the problem that existing logistics transportation solutions have limited integration depth and overall resource utilization when scheduling drones and riders.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a transportation optimization method based on intelligent scheduling is provided, including: Collect task information for multiple transportation tasks with the same delivery time window requirement, wherein the task information includes the starting location, target location, and carrying capacity requirements of the items to be delivered; Obtain resource information for all currently available logistics resources, including drones and riders, and the resource information includes current location and maximum carrying capacity; Based on all the task information and all the resource information, a human-machine collaborative transportation network is constructed, which includes multiple nodes and multiple edges. The multiple nodes include a task start point determined based on the starting position of the item to be delivered, a task end point determined based on the target position of the item to be delivered, a drone current node determined based on the drone's current position, a rider current node determined based on the rider's current position, and a transfer node for allowing safe handover of items between the drone and the rider. The multiple edges include a drone movement edge between two drone reachable nodes, a rider movement edge between two rider reachable nodes, and a transfer edge corresponding to the transfer node. The drone reachable nodes include the drone current node and the transfer node. The rider reachable nodes include the task start point, the task end point, the rider current node, and the transfer node. The human-machine collaborative transportation network includes all drone movement edges corresponding one-to-one with all drone reachable node pairs, all rider movement edges corresponding one-to-one with all rider reachable node pairs, and all transfer edges corresponding one-to-one with all transfer nodes. For each of the multiple transportation tasks, a human-machine collaborative transportation network is constructed that includes: The transportation decision matrix contains n elements and their corresponding values. This represents the total number of resources among all the logistics resources. This represents the total number of edges in the human-machine collaborative transportation network. The total number of future time elements is represented. Each row number of the transportation decision matrix corresponds to each logistics resource in all logistics resources. Each column number of the transportation decision matrix corresponds to each edge in the human-machine collaborative transportation network. The element value of the element is used to indicate whether to allocate the corresponding transportation task to the corresponding logistics resource and execute it in the corresponding time element and on the corresponding edge. Based on all the task information, all the resource information, and all the transportation decision matrices, construct multiple constraints; With the goal of maximizing the proportion of effective utilization time of global logistics resources, the optimal transportation decision matrix for each transportation task under the multiple constraints is obtained. Based on the optimization results, a transportation optimization scheme is generated and output to schedule all the logistics resources to complete the multiple transportation tasks.

[0005] Based on the above-mentioned invention, a novel scheme for global optimization of logistics transportation strategies through deep integration of drones and riders is provided. This involves first collecting task information for multiple transportation tasks and acquiring resource information for all currently available logistics resources, including drones and riders. Then, based on this information, a human-machine collaborative transportation network with multiple nodes and edges is constructed, along with transportation decision matrices for each transportation task and multiple constraints. With the goal of maximizing the effective utilization time of global logistics resources, the optimal transportation decision matrix for each transportation task under multiple constraints is obtained. Finally, based on the optimization results, a transportation optimization scheme for scheduling all logistics resources to complete multiple transportation tasks is generated and output. Thus, by intelligently coordinating and optimizing the scheduling of two heterogeneous resources, drones and riders, the utilization rate of logistics resources can be maximized while completing multiple transportation tasks with the same delivery time window requirements, facilitating practical application and promotion.

[0006] In one possible design, the multiple constraints include task execution constraints, task completion constraints, execution continuity constraints, execution duration constraints, relay synchronization constraints, capacity constraints, and delivery window constraints. The task execution constraint is used to restrict the drone to perform tasks only on the drone's moving side and the rider not to perform tasks on the drone's moving side. The task completion constraint is used to constrain all execution edges of any transportation task to be continuous in time and space, and the starting end of the first execution edge is the starting position of the corresponding task and the ending end of the last execution edge is the target position of the corresponding task. The execution continuity constraint is used to constrain that all execution time elements of any execution edge in any transportation task are sequentially continuous in time, and that all task executors of any execution edge are the same logistics resource. The execution time constraint is used to constrain the total execution time of any execution time element in any execution movement edge of any transportation task to be equal to the estimated execution time required for the task executor on that execution movement edge. The transit synchronization constraint is used to constrain that the earliest execution time of any transit edge in any transportation task is later than the latest execution time of the preceding adjacent transit edge, and the latest execution time of any transit edge is earlier than the earliest execution time of the following adjacent transit edge. The capacity constraint is used to constrain the maximum capacity of any logistics resource to meet the total capacity requirements of all transportation tasks assigned to that logistics resource at any execution time. The delivery time window constraint is used to ensure that the latest execution time of the last execution edge of any transportation task meets the delivery time window requirement of that transportation task.

[0007] In one possible design, the estimated execution time is estimated as follows: Obtain the distance of the movement route corresponding to the moving edge and the current environment data, wherein the current environment data packet contains current traffic condition information and / or current weather condition information; Based on the distance, the current environmental data, and the movement attribute information of the task executor, the required movement time of the task executor on the movement route is estimated as the estimated execution time. The movement attribute information includes the movement speed and the time required for the drone to take off and descend.

[0008] In one possible design, with the objective of maximizing the proportion of effective utilization time of global logistics resources, the optimal transportation decision matrix for each transportation task under the given multiple constraints is obtained, including: Construct a fitness function with the goal of maximizing the proportion of effective utilization time of global logistics resources; Based on the multiple constraints and the fitness function, an optimization algorithm is used to optimize the multidimensional vector composed of all the transportation decision matrices to obtain the optimal multidimensional vector with the best fitness under the multiple constraints. Based on the optimal multidimensional vector, the optimal transportation decision matrix for each transportation task under the multiple constraints is obtained.

[0009] In one possible design, when the element is indicated by the value "1" to assign the corresponding transportation task to the corresponding logistics resource and execute it at the corresponding time element and on the corresponding edge, and by the value "0" to indicate other cases, a fitness function is constructed with the objective of maximizing the proportion of effective utilization time of global logistics resources, including: Construct a fitness function with the objective of maximizing the proportion of effective utilization time of global logistics resources according to the following formula. :

[0010] In the formula, This represents the total number of tasks in the multiple transportation missions. Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates the first The elements in the transportation decision matrix for each transportation task This represents the total number of time elements from the current time element to the latest completion time element of the multiple transportation tasks.

[0011] In one possible design, the optimization algorithm may employ particle swarm optimization, Newton's optimization, genetic optimization, gray wolf optimization, whale optimization, or tuna swarm optimization.

[0012] Secondly, a transportation optimization system based on intelligent scheduling is provided, including a task information collection unit, a resource information acquisition unit, a collaborative network construction unit, a decision matrix construction unit, a constraint condition construction unit, a decision matrix optimization unit, and an optimization scheme generation unit. The task information collection unit is used to collect task information of multiple transportation tasks with the same delivery time window requirement, wherein the task information includes the starting location, target location and carrying capacity requirements of the items to be delivered. The resource information acquisition unit is used to acquire resource information of all currently available logistics resources, wherein the logistics resources include drones and riders, and the resource information includes the current location and maximum carrying capacity. The collaborative network construction unit is communicatively connected to the task information collection unit and the resource information acquisition unit, respectively. It is used to construct a human-machine collaborative transportation network containing multiple nodes and multiple edges based on all the task information and all the resource information. The multiple nodes include a task start point determined based on the starting position of the item to be delivered, a task end point determined based on the target position of the item to be delivered, a drone current node determined based on the drone's current position, a rider current node determined based on the rider's current position, and a transfer node for allowing the drone and rider to safely hand over items. The multiple edges... The system includes drone movement edges between two drone reachable nodes, rider movement edges between two rider reachable nodes, and transit edges corresponding to the transit nodes. Each drone reachable node includes the current drone node and the transit node. Each rider reachable node includes the task start point, the task end point, the current rider node, and the transit node. The human-machine collaborative transportation network includes all drone movement edges corresponding to all drone reachable node pairs, all rider movement edges corresponding to all rider reachable node pairs, and all transit edges corresponding to all transit nodes. The decision matrix construction unit, communicatively connected to the collaborative network construction unit, is used to construct a decision matrix based on the human-machine collaborative transportation network for each of the multiple transportation tasks. The transportation decision matrix contains n elements and their corresponding values. This represents the total number of resources among all the logistics resources. This represents the total number of edges in the human-machine collaborative transportation network. The total number of future time elements is represented. Each row number of the transportation decision matrix corresponds to each logistics resource in all logistics resources. Each column number of the transportation decision matrix corresponds to each edge in the human-machine collaborative transportation network. The element value of the element is used to indicate whether to allocate the corresponding transportation task to the corresponding logistics resource and execute it in the corresponding time element and on the corresponding edge. The constraint construction unit is communicatively connected to the task information collection unit, the resource information acquisition unit, and the decision matrix construction unit, and is used to construct multiple constraints based on all the task information, all the resource information, and all the transportation decision matrices. The decision matrix optimization unit is communicatively connected to the constraint construction unit and is used to optimize the transportation decision matrix of each transportation task under the multiple constraints with the goal of maximizing the proportion of effective utilization time of global logistics resources. The optimization scheme generation unit is communicatively connected to the decision matrix optimization unit, and is used to generate and output a transportation optimization scheme for scheduling all logistics resources to complete the multiple transportation tasks based on the optimization results.

[0013] Thirdly, the present invention provides a computer device comprising a storage module, a processing module, and a transceiver module connected in sequence for communication, wherein the storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program and execute the transportation optimization method as described in the first aspect or any possible design in the first aspect.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the transportation optimization method as described in the first aspect or any possible design within the first aspect.

[0015] Fifthly, the present invention provides a computer program product, including a computer program or instructions, which, when executed by a computer, implement the transportation optimization method as described in the first aspect or any possible design in the first aspect.

[0016] The beneficial effects of the above scheme are: (1) This invention creatively provides a new scheme for global optimization of logistics transportation strategy by deeply integrating drones and riders. First, it collects task information of multiple transportation tasks and obtains resource information of all available logistics resources including drones and riders. Then, based on this information, it constructs a human-machine collaborative transportation network with multiple nodes and multiple edges, transportation decision matrices for each transportation task, and multiple constraints. With the goal of maximizing the proportion of effective utilization time of global logistics resources, it optimizes the transportation decision matrix of each transportation task under multiple constraints. Finally, it generates and outputs a transportation optimization scheme for scheduling all logistics resources to complete multiple transportation tasks based on the optimization results. Thus, by intelligently coordinating and optimizing the scheduling of two heterogeneous resources, drones and riders, it can maximize the utilization rate of logistics resources while completing multiple transportation tasks with the same delivery time window requirement, which is convenient for practical application and promotion. Attached Figure Description

[0017] 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.

[0018] Figure 1 This is a flowchart illustrating the transportation optimization method based on intelligent scheduling provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the structure of a transportation optimization system based on intelligent scheduling provided in an embodiment of this application.

[0020] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these embodiments without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0022] It should be understood that although the terms "first" and "second", etc., may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the invention.

[0023] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, or A and B exist simultaneously. Another example is A, B and / or C, which can mean that any one of A, B, and C or any combination thereof exists. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone or A and B exist simultaneously. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0024] Example like Figure 1 As shown, the intelligent scheduling-based transportation optimization method provided in the first aspect of this embodiment can be executed, but is not limited to, by computer devices with certain computing resources, such as servers, personal computers (PCs, referring to a type of multi-purpose computer suitable for personal use in terms of size, price, and performance; desktops, laptops, mini-laptops, tablets, and ultrabooks all belong to personal computers), smartphones, personal digital assistants (PDAs), or wearable devices. Figure 1 As shown, the transportation optimization method includes, but is not limited to, the following steps S1 to S7.

[0025] S1. Collect task information for multiple transportation tasks with the same delivery time window requirement, wherein the task information includes, but is not limited to, the starting location, target location, and carrying capacity requirements of the items to be delivered.

[0026] In step S1, the transportation task is a regular express delivery task. Therefore, the task information can be obtained routinely by accessing existing express delivery order servers, but is not limited to this. The handling capacity requirement can be expressed, but is not limited to, by the weight and / or volume of the items. The delivery time window requirement can be specifically expressed as a future time period; for example, each transportation task requires delivery to the corresponding target location between 6 PM and 8 PM on the same day. Furthermore, the task information can be collected periodically, but is not limited to this, such as every hour.

[0027] S2. Obtain resource information for all currently available logistics resources, wherein the logistics resources include drones and riders, and the resource information includes, but is not limited to, current location and maximum carrying capacity.

[0028] In step S2, the current availability of the logistics resources can be conventionally determined based on information such as the drone's remaining range, remaining battery power, and / or whether it is currently accepting tasks (this information can be routinely uploaded by the drone). It can also be conventionally determined based on, but not limited to, whether the rider is online and / or whether they are currently accepting tasks (this information can be routinely uploaded by the rider's terminal). Furthermore, the resource information can also be routinely uploaded by the drone or rider's terminal. The maximum carrying capacity can also be expressed through, but not limited to, the maximum load capacity and / or maximum volume, and must be consistent with the carrying capacity requirements.

[0029] S3. Based on all the task information and all the resource information, construct a human-machine collaborative transportation network containing multiple nodes and multiple edges. The multiple nodes include, but are not limited to, a task start point determined based on the starting position of the item to be delivered, a task end point determined based on the target position of the item to be delivered, a drone current node determined based on the drone's current position, a rider current node determined based on the rider's current position, and a transfer node for allowing safe handover of items between the drone and the rider. The multiple edges include, but are not limited to, drone movement edges between two drone reachable nodes, rider movement edges between two rider reachable nodes, and transfer edges corresponding to the transfer nodes. The drone reachable nodes include, but are not limited to, the drone current node and the transfer node. The rider reachable nodes include, but are not limited to, the task start point, the task end point, the rider current node, and the transfer node. The human-machine collaborative transportation network includes, but is not limited to, all drone movement edges corresponding one-to-one with all drone reachable nodes, all rider movement edges corresponding one-to-one with all rider reachable nodes, and all transfer edges corresponding one-to-one with all transfer nodes.

[0030] In step S3, the transit node can be specifically planned in advance based on geographical data covering the logistics area of ​​all task start points, all task end points, all current drone nodes, and all current rider nodes, such as an open space in a park. The drone movement edge represents an airspace movement route, the rider movement edge represents a ground movement route, and the transit edge is a virtual edge connecting the drone-reachable node and the rider-reachable node, representing the physical handover process of the goods. Furthermore, a drone-reachable node pair refers to a pair of drone-reachable nodes, and a rider-reachable node pair refers to a pair of rider-reachable nodes.

[0031] S4. For each of the multiple transportation tasks, a human-machine collaborative transportation network is constructed, comprising: The transportation decision matrix contains n elements and their corresponding values. This represents the total number of resources among all the logistics resources. This represents the total number of edges in the human-machine collaborative transportation network. The total number of future time elements is represented. Each row number of the transportation decision matrix corresponds one-to-one with each logistics resource among all logistics resources. Each column number of the transportation decision matrix corresponds one-to-one with each edge in the human-machine collaborative transportation network. The element value of the element is used to indicate whether to allocate the corresponding transportation task to the corresponding logistics resource and execute it in the corresponding time element and on the corresponding edge.

[0032] In step S4, for example, in the transportation decision matrix of a certain transportation task, the elements The element value indicates whether to assign the aforementioned transportation task to the first... The logistics resources and in the first The time element and the first time element Execution is performed on the edge of the strip, where, Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates less than or equal to A positive integer. The element The element values ​​need to be binarized, for example, This indicates that a certain transportation task is assigned to the first... The logistics resources and in the first The time element and the first time element It is executed on the edge of the strip, and This indicates other cases (i.e., not assigning the aforementioned transportation task to the first...). The logistics resources and in the first The time element and the first time element (To be executed on the edge). Furthermore... The value of must be greater than or equal to the total number of time elements from the current time element to the latest time element required by the delivery time window, and the unit of time element is, for example, 1 minute.

[0033] S5. Construct multiple constraints based on all the task information, all the resource information, and all the transportation decision matrices.

[0034] In step S5, the multiple constraints are used to ensure the rationality of the optimization results in the subsequent optimization process. Specifically, the multiple constraints include, but are not limited to, task execution constraints, task completion constraints, execution continuity constraints, execution duration constraints, relay synchronization constraints, capacity constraints, and delivery time window constraints.

[0035] The task execution constraints are used to restrict the drone to perform tasks only on the drone's movement edge and the rider to perform tasks not on the drone's movement edge. That is, the drone cannot perform tasks on the rider's movement edge or the transfer edge, while the rider can (because the rider can be directly responsible for item delivery or for item handover with the drone at the transfer node). Specifically, this can be achieved by locking elements. To achieve the task execution constraints.

[0036] The task completion constraint is used to ensure that all execution edges of any transportation task are continuous in time and space, and that the starting point of the first execution edge is the starting position of the corresponding task, and the ending point of the last execution edge is the target position of the corresponding task. The aforementioned continuity of all execution edges in time and space means that not only do all execution edges need to be connected sequentially, but they also need to be executed sequentially in time. This can be determined based on the execution time element order of all elements that are 1, to determine whether the constraint is successful.

[0037] The execution continuity constraint is used to ensure that all execution time elements of any execution edge in any transportation task are sequentially continuous in time, and that all task executors of any execution edge are the same logistics resource. The aforementioned task executor is the drone or the rider, and the aforementioned execution time element refers to the time element when a task is assigned and executed, so as to ensure that the same transportation task is handled by the same drone or the same rider on the same edge.

[0038] The execution time constraint is used to ensure that the total execution time of any execution movement edge in any transportation task is equal to the estimated execution time required by the task executor on that execution movement edge. The aforementioned execution movement edge refers to the drone movement edge or rider movement edge that has been assigned and executed, representing a segment of airspace / ground movement route. Therefore, specifically, the estimated execution time can be estimated, but is not limited to, in the following manner: First, obtain the distance of the movement route corresponding to the execution movement edge and the current environmental data, wherein the current environmental data includes, but is not limited to, current traffic conditions and / or current weather conditions; then, based on the distance, the current environmental data, and the task executor's movement attribute information, estimate the required movement time of the task executor on the movement route as the estimated execution time, wherein the movement attribute information includes, but is not limited to, movement speed and the time required for the drone to take off and descend. The aforementioned travel route can be conventionally planned using existing path planning algorithms, such as the A* algorithm (also known as the A* algorithm, a heuristic search algorithm that finds the lowest cost path across multiple nodes on a graphical plane). Furthermore, the estimation process for the required travel time can be conventionally derived by referring to existing route navigation algorithms.

[0039] The transit synchronization constraint is used to ensure that, in any transit edge of any transportation task, the earliest execution time element is later than the latest execution time element of its preceding adjacent transit edge, and the latest execution time element of its following adjacent transit edge is earlier than the earliest execution time element of its subsequent transit edge. The aforementioned transit edge refers to the transit edge with a task assigned and executed, ensuring that the drone and the rider must be within the same time window at the transit station to complete the item handover. Furthermore, the total number of time elements from the earliest to the latest execution time element of the transit edge can be constrained to exceed a certain threshold, allowing sufficient time for item handover (e.g., item handover requires 2 minutes).

[0040] The capacity constraint is used to constrain the maximum capacity of any logistics resource to meet the total capacity requirements of all transportation tasks assigned to that logistics resource at any execution time.

[0041] The delivery time window constraint is used to ensure that the latest execution time of the last execution edge of any transportation task meets the delivery time window requirement of that transportation task.

[0042] S6. With the goal of maximizing the proportion of effective utilization time of global logistics resources, optimize the transportation decision matrix of each transportation task under the multiple constraints.

[0043] In step S6, specifically, with the goal of maximizing the proportion of effective utilization time of global logistics resources, the optimal transportation decision matrix for each transportation task under the multiple constraints is obtained, including but not limited to the following steps S61 to S63.

[0044] S61. Construct a fitness function with the goal of maximizing the proportion of effective utilization time of global logistics resources.

[0045] In step S61, specifically, when the element is indicated by the value "1" to assign the corresponding transportation task to the corresponding logistics resource and execute it at the corresponding time element and on the corresponding edge, and by the value "0" to indicate other situations, a fitness function is constructed with the objective of maximizing the proportion of effective utilization time of global logistics resources. This includes: constructing a fitness function with the objective of maximizing the proportion of effective utilization time of global logistics resources according to the following formula. :

[0046] In the formula, This represents the total number of tasks in the multiple transportation missions. Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates the first The elements in the transportation decision matrix for each transportation task This represents the total number of time elements from the current time element to the latest completion time element of the multiple transportation tasks.

[0047] S62. Based on the multiple constraints and the fitness function, an optimization algorithm is used to optimize the multidimensional vector composed of all the transportation decision matrices to obtain the optimal multidimensional vector with the best fitness under the multiple constraints.

[0048] In step S62, the optimization algorithm may specifically include, but is not limited to, particle swarm optimization, Newton's optimization, genetic optimization, Grey Wolf Algorithm, whale optimization, or tuna swarm optimization. The technical principles of these optimization algorithms are all existing technologies; therefore, the specific optimization process can be conventionally derived based on existing technical means, and will not be elaborated further here.

[0049] S63. Based on the optimal multidimensional vector, the optimal transportation decision matrix for each transportation task under the multi-constraint conditions is obtained.

[0050] S7. Based on the optimization results, generate and output a transportation optimization scheme for scheduling all logistics resources to complete the multiple transportation tasks.

[0051] Therefore, based on the transportation optimization method described in steps S1 to S7 above, a new scheme for global optimization of logistics transportation strategy by deeply integrating drones and riders is provided. First, task information of multiple transportation tasks and resource information of all currently available logistics resources including drones and riders are collected. Then, based on this information, a human-machine collaborative transportation network with multiple nodes and edges, transportation decision matrices for each transportation task, and multiple constraints are constructed. With the goal of maximizing the effective utilization time of global logistics resources, the optimal transportation decision matrix for each transportation task under multiple constraints is obtained. Finally, a transportation optimization scheme for scheduling all logistics resources to complete multiple transportation tasks is generated and output based on the optimization results. Thus, by intelligently coordinating and optimizing the scheduling of two heterogeneous resources, drones and riders, the utilization rate of logistics resources can be maximized while completing multiple transportation tasks with the same delivery time window requirements, which is convenient for practical application and promotion.

[0052] like Figure 2 As shown, the second aspect of this embodiment provides a virtual system for implementing the transportation optimization method described in the first aspect, including a task information collection unit, a resource information acquisition unit, a collaborative network construction unit, a decision matrix construction unit, a constraint condition construction unit, a decision matrix optimization unit, and an optimization scheme generation unit; The task information collection unit is used to collect task information of multiple transportation tasks with the same delivery time window requirement, wherein the task information includes the starting location, target location and carrying capacity requirements of the items to be delivered. The resource information acquisition unit is used to acquire resource information of all currently available logistics resources, wherein the logistics resources include drones and riders, and the resource information includes the current location and maximum carrying capacity. The collaborative network construction unit is communicatively connected to the task information collection unit and the resource information acquisition unit, respectively. It is used to construct a human-machine collaborative transportation network containing multiple nodes and multiple edges based on all the task information and all the resource information. The multiple nodes include a task start point determined based on the starting position of the item to be delivered, a task end point determined based on the target position of the item to be delivered, a drone current node determined based on the drone's current position, a rider current node determined based on the rider's current position, and a transfer node for allowing the drone and rider to safely hand over items. The multiple edges... The system includes drone movement edges between two drone reachable nodes, rider movement edges between two rider reachable nodes, and transit edges corresponding to the transit nodes. Each drone reachable node includes the current drone node and the transit node. Each rider reachable node includes the task start point, the task end point, the current rider node, and the transit node. The human-machine collaborative transportation network includes all drone movement edges corresponding to all drone reachable node pairs, all rider movement edges corresponding to all rider reachable node pairs, and all transit edges corresponding to all transit nodes. The decision matrix construction unit, communicatively connected to the collaborative network construction unit, is used to construct a decision matrix based on the human-machine collaborative transportation network for each of the multiple transportation tasks. The transportation decision matrix contains n elements and their corresponding values. This represents the total number of resources among all the logistics resources. This represents the total number of edges in the human-machine collaborative transportation network. The total number of future time elements is represented. Each row number of the transportation decision matrix corresponds to each logistics resource in all logistics resources. Each column number of the transportation decision matrix corresponds to each edge in the human-machine collaborative transportation network. The element value of the element is used to indicate whether to allocate the corresponding transportation task to the corresponding logistics resource and execute it in the corresponding time element and on the corresponding edge. The constraint construction unit is communicatively connected to the task information collection unit, the resource information acquisition unit, and the decision matrix construction unit, and is used to construct multiple constraints based on all the task information, all the resource information, and all the transportation decision matrices. The decision matrix optimization unit is communicatively connected to the constraint construction unit and is used to optimize the transportation decision matrix of each transportation task under the multiple constraints with the goal of maximizing the proportion of effective utilization time of global logistics resources. The optimization scheme generation unit is communicatively connected to the decision matrix optimization unit, and is used to generate and output a transportation optimization scheme for scheduling all logistics resources to complete the multiple transportation tasks based on the optimization results.

[0053] The working process, working details and technical effects of the aforementioned system provided in the second aspect of this embodiment can be found in the transportation optimization method described in the first aspect, and will not be repeated here.

[0054] like Figure 3 As shown, the third aspect of this embodiment provides a computer device for executing the transportation optimization method as described in the first aspect, including a storage module, a processing module, and a transceiver module connected in sequence. The storage module stores a computer program, the transceiver module sends and receives messages, and the processing module reads the computer program and executes the transportation optimization method as described in the first aspect. Specifically, the storage module may include, but is not limited to, random-access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; the processing module may, but is not limited to, use a microprocessor of the STM32F105 series. Furthermore, the computer device may also include, but is not limited to, a power supply module, a display screen, and other necessary components.

[0055] The working process, working details and technical effects of the aforementioned computer equipment provided in the third aspect of this embodiment can be found in the transportation optimization method described in the first aspect, and will not be repeated here.

[0056] This fourth aspect of the embodiment provides a computer-readable storage medium storing instructions comprising the transportation optimization method as described in the first aspect. Specifically, the computer-readable storage medium stores instructions that, when executed on a computer, perform the transportation optimization method as described in the first aspect. The computer-readable storage medium refers to a data storage medium and may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0057] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment can be found in the transportation optimization method described in the first aspect, and will not be repeated here.

[0058] This fifth aspect of the embodiment provides a computer program product, including a computer program or instructions, which, when executed by a computer, implement the transportation optimization method as described in the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0059] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A transportation optimization method based on intelligent scheduling, characterized in that, include: Collect task information for multiple transportation tasks with the same delivery time window requirement, wherein the task information includes the starting location, target location, and carrying capacity requirements of the items to be delivered; Obtain resource information for all currently available logistics resources, including drones and riders, and the resource information includes current location and maximum carrying capacity; Based on all the task information and all the resource information, a human-machine collaborative transportation network is constructed, which includes multiple nodes and multiple edges. The multiple nodes include a task start point determined based on the starting position of the item to be delivered, a task end point determined based on the target position of the item to be delivered, a drone current node determined based on the drone's current position, a rider current node determined based on the rider's current position, and a transfer node for allowing safe handover of items between the drone and the rider. The multiple edges include a drone movement edge between two drone reachable nodes, a rider movement edge between two rider reachable nodes, and a transfer edge corresponding to the transfer node. The drone reachable nodes include the drone current node and the transfer node. The rider reachable nodes include the task start point, the task end point, the rider current node, and the transfer node. The human-machine collaborative transportation network includes all drone movement edges corresponding one-to-one with all drone reachable node pairs, all rider movement edges corresponding one-to-one with all rider reachable node pairs, and all transfer edges corresponding one-to-one with all transfer nodes. For each of the multiple transportation tasks, a human-machine collaborative transportation network is constructed that includes: The transportation decision matrix contains n elements and their corresponding values. This represents the total number of resources among all the logistics resources. This represents the total number of edges in the human-machine collaborative transportation network. The total number of future time elements is represented. Each row number of the transportation decision matrix corresponds to each logistics resource in all logistics resources. Each column number of the transportation decision matrix corresponds to each edge in the human-machine collaborative transportation network. The element value of the element is used to indicate whether to allocate the corresponding transportation task to the corresponding logistics resource and execute it in the corresponding time element and on the corresponding edge. Based on all the task information, all the resource information, and all the transportation decision matrices, construct multiple constraints; With the goal of maximizing the proportion of effective utilization time of global logistics resources, the optimal transportation decision matrix for each transportation task under the multiple constraints is obtained. Based on the optimization results, a transportation optimization scheme is generated and output to schedule all the logistics resources to complete the multiple transportation tasks.

2. The transportation optimization method according to claim 1, characterized in that, The multiple constraints include task execution constraints, task completion constraints, execution continuity constraints, execution duration constraints, transit synchronization constraints, capacity constraints, and delivery window constraints. The task execution constraint is used to restrict the drone to perform tasks only on the drone's moving side and the rider not to perform tasks on the drone's moving side. The task completion constraint is used to constrain all execution edges of any transportation task to be continuous in time and space, and the starting end of the first execution edge is the starting position of the corresponding task and the ending end of the last execution edge is the target position of the corresponding task. The execution continuity constraint is used to constrain that all execution time elements of any execution edge in any transportation task are sequentially continuous in time, and that all task executors of any execution edge are the same logistics resource. The execution time constraint is used to constrain the total execution time of any execution time element in any execution movement edge of any transportation task to be equal to the estimated execution time required for the task executor on that execution movement edge. The transit synchronization constraint is used to constrain that the earliest execution time of any transit edge in any transportation task is later than the latest execution time of the preceding adjacent transit edge, and the latest execution time of any transit edge is earlier than the earliest execution time of the following adjacent transit edge. The capacity constraint is used to constrain the maximum capacity of any logistics resource to meet the total capacity requirements of all transportation tasks assigned to that logistics resource at any execution time. The delivery time window constraint is used to ensure that the latest execution time of the last execution edge of any transportation task meets the delivery time window requirement of that transportation task.

3. The transportation optimization method according to claim 2, characterized in that, The estimated execution time is obtained as follows: Obtain the distance of the movement route corresponding to the moving edge and the current environment data, wherein the current environment data packet contains current traffic condition information and / or current weather condition information; Based on the distance, the current environmental data, and the movement attribute information of the task executor, the required movement time of the task executor on the movement route is estimated as the estimated execution time. The movement attribute information includes the movement speed and the time required for the drone to take off and descend.

4. The transportation optimization method according to claim 1, characterized in that, With the objective of maximizing the proportion of effective utilization time of global logistics resources, the optimal transportation decision matrix for each transportation task under the given multiple constraints is obtained, including: Construct a fitness function with the goal of maximizing the proportion of effective utilization time of global logistics resources; Based on the multiple constraints and the fitness function, an optimization algorithm is used to optimize the multidimensional vector composed of all the transportation decision matrices to obtain the optimal multidimensional vector with the best fitness under the multiple constraints. Based on the optimal multidimensional vector, the optimal transportation decision matrix for each transportation task under the multiple constraints is obtained.

5. The transportation optimization method according to claim 4, characterized in that, When the element is indicated by the value "1" to assign the corresponding transportation task to the corresponding logistics resource and execute it at the corresponding time element and on the corresponding edge, and by the value "0" to indicate other cases, a fitness function is constructed with the objective of maximizing the proportion of effective utilization time of global logistics resources, including: Construct a fitness function with the objective of maximizing the proportion of effective utilization time of global logistics resources according to the following formula. : In the formula, This represents the total number of tasks in the multiple transportation missions. Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates less than or equal to positive integers, Indicates the first The elements in the transportation decision matrix for each transportation task This represents the total number of time elements from the current time element to the latest completion time element of the multiple transportation tasks.

6. The transportation optimization method according to claim 4, characterized in that, The optimization algorithm used is Particle Swarm Optimization, Newton's Optimization, Genetic Optimization, Gray Wolf Optimization, Whale Optimization, or Tuna Swarm Optimization.

7. A transportation optimization system based on intelligent scheduling, characterized in that, It includes a task information collection unit, a resource information acquisition unit, a collaborative network construction unit, a decision matrix construction unit, a constraint condition construction unit, a decision matrix optimization unit, and an optimization scheme generation unit; The task information collection unit is used to collect task information of multiple transportation tasks with the same delivery time window requirement, wherein the task information includes the starting location, target location and carrying capacity requirements of the items to be delivered. The resource information acquisition unit is used to acquire resource information of all currently available logistics resources, wherein the logistics resources include drones and riders, and the resource information includes the current location and maximum carrying capacity. The collaborative network construction unit is communicatively connected to the task information collection unit and the resource information acquisition unit, respectively. It is used to construct a human-machine collaborative transportation network containing multiple nodes and multiple edges based on all the task information and all the resource information. The multiple nodes include a task start point determined based on the starting position of the item to be delivered, a task end point determined based on the target position of the item to be delivered, a drone current node determined based on the drone's current position, a rider current node determined based on the rider's current position, and a transfer node for allowing the drone and rider to safely hand over items. The multiple edges... The system includes drone movement edges between two drone reachable nodes, rider movement edges between two rider reachable nodes, and transit edges corresponding to the transit nodes. Each drone reachable node includes the current drone node and the transit node. Each rider reachable node includes the task start point, the task end point, the current rider node, and the transit node. The human-machine collaborative transportation network includes all drone movement edges corresponding to all drone reachable node pairs, all rider movement edges corresponding to all rider reachable node pairs, and all transit edges corresponding to all transit nodes. The decision matrix construction unit, communicatively connected to the collaborative network construction unit, is used to construct a decision matrix based on the human-machine collaborative transportation network for each of the multiple transportation tasks. The transportation decision matrix contains n elements and their corresponding values. This represents the total number of resources among all the logistics resources. This represents the total number of edges in the human-machine collaborative transportation network. The total number of future time elements is represented. Each row number of the transportation decision matrix corresponds to each logistics resource in all logistics resources. Each column number of the transportation decision matrix corresponds to each edge in the human-machine collaborative transportation network. The element value of the element is used to indicate whether to allocate the corresponding transportation task to the corresponding logistics resource and execute it in the corresponding time element and on the corresponding edge. The constraint construction unit is communicatively connected to the task information collection unit, the resource information acquisition unit, and the decision matrix construction unit, and is used to construct multiple constraints based on all the task information, all the resource information, and all the transportation decision matrices. The decision matrix optimization unit is communicatively connected to the constraint construction unit and is used to optimize the transportation decision matrix of each transportation task under the multiple constraints with the goal of maximizing the proportion of effective utilization time of global logistics resources. The optimization scheme generation unit is communicatively connected to the decision matrix optimization unit, and is used to generate and output a transportation optimization scheme for scheduling all logistics resources to complete the multiple transportation tasks based on the optimization results.

8. A computer device, characterized in that, It includes a storage module, a processing module, and a transceiver module that are sequentially connected in communication. The storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program and execute the transportation optimization method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that... The computer-readable storage medium stores instructions that, when executed on a computer, perform the transportation optimization method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the transportation optimization method as described in any one of claims 1 to 6.

Images