Transportation connection planning method and device, electronic equipment and storage medium

Abstract

The application provides a transportation connection planning method and device, an electronic device and a storage medium, and belongs to the technical field of logistics transportation. The method comprises the following steps: obtaining a target transportation task combination; determining a candidate connection point of each to-be-planned transportation task, and splitting the corresponding to-be-planned transportation task according to the candidate connection point; determining a transportation task set corresponding to the target transportation task combination within a preset scheduling period according to the split to-be-planned transportation task; constructing a task connection constraint based on the transportation task set; solving a preset task execution object allocation model based on the task connection constraint and a preset scheduling interval constraint as constraint conditions and the minimum object quantity as a solving target to obtain transportation connection planning data; and determining a target task execution object for executing each transportation task in the transportation task set according to the transportation connection planning data. The application can improve the decision efficiency of transportation connection planning.

Description

Technical Field

[0001] This application relates to the field of logistics and transportation technology, and in particular to a transportation connection planning method and apparatus, electronic equipment and storage medium. Background Technology

[0002] The rapid development of internet technology has promoted the prosperity of the e-commerce industry. The development of e-commerce has further driven the growth of demand in the logistics and transportation industry, while also placing higher demands on the efficiency, cost control, and service quality of trunk logistics transportation.

[0003] In long-distance trunk transportation scenarios, to reduce labor costs and improve transportation safety, the driver relay transportation model has emerged. This transportation model breaks down long-distance tasks by setting up pick-up points along the way, transforming the traditional dual-driver alternation model into a single-driver segmented model. In this way, this transportation model can achieve the effect of "changing drivers without changing vehicles," effectively avoiding driver fatigue and thus improving the quality of driver rest.

[0004] However, the planning of connection points and scheduling of transportation tasks in the driver relay transportation mode in related technologies mainly rely on human experience, resulting in low decision-making efficiency in planning scenarios involving large-scale route and vehicle resources. Summary of the Invention

[0005] The main objective of this application is to provide a transportation connection planning method and apparatus, electronic device and storage medium, which aims to improve the decision-making efficiency of transportation connection planning.

[0006] To achieve the above objectives, a first aspect of this application proposes a transportation connection planning method, the method comprising: Obtain a target transportation task combination, which includes two transportation tasks to be planned, each of which represents a round-trip transportation task between the origin and destination of the target transportation task combination. Determine candidate pick-up points for each of the planned transportation tasks, and split the corresponding planned transportation tasks according to the candidate pick-up points; Based on the split transportation tasks to be planned, determine the set of transportation tasks corresponding to the target transportation task combination within the preset scheduling cycle; Based on the set of transportation tasks, a task connection constraint is constructed. The task connection constraint and the preset shift interval constraint are used as constraints. The preset task execution object allocation model is solved with the minimum number of objects as the solution objective to obtain transportation connection planning data. Based on the transportation connection planning data, determine the target task execution object for each transportation task in the set of transportation tasks.

[0007] To achieve the above objectives, a second aspect of this application provides a transportation connection planning device, the device comprising: An acquisition unit is used to acquire a target transportation task combination, which includes two transportation tasks to be planned, each representing a round-trip transportation task between the origin and destination of the target transportation task combination. A splitting unit is used to determine candidate connection points for each of the planned transportation tasks and to split the corresponding planned transportation tasks according to the candidate connection points. The first determining unit is used to determine, based on the split transportation tasks to be planned, the set of transportation tasks corresponding to the target transportation task combination within a preset scheduling cycle. The solution unit is used to construct task connection constraints based on the set of transportation tasks, use the task connection constraints and the preset shift interval constraints as constraints, and solve the preset task execution object allocation model with the minimum number of objects as the solution objective to obtain transportation connection planning data. The second determining unit is used to determine the target task execution object for each transportation task in the transportation task set based on the transportation connection planning data.

[0008] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0009] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0010] The transportation connection planning method, apparatus, electronic device, and storage medium proposed in this application decompose the corresponding transportation tasks to be planned based on candidate connection points, and then generate a set of transportation tasks within the scheduling cycle based on the decomposed tasks; further, through a task execution object allocation model, under the premise of task connection constraints and scheduling interval constraints, global optimization is performed with the minimum number of objects as the solution objective, and the theoretically optimal transportation connection planning data is automatically obtained; finally, the target task execution object of each transportation task in the transportation task set is accurately determined based on the transportation connection planning data, which solves the problem of low decision-making efficiency in large-scale route and vehicle resource planning scenarios caused by relying on human experience in related existing technologies, and improves the decision-making efficiency of transportation connection planning. Attached Figure Description

[0011] Figure 1 This is a flowchart of the transportation connection planning method provided in the embodiments of this application; Figure 2 This is provided by the embodiments of this application. Figure 1 The flowchart of step S102 in the document; Figure 3A This is a schematic diagram of the transportation task scheduling Gantt chart for the first task type provided in this application; Figure 3B This is a schematic diagram of the transportation task scheduling Gantt chart for the second task type provided in this application; Figure 4 This is another flowchart of the transportation connection planning method provided in the embodiments of this application; Figure 5 This is a flowchart of the construction task connection constraints provided in the embodiments of this application; Figure 6 This is another flowchart of the transportation connection planning method provided in the embodiments of this application; Figure 7 This is a schematic diagram of the transportation connection planning device provided in the embodiments of this application; Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0012] 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 merely illustrative and not intended to limit the scope of this application.

[0013] It should be noted that 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 may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0014] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0015] The rapid development of internet technology has promoted the prosperity of the e-commerce industry. The development of e-commerce has further driven the growth of demand in the logistics and transportation industry, while also placing higher demands on the efficiency, cost control, and service quality of trunk logistics transportation.

[0016] In long-distance trunk transportation scenarios, to reduce labor costs and improve transportation safety, the driver relay transportation model has emerged. This transportation model breaks down long-distance tasks by setting up pick-up points along the way, transforming the traditional dual-driver alternation model into a single-driver segmented model. In this way, this transportation model can achieve the effect of "changing drivers without changing vehicles," effectively avoiding driver fatigue and thus improving the quality of driver rest.

[0017] The relevant technologies rely mainly on human experience for the selection of transfer points and scheduling planning in the driver relay transportation mode. This approach suffers from low decision-making efficiency and high error rate in planning scenarios involving large-scale route and vehicle resources.

[0018] Based on this, embodiments of this application provide a transportation connection planning method and apparatus, electronic device and storage medium, aimed at improving the decision-making efficiency of transportation connection planning.

[0019] The transportation connection planning method, apparatus, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the transportation connection planning method in this application is described.

[0020] The transportation connection planning method provided in this application relates to the field of logistics and transportation technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the transportation connection planning method, but is not limited to the above forms.

[0021] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0022] Figure 1 This is an optional flowchart of the transportation connection planning method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0023] Step S101: Obtain the target transportation task combination; Step S102: Determine the candidate transfer points for each planned transportation task, and split the corresponding planned transportation task according to the candidate transfer points. Step S103: Based on the split transportation tasks to be planned, determine the set of transportation tasks corresponding to the target transportation task combination within the preset scheduling cycle. Step S104: Construct task connection constraints based on the transportation task set, use task connection constraints and preset shift interval constraints as constraints, and solve the preset task execution object allocation model with the minimum number of objects as the solution objective to obtain transportation connection planning data. Step S105: Determine the target task execution object for each transportation task in the set of transportation tasks based on the transportation connection planning data.

[0024] Steps S101 to S105, as illustrated in this embodiment, involve splitting the corresponding planned transportation tasks based on candidate connection points, and then generating a set of transportation tasks within the scheduling cycle based on the split tasks. Further, through a task execution object allocation model, under the premise of task connection constraints and scheduling interval constraints, global optimization is performed with the minimum number of objects as the solution objective, automatically obtaining the theoretically optimal transportation connection planning data. Finally, based on the transportation connection planning data, the target task execution object for each transportation task in the transportation task set is accurately determined. This solves the problem of low decision-making efficiency in large-scale route and vehicle resource planning scenarios caused by relying on manual experience in existing technologies, thus improving the decision-making efficiency of transportation connection planning.

[0025] In step S101 of some embodiments, the target transportation task combination can represent a set of associated tasks bundled together in a logistics transportation scenario to facilitate round-trip scheduling. The target transportation task combination includes two unplanned transportation tasks. These two unplanned transportation tasks represent round-trip transportation tasks between the origin and destination of the target transportation task combination; that is, two trunk line transportation journeys that exchange origin and destination but have opposite transportation directions, such as two unplanned transportation tasks from Shenzhen to Beijing and back. The unplanned transportation tasks represent specific one-way transportation routes, such as a transportation task from Shenzhen to Beijing. Each unplanned transportation task includes corresponding transportation task information, which may specifically include the latitude and longitude of the origin and destination, departure time, and arrival time. Subsequently, during transportation connection planning, each target transportation task combination is planned separately.

[0026] Before planning transportation connections, the original transportation data can be preprocessed. Specifically, invalid transportation tasks with missing or incomplete information can be screened out, and the selected invalid transportation tasks and their combinations can be filtered out to select long-distance trunk line tasks that meet the intelligent driving relay mode, thus obtaining the target transportation task combination.

[0027] In step S102 of some embodiments, candidate transfer points for each planned transportation task can be determined first. The candidate transfer point represents the geographical location of the transportation route of the planned transportation task, which is divided for task handover, driver rest, or changing driving mode (such as changing from two drivers to one driver). The candidate transfer point can be represented in the form of geographical latitude and longitude coordinates.

[0028] In some embodiments, please refer to Figure 2 The process involves determining candidate pick-up points for each planned transportation task, including the following steps S201 to S203: Step S201: Perform route planning for each transportation task to be planned to obtain the corresponding set of target waypoints; Step S202: Based on multiple preset ratio coefficients and the total mileage of each planned transportation task, the planned transportation task is divided into routes to obtain multiple reference connection points. Step S203: Based on the preset neighborhood range corresponding to the reference connection point, select the candidate connection point corresponding to the transportation task to be planned from the target route point set.

[0029] In step S201 of some embodiments, route planning can be performed on each planned transportation task to obtain a corresponding set of target waypoints. The set of target waypoints represents the geographic coordinate sequence constituting the complete travel trajectory of the planned transportation task. The set of target waypoints can include the latitude and longitude information of multiple waypoints for the planned transportation task, as well as the mileage information to different waypoints. Since trunk logistics transportation typically spans long geographical distances (e.g., over 1000 kilometers) and involves numerous waypoints, precise trajectories along the route can be obtained through route planning technology to ensure the scientific validity and feasibility of site selection. Specifically, the route planning interface of a Geographic Information System (GIS) can be called, and the latitude and longitude coordinates of the origin and destination of the planned transportation task can be input. The GIS can then return the latitude and longitude coordinate sequence along the transportation route, thereby obtaining the set of target waypoints. For example, for a planned transportation task from Shenzhen to Zhengzhou, the GIS will calculate and output a list of coordinates for all highway sections, service areas, and other nodes along the route, providing data support for subsequent selection of suitable connecting locations.

[0030] In step S202 of some embodiments, the planned transportation task can be routed according to multiple preset ratio coefficients and the total mileage corresponding to each planned transportation task, resulting in multiple reference connection points. The preset ratio coefficients represent the route segmentation ratios set to evenly distribute driving tasks or meet specific operating modes, such as 1 / 3, 1 / 2, or 2 / 3. Each ratio coefficient can calculate a corresponding reference connection point. Specifically, the total mileage of the planned transportation task can be obtained first, and then the corresponding mileage positions can be calculated according to the preset ratio coefficients, with the calculated mileage positions used as reference connection points. For example, if the preset ratio coefficients are set to 1 / 3, 1 / 2, and 2 / 3, and the total task mileage is 1200 kilometers, three reference connection points can be marked at mileage positions 400 kilometers, 600 kilometers, and 800 kilometers from the origin of the planned transportation task. In this way, the approximate connection area can be quickly located using reference connection points, narrowing the search range for connection points, avoiding blind searching along the entire long-distance route, and reducing computational complexity.

[0031] In step S203 of some embodiments, candidate connection points corresponding to the planned transportation task are selected from the target route point set based on a preset neighborhood range corresponding to the reference connection point. The preset neighborhood range is determined based on the reference connection point and a preset second distance threshold between the reference connection point and the reference connection point. The second distance threshold represents the maximum distance limit allowed for the selected actual connection point to deviate from the reference connection point, for example, 50 kilometers. The preset neighborhood range represents the search interval defined by the second distance threshold, centered on or based on the reference connection point. As exemplified above, if the second distance threshold is 50 kilometers, for a reference connection point at 1 / 3 of the distance, assuming the two transportation tasks interrupted by the reference connection point are task1 and task2, the candidate connection points x, y, and z within the preset neighborhood range of the reference connection point at 1 / 3 of the distance are selected through the following constraints: distance(1 / 3)-50km<=distance(x) <distance(1 / 3);(1) distance(1 / 3)<=distance(y) <distance(1 / 3)+50km;(2) distance(1 / 3)+50km<=distance(z);(3) task1<=1000km and task2<=1000km; (4) Thus, for each reference pick-up point, three candidate pick-up points can be obtained. Each candidate pick-up point represents a specific latitude and longitude coordinate selected from the set of target waypoints that falls within the neighborhood of the reference pick-up point and meets the actual road conditions. If there are three reference pick-up points, nine (or fewer) candidate pick-up points can be obtained. The number of reference pick-up points can be set according to actual needs; the above example does not constitute a limitation on the examples in this application. This allows for accurate selection of geographical coordinates with actual parking or pick-up potential from a massive number of waypoints, reducing computational complexity.

[0032] This application's embodiments address the technical challenges of large computational scale and high complexity in connecting point location selection during long-distance trunk transportation by employing a hierarchical screening strategy. By referencing the local neighborhood of connecting points for screening, the search space of the connecting point location algorithm is reduced while ensuring the rationality of the connecting point location, thus lowering computational complexity and improving the efficiency of connecting point location calculation. Furthermore, it ensures that the generated candidate connecting points not only conform to geographical realities but also meet the operational requirements of the intelligent driving relay mode.

[0033] After determining the candidate transfer points, the corresponding planned transportation tasks can be broken down based on each candidate transfer point. For example, the target transportation task combination includes the following two planned transportation tasks: Task 1: Shenzhen to Zhengzhou, task time from 04:00 on November 1st to 06:00 on November 2nd, and Task 2: Zhengzhou to Shenzhen, task time from 06:00 on November 1st to 08:00 on November 2nd. If the selected candidate transfer point is Jiujiang, the planned transportation tasks in the target transportation task combination can be broken down based on this candidate transfer point to obtain... The following tasks are assigned: Task 1: Shenzhen to Jiujiang, from 04:00 to 17:00 on November 1st; Task 2: Jiujiang to Zhengzhou, from 17:00 on November 1st to 06:00 on November 2nd; Task 3: Zhengzhou to Jiujiang, from 06:00 to 19:00 on November 1st; Task 4: Jiujiang to Shenzhen, from 19:00 on November 1st to 08:00 on November 2nd. By breaking down the planned transportation tasks in the target transportation task combination based on candidate transfer points, a transportation task plan for the day can be obtained.

[0034] In step S103 of some embodiments, based on the split transportation tasks to be planned, a set of transportation tasks corresponding to the target transportation task combination within a preset scheduling cycle is determined. The preset scheduling cycle represents the time span for scheduling planning, which may include a complete operating month or a specific number of days (such as a consecutive week); the transportation task set represents all transportation sub-tasks obtained by expanding the daily split tasks obtained in the aforementioned steps according to the scheduling cycle. The transportation sub-tasks in the transportation task set are all tasks waiting to be assigned to task execution objects, and each transportation sub-task includes corresponding transportation task information. In actual planning scenarios, the transportation tasks to be planned usually have fixed schedules, that is, specific dates of execution each week (such as Monday to Saturday). As exemplified above, if the task schedule of the target transportation task combination is daily departures and the scheduling cycle is 31 days, then the four daily sub-tasks split in step S102 (each round trip is split into two segments) can be expanded into 124 specific transportation sub-tasks in the time dimension.

[0035] In step S104 of some embodiments, a task execution object can be assigned to each transportation subtask in the transportation task set. Specifically, a task connection constraint can be constructed based on the transportation task set, and the task connection constraint and the preset scheduling interval constraint can be used as constraints. The preset task execution object allocation model is solved with the minimum number of objects as the solution objective to obtain transportation connection planning data. In this context, the task execution object represents the driver (i.e., the driver) performing the transportation task; the task connection constraint represents the spatiotemporal logical constraints that must be met when allocating consecutive tasks; and the shift interval constraint represents the constraint on ensuring the rest time of the task execution object. For example, starting from the first transportation task performed by the task execution object, every preset time period (e.g., two days), two consecutive rest periods of duration N (the value of N can be customized) need to be provided to ensure that the task execution object has a fixed continuous rest period every day, avoiding fatigue driving. The objective of finding the minimum number of objects represents minimizing the number of task execution objects allocated to the transportation task set. For each transportation task set obtained by dividing the candidate connection point, the preset task execution object allocation model can be solved using the above constraints and objectives to obtain the minimum number of objects corresponding to each transportation task set. The task execution object allocation model can be a multi-objective resource scheduling optimization model, and its solution strategy can be implemented using a heuristic greedy algorithm.

[0036] In some embodiments, the transportation connection planning data is obtained by solving a preset task execution object allocation model with the constraints of task connection constraints and preset scheduling interval constraints, and with the goal of minimizing the number of objects, including the following steps: The model uses a set of transportation tasks as input to a pre-defined task execution object allocation model. Based on task connection constraints and pre-defined shift interval constraints, it selects the task execution objects corresponding to the transportation tasks in the pre-defined set of used objects. When the filtering result indicates successful filtering, transportation connection planning data is generated based on the selected candidate task execution objects, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved.

[0037] In this embodiment, specifically, the set of transportation tasks is used as the input to the preset task execution object allocation model. The input data of the task execution object allocation model can include the transportation task information of each transportation sub-task in the transportation task set, such as task start time, task end time, origin and destination. The input data of the model can also include the state set information of the task execution objects. Specifically, the state set information can include the available object set S, the used object set A, and the unused object set U. This allows the model to know which driver resources are available. The used object set includes task execution objects that have been assigned at least one transportation task in the current scheduling calculation process. The unused object set includes task execution objects that have not been assigned a transportation task. The available object set includes candidate task execution objects that can be assigned transportation tasks, selected from the used object set or the unused object set. The solution objective of the task execution object allocation model is to minimize the total number of task execution objects. When allocating task execution objects to transportation sub-tasks, it can be determined first whether the task execution objects of the assigned tasks can continue to execute other tasks after completing the previously assigned tasks. That is, available task execution objects can be selected from the used object set first. Specifically, when task execution objects exist in the used object set, the task execution objects in the used object set can be traversed first, and their availability can be judged in turn. For each task execution object in the used object set, it can be determined whether it meets the task connection constraints and layout interval constraints. In this way, the task execution objects corresponding to the transportation tasks in the transportation task set can be filtered from the used object set to obtain the filtering results.

[0038] When the filtering result indicates that the filtering is successful, it means that there is at least one task execution object in the set of used objects that meets the above constraints. At this time, the object identifier corresponding to the filtered task execution object can be stored in the set of available objects, and the task identifier of the corresponding transportation subtask can be added to the set of tasks to be executed corresponding to the filtered candidate task execution object. There can be multiple candidate task execution objects corresponding to one transportation subtask.

[0039] Furthermore, transportation connection planning data can be generated based on the selected candidate task execution objects, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved. The minimum number of objects can be determined based on the number of objects in the selected candidate task execution objects. Transportation connection planning data can include information such as task execution objects, corresponding transportation tasks, task execution time, task execution sequence, origin and destination of transportation tasks, etc. In terms of data structure, it is typically represented as a detailed instruction set linking people, vehicles, goods, yards, and time; visually, it is represented as a transportation task scheduling Gantt chart. For example, please refer to... Figure 3A , Figure 3AThis is a schematic diagram of the transportation task scheduling Gantt chart for the first task type provided in this application. The horizontal axis represents the time axis (date and specific time), showing the time span of the transportation task execution. The vertical axis represents the task execution object number (e.g., task execution objects 1 to 4). Each row represents the work schedule of a specific task execution object. Each square represents a specific transportation task, corresponding to the vehicle number legend in the upper right corner (vehicle 1, vehicle 2, etc.). Note that different colored squares may appear in the same row (same task execution object), which reflects the driver-vehicle debinding feature of this application, that is, the same driver can drive different vehicles in different segments. The key parameters of the transportation task are marked in detail inside the square, which may include the origin and destination of the transportation task, such as Dongguan City to Shangrao City, the start and end time of the transportation task, such as 09:00 departure and 22:10 arrival, and the distance and time of the transportation task, such as 891km / 13.2h. The dotted lines between different squares are used to connect the previous transportation task and the next transportation task of the same task execution object, indicating the connection process between transportation tasks. The labels on the dotted lines (such as 24.0h rest) indicate the rest period between two transport tasks. Figure 3A This shows a Gantt chart illustrating the scheduling for scenarios where task execution objects should ideally only perform round-trip tasks between two points. For example, task execution object 1 first executes the journey from Dongguan to Shangrao (outbound), then after a break, executes the journey from Shangrao to Dongguan (return).

[0040] This application's embodiments perform rigorous constraint screening on the set of used objects to ensure that the generated scheduling results strictly comply with transportation timeliness (task connection constraints) and driving compliance (scheduling interval constraints), avoiding the risk of fatigue driving caused by human scheduling negligence in related technologies. Simultaneously, this application maximizes the task saturation of task execution objects by prioritizing the reuse of already used task execution objects, reducing idle capacity and minimizing labor costs in trunk logistics transportation, thereby achieving the effect of reducing operating costs while ensuring transportation safety.

[0041] In some embodiments, when the filtering result indicates successful filtering, transportation connection planning data is generated based on the filtered candidate task execution objects, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved, including the following steps: When there are multiple candidate task execution objects selected, the target task execution object corresponding to the transportation task is determined from the multiple candidate task execution objects based on the transportation task type preference target. Transportation connection planning data is generated based on the target task execution object, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved.

[0042] As mentioned above, there can be multiple candidate task execution objects for each transportation subtask. When there are multiple candidate task execution objects, the unique target task execution object corresponding to the transportation subtask can be selected from the multiple candidate task execution objects according to the solution objective of the transportation task preference type.

[0043] In this embodiment, specifically, the solution objective of the task execution object allocation model also includes a transportation task type preference objective. This objective is a preset transportation strategy selection logic designed to optimize the topology of transportation routes and improve the user experience. The transportation task types include a first task type and a second task type. The first task type indicates that the origin of the current planned transportation task is the same as the destination of the previous executed task of the candidate task execution object, and the destination of the current planned transportation task is the same as the origin of the previous executed task of the candidate task execution object. The first task type represents a closed-loop round-trip task type in logistics scheduling, meaning the endpoint of the current transportation task returns to the starting point of the previous transportation task, thus forming a spatial closed loop. When the transportation task type preference is set to the first task type, it means that the target task execution object whose previous executed task can form a round-trip transportation task with the current planned transportation task is selected from among multiple candidate task execution objects (i.e., after executing the transportation task from A to B, the transportation task from B to A is executed first). For example, in the set of used objects, there are two candidate task execution objects that both meet the above constraints. Candidate task execution object A has just completed the transportation task from the Shenzhen distribution center to the Jiujiang transfer point (i.e., the previous task executed by the candidate task execution object), and candidate task execution object B has just completed the transportation task from the Zhengzhou distribution center to the Jiujiang transfer point (i.e., the previous task executed by the candidate task execution object). The current transportation task to be planned is to return from the Jiujiang transfer point to the Shenzhen distribution center. If the solution objective is to prefer the first task type, that is, to prioritize the selection of candidate task execution object A as the target task execution object for the corresponding transportation task.

[0044] The transportation task type also includes a second task type. The second task type indicates that the origin of the current planned transportation task is the same as the destination of the previous executed task of the candidate task execution object, but the destination of the current planned transportation task is different from the origin of the previous executed task of the candidate task execution object. The second task type represents a relay extension task or a complete segment task in logistics scheduling, used for relay transportation on long-distance trunk lines to ensure one-way flow of goods. When the transportation task type preference is the second task type, it means that priority is given to selecting the target task execution object from among multiple candidate task execution objects whose previous executed task can form a complete segment transportation task with the current planned transportation task (i.e., after executing the transportation task from A to B, priority is given to executing the transportation task from B to C). For example, in the set of used objects, there are two candidate task execution objects that both satisfy the above constraints. Candidate task execution object A has just completed a transportation task from the Shenzhen distribution center to the Jiujiang transfer point, and candidate task execution object B has just completed a transportation task from the Zhengzhou distribution center to the Jiujiang transfer point. The current planned transportation task is to continue transportation from the Jiujiang transfer point to the Zhengzhou distribution center. At this point, the origin (Jiujiang) of the current transportation task to be planned is the same as the destination of the previous task of candidate task execution object A, but the destination (Zhengzhou) is different from the origin (Shenzhen) of the previous task. If the goal of solving is to prefer the second task type, that is, to prioritize the selection of candidate task execution object A as the target task execution object of the corresponding transportation task.

[0045] It should be noted that if there are multiple candidate task execution objects that meet the transportation task type preference, then a candidate task execution object can be randomly selected from the candidate task execution objects as the target task execution object.

[0046] Thus, through the aforementioned steps, the target task execution object corresponding to a transportation task can be determined from multiple candidate task execution objects based on transportation task type preferences. Further, transportation connection planning data can be generated based on the target task execution object, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved. Specifically, the currently planned transportation task can be bound to its corresponding target task execution object, and this binding relationship can be written into the final planning table, while simultaneously updating the status of the target task execution object for the next round of calculation.

[0047] In some embodiments, please refer to Figure 3B , Figure 3B This is a schematic diagram of the transportation task scheduling Gantt chart for the second task type provided in this application. Figure 3B Basic information of the Gantt chart for scheduling and Figure 3A The same as in, but Figure 3B This describes a scenario where the task execution object is best suited to perform the entire transportation task. Figure 3BThe text shows that the transportation tasks performed by the task execution objects have a unidirectional extension trend. For example, the task is executed from Dongguan to Shangrao first, and then after a rest, the task is executed from Shangrao to Linyi. The transportation task path forms a structure from A to B and from B to C, which is suitable for long-distance relay transportation.

[0048] This application's embodiment solves the problem of random allocation under resource-sufficient conditions by introducing an optimization mechanism based on transportation task type preferences, thus improving the scientific nature of the scheduling scheme. By prioritizing round-trip or full-segment tasks, it avoids fragmentation of transportation tasks, reduces the risk of task performers being stranded in non-local cities, and ensures the regularity of transportation routes. Therefore, this application's embodiment can ensure that the task arrangement for each task performer conforms to optimal business logic and compliance requirements while using the minimum number of objects.

[0049] In some embodiments, the transportation connection planning data is obtained by solving a preset task execution object allocation model with the constraints of task connection constraints and preset scheduling interval constraints, and with the goal of minimizing the number of objects, in order to obtain transportation connection planning data. The method further includes the following steps: When the filtering result indicates that the filtering failed, the input of the model is assigned with the transportation task set as the preset task execution object, and the target task execution object corresponding to the transportation task in the preset unused object set is randomly selected. Transportation connection planning data is generated based on the target task execution object, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved.

[0050] As previously described, the algorithm first filters candidate task execution objects corresponding to transportation tasks in the transportation task set from the used object set. If the filtering result indicates a failure, it means that after traversing the used object set, no task execution object simultaneously satisfies both the task connection constraint and the scheduling interval constraint. In this case, a target task execution object corresponding to the transportation task in the transportation task set can be randomly selected from a pre-defined unused object set. The unused object set represents a resource pool of idle task execution objects that have not yet been assigned any transportation tasks in the current scheduling cycle. Specifically, when the filtering result indicates a failure, the transportation task set is used as the input to the task execution object allocation model. Since the task execution objects in the unused object set are completely idle, their initial positions and time windows are highly flexible (or it is assumed that they can originate from any station). Therefore, the algorithm adopts a random selection strategy to select the target task execution object from this set. For example, when a transportation task from Zhengzhou to Shenzhen to be assigned cannot be undertaken by an existing task execution object A or task execution object B, a new task execution object C can be automatically selected from the pool of standby task execution objects to execute the transportation task, and the status of task execution object C will be updated from unused to used.

[0051] Then, transportation connection planning data can be generated based on the target task execution object, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved. The global resource status can be updated, and the selected target task execution object can be moved into the used object set so that the capacity of the target task execution object can be reused when subsequent tasks are allocated.

[0052] This application's embodiments ensure the completeness of the scheduling algorithm and the reliability of task execution by dynamically introducing new resources as a compensation mechanism when existing capacity cannot meet demand. As a fallback strategy, this application's embodiments, while increasing the number of task execution objects locally, guarantee that every transportation task is effectively covered globally, avoiding task backlog or scheduling failures due to excessively tight resource constraints. Simultaneously, by distinguishing between used and unused object sets and clarifying the priority of resource allocation, a strategy of reusing first and adding later is adopted. This ensures the smooth completion of all trunk line tasks while controlling the total number of required task execution objects to a theoretically minimum, thus optimizing the allocation of transportation capacity resources.

[0053] In some embodiments, please refer to Figure 4 Based on the set of transportation tasks, task connection constraints are constructed. Using these constraints and preset scheduling interval constraints as conditions, and with the goal of minimizing the number of objects, a preset task execution object allocation model is solved to obtain transportation connection planning data. The transportation connection planning method provided in this embodiment further includes the following steps S401 to S403: Step S401: For each target transportation task combination, select at least one target transfer point from the candidate transfer points whose number of task execution objects is the minimum number of task execution objects. Step S402: Determine the city identifier corresponding to each target connection point, and count the frequency of each city identifier in all target transportation task combinations; Step S403: Determine the global connection point among the target connection points corresponding to the target transportation task combination based on the frequency corresponding to each city identifier.

[0054] The transportation connection planning data includes the number of task execution objects required for each set of transportation tasks derived from each candidate connection point. For each candidate connection point, the system splits the original planned transportation task into a set of transportation tasks based on its geographical location and independently calculates the number of task execution objects required under the corresponding splitting scheme using the task execution object allocation model. For example, for a target transportation task combination from Shenzhen to Zhengzhou, the system may generate two candidate connection points, A and B. The task execution object allocation model will calculate separately: if A is selected, 3 task execution objects are required to complete the tasks in the transportation task set; if B is selected, 4 task execution objects are required.

[0055] In step S401 of some embodiments, for each target transportation task combination, at least one target connection point with the minimum number of task execution objects can be selected from the candidate connection points. As described above, the task execution object allocation model can be solved to obtain the number of task execution objects corresponding to the transportation task set divided according to each candidate connection point. For the same transportation task set, the number of task execution objects may be the same. For example, the number of task execution objects corresponding to candidate connection points A and B may both be 9, and the number of task execution objects corresponding to candidate connection points C and D may both be 6. The target connection point indicates that for all candidate connection points corresponding to the target transportation task combination, at least one target connection point corresponding to the minimum number of task execution objects can be determined. As exemplified above, candidate connection points C and D are determined as target connection points.

[0056] It is understandable that both target and candidate transfer points are represented by latitude and longitude coordinates. Different transfer points have different coordinates, but may belong to the same city. Therefore, based on the at least one target transfer point obtained from the aforementioned steps, a unique global transfer point corresponding to the target transportation task combination can be determined.

[0057] In step S402 of some embodiments, the city identifier corresponding to each target connection point can be determined first. The city identifier represents the name of the administrative region to which the target connection point belongs. The latitude and longitude coordinates of the target connection point can be resolved into a specific city name (such as Jiujiang City, Shangrao City, etc.) by calling the geographic reverse encoding interface of GIS. Then, the frequency of each city identifier can be counted in all target transportation task combinations, where the frequency represents the total number of times a certain city appears as the optimal solution in all target transportation task combinations in the entire logistics network. For example, there are 3 target transportation task combinations. The target connection points of target transportation task combination 1 are as follows: point A in city 1, point B in city 1, and point E in city 2; the target connection points of target transportation task combination 2 are as follows: point C in city 1 and point F in city 2; the target connection point of target transportation task combination 3 is as follows: point G in city 3. The frequency of city 1 is 3 times, the frequency of city 2 is 2 times, and the frequency of city 3 is 1 time in the 3 target transportation task combinations.

[0058] In step S403 of some embodiments, a global connection point can be determined among the target connection points corresponding to the target transportation task combination based on the frequency corresponding to each city identifier. The global connection point refers to the actual operational connection location finally determined after comprehensively considering the resource efficiency (local optimum) of a single target transportation task combination and the management synergy (global optimum) of the entire logistics network. Specifically, for a specific target transportation task combination, if multiple target connection points with the fewest task execution objects are selected, the global connection point can be determined for the target transportation task combination based on the frequency of the city identifiers counted in step S402, ranked from highest to lowest frequency. Specifically, the target connection point in the city corresponding to the city identifier with the highest frequency is taken as the global connection point of the target transportation task combination. For example, if target transportation task combination 1 includes city 1, and city 1 is to be selected as the connection point, since the city identifiers corresponding to points A and B are both city 1, one of points A and B can be randomly selected as the target connection point for target transportation task combination 1. If target transportation task combination 2 includes city 1, point C in city 1 is selected as the global connection point. Since the target transportation task combination 3 only contains city 3, city 3 can be selected as the global connection point. In this way, the global optimal solution can be extracted from a large number of local optimal solutions, ensuring that as many target transportation task combinations as possible can share the connection facilities of the same city without increasing the task execution object cost of a single target transportation task combination (while still maintaining the minimum number of task execution objects).

[0059] This application's embodiments improve the scale effect and management efficiency of trunk logistics networks through a decision-making logic that moves from local optimization to global aggregation. First, it ensures that the selection of transfer points for each target transportation task combination is absolutely optimal in terms of labor costs (minimizing the number of task execution objects). Second, by introducing city frequency as a secondary screening indicator, it causes dispersed transfer points to cluster as much as possible in a few central cities. Thus, this application's embodiments enable centralized construction or leasing of transfer service areas, reducing the marginal cost of infrastructure, and facilitating centralized scheduling management of task execution objects, thereby achieving a dual optimization of the accuracy and economy of logistics network planning.

[0060] In some embodiments, please refer to Figure 5 The task connection constraints are constructed based on the set of transportation tasks, including the following steps S501 to S504: Step S501: Sort the transportation tasks in the transportation task set according to the task start time of each transportation task in the transportation task set to obtain the transportation task sequence. Step S502: Construct spatial connection constraints based on the empty driving distance between two transportation tasks with adjacent task start times in the transportation task sequence and a preset first distance threshold. Step S503: Based on the task end time of historical transportation tasks, the empty running time between two transportation tasks with adjacent task start times in the transportation task sequence, and the task start time of transportation tasks in the transportation task sequence, construct time connection constraints. The task end time of historical transportation tasks represents the end time of the last transportation task in the set of transportation tasks planned in the previous historical period. Step S504: Construct task connection constraints based on spatial connection constraints and temporal connection constraints.

[0061] Task coordination constraints include spatial coordination constraints and temporal coordination constraints. Spatial coordination constraints are used to limit the rationality of transportation task allocation in the geospatial dimension, and their core logic is to control ineffective empty mileage. Temporal coordination constraints are used to verify the feasibility of transportation task allocation in the temporal dimension. The specific meaning and construction method of task coordination constraints will be introduced next.

[0062] In step S501 of some embodiments, the transportation tasks in the transportation task set can be sorted according to the task start time (i.e., the planned departure time) of each transportation task in the transportation task set to obtain a transportation task sequence. The transportation task sequence represents a linear list generated by arranging the discrete, split, and shift-cycle-expanded transportation task set in ascending order (earliest) according to the time dimension. Through time sorting, the algorithm can simulate processing transportation tasks sequentially, providing a data foundation for subsequently generating a transportation task layout Gantt chart. For example, if the transportation task set contains task A departing at 04:00 on November 1st and task B departing at 06:00 on November 1st, after sorting, task A is placed before task B.

[0063] In step S502 of some embodiments, spatial connection constraints can be constructed based on the empty driving distance between two transportation tasks with adjacent start times in the transportation task sequence and a preset first distance threshold. The spatial connection constraint limits the range of ineffective scheduling of transportation vehicles between two transportation tasks to prevent excessively high empty driving costs. The empty driving distance represents the actual distance traveled by the task execution object from the destination of the previous transportation task (e.g., Jiujiang) to the origin of the current planned transportation task (e.g., Nanchang). The first distance threshold represents the maximum allowed empty driving limit set according to business rules. In this embodiment, the first distance threshold can be set as the maximum distance between the origin and destination of the original transportation task.

[0064] For example, in a target transportation task combination, there are two transportation tasks to be planned: Task 1 is from Beijing to Sanya (assuming a distance of 1000km); Task 2 is from Haikou to Tianjin (assuming a distance of 1000km). The empty driving distance refers to the distance between Sanya and Haikou, and the distance between Tianjin and Beijing, before Task 2 can be executed. In a driver relay scenario, the distance between the origin of Task 1 (Beijing) and the destination of Task 2 (Tianjin) is usually relatively short; the same applies to the empty driving distance between the two tasks (Sanya and Haikou). We can first obtain the distance between Beijing and Tianjin (set as d1=50km), and the distance between Sanya and Haikou (set as d2=30km). When the task execution object allocation model decides the next transportation task for the task execution object at its current location, the empty driving distance between the two transportation tasks must be less than the maximum value of d1 and d2. For example, after the task execution object completes the previous transportation task, its current location is Sanya. At this time, the task execution object has two choices: one is to return to Beijing and execute Task 1 from Beijing to Sanya, where the empty driving distance is 1000km; the other is to drive empty to Haikou and execute Task 2 from Haikou to Tianjin, where the empty driving distance is 30km. In order to meet the spatial connection constraint, the empty driving distance should be less than the maximum value of d1 and d2 mentioned above. At this time, only 30km meets the condition, so we should choose to go to Haikou and execute Task 2.

[0065] Spatial connectivity constraints are designed to ensure that after completing a transportation task, the task execution object can only perform the nearest transportation task, preventing situations where the empty driving distance is too long. For example, as mentioned above, after completing task 1 and arriving in Sanya, the object may drive a long distance back to Beijing empty to continue performing task 1.

[0066] In step S503 of some embodiments, a time continuity constraint can be constructed based on the task end time of historical transportation tasks, the empty running time between two transportation tasks with adjacent task start times in the transportation task sequence, and the task start time of transportation tasks in the transportation task sequence. The task end time of historical transportation tasks represents the end time of the last transportation task in the set of planned transportation tasks in the previous historical period. The time continuity constraint indicates that the end time of the previous transportation task plus the empty running time of the task execution object does not exceed the start time of the next transportation task (i.e., the transportation task currently to be planned), to ensure the continuity of the scheduling plan.

[0067] In step S504 of some embodiments, task connection constraints are constructed based on spatial connection constraints and temporal connection constraints. Only when a task execution object satisfies both spatial connection constraints and temporal connection constraints can it be selected as a candidate task execution object.

[0068] This application's embodiments ensure the feasibility and economy of the automatic scheduling scheme by constructing task connection constraints. First, spatial constraints are used to strictly control ineffective empty mileage and reduce transportation loss costs. Then, by introducing time constraints, the temporal continuity of scheduling new and old transportation tasks is ensured. These multi-dimensional constraints lay the logical foundation for achieving globally optimal intelligent decision-making in complex transportation connection planning scenarios.

[0069] In step S105 of some embodiments, the target task execution object for each transportation task in the set of transportation tasks can be determined based on transportation connection planning data. Specifically, based on the number of task execution objects and scheduling of different candidate connection point schemes calculated in the aforementioned steps, the frequency of each candidate connection point (city dimension) in all target transportation task combinations can be counted from a global perspective to determine the final connection point for each target transportation task combination, and thereby lock the final target task execution object and its corresponding sequence of transportation tasks to be executed. For example, Jiujiang is ultimately determined as the best connection point, and the output is as follows: Figure 3A or Figure 3B The schedule shown clearly designates task recipient A to perform the Shenzhen-Jiujiang segment at specific times, and task recipient B to perform the Jiujiang-Zhengzhou segment. This not only decouples the personnel and vehicles but also ensures that each transportation segment has a designated task recipient responsible for it, and that the task recipients' schedules comply with fatigue driving regulations and operational efficiency requirements.

[0070] In some embodiments, please refer to Figure 6 , Figure 6 A flowchart illustrating the transportation connection planning method provided in this application embodiment is shown. Specifically, the process begins with data input, followed by obtaining the set of target waypoints corresponding to the transportation task to be planned, and then determining the candidate connection points. Further, the transportation task to be planned is split according to the candidate connection points and expanded according to a preset scheduling cycle to obtain a transportation task set. Then, the task execution object allocation model is called to calculate the minimum number of task execution objects, and the target task execution object corresponding to each transportation task in the transportation task set is determined. Finally, based on the model output results, the global connection point for each target transportation task combination is decided to achieve global optimization, and finally, the transportation connection planning data is output.

[0071] Please see Figure 7 This application also provides a transportation connection planning device 700, which can implement the above-mentioned transportation connection planning method. The device includes: The acquisition unit 701 is used to acquire a target transportation task combination, which includes two transportation tasks to be planned. The two transportation tasks to be planned represent the round-trip transportation tasks between the origin and the destination of the target transportation task combination. The splitting unit 702 is used to determine the candidate connection points for each planned transportation task and split the corresponding planned transportation task according to the candidate connection points. The first determining unit 703 is used to determine the set of transportation tasks corresponding to the target transportation task combination within a preset scheduling cycle based on the split transportation tasks to be planned. Solver 704 is used to construct task connection constraints based on the set of transportation tasks, and to solve the preset task execution object allocation model with the task connection constraints and the preset shift interval constraints as constraints and the minimum number of objects as the solution objective, so as to obtain transportation connection planning data. The second determining unit 705 is used to determine the target task execution object of each transportation task in the set of transportation tasks based on the transportation connection planning data.

[0072] The specific implementation of this transportation connection planning device is basically the same as the specific implementation of the above-mentioned transportation connection planning method, and will not be described again here.

[0073] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described transportation connection planning method. This electronic device can be any smart terminal, including a tablet computer, an in-vehicle computer, or similar device.

[0074] Please see Figure 8 , Figure 8 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 801 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 802 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called and executed by the processor 801 using the transportation connection planning method of the embodiments of this application. The 803 input / output interface is used to implement information input and output. The communication interface 804 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 805 transmits information between various components of the device (e.g., processor 801, memory 802, input / output interface 803, and communication interface 804); The processor 801, memory 802, input / output interface 803, and communication interface 804 are connected to each other within the device via bus 805.

[0075] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described transportation connection planning method.

[0076] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor 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.

[0077] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0078] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0079] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0080] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0081] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0082] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0084] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0085] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0086] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A transportation connection planning method, characterized in that, The method includes: Obtain a target transportation task combination, which includes two transportation tasks to be planned, each of which represents a round-trip transportation task between the origin and destination of the target transportation task combination. Determine candidate pick-up points for each of the planned transportation tasks, and split the corresponding planned transportation tasks according to the candidate pick-up points; Based on the split transportation tasks to be planned, determine the set of transportation tasks corresponding to the target transportation task combination within the preset scheduling cycle; Based on the set of transportation tasks, a task connection constraint is constructed. The task connection constraint and the preset shift interval constraint are used as constraints. The preset task execution object allocation model is solved with the minimum number of objects as the solution objective to obtain transportation connection planning data. Based on the transportation connection planning data, determine the target task execution object for each transportation task in the set of transportation tasks.

2. The method according to claim 1, characterized in that, The transportation connection planning data includes the number of task execution objects required for the transportation task set obtained from each candidate connection point. After constructing task connection constraints based on the transportation task set, using the task connection constraints and preset scheduling interval constraints as constraints, and solving a preset task execution object allocation model with the goal of minimizing the number of objects, the method further includes: For each of the target transportation task combinations, at least one target connection point is selected from the candidate connection points whose number of task execution objects is the minimum number of task execution objects. Determine the city identifier corresponding to each target connection point, and count the frequency of each city identifier in all target transportation task combinations; Based on the frequency corresponding to each city identifier, a global connection point is determined among the target connection points corresponding to the target transportation task combination.

3. The method according to claim 2, characterized in that, The task coordination constraints include spatial coordination constraints and temporal coordination constraints. The construction of task coordination constraints based on the transportation task set includes: The transportation tasks in the transportation task set are sorted according to the task start time of each transportation task in the transportation task set to obtain a transportation task sequence; Spatial connection constraints are constructed based on the empty driving distance between two transportation tasks with adjacent start times in the transportation task sequence and a preset first distance threshold. Based on the task end time of historical transportation tasks, the empty running time between two transportation tasks with adjacent task start times in the transportation task sequence, and the task start time of transportation tasks in the transportation task sequence, a time connection constraint is constructed. The task end time of the historical transportation task represents the end time of the last transportation task in the set of planned transportation tasks in the previous historical period. Task connection constraints are constructed based on the spatial connection constraints and the temporal connection constraints.

4. The method according to claim 1, characterized in that, The process involves solving a preset task execution object allocation model using the task connection constraints and preset shift interval constraints as constraints, with the goal of minimizing the number of objects, to obtain transportation connection planning data, including: Using the transportation task set as the input to the preset task execution object allocation model, and based on the task connection constraints and the preset shift interval constraints, the task execution objects corresponding to the transportation tasks in the transportation task set are selected from the preset used object set. When the filtering result indicates successful filtering, transportation connection planning data is generated based on the filtered candidate task execution objects, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved.

5. The method according to claim 4, characterized in that, The solution objective also includes a transportation task type preference objective. The transportation task type includes a first task type and a second task type. The first task type indicates that the origin of the current planned transportation task is the same as the destination of the previous executed task of the candidate task object, and the destination of the current planned transportation task is the same as the origin of the previous executed task of the candidate task object. The second task type indicates that the origin of the current planned transportation task is the same as the destination of the previous executed task of the candidate task object, and the destination of the current planned transportation task is not the same as the origin of the previous executed task of the candidate task object. When the filtering result indicates successful filtering, transportation connection planning data is generated based on the filtered candidate task objects, the corresponding transportation tasks in the transportation task set, and the minimum number of objects solved, including: When there are multiple candidate task execution objects selected, the target task execution object corresponding to the transportation task is determined from the multiple candidate task execution objects based on the transportation task type preference target. Transportation connection planning data is generated based on the target task execution object, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved.

6. The method according to claim 4, characterized in that, The process of solving the preset task execution object allocation model using the task connection constraints and the preset scheduling interval constraints as constraints, and with the goal of minimizing the number of objects, to obtain transportation connection planning data, also includes: When the filtering result indicates that the filtering failed, the target task execution object of the corresponding transportation task in the transportation task set is randomly selected from the preset unused object set, using the transportation task set as the input of the preset task execution object allocation model. Transportation connection planning data is generated based on the target task execution object, the corresponding transportation tasks in the transportation task set, and the minimum number of objects to be solved.

7. The method according to claim 1, characterized in that, The process of determining candidate transfer points for each of the planned transportation tasks includes: For each of the transportation tasks to be planned, a route is planned to obtain the corresponding set of target waypoints. Based on multiple preset ratio coefficients and the total mileage of each planned transportation task, the planned transportation task is divided into multiple reference connection points. Candidate connection points for the planned transportation task are obtained by filtering from the target route point set according to the preset neighborhood range corresponding to the reference connection point. The preset neighborhood range is determined based on the reference connection point and a preset second distance threshold between the reference connection point and the reference connection point.

8. A transportation connection planning device, characterized in that, The device includes: An acquisition unit is used to acquire a target transportation task combination, which includes two transportation tasks to be planned, each representing a round-trip transportation task between the origin and destination of the target transportation task combination. A splitting unit is used to determine candidate connection points for each of the planned transportation tasks and to split the corresponding planned transportation tasks according to the candidate connection points. The first determining unit is used to determine, based on the split transportation tasks to be planned, the set of transportation tasks corresponding to the target transportation task combination within a preset scheduling cycle. The solution unit is used to construct task connection constraints based on the set of transportation tasks, use the task connection constraints and the preset shift interval constraints as constraints, and solve the preset task execution object allocation model with the minimum number of objects as the solution objective to obtain transportation connection planning data. The second determining unit is used to determine the target task execution object for each transportation task in the transportation task set based on the transportation connection planning data.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the transportation connection planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the transportation connection planning method according to any one of claims 1 to 7.

Images