Delivery task scheduling method, device and storage medium

Abstract

This application provides a delivery task scheduling method, device, and storage medium. The method includes: obtaining task attribute information corresponding to multiple delivery tasks to be executed, the task attribute information including task urgency and resource scarcity; wherein, task urgency is determined based on the type of goods to be delivered by the delivery task, and resource scarcity is determined based on the inventory of the goods to be delivered by the delivery task; determining the task priority of each delivery task among the multiple delivery tasks based on the task attribute information; allocating delivery vehicles to each delivery task according to the task priority of each delivery task, obtaining the delivery vehicles corresponding to each delivery task, scheduling the delivery vehicles corresponding to each delivery task, and executing each delivery task. This technical solution can improve the rationality and practicality of delivery services.

Description

Technical Field

[0001] This application relates to the field of task scheduling, and more particularly to delivery task scheduling methods, devices, and storage media. Background Technology

[0002] With the rapid development of drone technology, drones are increasingly being used in logistics delivery, emergency rescue, and other fields. Compared with traditional manual and vehicle delivery methods, drone delivery has advantages such as high flexibility, fast response speed, and no restriction by ground traffic conditions. It can effectively adapt to diverse delivery scenarios such as short-distance delivery, remote area delivery, and emergency material replenishment, and is gradually becoming an important part of the smart logistics system and emergency material support system.

[0003] Most existing drone dispatching solutions only sort and dispatch tasks based on delivery distance or order time, which affects the rationality and practicality of delivery services. Summary of the Invention

[0004] This application provides a delivery task scheduling method, equipment, and storage medium, aiming to improve the rationality and practicality of delivery services.

[0005] Firstly, a delivery task scheduling method is provided, including: Obtain task attribute information corresponding to multiple delivery tasks to be executed. The task attribute information includes task urgency and resource scarcity. The task urgency is determined based on the type of items to be delivered, and the resource scarcity is determined based on the inventory of the items to be delivered. Based on the task attribute information, determine the task priority of each delivery task among multiple delivery tasks; Based on the task priority of each delivery task, a delivery vehicle is assigned to each delivery task, and the delivery vehicle corresponding to each delivery task is obtained. The delivery vehicle corresponding to each delivery task is then dispatched to execute each delivery task.

[0006] In this technical solution, task attribute information corresponding to multiple delivery tasks to be executed is obtained. The task attribute information includes the urgency of the task and the scarcity of resources. Then, based on the task attribute information, the task priority of each delivery task is determined, and delivery vehicles are allocated to each delivery task according to the task priority. The delivery vehicles corresponding to each delivery task are then scheduled to execute each task. Since the urgency of the task is determined based on the type of goods to be delivered, and the scarcity of resources is determined based on the inventory of the goods to be delivered, defining the urgency of the task by the type of goods can accurately distinguish between urgently needed supplies and ordinary supplies, matching delivery priorities from the demand dimension and avoiding delays in the delivery of urgent supplies. Defining the scarcity of resources by the inventory of goods can identify scarce supply delivery tasks from the supply dimension, prioritizing the delivery and circulation of scarce inventory supplies and preventing the accumulation or shortage of scarce supplies. Therefore, it can ensure the timeliness of delivery of highly urgent and scarce supplies and improve the rationality and practicality of delivery services.

[0007] In conjunction with the first aspect, in one possible implementation, the task attribute information also includes a distance coefficient and a user permission coefficient. The distance coefficient is negatively correlated with the delivery distance corresponding to the delivery task, and the user permission coefficient is positively correlated with the permission level of the user initiating the delivery task. The multiple delivery tasks include a target delivery task. The task priority of each delivery task among the multiple delivery tasks is determined based on the task attribute information, including: weighted summation of the urgency of the target delivery task, the resource scarcity of the target delivery task, the distance coefficient of the target delivery task, and the user permission coefficient of the target delivery task to obtain the task priority of the target delivery task.

[0008] Based on the urgency of the task and the scarcity of resources, the task priority of the delivery task is determined by combining the distance coefficient and user permission coefficient corresponding to the delivery task. This can avoid task delays caused by long-distance delivery time, take into account the impact of delivery distance on the actual delivery effect, and match the service priority needs of different users, thereby further improving the accuracy and comprehensiveness of task priority determination and making task scheduling fit the actual delivery scenario needs.

[0009] In conjunction with the first aspect, in one possible implementation, before the above-mentioned weighted summation of the task urgency, resource scarcity, distance coefficient, and user permission coefficient corresponding to the target delivery task to obtain the task priority, the method further includes: determining the weights corresponding to the task urgency, resource scarcity, distance coefficient, and user permission coefficient according to the delivery scenario to which the target delivery task belongs.

[0010] By determining the weights of task urgency, resource scarcity, distance coefficient, and user permission coefficient based on the delivery scenario, the scenario adaptability and flexibility of the scheduling scheme can be improved.

[0011] Based on the first aspect, in one possible implementation, multiple delivery tasks include target delivery tasks; the above-mentioned acquisition of task attribute information corresponding to multiple delivery tasks to be executed includes: acquiring a target demand vector; the target demand vector is obtained by converting the delivery demand information input by the user, and the target demand vector includes the type of target item to be delivered; determining the inventory of the target item according to the type of the target item; generating the delivery task corresponding to the target demand vector to obtain the target delivery task; determining the task urgency corresponding to the target delivery task according to the type of the target item, and determining the resource scarcity corresponding to the target delivery task according to the inventory of the target item.

[0012] The delivery demand information is converted into demand vectors and corresponding delivery tasks are generated. This determines the urgency and resource scarcity of delivery tasks and their corresponding tasks, enabling the digital standardization of user delivery demands and improving the efficiency and standardization of task information collection.

[0013] In conjunction with the first aspect, in one possible implementation, after generating the delivery task corresponding to the target demand vector, the method further includes: determining a material attribute vector that matches the target demand vector, wherein the material attribute vector includes at least one of the target item's load capacity, volume, and storage attributes; and determining a candidate vehicle set based on the material attribute vector, wherein the candidate vehicle set includes at least one candidate vehicle that is adapted to the target delivery task.

[0014] Determining candidate vehicles that are suitable for delivery tasks based on material attribute vectors can improve the accuracy of vehicle matching.

[0015] In conjunction with the first aspect, in one possible implementation, multiple delivery tasks include a target delivery task; the above-mentioned allocation of delivery vehicles to each delivery task according to the task priority of each delivery task to obtain the delivery vehicle corresponding to each delivery task includes: determining the execution order of the target tasks according to the task priority of the target delivery task; when the execution order is the target delivery task, sending a broadcast message to each candidate vehicle in the candidate vehicle set corresponding to the target delivery task; wherein, the candidate vehicle set includes at least one candidate vehicle adapted to the target delivery task, and the broadcast message includes the task information of the target delivery task; receiving bidding information sent by each candidate vehicle, the bidding information including the task cost determined by each candidate vehicle based on the task information; and selecting a target candidate vehicle from the candidate vehicle set as the delivery vehicle corresponding to the target delivery task according to the bidding information, wherein the target candidate vehicle is the candidate vehicle with the lowest task cost.

[0016] Allocating delivery vehicles to delivery tasks through broadcast bidding can minimize the cost of single-task delivery, improve the utilization efficiency of vehicle resources and delivery economy, and reduce dependence on central servers.

[0017] In conjunction with the first aspect, in one possible implementation, the target delivery task is used to deliver the target item, and the task information includes the demand quantity of the target item and the storage location of the target item; the candidate vehicle determines the distance between the candidate vehicle and the target item, the power consumption required for the target delivery task, and the load matching degree between the candidate vehicle and the target delivery task based on the load capacity of the target item and the storage location of the target item, and determines the task cost based on the distance, power consumption, and load matching degree.

[0018] Based on the distance between the vehicle and the goods, the power consumption required for the delivery task, and the load matching degree between the vehicle and the target delivery task, the task cost is calculated so that the calculated task cost is close to the actual delivery cost and execution difficulty, ensuring that the finally selected vehicle can balance low delivery cost and high task adaptability.

[0019] In conjunction with the first aspect, in one possible implementation, the above-mentioned allocation of delivery vehicles to each delivery task according to the task priority of each delivery task to obtain the delivery vehicle corresponding to each delivery task further includes: in response to the failure of the target candidate vehicle, or the target candidate vehicle being scheduled to execute other delivery tasks with higher task priority, after removing the target candidate vehicle from the candidate vehicle set, resending broadcast messages to each candidate vehicle in the candidate vehicle set to reallocate delivery vehicles to the target delivery task.

[0020] When a vehicle malfunctions or is occupied by a higher-priority task, the selected vehicle is removed and a new broadcast bidding is conducted. This can avoid task interruption and delivery timeout caused by the failure of a single vehicle, and improve the fault tolerance, stability and anti-interference capability of delivery scheduling.

[0021] Secondly, a delivery task scheduling device is provided, comprising: The task attribute acquisition module is used to acquire task attribute information corresponding to multiple delivery tasks to be executed. The task attribute information includes task urgency and resource scarcity. The task urgency is determined based on the type of items to be delivered by the delivery task, and the resource scarcity is determined based on the inventory of the items to be delivered by the delivery task. The priority determination module is used to determine the task priority of each delivery task among multiple delivery tasks based on task attribute information. The scheduling module is used to allocate delivery vehicles to each delivery task according to the task priority of each delivery task, obtain the delivery vehicles corresponding to each delivery task, schedule the delivery vehicles corresponding to each delivery task, and execute each delivery task.

[0022] Thirdly, a computer device is provided, including a memory and a processor, the memory being connected to the processor, the processor being configured to execute one or more computer programs stored in the memory, and the processor, when executing the one or more computer programs, causing the computer device to implement the delivery task scheduling method of the first aspect described above.

[0023] Fourthly, a computer-readable storage medium is provided, which stores a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the delivery task scheduling method of the first aspect.

[0024] This application can achieve the following technical effects: Since the urgency of a task is determined based on the type of items to be delivered, and the scarcity of resources is determined based on the inventory of the items to be delivered, defining the urgency of a task by item type can accurately distinguish between essential emergency supplies and ordinary supplies, matching delivery priorities from the demand dimension and avoiding delays in the delivery of emergency supplies. Defining resource scarcity by item inventory can identify scarce supply delivery tasks from the supply dimension, prioritizing the delivery and circulation of scarce inventory supplies and preventing the accumulation or shortage of scarce supplies. Therefore, it can ensure the timeliness of delivery of highly urgent and scarce supplies and improve the rationality and practicality of delivery services. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the composition of a task scheduling system provided in an embodiment of this application; Figure 2 A flowchart illustrating a delivery task scheduling method provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a delivery task scheduling device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0028] It should be noted that, unless there is a conflict, the various features in the embodiments of this application can be combined with each other, all of which are within the protection scope of this application. Furthermore, although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Moreover, the terms "first," "second," and "third" used in this application do not limit the data or execution order, but only distinguish identical or similar items with essentially the same function and effect.

[0029] The technical solution of this application is applicable to task delivery scenarios, which can be urban short-distance instant delivery scenarios, completing the instant delivery of food delivery, fresh food supermarkets, express parcels and other supplies; task delivery scenarios can also be remote area supply delivery scenarios, completing the delivery of daily necessities, commonly used medicines, drinking water, epidemic prevention materials and other supplies; task delivery scenarios can also be emergency rescue supply scenarios, completing the delivery of emergency supplies such as first aid medicines, life-saving equipment, emergency food, lighting and communication support equipment and other emergency supplies; and so on, and is not limited to the examples here.

[0030] The technical solution of this application is applied to a task scheduling system. For ease of understanding, the task scheduling system of this application is first introduced. See [link to relevant documentation]. Figure 1 , Figure 1 This is a schematic diagram of the composition of a task scheduling system provided in an embodiment of this application, as shown below. Figure 1 As shown, the task scheduling system 10 includes a user interaction device 101, an edge scheduling device 102, a cloud device 103, and an execution device 104, wherein: User interaction device 101 is used to display the delivery request publishing interface, through which users can enter delivery request information such as the type of items to be delivered, quantity and / or weight of the materials, and delivery urgency. User interaction device 101 is also used to verify and authenticate the user's identity information and determine the user's permission level. User interaction device 101 can also obtain the task progress information of the delivery task, including task status and estimated arrival time.

[0031] The edge scheduling device 102 is deployed on an edge server or edge server cluster close to the task execution area. It is used to receive delivery request information submitted by the user interaction device 101 and realize the matching of material demand with vehicle resources. The edge scheduling device 102 can also evaluate task priority by comprehensively considering multiple factors such as material urgency, resource scarcity, delivery distance, and user permissions. The edge scheduling device 102 can also plan delivery routes.

[0032] Cloud device 103 is used for system-wide data storage, macro-level control, and situational monitoring. It enables real-time querying and resource locking of material inventory and equipment resources, providing data support for scheduling decisions by edge scheduling device 102. Cloud device 103 also provides compliance data for delivery route planning based on the global map and no-fly zone services, mitigating risks. Furthermore, it monitors the status of vehicles (tools used to transport goods) to obtain delivery task progress information.

[0033] The execution device 104 serves as the final carrier for the delivery task. It can include heavy-duty drones, high-speed lightweight drones, and cold chain drones, adapting to the delivery needs of different materials and scenarios. Heavy-duty drones are primarily used for delivering large quantities of heavy-weight daily necessities and engineering parts; high-speed lightweight drones are suitable for short-distance, high-efficiency emergency supplies and small-item delivery scenarios; and cold chain drones can meet the specialized delivery needs of temperature-controlled materials such as fresh produce and medicines. During the delivery task, the execution device 104 receives task instructions from the edge scheduling device 102, executes the delivery task according to the delivery route, and sends its own status, location information, task progress, and other data to the cloud device 103.

[0034] based on Figure 1 The task scheduling system shown can implement the technical solution of this application, which is specifically applied to edge scheduling devices. The technical solution of this application is described in detail below.

[0035] See Figure 2 , Figure 2 This is a flowchart illustrating a delivery task scheduling method provided in an embodiment of this application, as shown below. Figure 2 As shown, the method includes the following steps: S201, Obtain task attribute information corresponding to multiple delivery tasks to be executed.

[0036] Here, a delivery task refers to a task generated to meet the user's delivery needs, which is executed by a vehicle; the vehicle is used to carry the items to be delivered for the delivery task and deliver the items to the destination according to the delivery route.

[0037] Task attribute information includes task urgency and resource scarcity; task urgency is determined based on the type of items to be delivered, and resource scarcity is determined based on the inventory of the items to be delivered.

[0038] In some embodiments, the multiple delivery tasks to be executed include a target delivery task, which can be any one of the multiple delivery tasks; the task attribute information corresponding to the target delivery task can be determined through the following steps A1-A4: A1. Obtain the target requirement vector.

[0039] Here, the target demand vector is a standardized vector representing a user's delivery needs, derived from the user's input delivery demand information. The target demand vector includes the type of the target item to be delivered, which includes, but is not limited to, medicines, drinking water, and building materials. It also includes the delivery location of the target item, which refers to the location where the item needs to be delivered, and can be represented as geographic coordinates. Furthermore, it includes the required quantity of the target item, which can be either weight or quantity, depending on the type of item. For example, if the target item is measured in boxes, barrels, bottles, or other packaging containers, the required quantity is the number of items; if it is measured in kilograms or other weight units, the required quantity is the weight. The target demand vector can also include the expected delivery time window, which can be represented as a time range. Finally, it can include the urgency level specified by the user, and so on, not limited to the information listed here.

[0040] For example, the target demand vector can be represented as R, R={Type, Q, Location, TimeWindow, Urgency}, where Type represents the type of the target item, Q represents the quantity of the target item required, Location represents the delivery location of the target item, TimeWindow represents the expected delivery time window of the target item, and Urgency represents the urgency level.

[0041] In one specific implementation, the user interaction device acquires natural language or a form expressing the user's delivery request, converts the natural language or form into a standardized vector to obtain a target demand vector, and sends the target demand vector to the edge scheduling device. Alternatively, the user interaction device may also send a delivery task request carrying the natural language or form to the edge scheduling device, which then converts the natural language or form in the delivery task request to obtain the target demand vector.

[0042] A2. Determine the inventory of the target item based on its type.

[0043] In one specific implementation, a resource query request can be sent to a cloud device, carrying the type of the target item and the required quantity of the target item. The cloud device queries the database for the inventory of the target item based on its type. If the inventory of the target item is greater than or equal to the required quantity, a resource query response is sent to an edge scheduling device, carrying the inventory of the target item and its attribute information to determine the inventory. The attribute information includes, but is not limited to, the volume of the target item, its storage attributes (e.g., ambient temperature storage / refrigerated storage / frozen storage, fragile, shockproof, etc.), and its storage location. Furthermore, the cloud device locks an equal amount of the target item's inventory based on the required quantity to prevent over-allocation. If the inventory of the target item is less than the required quantity, the cloud device triggers a resource replenishment process, notifying the cloud device to replenish the target item to increase its inventory.

[0044] A3. Generate the delivery tasks corresponding to the target demand vector to obtain the target delivery tasks.

[0045] In one specific implementation, a task identifier corresponding to the target demand vector can be generated to obtain a target delivery task identifier, which is used to uniquely identify the target delivery task. Based on the target demand vector and the attribute information of the target item, task information for the target delivery task is generated. This task information includes, but is not limited to, the target delivery task identifier, the type of the target item, the load capacity of the target item, the volume of the target item, the storage location of the target item, the delivery location of the target item, the expected delivery time window of the target item, and the storage attributes of the target item, thereby obtaining the target delivery task. The load capacity of the target item is obtained based on the demand for the target item.

[0046] A4. Determine the urgency of the target delivery task based on the type of the target item, and determine the resource scarcity of the target delivery task based on the inventory of the target item.

[0047] In one specific implementation, based on a preset mapping relationship between item type and task urgency, the task urgency corresponding to the type of the target item is determined as the task urgency of the target delivery task. For example, the mapping relationship between item type and task urgency is shown in Table 1:

[0048] Table 1 Assuming the target item is of type 1, the urgency level of the target delivery task is determined to be Ed = e1.

[0049] The resource scarcity corresponding to the target delivery task is negatively correlated with the inventory of the target item. That is, the more inventory of the target item, the lower the resource scarcity corresponding to the target delivery task; the less inventory of the target item, the higher the resource scarcity corresponding to the target delivery task.

[0050] In one specific implementation, the resource scarcity corresponding to the target delivery task can be determined according to the following formula: Sd=1-(cs_d / cs_max), where Sd represents the resource scarcity of the target delivery task, cs_d represents the actual inventory of the target item, and cs_max represents the maximum inventory of the target item.

[0051] In steps A1-A4 above, delivery demand information is converted into demand vectors and delivery tasks corresponding to the demand vectors are generated. This determines the urgency and resource scarcity of delivery tasks and their corresponding tasks, thereby achieving digital standardization of user delivery demands and improving the efficiency and standardization of task information collection.

[0052] In addition to the aforementioned task urgency and resource scarcity, task attribute information can also include distance coefficients and user permission coefficients.

[0053] The distance coefficient is negatively correlated with the delivery distance corresponding to the delivery task. That is, the farther the delivery distance for the target delivery task, the smaller the distance coefficient; conversely, the closer the delivery distance, the larger the distance coefficient. The delivery distance corresponding to the target delivery task is the distance between the storage location and the delivery location of the target item, and can be obtained based on the task information of the target delivery task.

[0054] In one specific implementation, the distance coefficient corresponding to the target delivery task can be determined according to the following formula: Dd=1 / (1+c / dd), where Dd represents the distance coefficient corresponding to the target delivery task, c represents the distance constant, and dd represents the delivery distance corresponding to the target delivery task.

[0055] The user permission coefficient is positively correlated with the permission level of the user initiating the delivery task. That is, the higher the permission level of the user corresponding to the target delivery task, the larger the user permission coefficient of the target delivery task; the lower the permission level of the user corresponding to the target delivery task, the smaller the user permission coefficient of the target delivery task.

[0056] In one specific implementation, based on a preset mapping relationship between permission levels and user permission coefficients, the user permission coefficient corresponding to the permission level of the user initiating the target delivery task is determined as the user permission coefficient corresponding to the target delivery task. For example, the mapping relationship between permission levels and user permission coefficients is shown in Table 2:

[0057] Table 2 Assuming the user initiating the target delivery task has a permission level of Level 1, then the user permission coefficient corresponding to the target delivery task is determined to be Ld=l1.

[0058] It is understandable that for each of the multiple delivery tasks, the task attribute information corresponding to the delivery task can be determined in the manner described above, thereby obtaining the task attribute information corresponding to multiple delivery tasks.

[0059] In some embodiments, after generating the delivery task corresponding to the target demand vector and obtaining the target delivery task, candidate vehicles adapted to the target delivery task can be determined through the following steps B1-B2: B1. Determine the material attribute vector that matches the target demand vector.

[0060] The resource attribute vector matching the target demand vector represents the resource attributes of the target items to be delivered in the target delivery task. This resource attribute vector includes at least one of the target items' load capacity, volume, and storage attributes. It may also include the storage location of the target items. The resource attribute vector matching the target demand vector is obtained based on the task information of the target task.

[0061] For example, the material attribute vector matching the target demand vector can be represented as M, M={Weight, Volume, StorageCondition, SourceLocation}, where Weight represents the load of the target item, Volume represents the volume of the target item, StorageCondition represents the storage attribute of the target item, and SourceLocation represents the storage location of the target item.

[0062] B2. Based on the material attribute vector that matches the target demand vector, determine the set of candidate vehicles corresponding to the target delivery task.

[0063] The candidate vehicle set corresponding to the target delivery task includes at least one candidate vehicle that is compatible with the target delivery task.

[0064] In one specific implementation, the material attribute vector matching the target demand vector includes the target item's load capacity, volume, and storage attributes. Idle vehicles that simultaneously meet the following conditions can be selected from the set of available vehicles as candidate vehicles suitable for the target delivery task: Condition 1: The maximum load capacity of the vehicle is greater than the load capacity of the target item; the maximum load capacity of the vehicle refers to the maximum quantity or weight that the vehicle can carry.

[0065] Condition 2: The cargo hold volume of the vehicle is greater than the volume of the target item; Condition 3: The vehicle's temperature control capabilities must match the storage attributes of the target item. For example, if the target item's storage attributes include refrigerated storage, then the vehicle must have cold chain transportation capabilities.

[0066] If an idle vehicle simultaneously meets conditions 1, 2, and 3, then that idle vehicle will be considered a candidate vehicle suitable for the target mission.

[0067] If there are idle vehicles that meet condition 3 but not condition 1 or condition 2, the target delivery task can be split into multiple sub-tasks to obtain a set of sub-tasks corresponding to the target delivery task. Based on the task information of the target task, task information is generated for each sub-task in the set of sub-tasks corresponding to the target delivery task. Each sub-task is used as a new target delivery task. Based on the task information corresponding to each sub-task, the task attribute information corresponding to the new target delivery task is determined according to the method of determining task attribute information described above. Steps B1-B2 above are executed to determine the set of candidate vehicles corresponding to the new target delivery task. Then, the subsequent steps S202-S203 are executed.

[0068] The task information for each subtask includes a subtask identifier, which identifies the subtask. The task information for each subtask may also include the target delivery task identifier, the type of the sub-item (the item to be delivered by the subtask, derived from the target item), the sub-item's load capacity, storage location, delivery location, expected delivery time window, and storage attributes. Except for the subtask identifier, load capacity, volume, and storage location, all other content (including type, delivery location, expected delivery time window, and storage attributes) is identical across all subtasks.

[0069] If the items to be delivered by each subtask are scattered in different storage locations, the storage locations in the task information for each subtask will be different; if the items to be delivered by each subtask are in the same storage location, the storage locations in the task information for each subtask will be the same.

[0070] The load capacity in the task information for each sub-task is obtained by breaking down the demand for the target item based on the vehicle's maximum load capacity. Similarly, the volume in the task information for each sub-task is obtained by breaking down the volume of the target item based on the vehicle's cargo hold volume. If there is no available vehicle in the set that meets condition 1, then the demand for the target item must be broken down based on the maximum load capacity of the available vehicles to obtain the load capacity in the task information for each sub-task. If there is no available vehicle in the set that meets condition 2, then the volume of the target item must be broken down based on the cargo hold volume of the available vehicles to obtain the volume in the task information for each sub-task.

[0071] In steps B1-B2 above, determining candidate vehicles suitable for the delivery task based on the material attribute vector can improve the accuracy of vehicle matching.

[0072] It is understandable that for each of the multiple delivery tasks, the set of candidate vehicles corresponding to the delivery task can be determined in the manner described above, thereby obtaining the set of candidate vehicles corresponding to each delivery task.

[0073] S202, determine the task priority of each delivery task among the multiple delivery tasks based on the task attribute information corresponding to the multiple delivery tasks.

[0074] Among them, task priority reflects the order in which delivery tasks are carried out.

[0075] When task attribute information includes task urgency and resource scarcity, for a target delivery task, the task priority can be obtained by weighted summing of the task urgency and resource scarcity. The task priority of the target delivery task is represented as P1, where P1 = w1 × Ed + w2 × Sd, where Ed represents the task urgency, Sd represents the resource scarcity, and w1 and w2 are the weights corresponding to the task urgency and resource scarcity.

[0076] When the task attribute information also includes distance coefficients and user permission coefficients, for a target delivery task, the task priority can be obtained by weighted summing of the task urgency, resource scarcity, distance coefficient, and user permission coefficient. That is, P1 = w1 × Ed + w2 × Sd + w3 × Dd + w4 × Ld, where Dd represents the distance coefficient, Ld represents the user permission coefficient, and w3 and w4 are the weights corresponding to the distance coefficient and user permission coefficient, respectively.

[0077] Based on the urgency of the task and the scarcity of resources, the task priority of the delivery task is determined by combining the distance coefficient and user permission coefficient corresponding to the delivery task. This can avoid task delays caused by long-distance delivery time, take into account the impact of delivery distance on the actual delivery effect, and match the service priority needs of different users, thereby further improving the accuracy and comprehensiveness of task priority determination and making task scheduling fit the actual delivery scenario needs.

[0078] In some embodiments, before obtaining the task priority of the target delivery task by weighted summation of the task urgency, resource scarcity, distance coefficient, and user permission coefficient corresponding to the target delivery task, the weights of the task urgency, resource scarcity, distance coefficient, and user permission coefficient can be determined according to the delivery scenario to which the target delivery task belongs.

[0079] For example, if the target delivery task belongs to a medical scenario, then w1=0.5, w2=0.3, w3=0.1, w4=0.1; or, if the target delivery task belongs to a construction site scenario, then w1=0.2, w2=0.2, w3=0.4, w4=0.2.

[0080] Specifically, based on the scenario description information input by the user, the delivery scenario to which the target delivery task belongs can be determined, and then the weights corresponding to the task urgency, resource scarcity, distance coefficient, and user permission coefficient can be determined.

[0081] By determining the weights of task urgency, resource scarcity, distance coefficient, and user permission coefficient based on the delivery scenario, the scenario adaptability and flexibility of the scheduling scheme can be improved.

[0082] It is understandable that for each of the multiple delivery tasks, the task priority of the delivery task can be determined in the manner described above, thereby obtaining the task priority of each delivery task in the multiple delivery tasks.

[0083] It should be noted that if a delivery task (i.e., the aforementioned sub-task) is derived from an original delivery task, then the urgency, resource scarcity, and user permission coefficients of each delivery task derived from the same delivery task are the same. If the storage locations of the sub-items to be delivered by each delivery task derived from the same delivery task are the same, then the distance coefficients of each delivery task derived from the same delivery task are the same; if the storage locations of the sub-items to be delivered by each delivery task derived from the same delivery task are different, then the distance coefficients of each delivery task derived from the same delivery task are different.

[0084] S203: Based on the task priority of each delivery task, allocate delivery vehicles to each delivery task, obtain the delivery vehicles corresponding to each delivery task, schedule the delivery vehicles corresponding to each delivery task, and execute each delivery task.

[0085] In some embodiments, a delivery vehicle may be assigned to a target delivery task through the following steps C1-C4: C1. Determine the execution order of the target delivery tasks based on their priority.

[0086] Specifically, delivery tasks can be sorted according to their priority from highest to lowest to obtain their execution order, thus determining the execution order of the target delivery task. For delivery tasks with the same priority, they can be further sorted according to their creation time to obtain their execution order. It should be noted that if a delivery task (i.e., the aforementioned sub-task) is derived from an existing delivery task, then all delivery tasks derived from the same delivery task will have the same creation time.

[0087] C2. When the execution order reaches the target delivery task, send a broadcast message to each candidate vehicle in the candidate vehicle set corresponding to the target delivery task.

[0088] For an introduction to the candidate vehicle set corresponding to the target delivery task, please refer to the relevant descriptions in steps B1-B2 above, which will not be repeated here.

[0089] The broadcast message includes task information for the target delivery task; for details on the task information for the target delivery task, please refer to the relevant description in step S201 above, which will not be repeated here.

[0090] Broadcast messages are used to instruct each candidate vehicle in the candidate vehicle set corresponding to the target delivery task to bid for the target delivery task.

[0091] C3. Receive bidding information sent by each candidate vehicle.

[0092] The bidding information includes the task cost determined for each candidate vehicle based on the task information of the target delivery task.

[0093] Each candidate vehicle determines the distance between itself and the target item, the power consumption required for the target delivery task, and the load matching degree between itself and the target delivery task based on the load capacity and storage location of the target item. The task cost is determined based on the distance between itself and the target item, the power consumption required for the target delivery task, and the load matching degree between itself and the target delivery task.

[0094] Specifically, the candidate vehicle determines the distance between itself and the target item based on the distance between its own location and the storage location of the target item; the candidate vehicle determines the power consumption required for the target delivery task based on the distance between itself and the target item and the delivery speed of the vehicle (such as the flight speed of a drone); and the candidate vehicle determines the load matching degree between itself and the target delivery task based on the load capacity of the target item and the maximum load capacity of the candidate vehicle.

[0095] The specific formula for calculating load matching degree is as follows: LoadMatch represents the load matching degree between the candidate vehicle and the target delivery task, MaxPayload represents the maximum load of the candidate vehicle, and λ represents the optimal load rate, that is, the load rate of the vehicle under ideal loading conditions, for example, λ=0.8.

[0096] The formula for calculating the task cost is as follows: Cost = k1 × Dist + k2 × Energy + k3 × (1 - LoadMatch), where Dist represents the distance between the candidate vehicle and the target item, Energy represents the power consumption required for the target delivery task, and k1, k2 and k3 represent the weights of distance, power consumption and load matching degree, respectively.

[0097] Based on the distance between the storage location of the vehicle and the goods, the power consumption required for the delivery task, and the load matching degree between the vehicle and the target delivery task, the task cost is calculated so that the calculated task cost is close to the actual delivery cost and execution difficulty, ensuring that the finally selected vehicle can balance low delivery cost and high task adaptability.

[0098] C4. Based on the bidding information sent by each candidate vehicle, select the target candidate vehicle from the set of candidate vehicles corresponding to the target delivery task, and use it as the delivery vehicle corresponding to the target delivery task.

[0099] Among them, the target candidate vehicle is the candidate vehicle with the lowest mission cost.

[0100] After selecting a target candidate vehicle as the delivery vehicle corresponding to the target delivery task, a confirmation instruction can be sent to the target candidate vehicle to indicate that the target candidate vehicle has the right to perform the target delivery task, and a rejection notification can be sent to other candidate vehicles in the candidate vehicle set corresponding to the target delivery task, to indicate that the other candidate vehicles have not been granted the right to perform the target delivery task.

[0101] In steps C1-C4 above, allocating delivery vehicles to delivery tasks through broadcast bidding can minimize the cost of single-task delivery and improve the utilization efficiency of vehicle resources and the economy of delivery.

[0102] It is understandable that for each of the multiple delivery tasks, a delivery vehicle can be assigned to the delivery task according to the steps C2-C4 above, thereby obtaining the delivery vehicle corresponding to each delivery task.

[0103] In some embodiments, after selecting a target candidate vehicle as the delivery vehicle corresponding to the target delivery task, in response to a failure of the target candidate vehicle, or the target candidate vehicle being scheduled to perform other delivery tasks with higher priority, the target candidate vehicle is removed from the set of candidate vehicles corresponding to the target delivery task, and the above steps C2-C4 are re-executed to reallocate a delivery vehicle to the target delivery task.

[0104] After assigning delivery vehicles to each delivery task and obtaining the delivery vehicles corresponding to each delivery task, during the process of scheduling the delivery vehicles corresponding to each delivery task and executing each delivery task, the delivery vehicles corresponding to each delivery task execute each delivery task according to the delivery route. The delivery route is formed through the following steps: Step 1: Based on the A* algorithm, plan multiple discrete path points from the storage location of the target item to the delivery location of the target item for the delivery task. Then, perform B-spline curve fitting on the planned discrete path points to obtain the global path.

[0105] Step 2: The delivery vehicle senses dynamic obstacles (such as birds, other delivery vehicles, etc.), makes a local deflection based on the global path, and returns to the original global path after bypassing the dynamic obstacles, thus forming the delivery path.

[0106] By combining global planning with local obstacle avoidance, we can reduce the ineffective delivery mileage and energy consumption of delivery vehicles, thereby lowering the energy cost per delivery.

[0107] In the above Figure 2In the corresponding technical solution, task attribute information corresponding to multiple delivery tasks to be executed is obtained. The task attribute information includes the urgency of the task and the scarcity of resources. Then, based on the task attribute information, the task priority of each delivery task is determined, and delivery vehicles are allocated to each delivery task according to the task priority. The delivery vehicles corresponding to each delivery task are then dispatched to execute each task. Since the urgency of the task is determined based on the type of goods to be delivered, and the scarcity of resources is determined based on the inventory of the goods to be delivered, defining the urgency of the task by the type of goods can accurately distinguish between urgently needed supplies and ordinary goods, matching delivery priorities from the demand dimension and avoiding delays in the delivery of urgent supplies. Defining the scarcity of resources by the inventory of goods can identify scarce supply delivery tasks from the supply dimension, prioritizing the delivery and circulation of scarce inventory goods and preventing the accumulation or shortage of scarce goods. Therefore, it can ensure the timeliness of delivery of highly urgent and scarce goods and improve the rationality and practicality of delivery services.

[0108] The method of this application has been described above; the apparatus of this application will be described below.

[0109] See Figure 3 , Figure 3 This is a schematic diagram of the structure of a delivery task scheduling device provided in an embodiment of this application, as shown below. Figure 3 As shown, the delivery task scheduling device 30 includes: The task attribute acquisition module 301 is used to acquire task attribute information corresponding to multiple delivery tasks to be executed. The task attribute information includes task urgency and resource scarcity. The task urgency is determined based on the type of items to be delivered by the delivery task, and the resource scarcity is determined based on the inventory of the items to be delivered by the delivery task. The priority determination module 302 is used to determine the task priority of each delivery task among multiple delivery tasks based on task attribute information. The scheduling module 303 is used to allocate delivery vehicles to each delivery task according to the task priority of each delivery task, obtain the delivery vehicles corresponding to each delivery task, schedule the delivery vehicles corresponding to each delivery task, and execute each delivery task.

[0110] It should be noted that the aforementioned delivery task scheduling device 30 can execute the delivery task scheduling method provided in the embodiments of this application, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in the embodiments can be found in the delivery task scheduling method provided in the embodiments of this application.

[0111] See Figure 4 , Figure 4This is a schematic diagram of the structure of a computer device 40 provided in an embodiment of this application. The computer device 40 includes a processor 401 and a memory 402. The memory 402 is connected to the processor 401, for example, via a bus.

[0112] Processor 401 is configured to support the computer device 40 in performing the corresponding functions in the methods described in the above method embodiments. Processor 401 may be a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof. The aforementioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The aforementioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0113] Memory 402 is used to store program code, etc. Memory 402 may include volatile memory (VM), such as random access memory (RAM); memory 402 may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); memory 402 may also include combinations of the above types of memory.

[0114] The memory 402 is used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the delivery task scheduling method in the embodiments of this application. The processor executes various functional applications and data processing of the delivery task scheduling method by running the non-volatile software programs, instructions, and modules stored in the memory, thereby realizing the functions of the delivery task scheduling method provided in the above method embodiments.

[0115] Memory 402 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function. The data storage area may store data created based on the use of the delivery task scheduling device. In some embodiments, the memory may include memory remotely located relative to the processor, which can be connected to the delivery task scheduling device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0116] The one or more modules are stored in the memory. When executed by the one or more processors, they perform the delivery task scheduling method in any of the above method embodiments. For example, they perform the method steps described in the above method embodiments to realize the functions of the modules described in the above device embodiments.

[0117] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the method described in the foregoing embodiments.

[0118] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0119] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A delivery task scheduling method, characterized in that, include: Obtain task attribute information corresponding to multiple delivery tasks to be executed. The task attribute information includes task urgency and resource scarcity. The task urgency is determined based on the type of items to be delivered in the delivery task, and the resource scarcity is determined based on the inventory of the items to be delivered in the delivery task. Based on the task attribute information, determine the task priority of each of the multiple delivery tasks; Based on the task priority of each delivery task, a delivery vehicle is assigned to each delivery task to obtain the delivery vehicle corresponding to each delivery task, and the delivery vehicle corresponding to each delivery task is scheduled to execute the delivery task.

2. The method according to claim 1, characterized in that, The task attribute information also includes a distance coefficient and a user permission coefficient. The distance coefficient is negatively correlated with the delivery distance corresponding to the delivery task, and the user permission coefficient is positively correlated with the permission level corresponding to the user who initiated the delivery task. The multiple delivery tasks include a target delivery task. The step of determining the task priority of each delivery task among the multiple delivery tasks based on the task attribute information includes: The task priority of the target delivery task is obtained by weighted summing of the task urgency, resource scarcity, distance coefficient, and user permission coefficient corresponding to the target delivery task.

3. The method according to claim 2, characterized in that, Before obtaining the task priority of the target delivery task by weighted summation of the task urgency, resource scarcity, distance coefficient, and user permission coefficient corresponding to the target delivery task, the method further includes: Based on the delivery scenario to which the target delivery task belongs, determine the weights corresponding to the task urgency, resource scarcity, distance coefficient, and user permission coefficient.

4. The method according to any one of claims 1-3, characterized in that, The multiple delivery tasks include the target delivery task; The step of obtaining task attribute information corresponding to multiple delivery tasks to be executed includes: Obtain the target demand vector; the target demand vector is obtained by converting the delivery demand information input by the user, and the target demand vector includes the type of the target item to be delivered; Determine the inventory of the target item based on its type; Generate the delivery task corresponding to the target demand vector to obtain the target delivery task; Based on the type of the target item, determine the urgency of the target delivery task, and based on the inventory of the target item, determine the resource scarcity of the target delivery task.

5. The method according to claim 4, characterized in that, After generating the delivery task corresponding to the target demand vector and obtaining the target delivery task, the process further includes: Determine a material attribute vector that matches the target demand vector, wherein the material attribute vector includes at least one of the target item's load capacity, volume, and storage attributes; Based on the material attribute vector, a set of candidate vehicles corresponding to the target delivery task is determined, and the set of candidate vehicles includes at least one candidate vehicle that is adapted to the target delivery task.

6. The method according to any one of claims 1-3, characterized in that, The multiple delivery tasks include the target delivery task; The step of allocating delivery vehicles to each delivery task according to the task priority of each delivery task, and obtaining the delivery vehicles corresponding to each delivery task, includes: The execution order of the target delivery tasks is determined based on their task priorities. When the execution sequence turns to the target delivery task, a broadcast message is sent to each candidate vehicle in the candidate vehicle set corresponding to the target delivery task; wherein, the candidate vehicle set includes at least one candidate vehicle adapted to the target delivery task, and the broadcast message includes the task information of the target delivery task; Receive bidding information sent by each candidate vehicle, the bidding information including the mission cost determined by each candidate vehicle based on the mission information; Based on the bidding information, a target candidate vehicle is selected from the candidate vehicle set as the delivery vehicle corresponding to the target delivery task. The target candidate vehicle is the candidate vehicle with the lowest task cost.

7. The method according to claim 6, characterized in that, The target delivery task is used to deliver a target item. The task information includes the load capacity of the target item and the storage location of the target item. Based on the load capacity of the target item and the storage location of the target item, the candidate vehicle determines the distance between the candidate vehicle and the target item, the power consumption required for the target delivery task, and the load matching degree between the candidate vehicle and the target delivery task. The task cost is determined based on the distance, the power consumption, and the load matching degree.

8. The method according to claim 6, characterized in that, The step of allocating delivery vehicles to each delivery task according to the task priority of each delivery task, thereby obtaining the delivery vehicles corresponding to each delivery task, further includes: In response to a failure of the target candidate vehicle, or if the target candidate vehicle is scheduled to perform other delivery tasks with higher priority, after removing the target candidate vehicle from the candidate vehicle set, a broadcast message is resent to each candidate vehicle in the candidate vehicle set to reassign a delivery vehicle to the target delivery task.

9. A computer device, characterized in that, The device includes a memory and a processor, the memory being connected to the processor, the processor being configured to execute one or more computer programs stored in the memory, the processor causing the computer device to perform the method as described in any one of claims 1-8 when executing the one or more computer programs.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-8.

Images