Vehicle transportation route optimization method and device, planning method, equipment and medium

Abstract

The embodiment of the application provides a vehicle transportation line optimization method and device, a planning method, equipment and a medium, and belongs to the technical field of vehicle transportation planning. The method comprises the following steps: acquiring vehicle attribute data of multiple vehicle types capable of performing line transportation demand in a single vehicle in a goods transportation scene, and transportation demand data and empty running transportation data of multiple transportation network points based on a transportation line; for each vehicle type, constructing a transportation space-time network graph according to the transportation demand data and the empty running transportation data; constructing line transportation constraint conditions according to the multiple transportation space-time network graphs, vehicle transportation attribute data, vehicle transportation resource data and vehicle transfer resource data; constructing a vehicle transportation line optimization target according to the multiple transportation space-time network graphs and the vehicle transportation resource data; and obtaining a transportation line optimization scheme based on the line transportation constraint conditions and the vehicle transportation line optimization target. The embodiment of the application can improve the accuracy of vehicle transportation line optimization.

Description

Technical Field

[0001] This application relates to the field of vehicle transportation planning technology, and in particular to a method and apparatus for optimizing vehicle transportation routes, a planning method, equipment and medium. Background Technology

[0002] Vehicle transportation route optimization refers to the process of systematically planning and calculating to design the most efficient vehicle travel routes, thereby reducing transportation costs, increasing delivery speed, and minimizing resource waste. For example, in logistics vehicle transportation scenarios, by comprehensively managing transportation routes, a large number of vehicles can be efficiently dispatched daily to complete cargo transportation tasks.

[0003] Currently, in the absence of algorithm-assisted decision-making, related technologies typically rely on the personal experience of regional planners to manually combine transportation routes that meet business requirements and can be executed by a single vehicle. Based on subjective judgment, tasks with higher combination efficiency are assigned to the company's own fleet, while less efficient combinations are outsourced to third-party suppliers. While this experience-driven operational model may achieve relative optimization of local route combinations, it has many limitations in the overall vehicle transportation route optimization process. Therefore, the accuracy of the methods employed in this field for vehicle transportation route optimization remains insufficient. Summary of the Invention

[0004] The main objective of this application is to propose a method and apparatus for optimizing vehicle transportation routes, a planning method, equipment, and a medium that can improve the accuracy of vehicle transportation route optimization.

[0005] To achieve the above objectives, a first aspect of this application proposes a method for optimizing vehicle transportation routes, the method comprising: The system acquires vehicle attribute data corresponding to various vehicle types capable of performing route transportation needs in a freight transportation scenario. The vehicle attribute data includes vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The vehicle transportation attribute data is used to indicate attribute data related to the transportation vehicle. The vehicle transportation resource data is used to indicate resource data consumed by the transportation vehicle when performing route transportation needs. The vehicle transfer resource data is used to indicate resource data consumed by a third-party vehicle when performing route transportation needs. The freight transportation scenario includes multiple transportation routes. Acquire inter-point transportation data for the cargo transportation scenario, which includes transportation demand data and empty-run transportation data of multiple transportation points in the cargo transportation scenario based on transportation routes; For each vehicle type, a corresponding transportation spatiotemporal network diagram is constructed based on the transportation demand data and the empty-run transportation data. The transportation spatiotemporal network diagram includes multiple network nodes, and each network node is the transportation network point associated with the vehicle type in the cargo transportation scenario. Based on multiple transport spatiotemporal network diagrams, vehicle transport attribute data, vehicle transport resource data, and vehicle transfer resource data, route transport constraints corresponding to various vehicle types are constructed. Based on the multiple spatiotemporal network diagrams of transportation and the vehicle transportation resource data, a vehicle transportation route optimization objective is constructed. Based on the route transportation constraints and the vehicle transportation route optimization objectives, the target transportation route scheme is obtained.

[0006] To achieve the above objectives, a second aspect of this application proposes a vehicle transportation route planning method, the method comprising: Obtain target transportation route schemes corresponding to multiple transportation routes in a cargo transportation scenario. The target transportation route schemes are constructed based on the vehicle transportation route optimization method described in any of the first aspect embodiments. The target transportation route schemes are used to indicate the combination scheme of vehicle data for executing the transportation needs of each route. Based on the target transportation route plan, control the vehicles corresponding to the transportation needs of each route to execute the transportation requirements.

[0007] To achieve the above objectives, a third aspect of this application provides a vehicle transport route optimization device, the device comprising: The vehicle data acquisition module is used to acquire vehicle attribute data corresponding to various vehicle types that can perform route transportation needs in a freight transportation scenario. The vehicle attribute data includes vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The vehicle transportation attribute data is used to indicate attribute data related to the transportation vehicle. The vehicle transportation resource data is used to indicate the resource data consumed by the transportation vehicle when performing route transportation needs. The vehicle transfer resource data is used to indicate the resource data consumed by a third-party vehicle when performing route transportation needs. The freight transportation scenario includes multiple transportation routes. The network point data acquisition module is used to acquire inter-network point transportation data in the cargo transportation scenario. The inter-network point transportation data includes transportation demand data and empty-run transportation data of multiple transportation network points in the cargo transportation scenario based on the transportation route. The graph construction module is used to construct a corresponding transportation spatiotemporal network graph for each vehicle type based on the transportation demand data and the empty-run transportation data. The transportation spatiotemporal network graph includes multiple network nodes, and each network node is the transportation network point associated with the vehicle type in the cargo transportation scenario. The constraint construction module is used to construct route transportation constraints corresponding to various vehicle types based on multiple transportation spatiotemporal network diagrams, vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The function construction module is used to construct vehicle transportation route optimization objectives based on multiple transportation spatiotemporal network diagrams and vehicle transportation resource data; The function solving module is used to obtain the target transportation route scheme based on the route transportation constraints and the vehicle transportation route optimization objective.

[0008] To achieve the above objectives, a fourth aspect of the present 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 any one of the embodiments of the first and second aspects described above.

[0009] To achieve the above objectives, a fifth 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 any one of the embodiments of the first and second aspects described above.

[0010] The vehicle transportation route optimization method, apparatus, planning method, equipment, and medium proposed in this application, when optimizing vehicle transportation routes in a freight transportation scenario, can first acquire vehicle attribute data and inter-point transportation data corresponding to various vehicle types capable of fulfilling route transportation needs on a single vehicle in the freight transportation scenario. The vehicle attribute data includes vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data to comprehensively consider various resource data related to route optimization. The inter-point transportation data includes transportation demand data and empty-run transportation data based on transportation routes at multiple transportation points in the freight transportation scenario to consider the number of empty runs generated by connecting transportation needs. The process involves several steps: First, for each vehicle type, a corresponding spatiotemporal network diagram is constructed based on transportation demand data and empty-run transportation data. This diagram includes multiple network nodes, each representing a transportation network point associated with the vehicle type in the freight transportation scenario. Second, based on multiple spatiotemporal network diagrams, vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data, route transportation constraints corresponding to various vehicle types are constructed. Third, vehicle transportation route optimization objectives are established based on these diagrams and resource data. Finally, a transportation route optimization scheme is obtained based on the route transportation constraints and the optimization objectives. This embodiment of the application comprehensively considers various factors related to vehicle transportation routes from a global perspective and combines spatiotemporal network diagrams of multiple vehicle types to combine routes for single-vehicle route transportation needs. Therefore, this embodiment can improve the accuracy of vehicle transportation route optimization. Attached Figure Description

[0011] Figure 1 This is a flowchart of a vehicle transportation route optimization method provided in an embodiment of this application; Figure 2 yes Figure 1 A flowchart of step S130 in the process; Figure 3 This is a schematic diagram of the transportation spatiotemporal network diagram provided in the embodiments of this application; Figure 4 yes Figure 1 A flowchart of step S140 in the process; Figure 5 yes Figure 4 A flowchart of step S420 in the process; Figure 6 yes Figure 4 A flowchart of step S440 in the process; Figure 7 yes Figure 4 A flowchart of step S450 in the process; Figure 8 yes Figure 1A flowchart of step S150 in the process; Figure 9 This is a schematic diagram of a vehicle transportation route optimization device provided in an embodiment of this application; Figure 10 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment 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., used in the specification, claims, and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. 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.

[0014] Vehicle transportation route optimization refers to the process of systematically planning and calculating to design the most efficient vehicle routes to reduce transportation costs, improve delivery speed, and minimize resource waste. For example, in logistics vehicle transportation scenarios, by coordinating and managing transportation routes, a massive number of vehicles can be efficiently dispatched daily to complete cargo transportation tasks. Currently, logistics transportation companies typically use a two-tiered "regional-area" management system to coordinate transportation routes, requiring the efficient dispatch of a large number of vehicles daily to complete cargo transportation tasks. Therefore, how to scientifically plan vehicle transportation routes and effectively control operating costs has become one of the core operational challenges for enterprises.

[0015] In the absence of algorithm-assisted decision-making, regional planners primarily rely on personal experience to manually combine transportation routes that meet business requirements and can be executed by individual vehicles. Based on subjective judgment, they assign more efficient combinations to their own fleet, while subcontracting less efficient combinations to third-party suppliers. This experience-driven operational model, while potentially achieving relative optimization of local route combinations, struggles to systematically coordinate multiple key indicators closely related to overall operating costs from a holistic perspective. These indicators include average vehicle mileage, empty mileage, and the number of routes that could not be combined. Furthermore, routes that could be combined are often subcontracted to external suppliers, resulting in higher operating costs. Consequently, overall operating costs are difficult to quantify accurately and effectively control. Therefore, the methods employed by related technologies are still insufficiently accurate in optimizing vehicle transportation routes. To systematically improve the quality of route combinations and achieve overall cost optimization, it is urgent to introduce automated intelligent systems to efficiently and scientifically plan vehicle transportation routes, generating route combination schemes with optimal total operating costs. These schemes can then be used by regional planners for reference and minor adjustments before practical application.

[0016] Based on this, embodiments of this application provide a method and apparatus for optimizing vehicle transportation routes, a planning method, equipment, and a medium, which can improve the accuracy of vehicle transportation route optimization.

[0017] This application's embodiments can acquire and process relevant data based on artificial intelligence (AI) technology. AI is the theory, methods, technology, and application system that uses digital computers or computers-controlled machines to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results. Basic AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operating / interactive systems, and mechatronics. AI software technologies mainly include computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0018] The vehicle transportation route optimization method provided in this application relates to the field of vehicle transportation planning 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, content delivery networks (CDN), and big data and artificial intelligence platforms; the software can be an application implementing the vehicle transportation route optimization method, but is not limited to the above forms.

[0019] 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 devices, network personal computers (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.

[0020] It should be noted that in various specific embodiments of this application, when processing data related to the object's identity or characteristics, such as object level and object resource data, is required, the object's permission or consent will be obtained first. Furthermore, the collection, use, and processing of this data will comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require obtaining sensitive personal information of an object, separate permission or consent from the object will be obtained through pop-ups or redirects to confirmation pages. Only after obtaining the object's separate permission or consent will the necessary object-related data for the proper functioning of the embodiments of this application be obtained.

[0021] Please see Figure 1 , Figure 1This is an optional flowchart of the vehicle transportation route optimization method provided in the embodiments of this application. In some embodiments of this application, Figure 1 The method described below may include, but is not limited to, steps S110 to S160. Figure 1 These six steps will be explained in detail.

[0022] Step S110: Obtain vehicle attribute data corresponding to various vehicle types that can perform route transportation requirements by a single vehicle in the freight transportation scenario. The vehicle attribute data includes vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The freight transportation scenario includes multiple transportation routes. Step S120: Obtain inter-point transportation data in the freight transportation scenario. The inter-point transportation data includes transportation demand data and empty-run transportation data based on transportation routes of multiple transportation points in the freight transportation scenario. Step S130: For each vehicle type, construct a corresponding transportation spatiotemporal network diagram based on transportation demand data and empty-run transportation data. The transportation spatiotemporal network diagram includes multiple network nodes, and each network node is a transportation network point associated with the vehicle type in the cargo transportation scenario. Step S140: Based on multiple transportation spatiotemporal network diagrams, vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data, construct route transportation constraints corresponding to various vehicle types. Step S150: Based on multiple transportation spatiotemporal network diagrams and vehicle transportation resource data, construct vehicle transportation route optimization objectives; Step S160: Solve the route transportation constraints and vehicle transportation route optimization objectives to obtain the transportation route optimization scheme.

[0023] In step S110 of some embodiments, this step can extract core data related to transport vehicles from the logistics company's operation management system. The route demand pool corresponding to the route transportation needs in the transportation scenario contains two types of demands: one type can be fully executed by a single vehicle for all its weekday schedules; the other type consists of a few complex demands that cannot be executed by a single vehicle. In this application embodiment, a time-distance matrix storing vehicles and transportation times can be pre-constructed. Therefore, when a demand is from location A to location B, with a time interval of a to b, if there are daily departures throughout the week, then after a vehicle travels from location A to location B on Monday, if the vehicle can return empty (i.e., without transporting goods) from location B to location A and can also pick up a task from location A to location B on Tuesday, then it can be said that the vehicle can complete this demand. If it cannot pick up a task, then another vehicle needs to be dispatched on Tuesday, which is not a demand of a single vehicle but a complex demand. Based on this, this application embodiment studies the algorithmic problem in a single-vehicle route combination system.

[0024] In this embodiment, the allocation of vehicle resources for transportation routes can be more accurate by comprehensively considering operating costs (i.e., transportation resources) based on the attributes of different vehicle types and empty-run constraints. Specifically, each vehicle type can have its corresponding vehicle attribute data. The vehicle transportation attribute data indicates the attribute information of the corresponding vehicle type, such as vehicle type (e.g., van, refrigerated truck), rated load capacity (also known as tonnage, such as 5 tons, 10 tons), fuel efficiency (e.g., 15L / 100km fuel consumption), vehicle size, volume requirements, and other physical parameters. The vehicle transportation resource data indicates the unit fuel cost, fixed vehicle cost resources (e.g., charter fees, tailgate fees, etc.), additional costs (if the total charter time is ≥16 hours, a dual-driver surcharge is used; otherwise, a single-driver surcharge is used), real-time vehicle location, current loading rate, driver working hours (including legal driving time limits), driver transportation costs, maintenance status, and other dynamic information for the corresponding vehicle type during transportation. The vehicle transfer resource data indicates the resource data required when entrusting the route transportation demand to a third-party supplier vehicle. In other words, if a route cannot be included in any vehicle package, its cost is calculated based on its standard price, and the service is handled by an external supplier's vehicle, with the company paying the corresponding labor cost at the standard price. A vehicle package refers to a complete combination of transportation routes expressed through a path. Freight transport scenarios include multiple transportation routes, each corresponding to different transportation needs. This application's embodiments can combine different vehicle resources for different transportation routes to achieve global optimization of total operating costs. For example, for logistics company P, its corresponding freight transport scenario has three transportation routes: route A from location A1 to location A2, route B from location A2 to location A3, and route C from location A1 to location A4. Route A primarily utilizes large-capacity, low-fuel-consumption heavy trucks, reducing unit costs through optimized loading rates and trailer swapping. Route B employs flexible medium-sized vehicles and reserves some elastic capacity to cope with peak demand in urban delivery and ensure service quality. Route C invests in high-efficiency, information-based vehicles and integrates with the IT systems of e-commerce platforms to create value by improving turnover efficiency. Therefore, each transportation route can meet different transportation needs.

[0025] In step S120 of some embodiments, this application embodiment can extract key data from multiple transportation points in a cargo transportation scenario based on predetermined transportation routes through the interface between the Transportation Management System (TMS) and the Geographic Information System (GIS) platform. Transportation demand data reflects the actual needs of customers for transportation services, including the origin and destination points of the order, cargo volume and weight, the customer's required delivery time window (e.g., delivery before 16:00 on the same day), transportation priorities (urgent and regular shipments), etc. This type of data is usually generated by the order management system and transmitted via the TMS. "Empty driving transportation data" refers to the operational information generated when a vehicle moves from one point to another without cargo, including the shortest empty driving time and distance calculated based on real-time or predicted road conditions, fuel consumption and cost in empty driving mode, and an upper limit for empty driving distance set to maintain economy (e.g., the empty driving cost will be significantly higher than re-dispatch when exceeding 80 kilometers). This step is linked with S110 because the accuracy of empty-run data depends on vehicle attributes (such as the difference in empty-run fuel consumption between different models), while transportation demand data provides a basis for S130 to construct task arcs between network nodes.

[0026] It should be noted that the embodiments of this application can first perform data preprocessing to filter out the required vehicle attribute data and inter-point transportation data, and obtain empty-run transportation data (empty-run distance and empty-run time data) between each transportation network point by connecting to a pre-set GIS system, and pre-generate a corresponding relationship table. It should be noted that if the distance between each transportation network point is related to demand, i.e., for the same route from location A to location B, the distance after the transportation route is created will have different mileages due to different routes taken by the drivers, such as 20km and 22km; however, if it is empty-run transportation (empty runs) from location A to location B, it will default to the standard empty-run method based on the time-distance matrix. By forming a correspondence table between empty-run distance and time, redundant calculation time caused by repeatedly requesting the GIS system during route combination can be effectively avoided, improving overall efficiency.

[0027] In step S130 of some embodiments, this application embodiment can draw a corresponding "transportation spatiotemporal network diagram" in a spatiotemporal coordinate system for each vehicle type using the obtained transportation demand data and empty-run transportation data. This is a modeling method that maps discrete network points and transportation tasks into a directed graph structure. The algorithm in this paper is based on a directed connection network to construct a mathematical model. In the graph, nodes represent the set of originating or destination network points of the demand route, and edges represent directed connection arcs between nodes. Based on this, each "network node" in the constructed transportation spatiotemporal network diagram represents a transportation network point in the freight transportation scenario that is associated with that vehicle type. For example, a refrigerated truck can only serve network points with cold chain facilities, so these network points will become nodes in the network diagram of that vehicle type. Each node has two types of attributes: time attributes: such as the start / end time of the demand, or the dwell time of the vehicle at a certain network point; spatial attributes: such as network point location information; more attributes (such as tonnage, volume, stable departure rate, etc.) can be added in the future to further constrain the feasibility of connection between routes. The connection between network nodes in the same transportation spatiotemporal network diagram is called a node arc. Node arcs can be divided into four types: (1) Demand arc: connects the start and end nodes of a certain route transportation demand, that is, it represents a transportation task with cargo, with time window and cargo quantity attributes; (2) Rest arc: on the same transportation network point, connects the end node of the previous route transportation demand and the start node of the next route transportation demand, indicating that the vehicle is waiting at the transportation network point, that is, a virtual node and connection arc inserted at a specific time interval to meet the driver's continuous driving time regulations, such as setting a rest node every two hours; (3) Cross-day arc (such as 24:00 to 00:00); (4) Empty driving arc: connects different transportation network points, starting from the end node of the previous route transportation demand and ending at the time of empty driving to another transportation network point. This time may correspond to the start of other demands or only be an idle time point, that is, it represents movement without cargo, subject to the upper limit of empty driving distance and economic judgment. The embodiments of this application can be linked with the vehicle attributes of S110 by mapping separately according to vehicle type, because the node set of different vehicle types may be different. For example, dangerous goods transport vehicles can only connect to network points with dangerous goods storage qualifications.

[0028] Understandably, a vehicle's transportation route combination can be represented as a cyclical path composed of multiple arcs. In this embodiment, various costs of self-operated vehicles (including driver income, variable costs, and fixed costs) can be associated with the arcs, thereby expressing a complete transportation route combination (also known as a "vehicle package") through the path. In the future, attributes such as empty-run distance limits can be added to the arcs according to actual business needs. That is, if an empty-run arc requires 100km after querying, but the business requires that the empty run between all tasks cannot exceed 80km, then such an empty-run arc will not be generated. Simply put, this indirectly expresses that the vehicle cannot run in that direction and must use another method to accept the next task.

[0029] Please refer to Figure 2 , Figure 2 This is a flowchart of step S130 provided in an embodiment of this application. In some embodiments, step S130 may specifically include, but is not limited to, steps S210 to S220, as described below. Figure 2 These two steps will be explained in detail.

[0030] Step S210: For each vehicle type, determine the transportation network points associated with the vehicle type from multiple network nodes based on transportation demand data. The transportation demand data includes transportation sub-demands. Step S220: Construct node arcs based on the transportation network points and empty-run transportation data associated with the transportation sub-demands, and construct the corresponding transportation spatiotemporal network diagram based on all node arcs.

[0031] In step S210 of some embodiments, the transportation demand data may include multiple transportation sub-demands. These sub-demands actually reflect the customer's specific requirements for transportation services, such as specific origin and destination points, cargo volume, and time windows. Based on this transportation demand data, embodiments of this application can filter transportation points matching specific vehicle types from the entire transportation network. This involves analyzing the attributes of each vehicle type, such as load capacity, size, and applicable road conditions, to determine which transportation points the corresponding vehicles can effectively serve. In this way, embodiments of this application can ensure that vehicles corresponding to each vehicle type are assigned to tasks best suited to their capabilities and characteristics, thereby improving the efficiency and effectiveness of the entire transportation system.

[0032] In step S220 of some embodiments, this application embodiment can construct node arcs in each transportation spatiotemporal network diagram based on the determined transportation network points and "empty-run transportation data". A node arc is a line segment connecting different nodes in the network, representing the movement path of a vehicle between different network points. These paths may be cargo-loaded task arcs or empty-run arcs. This application embodiment can determine the specific attributes of these arcs, such as length, required time, and cost, based on transportation demand data and empty-run transportation data. Once all node arcs are determined, they can be connected to form a complete transportation spatiotemporal network diagram. This diagram not only shows the movement path of vehicles between different network points but also reflects the spatiotemporal structure and dynamic characteristics of the entire transportation system. Through this transportation spatiotemporal network diagram, one can more intuitively see how vehicles flow in the network and how they meet various transportation demands.

[0033] For example, such as Figure 3The diagram shown is a structural schematic of a transportation spatiotemporal network diagram provided in an embodiment of this application. This transportation spatiotemporal network diagram illustrates a transportation combination path for a vehicle type executing four demands. There are four transportation network points associated with vehicle P in this diagram: network point A, network point B, network point C, and network point D. The horizontal axis in the diagram represents different times of day (from 00:00 to 24:00). Traffic flow is represented by bold lines with direction, while unbold lines represent rest arcs. The endpoints connecting each node arc in the diagram can contain corresponding two-dimensional information about the transportation network point and time. The traffic flow on the node arc represents the usage quantity of a certain type of vehicle. In this embodiment, node arcs can be connected in series to form a loop. If a loop contains only one demand arc, it indicates that the vehicle only executes that single demand. Specifically, vehicle P can first rest at network point A for a time interval t1, then transport goods K1 from network point A to network point B according to demand 1, and then rest at network point B for a time interval t2, transporting goods K2 from network point B to network point C according to demand 2. During the break time t3 at point C, according to demand 3, goods K3 are transported from point C to point D. During the break time t4 at point D, according to demand 4, goods K4 are transported from point D to point B. During the break time t5 at point B, since there is no demand to execute at this time, in order to execute demand 1 again, goods can be transported empty from point B to point A. The goods K1, K2, K3, and K4 corresponding to different demands can be the same or different, and the time intervals t1, t2, t3, t4, and t5 can also be the same or different, and can be flexibly set according to actual needs.

[0034] In step S140 of some embodiments, the embodiments of this application can synthesize multiple transportation spatiotemporal network diagrams, as well as vehicle transportation attribute data, vehicle transportation resource data and vehicle transfer resource data, to derive route transportation constraints applicable to different vehicle types. These constraints are mathematical expressions that ensure the solution results conform to real-world operating rules, which is equivalent to a mathematical model built based on a directed connection network. For example, vehicle loop constraints require that each vehicle's path forms a closed loop in the transportation spatiotemporal network graph, starting from a certain starting node and eventually returning to the same type of starting node. This is achieved through the zero-point arc mechanism. Capacity constraints limit the total weight of goods carried on any path to a value that is based on the approved load capacity in the vehicle transportation attribute data. Empty driving limit constraints convert the upper limit of empty driving distance into a mathematical condition; once the empty driving distance exceeds the threshold, the arc cannot be selected in the model or triggers vehicle replacement logic. Time continuity constraints ensure that the end time of the previous task plus the necessary loading, unloading, and preparation time is not later than the earliest start time of the next task. The time data here comes from the transportation demand time window and arc time attributes. In addition, there are constraints related to transfer resources, such as the time spent at the transfer station must not exceed the maximum value specified in the vehicle transfer resource data. These constraints accurately map the business rules to the mathematical model, and together with the subsequently generated vehicle transportation route optimization objective, they constitute a complete optimization problem.

[0035] In other words, this application's embodiments can extract and clarify the constraints that different types of vehicle packages need to meet based on business rules and practical experience. These constraints mainly include two categories: first, attribute constraints, which include business restrictions that can be directly determined between pairs of routes, such as tonnage, mode of transport, vehicle type, volume requirements, contract period, and the region to which the route belongs; second, empty-run constraints, which set an upper limit on the total empty-run distance between routes within the combined vehicle package to ensure compliance with actual operational requirements. Furthermore, more constraints can be added as needed to improve the accuracy of route optimization.

[0036] It should be noted that the embodiments of this application can construct an integer programming model based on the flow of arcs. Each vehicle type corresponds to a transportation spatiotemporal network diagram, and the maximum flow at a certain time node in the diagram is the number of vehicles of that type required in that area. The integration result of the flows in each spatiotemporal network diagram is the total number of vehicles that the planners in that area need to prepare. Routes corresponding to demand arcs that are not traversed by any vehicles indicate that they cannot be carried by the area's own fleet and must be handed over to external third-party suppliers or executed through bidding.

[0037] Please refer to Figure 4 , Figure 4 This is a flowchart of step S140 provided in an embodiment of this application. In some embodiments, step S140 may specifically include, but is not limited to, steps S410 to S450, as described below. Figure 4 These five steps will be explained in detail.

[0038] Step S410: For each transportation route, determine the effective node arcs when executing the transportation route based on the corresponding vehicle type according to multiple transportation spatiotemporal network diagrams. Step S420: Construct route allocation constraints based on the valid node arcs corresponding to various vehicle types; Step S430: Determine the vehicle quantity requirement data corresponding to each vehicle type from the vehicle transportation attribute data, and construct vehicle quantity constraints based on the effective node arcs corresponding to multiple vehicle types and the vehicle quantity requirement data corresponding to multiple vehicle types. Step S440: Based on the node type of the effective node arcs corresponding to various vehicle types, construct node flow constraints. Step S450: Integrate the constraints of route allocation, vehicle quantity, and node flow to obtain the route transportation constraints.

[0039] In step S410 of some embodiments, for each transport route, multiple transport spatiotemporal network diagrams previously constructed for different vehicle types can be carefully examined. These transport spatiotemporal network diagrams depict the movement paths of vehicles between different network points, including demand arcs (transport tasks with cargo) and empty arcs (movements without cargo). A valid node arc refers to the node arc selected when the corresponding vehicle type executes the transport route, such as... Figure 3 The line segment in the direction of the destination. Through this process, suitable vehicle types and their corresponding valid node arcs can be selected for each transportation route.

[0040] In step S420 of some embodiments, the route allocation constraint is to ensure that each transport route can be effectively executed by the appropriate type of vehicle. Factors such as the matching degree between vehicle type and route, and whether the vehicle capacity meets the route demand, can be considered. By setting these constraints, unsuitable vehicle types can be prevented from being assigned to unsuitable routes, thereby ensuring transport efficiency and service quality. For example, the route allocation constraint is equivalent to the demand route coverage constraint, ensuring that each transport route i is selected by at most one vehicle.

[0041] Among them, effective node arcs include rest arcs and non-rest arcs. A rest arc refers to the arc formed by the time period between the end of the transportation demand on the previous route and the beginning of the transportation demand on the next route at the same transportation network point in the transportation spatiotemporal network diagram. Non-rest arcs can include demand arcs, empty-run arcs, etc.

[0042] Please refer to Figure 5 , Figure 5 This is a flowchart of step S420 provided in an embodiment of this application. In some embodiments, step S420 may specifically include, but is not limited to, steps S510 to S520, as described below. Figure 5 These two steps will be explained in detail.

[0043] Step S510: Determine the set of node arcs to be executed for the same transportation route based on the valid node arcs corresponding to various vehicle types. Step S520: Construct route allocation constraints based on the node arc execution set corresponding to multiple route transportation needs.

[0044] In steps S510 and S520 of some embodiments, this application embodiment can determine a specific set of node arcs for each transportation route. These node arcs will constitute the execution path of the route. First, referring to the multiple transportation spatiotemporal network diagrams previously constructed for different vehicle types, node arcs that can effectively execute the route's tasks are selected for each transportation route. The selection of these node arcs is based on the matching degree between vehicle type and route, as well as the attributes of the node arcs themselves, such as time window and vehicle capacity. In this way, it can be ensured that each transportation route has a corresponding set of node arc executions, and the node arcs in this set are all suitable for executing the route's tasks. Furthermore, to ensure that each transportation route can only be selected for execution by one vehicle to avoid resource waste and conflicts, the set of node arc executions corresponding to the transportation demand of each route can be analyzed, and a series of constraints can be set in combination with vehicle transportation attribute data and transportation resource data. These constraints may include the matching degree between vehicle type and route, whether the vehicle capacity meets the route demand, etc. By setting these constraints, the vehicle allocation of each route can be effectively controlled to ensure that each route has one and only one vehicle executing the task.

[0045] In step S430 of some embodiments, this application embodiment can determine the vehicle quantity requirement corresponding to each vehicle type from vehicle transportation attribute data. This includes analyzing the availability, working hours, maintenance status, etc., of each vehicle to determine the number of vehicles of each type that can be put into operation. Then, combined with the determined valid node arcs, vehicle quantity constraints can be constructed. These conditions ensure that a sufficient number of suitable vehicles are available for allocation when performing transportation tasks, while avoiding waste of resources. For example, ensuring that the number of vehicle packages using vehicle type k does not exceed the existing number of vehicles of vehicle type k.

[0046] In step S440 of some embodiments, this application embodiment can construct node flow constraints based on the node type of the effective node arc corresponding to different vehicle types. This aims to control the inbound and outbound flow of each network node, ensuring smooth traffic flow and avoiding congestion. For example, some nodes may be limited by geographical location or facility constraints, allowing only a certain number of vehicles to enter and exit simultaneously. By setting these constraints, we can optimize vehicle flow in the network and improve overall transportation efficiency.

[0047] Please refer to Figure 6 , Figure 6 This is a flowchart of step S440 provided in an embodiment of this application. In some embodiments, step S440 may specifically include, but is not limited to, steps S610 to S640, as described below. Figure 6 These four steps will be explained in detail.

[0048] Step S610: Filter the valid node arcs corresponding to various vehicle types to obtain the first rest arc and the first non-rest arc corresponding to the originating node, and the second rest arc and the second non-rest arc corresponding to the destination node. Step S620: Sum the execution flow of the second rest arc and the execution flow of the second non-rest arc corresponding to various vehicle types to obtain the total data of node inflow flow; Step S630: Sum the execution flow of the first rest arc and the execution flow of the first non-rest arc corresponding to various vehicle types to obtain the total outflow data of the node; Step S640: Construct node flow constraints based on the total inflow data and outflow data of the nodes.

[0049] In steps S610 to S640 of some embodiments, a rest arc refers to a point in time when the vehicle needs to rest during transportation, while a non-rest arc is the path the vehicle travels normally. Through this filtering process, we can ensure that only suitable node arcs are used in subsequent transportation plans. The set of first rest arcs corresponding to the originating node can be represented as... That is, the set of resting arcs starting from node n, and the set of the first non-resting arcs corresponding to the starting node can be represented as: This refers to the set of transport arcs / empty arcs originating from node n. The set of second rest arcs corresponding to the destination node can be represented as... That is, the set of resting arcs with node n as the destination node, and the set of the second non-resting arcs corresponding to the destination node can be represented as: This refers to the set of transport arcs / empty arcs with node n as the destination node. Thus, the total outflow data of a node can be determined based on the execution flow of the arc corresponding to the originating node, and the total inflow data of a node can be determined based on the execution flow of the arc corresponding to the destination node. Therefore, the node flow constraints can be constructed based on the principle that "the inflow to each node = the outflow."

[0050] In step S450 of some embodiments, the embodiments of this application can integrate the previously constructed route allocation constraints, vehicle quantity constraints, and node flow constraints to summarize these scattered constraints into a unified set of route transportation constraints. This set of constraints will serve as input to subsequent optimization algorithms to solve for the optimal transportation route combination scheme. By integrating these constraints, we can ensure that the final transportation scheme meets various business needs while also conforming to actual operational constraints.

[0051] This application's embodiments enable the construction of a comprehensive and refined vehicle transportation route combination optimization model. This model not only considers the matching degree between vehicle type and transportation route, but also fully takes into account various actual operational factors such as vehicle quantity and node traffic, improving vehicle utilization and transportation efficiency, and ensuring the smoothness and stability of the transportation process. In summary, this solution, through data-driven and model optimization methods, achieves precise and optimized transportation route combination, bringing significant technological progress and economic benefits to the logistics and transportation industry.

[0052] Please refer to Figure 7 , Figure 7 This is a flowchart of step S450 provided in an embodiment of this application. In some embodiments, step S450 may specifically include, but is not limited to, steps S710 to S740, as described below. Figure 7 These four steps will be explained in detail.

[0053] Step S710: Determine the vehicle volume requirement data corresponding to each vehicle type from the vehicle transportation attribute data, and construct vehicle volume constraints based on the vehicle volume requirement data. Step S720: Obtain empty driving constraint data corresponding to each vehicle type, and construct empty driving constraint conditions based on the empty driving constraint data; Step S730: Obtain the regional constraint data corresponding to the transportation demand of each route, and construct the regional constraint conditions of the route based on the regional constraint data. Step S740: Integrate the constraints of route allocation, vehicle quantity, node flow, vehicle volume, empty running, and route area to obtain the route transportation constraints.

[0054] In steps S710 to S740 of some embodiments, when constructing route transportation constraints, this application embodiment can extract volume information for each vehicle type from vehicle transportation attribute data. This data reflects the maximum volume of goods that a vehicle can carry, and corresponding vehicle volume constraints are constructed based on this volume requirement data. These constraints ensure that the volume of the selected vehicle can meet the volume requirements of the goods when performing a transportation task, avoiding transportation problems caused by insufficient vehicle volume. This effectively manages vehicle loading capacity and improves transportation efficiency. Furthermore, empty-run constraints can be constructed based on empty-run constraint data for each vehicle type (including restrictions on vehicles performing empty-run tasks, such as maximum empty-run distance and empty-run time) to ensure that vehicles do not exceed specified limits when performing empty-run tasks. These constraints help optimize vehicle routes, reduce unnecessary empty runs, and thus lower operating costs. Additionally, this application embodiment can also obtain regional limitation data corresponding to each route transportation demand. This data defines the geographical area involved in the transportation task, and route area constraints are constructed based on this regional limitation data to ensure that the transportation task is carried out within the specified area. These constraints help us better manage the transportation network and ensure that transportation tasks comply with regional requirements and regulations. Furthermore, the various constraints previously constructed are integrated, including route allocation constraints, vehicle quantity constraints, node flow constraints, vehicle volume constraints, empty-run constraints, and route area constraints. This integration yields a comprehensive set of route transportation constraints, which will serve as input to subsequent optimization algorithms to solve for the optimal transportation route combination scheme. By integrating these constraints, we can ensure that the final transportation scheme satisfies both various business needs and actual operational constraints.

[0055] In step S150 of some embodiments, the embodiments of this application can design a vehicle transportation route optimization objective based on multiple transportation spatiotemporal network diagrams and vehicle transportation resource data. This function mathematically expresses the desired optimization objective, namely, minimizing total resources (costs). Total resources can be subdivided into driver salaries (linked to driving time), fuel costs (related to driving distance and vehicle fuel consumption), toll fees, vehicle depreciation or rental costs, etc. These cost factors are partly derived from vehicle transportation attribute data (such as fuel consumption rate) and empty-run transportation data (such as empty-run fuel unit price). In other words, the embodiments of this application can achieve highly realistic comprehensive operating cost optimization. That is, the constructed model (vehicle transportation route optimization objective) breaks through the limitations of a single cost item and incorporates key operating elements such as driver income (linked to task mileage), vehicle fuel consumption (related to total mileage), vehicle fixed costs and depreciation into the optimization framework, constructing a comprehensive cost model that highly replicates the real operating scenario, and is committed to achieving the global optimum of total operating costs.

[0056] Therefore, the embodiments of this application can adopt a multi-attribute compatible route-vehicle matching mechanism. This means that the transportation route itself contains numerous attributes, such as arrival, departure, arrival, and unloading times, as well as capacity, failure time, waiting time, and tonnage. When allocating a set of routes to specific vehicles, this algorithm establishes a multi-dimensional compatibility evaluation mechanism to ensure a deep match between the route's attributes and the vehicle's performance, specifications, and operational requirements. Furthermore, the algorithm not only calculates the actual mileage and time of vehicle task execution but also focuses on the empty mileage and time generated by connecting tasks. It deeply analyzes historical execution data from various regions, extracts empty mileage requirements that conform to local operational characteristics, and constructs a quantifiable empty mileage cost pricing formula based on this, making cost estimation more accurate. During the route combination generation process, the algorithm prioritizes ensuring business executability and strictly adheres to all business rule constraints. By customizing and constructing a business-goal-oriented resource allocation optimization model (i.e., the constructed vehicle transportation route optimization objective and corresponding route transportation constraints), it achieves an effective solution for core operational objectives (such as cost minimization) while satisfying complex business constraints.

[0057] Please refer to Figure 8 , Figure 8 This is a flowchart of step S150 provided in an embodiment of this application. In some embodiments, step S150 may specifically include, but is not limited to, steps S810 to S850, as described below. Figure 8 These five steps will be explained in detail.

[0058] Step S810: Determine the node arc transportation resource data corresponding to the node arc based on the node arc type and vehicle transportation resource data in the transportation spatiotemporal network diagram. Step S820: For multiple vehicle types, construct a node arc optimization function based on the node arc transportation resource data and the node arc execution label of the node arc; Step S830: Extract fixed transportation resource data corresponding to each vehicle type from the vehicle transportation resource data; Step S840: For various vehicle types, construct a fixed transportation optimization function based on the fixed transportation resource data and the node arcs passing through the zero point by executing labels. Step S850: Construct the vehicle transportation route optimization objective based on the nodal arc optimization function and the fixed transportation optimization function.

[0059] In step S810 of some embodiments, since the resource costs corresponding to different types of node arcs may differ, for example, a vehicle package is composed of attributes (empty driving, task, rest, etc.) from multiple graphs, which are used to share the driver's income, variable costs, and fixed costs respectively. For example, driver income = number of routes × route coefficient + cargo mileage × cargo mileage coefficient + empty driving mileage × empty driving mileage coefficient; variable cost = total mileage (cargo mileage + empty driving mileage) × fuel cost per kilometer; fixed cost = tailgate fee + vehicle fixed value + added value (if the total duration of the vehicle package is ≥ 16 hours, a dual-driver added value is used; otherwise, a single-driver added value is used). If a certain route cannot be combined into any vehicle package, the cost is calculated according to its standard price, and the vehicle is assigned to an external supplier for execution, with the company paying the corresponding labor cost according to the standard price. Based on this, the embodiments of this application can combine vehicle transportation resource data to determine the transportation resource data corresponding to each node arc, which will directly affect the vehicle's transportation capacity and cost on that node arc. For example, a mission arc may require specific vehicle types and load capacities, while an empty mission arc may take fuel efficiency and driver fatigue into account more.

[0060] In step S820 of some embodiments, the node arc execution label is used to characterize whether the corresponding arc is executed in actual transportation demand. The node arc execution label can be 0 or 1, where 0 indicates that it has not been executed and 1 indicates that it has been executed (equivalent to a valid node arc). For multiple vehicle types, a node arc optimization function is constructed based on the node arc transportation resource data and the node arc execution label. This node arc optimization function can characterize the total resources required for the node arcs executed for multiple vehicle types.

[0061] In steps S830 and S840 of some embodiments, for multiple vehicle types, this application embodiment can construct a fixed transportation optimization function based on fixed transportation resource data (such as vehicle purchase cost, depreciation cost, fixed operating cost, etc., corresponding to the fixed costs in the above embodiments) and the node arcs passing through the zero point (i.e., sky-crossing arcs) and their labels. These costs do not change with the transportation task and are the basic expenses for each vehicle type. By extracting this data, the total cost for each vehicle type can be calculated more accurately, providing important cost information for the subsequent optimization process.

[0062] In step S850 of some embodiments, the constructed nodal arc optimization function and fixed transportation optimization function can be combined to form a vehicle transportation route optimization objective. This comprehensive optimization function will simultaneously consider the transportation resources and fixed transportation costs of the nodal arc, as well as other possible business constraints, such as time windows and vehicle capacity.

[0063] In step S160 of some embodiments, the data preprocessing, spatiotemporal network graph construction, and modeling processes of this application embodiment can all be completed on a local computer, while the solution of the integer programming model is deployed and run on a server. For example, the Gurobi solver or heuristic algorithms (such as column generation, tabu search, and genetic algorithms) are called to perform large-scale numerical calculations on the generated vehicle transportation route optimization objective. The nodes and arcs in the network graph are mapped to decision variables (e.g., binary variables representing whether a vehicle passes through a certain arc), and the combination of variable values ​​that minimizes the objective function is searched under the premise of satisfying all constraints. By solving this optimization function, a globally optimal or near-optimal vehicle transportation route scheme can be obtained. This scheme will minimize transportation costs and maximize transportation efficiency while meeting all business needs. The final output vehicle transportation route scheme can include the specific driving path of each vehicle, task sequence, departure and arrival times, and expected cost details, which can be directly used for scheduling execution and visualization.

[0064] For example, the vehicle transportation route optimization objective constructed in this application embodiment can be established based on the following assumptions: 1. All routes are considered to operate at full capacity, i.e., executed day after day, thus simplifying the problem to a network flow problem within 24 hours; 2. Vehicles of the same model are homogeneous, applicable to all routes requiring that model, possessing interchangeability and unified scheduling conditions. Based on this, the generated vehicle transportation route optimization objective can be expressed as shown in Formula 1 below, and the corresponding set of route transportation constraints are shown in Formulas 2 to 5 below: (Formula 1) (Formula 2) (Formula 3) (Formula 4) (Formula 5) Where K is the set of vehicle types, a represents the node arc, and A k c represents the set of all node arcs in the spatiotemporal network graph of the transportation vehicle type k. a x represents the cost of node arc a (i.e., node arc transportation resource data). a This indicates the execution label of node arc a; it is 1 when executed and 0 otherwise. k This represents the cost of using one vehicle of model k (i.e., fixed transportation resource data). Let represent the set of node arcs passing through the zero point in the spatiotemporal network graph of vehicle type k. Represents the nodal arc optimization function. Let A represent the fixed transport optimization function. In the constraints, A... iLet I represent the set of transportation arcs (i.e., demand arcs) distributed across the spatiotemporal network graph corresponding to each feasible k vehicle type for demand i, where I represents the set of transportation route demands. This represents the upper limit of the number of vehicles of model k (i.e., the vehicle quantity requirement data). This represents the set of nodes in the spatiotemporal network graph for vehicle type k. Therefore, Formulas 2 and 5 are equivalent to the route allocation constraints in the above embodiment, Formula 3 is equivalent to the vehicle quantity constraints in the above embodiment, and Formula 4 is equivalent to the node flow constraints in the above embodiment. After the model (i.e., Formulas 1 to 5) is established, it can be sent to the server where the solver is located for solving, and finally converted into a business solution output.

[0065] In some embodiments, this application also provides a vehicle transportation route planning method, which includes, but is not limited to, the following steps: The target transportation route scheme is obtained for multiple transportation routes in a cargo transportation scenario. The target transportation route scheme is constructed based on the vehicle transportation route optimization method described in the above embodiment. The target transportation route scheme is used to indicate the combination scheme of vehicle data for executing the transportation needs of each route. Based on the target transportation route plan, control the vehicles corresponding to the transportation needs of each route to execute the transportation needs.

[0066] In this application, the embodiments can flexibly incorporate various business evaluation indicators (such as driver working hours, empty driving distance, empty driving ratio, etc.) within a preset time range, so as to provide a deterministic combination scheme for various input tasks and vehicle data, making the solution results more in line with the actual operation scenario, greatly improving the practicality and feasibility of the solution, and ensuring the timeliness of daily operation decisions.

[0067] This application provides a vehicle transportation route optimization method, proposing an algorithm for finding the exact optimal solution for vehicle transportation route combinations based on an operating cost model. Its core advantages are reflected in the following aspects: First, it constructs a more comprehensive cost evaluation model, considering not only the empty-running cost during task connection but also integrating multiple factors such as driver income related to task mileage, fuel consumption related to total mileage, vehicle fixed costs, depreciation expenses, and external supplier costs, thereby achieving systematic optimization of total operating costs. Second, the algorithm fully integrates diverse business constraints during the combination generation process, not only limited to the feasibility of task time connections but also including tonnage limits, vehicle type matching, loading volume, network point affiliation, and cargo type—a series of business attributes directly affecting combination feasibility and cost structure—making the solution more closely aligned with actual operational needs. Third, this method can output an exact optimal solution within a reasonable timeframe. For a typical area (e.g., Nanshan District, Shenzhen) involving transportation tasks and vehicle resource scheduling problems, it can achieve an accurate solution within an acceptable timeframe, especially in smaller area scenarios, where it can even achieve a second-level response. In dozens of real-world application cases, the algorithm proposed in this application successfully generated optimal solutions. Compared with scheduling schemes that rely on human experience, this algorithm can reduce global operating costs by about 4%. In terms of output efficiency, compared with planners manually arranging from scratch, this algorithm can save at least 50% of the time. Based on this, the embodiments of this application can produce the following technical effects: (1) It proposes for the first time a mathematical programming method for single-vehicle multi-route combination with the goal of optimizing overall operating costs, breaking through the limitations of traditional methods that only focus on local or single cost factors. (2) It has excellent solution efficiency. From data preprocessing to final output results, the entire process can be completed within 4 hours for most area instances; for smaller areas, it can achieve real-time solution at the second level. (3) The system operates stably and reliably, and can provide deterministic combination schemes for various input tasks and vehicle data within a preset time range, ensuring the timeliness of daily operation decisions. (4) The algorithm design closely follows the actual business, and its route combination form completely follows the business orientation. The model can also flexibly incorporate various business evaluation indicators (such as driver working hours, empty driving distance, and empty driving ratio), making the solution results more consistent with actual operating scenarios and greatly improving the practicality and feasibility of the solution. Therefore, the embodiments of this application can improve the accuracy of vehicle transportation route optimization.

[0068] Please see Figure 9 This application also provides a vehicle transportation route optimization device, the vehicle transportation route optimization device 900 including: The vehicle data acquisition module 910 is used to acquire vehicle attribute data corresponding to various vehicle types that can perform route transportation needs in a freight transportation scenario. The vehicle attribute data includes vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The vehicle transportation attribute data is used to indicate attribute data related to the transportation vehicle. The vehicle transportation resource data is used to indicate the resource data consumed when the transportation vehicle performs route transportation needs. The vehicle transfer resource data is used to indicate the resource data consumed when a third-party vehicle performs route transportation needs. The freight transportation scenario includes multiple transportation routes. The network data acquisition module 920 is used to acquire inter-network transportation data in the cargo transportation scenario. The inter-network transportation data includes transportation demand data and empty-run transportation data of multiple transportation networks based on transportation routes in the cargo transportation scenario. The graph construction module 930 is used to construct a corresponding transportation spatiotemporal network graph for each vehicle type based on transportation demand data and empty-run transportation data. The transportation spatiotemporal network graph includes multiple network nodes, and each network node is a transportation network point associated with the vehicle type in the cargo transportation scenario. The constraint construction module 940 is used to construct route transportation constraints for various vehicle types based on multiple transportation spatiotemporal network diagrams, vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. Function construction module 950 is used to construct vehicle transportation route optimization objectives based on multiple transportation spatiotemporal network diagrams and vehicle transportation resource data; The function solver module 960 is used to obtain the target transportation route scheme based on the route transportation constraints and the vehicle transportation route optimization objective.

[0069] It should be noted that the vehicle transportation route optimization device provided in this application embodiment is used to implement the vehicle transportation route optimization method provided in the above embodiment, and the specific implementation process corresponds to the vehicle transportation route optimization method in the above embodiment. It can be referred to the aforementioned vehicle transportation route optimization method, and will not be repeated here.

[0070] This application also provides an electronic device (i.e., a computer device), which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the vehicle transportation route optimization methods described in the above embodiments. This electronic device can be any smart terminal, including a tablet computer, an in-vehicle computer, or similar device.

[0071] Please see Figure 10 , Figure 10 This illustration shows the hardware structure of an electronic device according to another embodiment, the electronic device comprising: The processor 1010 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 1020 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1020 can store the operating system and other applications. 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 1020 and is called and executed by the processor 1010 to execute the vehicle transportation route optimization method of the embodiments of this application. The input / output interface 1030 is used to implement information input and output; The communication interface 1040 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 1050 transmits information between various components of the device (e.g., processor 1010, memory 1020, input / output interface 1030, and communication interface 1040); The processor 1010, memory 1020, input / output interface 1030 and communication interface 1040 are connected to each other within the device via bus 1050.

[0072] This application also provides a computer-readable storage medium storing a computer program for causing a computer to execute the vehicle transportation route optimization method described in the above embodiments.

[0073] 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.

[0074] This invention also provides a computer program product that stores program instructions, which, when executed by a computer, cause the computer to implement the vehicle transportation route optimization method described in any of the above embodiments.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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 method for optimizing vehicle transportation routes, characterized in that, The method includes: The system acquires vehicle attribute data corresponding to various vehicle types capable of performing route transportation needs in a freight transportation scenario. The vehicle attribute data includes vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The vehicle transportation attribute data is used to indicate attribute data related to the transportation vehicle. The vehicle transportation resource data is used to indicate resource data consumed by the transportation vehicle when performing route transportation needs. The vehicle transfer resource data is used to indicate resource data consumed by a third-party vehicle when performing route transportation needs. The freight transportation scenario includes multiple transportation routes. Acquire inter-point transportation data for the cargo transportation scenario, which includes transportation demand data and empty-run transportation data of multiple transportation points in the cargo transportation scenario based on transportation routes; For each vehicle type, a corresponding transportation spatiotemporal network diagram is constructed based on the transportation demand data and the empty-run transportation data. The transportation spatiotemporal network diagram includes multiple network nodes, and each network node is the transportation network point associated with the vehicle type in the cargo transportation scenario. Based on multiple transport spatiotemporal network diagrams, vehicle transport attribute data, vehicle transport resource data, and vehicle transfer resource data, route transport constraints corresponding to various vehicle types are constructed. Based on the multiple spatiotemporal network diagrams of transportation and the vehicle transportation resource data, a vehicle transportation route optimization objective is constructed. Based on the route transportation constraints and the vehicle transportation route optimization objectives, the target transportation route scheme is obtained.

2. The method according to claim 1, characterized in that, The transportation spatiotemporal network graph includes node arcs between multiple network nodes. Based on the multiple transportation spatiotemporal network graphs, the vehicle transportation attribute data, the vehicle transportation resource data, and the vehicle transfer resource data, route transportation constraints corresponding to various vehicle types are constructed, including: For each of the transport routes, the effective node arcs for executing the transport route corresponding to the vehicle type are determined based on the multiple transport spatiotemporal network graphs. Construct route allocation constraints based on the valid node arcs corresponding to the various vehicle types described; The vehicle quantity requirement data corresponding to each vehicle type is determined from the vehicle transportation attribute data, and vehicle quantity constraints are constructed based on the effective node arcs corresponding to multiple vehicle types and the vehicle quantity requirement data corresponding to multiple vehicle types. Based on the node type of the valid node arc corresponding to the various vehicle types, construct node flow constraints; The route allocation constraints, vehicle quantity constraints, and node flow constraints are integrated to obtain the route transportation constraints.

3. The method according to claim 2, characterized in that, The effective node arc includes rest arcs and non-rest arcs. The rest arc refers to the arc formed by the time period between the end of the transportation demand of the previous route and the start of the transportation demand of the next route at the same transportation point in the transportation spatiotemporal network diagram. The step of constructing node flow constraints based on the node types of valid node arcs corresponding to various vehicle types includes: Node arcs are filtered for valid node arcs corresponding to various vehicle types to obtain the first rest arc and the first non-rest arc corresponding to the originating node, and the second rest arc and the second non-rest arc corresponding to the destination node. The execution flow of the second rest arc and the execution flow of the second non-rest arc corresponding to various vehicle types are summed to obtain the total node inflow flow data; The execution flow of the first rest arc and the execution flow of the first non-rest arc corresponding to various vehicle types are summed to obtain the total outflow data of the node; Node flow constraints are constructed based on the total inflow data and the total outflow data of the nodes.

4. The method according to claim 2, characterized in that, The construction of route allocation constraints based on the valid node arcs corresponding to various vehicle types includes: The set of node arcs to be executed for the same transportation route is determined based on the valid node arcs corresponding to the various vehicle types described. The route allocation constraints are constructed based on the set of node arcs corresponding to the multiple route transportation requirements.

5. The method according to claim 2, characterized in that, The process of integrating the route allocation constraints, the vehicle quantity constraints, and the node flow constraints to obtain the route transportation constraints includes: Determine the vehicle volume requirement data corresponding to each vehicle type from the vehicle transportation attribute data, and construct vehicle volume constraints based on the vehicle volume requirement data; Obtain empty-run constraint data corresponding to each of the vehicle types, and construct empty-run constraint conditions based on the empty-run constraint data; Obtain the regional limitation data corresponding to the transportation demand of each route, and construct the regional constraint conditions of the route based on the regional limitation data. The route allocation constraints, vehicle quantity constraints, node flow constraints, vehicle volume constraints, empty running constraints, and route area constraints are integrated to obtain the route transportation constraints.

6. The method according to claim 2, characterized in that, The step of constructing a vehicle transportation route optimization objective based on multiple transportation spatiotemporal network diagrams and vehicle transportation resource data includes: Based on the node arc type of the node arc in the transportation spatiotemporal network diagram and the vehicle transportation resource data, determine the node arc transportation resource data corresponding to the node arc; For various vehicle types, a node arc optimization function is constructed based on the node arc transportation resource data and the node arc execution label of the node arc; Extract fixed transportation resource data corresponding to each vehicle type from the vehicle transportation resource data; For various vehicle types, a fixed transport optimization function is constructed by executing labels based on the fixed transport resource data and the node arcs of the node arcs passing through the zero point; The vehicle transportation route optimization objective is constructed based on the node arc optimization function and the fixed transportation optimization function.

7. A method for planning vehicle transportation routes, characterized in that, The method includes: The method for obtaining target transportation route schemes corresponding to multiple transportation routes in a cargo transportation scenario is constructed based on the vehicle transportation route optimization method according to any one of claims 1. The target transportation route scheme is used to indicate the combination scheme of vehicle data for executing the transportation needs of each route. Based on the target transportation route plan, control the vehicles corresponding to the transportation needs of each route to execute the transportation requirements.

8. A vehicle transportation route optimization device, characterized in that, The device includes: The vehicle data acquisition module is used to acquire vehicle attribute data corresponding to various vehicle types that can perform route transportation needs in a freight transportation scenario. The vehicle attribute data includes vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The vehicle transportation attribute data is used to indicate attribute data related to the transportation vehicle. The vehicle transportation resource data is used to indicate the resource data consumed by the transportation vehicle when performing route transportation needs. The vehicle transfer resource data is used to indicate the resource data consumed by a third-party vehicle when performing route transportation needs. The freight transportation scenario includes multiple transportation routes. The network point data acquisition module is used to acquire inter-network point transportation data in the cargo transportation scenario. The inter-network point transportation data includes transportation demand data and empty-run transportation data of multiple transportation network points in the cargo transportation scenario based on the transportation route. The graph construction module is used to construct a corresponding transportation spatiotemporal network graph for each vehicle type based on the transportation demand data and the empty-run transportation data. The transportation spatiotemporal network graph includes multiple network nodes, and each network node is the transportation network point associated with the vehicle type in the cargo transportation scenario. The constraint construction module is used to construct route transportation constraints corresponding to various vehicle types based on multiple transportation spatiotemporal network diagrams, vehicle transportation attribute data, vehicle transportation resource data, and vehicle transfer resource data. The function construction module is used to construct vehicle transportation route optimization objectives based on multiple transportation spatiotemporal network diagrams and vehicle transportation resource data; The function solving module is used to obtain the target transportation route scheme based on the route transportation constraints and the vehicle transportation route optimization objective.

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 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 a processor, it implements the method of any one of claims 1 to 7.

Images