Cargo transportation route optimization method and device, transportation method, equipment and medium

Abstract

Embodiments of the present application provide a kind of goods transport route optimization method and device, transport method, equipment and medium, belong to goods transport planning technical field.The method comprises: obtaining the target goods attribute data and the first transport attribute data of transport task in goods transport scene, and the second transport attribute data of transfer network point;Global transport network connectivity graph is constructed based on the first transport attribute data and the second transport attribute data, and global transport network connectivity graph includes multiple graph nodes and multiple node edges;According to target goods attribute data, node attribute data corresponding to graph node and node edge attribute data corresponding to node edge, construct multidimensional route optimization constraint condition;Determine goods transport route optimization target based on global transport network connectivity graph and preset transport mode constraint condition, and route optimization is carried out in combination with multidimensional route optimization constraint condition to obtain target route optimization scheme.The accuracy of goods transport route optimization can be improved by the embodiments of the present application.

Description

Technical Field

[0001] This application relates to the field of freight transportation planning technology, and in particular to a freight transportation route optimization method and apparatus, transportation method, equipment and medium. Background Technology

[0002] Freight transportation route optimization refers to the process of systematically planning and calculating the most efficient freight transportation route based on the city pairs corresponding to the origin and destination of the transported goods. This aims to reduce transportation costs, improve delivery speed, and minimize resource waste. For example, in the planning of air freight for large and bulky cargo, by comprehensively managing the transportation modes (such as road, rail, air, and water transport) and routes, daily transportation tasks can be efficiently scheduled.

[0003] Currently, in the absence of algorithm-assisted decision-making, related technologies typically rely on the personal experience of regional planners, using historical experience or simple rules to determine the transportation routes between "city pairs" that meet business requirements as the routes for transporting large air cargo. This experience-driven operational mode easily leads to a lack of flexibility in the planned transportation routes, making it difficult to cope with complex actual transportation needs and unexpected situations. Therefore, the accuracy of the methods used in related technologies for optimizing cargo transportation routes remains insufficient. Summary of the Invention

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

[0005] To achieve the above objectives, a first aspect of this application proposes a cargo transportation route optimization method, the method comprising: In a cargo transportation scenario, target cargo attribute data and first transportation attribute data corresponding to transportation tasks based on city pairs to be planned are obtained, and second transportation attribute data of transit points associated with city pairs to be planned are obtained, wherein the city pairs to be planned include originating points and destination points. Based on the first transportation attribute data and the second transportation attribute data, a graph is constructed to obtain a global transportation network connectivity graph. The global transportation network connectivity graph includes multiple graph nodes and multiple node edges. Each graph node is used to represent a transportation network point in a different geographical location. The transportation network point can be a starting point, a destination point, or a transit point. Obtain the node attribute data corresponding to each graph node and the node edge attribute data corresponding to each node edge. The node edge attribute data is used to indicate the relevant data of cargo transportation between two corresponding graph nodes based on different transportation methods. Based on the target cargo attribute data, the node attribute data, and the node edge attribute data, construct multidimensional routing optimization constraints. Based on the global transportation network connectivity graph and the preset transportation mode constraints, the cargo transportation route optimization target corresponding to the transportation task is determined. The transportation mode constraints are used to indicate that the generated target route optimization scheme should include at least one sub-route transportation segment based on air transportation. Based on the cargo transportation route optimization objective and the multi-dimensional route optimization constraints, route optimization is performed to obtain the target route optimization scheme.

[0006] To achieve the above objectives, a second aspect of this application provides a method for transporting goods, the method comprising: Obtain the target route optimization scheme corresponding to the transportation task based on the city pair to be planned in the cargo transportation scenario. The target route optimization scheme is constructed based on the cargo transportation route optimization method described in the first aspect. The target route optimization scheme is used to indicate the combination scheme of transportation path and transportation mode adopted to execute the transportation task. The transportation task is executed based on the target route optimization scheme.

[0007] To achieve the above objectives, a third aspect of this application provides a cargo transportation route optimization device, the device comprising: The first acquisition module is used to acquire target cargo attribute data and first transportation attribute data corresponding to transportation tasks based on the city pair to be planned in the cargo transportation scenario, and to acquire second transportation attribute data of transit points associated with the city pair to be planned, wherein the city pair to be planned includes a starting point and a destination point. The graph construction module is used to construct a graph based on the first transportation attribute data and the second transportation attribute data to obtain a global transportation network connectivity graph. The global transportation network connectivity graph includes multiple graph nodes and multiple node edges. Each graph node is used to represent a transportation network point in a different geographical location. The transportation network point is a starting point, a destination point, or a transit point. The second acquisition module is used to acquire node attribute data corresponding to each graph node and node edge attribute data corresponding to each node edge. The node edge attribute data is used to indicate relevant data on cargo transportation between two corresponding graph nodes based on different transportation methods. The constraint construction module is used to construct multidimensional route optimization constraints based on the target cargo attribute data, the node attribute data, and the node edge attribute data. The target determination module is used to determine the cargo transportation route optimization target corresponding to the transportation task based on the global transportation network connectivity graph and the preset transportation mode constraints. The transportation mode constraints are used to indicate that the generated target route optimization scheme should include at least one sub-route transportation segment based on air transportation. The route optimization module is used to optimize the route based on the cargo transportation route optimization objective and the multi-dimensional route optimization constraints to obtain the target route optimization scheme.

[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 freight transportation route optimization method, apparatus, transportation method, equipment, and medium proposed in this application can, during freight transportation route optimization, collect and integrate the first transportation attribute data corresponding to the transportation task and the second transportation attribute data of the associated transit points. This abstracts the complex physical transportation network into a global transportation network connectivity graph containing spatiotemporal information and constructs multi-dimensional route optimization constraints that conform to actual operational needs. Furthermore, before performing route optimization, this application determines the freight transportation route optimization target corresponding to the transportation task based on the global transportation network connectivity graph and preset transportation mode constraints. These transportation mode constraints require that the generated target route optimization scheme must include a sub-route transportation segment based on air transportation to ensure the aeronautical attributes of the scheme. Then, the freight transportation route optimization target is solved by limiting the multi-dimensional route optimization constraints to achieve route optimization, resulting in a target route optimization scheme that meets the constraints. Thus, this application can guide the rational allocation of transportation resources, improve the flexibility of planned transportation route schemes, and better cope with complex actual transportation needs and emergencies. Therefore, the freight transportation route optimization method provided in this application can improve the accuracy of freight transportation route optimization. Attached Figure Description

[0011] Figure 1 This is a flowchart of a cargo transportation route optimization method provided in an embodiment of this application; Figure 2 yes Figure 1 A flowchart of step S140 in the process; Figure 3 yes Figure 1 A flowchart of step S150 in the process; Figure 4 yes Figure 3 A flowchart of step S330 in the process; Figure 5 yes Figure 3 A flowchart of step S340 in the process; Figure 6 This is another flowchart of the cargo transportation route optimization method provided in the embodiments of this application; Figure 7 This is a flowchart of a cargo transportation method provided in an embodiment of this application; Figure 8 This is a schematic diagram of a cargo transportation route optimization device provided in an embodiment of this application; Figure 9 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] Freight transportation route optimization refers to the process of systematically planning and calculating the most efficient freight transportation route based on the city pairs corresponding to the origin and destination of the transported goods. This aims to reduce transportation costs, improve delivery speed, and minimize resource waste. For example, in the planning of air freight for large and bulky cargo, by comprehensively managing the transportation modes (such as road, rail, air, and water transport) and routes, daily transportation tasks can be efficiently scheduled.

[0015] Currently, in the absence of algorithm-assisted decision-making, the routing optimization methods adopted by related technologies include: (1) Manual planning based on fixed rules or historical experience: This method refers to routing planning that relies entirely on the personal experience of senior operators. These operators can specify one or several fixed transportation routes for a specific city pair based on the flight schedules they remember, the airlines they cooperate with, and past successful cases. However, this method is highly dependent on individuals, difficult to scale and standardize, and cannot cope with complex changes. (2) Simple "city pair" point-to-point route query system: This is a basic information system with a built-in routing table. When the starting city and destination city are entered, the system will retrieve and display the preset direct or simple transfer routes. It is essentially a "database query" tool and lacks optimization calculation capabilities. The routes are entered manually in advance, and the system itself will not create or optimize new routes. (3) Local optimization focusing on a single link or a single goal: Although on-site personnel may find problems with the planned routes, they may optimize a certain link in the transportation process. For example, optimizing only the air segment: only finding the cheapest or fastest flight between two locations, but ignoring the costs and time of land transportation connections before and after the flight. Or, optimizing only a single objective of cost or timeliness: aiming for the lowest cost may result in choosing a solution with extremely poor timeliness, or aiming for the fastest timeliness without considering high costs. There is a lack of ability to weigh multiple objectives.

[0016] It can be seen that the common core characteristics of the related technologies are: non-global, all are local and segmented planning, without considering the whole link from the "end to end" (network point to network point); static and rigid, unable to dynamically respond to changes in the network environment such as capacity, cost, and cargo volume, that is, the related technologies generally rely on manual labor, have low automation, and can only perform simple queries and displays. Therefore, the technical problems of the related technologies can include: (1) high total transportation cost: because the planning is local, the "nearby dispatch" strategy causes the cargo volume to surge to the core hub with the highest cost, and cannot intelligently utilize the surrounding lower-cost capacity resources, and cannot perform end-to-end cost calculation. It seems that the cost of each segment is controllable, but the total cost of the whole link is not optimal. (2) low overall transportation efficiency and uneven resource utilization: the capacity pressure of the core hub is too high, and it is easy to be overwhelmed and delayed, while the surrounding airport and land transportation resources are idle, resulting in a waste of the entire network capacity. The current system cannot actively and intelligently guide the cargo flow to idle resources to achieve network load balancing. (3) Inability to effectively guarantee and improve timeliness: Simple systems cannot handle complex "time window constraints" (such as the connection between receiving shifts, flight departure times, and delivery shifts), often resulting in "missing flights" or "being unable to deliver in time after arrival," leading to overall instability or even delays in timeliness. At the same time, it is impossible to aggregate cargo volume to support the operation of high-quality and time-efficient transport capacity. (4) Disconnect between planning schemes and actual operations, resulting in poor executability: Due to the lack of comprehensive consideration of multiple constraints (timeliness, time windows, number of nodes, etc.), the planned routes are often "theoretical paths" that cannot be smoothly executed in complex real-world operating networks, causing great difficulties for subsequent scheduling and operations. (5) Lack of flexibility and adaptability: When the transport capacity (referring to the means of transport used to complete the transport task, such as vehicles, ships, trains, airplanes, etc.), costs, or demands in the network change (such as adding flights or raising prices on a certain route), the existing rigid system cannot respond quickly and generate new optimal solutions, requiring manual intervention and adjustment, resulting in slow response speed.

[0017] In modern logistics systems, air transport, with its high timeliness, has become the preferred mode of transport for high-value, urgent, and large cargo (such as precision instruments and high-value industrial spare parts). However, related technologies for routing planning systems for large air cargo typically suffer from the following shortcomings: (1) Rigid and inflexible planning: Most systems only provide point-to-point routes between cities based on historical experience or simple rules, and cannot be dynamically optimized according to multiple dimensions such as actual transport capacity, cost, and timeliness. This results in a lack of flexibility in planning schemes, making it difficult to cope with complex actual transport needs and emergencies.

[0018] (2) Uneven utilization of resources: In the absence of global data support, front-line business personnel tend to default to the "nearest shipment" strategy. This behavior pattern leads to the excessive concentration of waybills in hubs of first-tier and super first-tier cities, resulting in tight transportation capacity and high costs in these areas, while transportation resources with more competitive prices in surrounding areas are idle and wasted, forming a situation of "uneven busy and idle".

[0019] (3) High-quality transport capacity is idle: Some low-priced and timely scattered or all-cargo aircraft resources often cannot open stable routes due to insufficient order volume or failure to be effectively included in the planning system, resulting in the inability to improve the overall transport network timeliness and high costs.

[0020] (4) Lack of global optimization: Existing solutions are mostly segmented and localized optimizations, failing to make overall plans from the perspective of the entire link from the originating point of goods to the destination point. They ignore the coupling relationship of various constraints such as delivery schedules, land transportation connections, flight schedules, and time windows, making it difficult to achieve the best end-to-end cost and timeliness.

[0021] Therefore, there is an urgent need in this field for a static routing planning technology for large aviation components that can integrate network resources, comprehensively consider various real-world constraints, and achieve end-to-end global optimization, so as to improve transportation efficiency and significantly reduce operating costs.

[0022] Based on this, embodiments of this application provide a method and apparatus for optimizing cargo transportation routes, a transportation method, equipment, and a medium, which can improve the accuracy of cargo transportation route optimization.

[0023] 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.

[0024] The freight transportation route optimization method and freight transportation method provided in this application relate to the field of freight transportation planning technology. The freight transportation route optimization method and freight transportation method provided in this application 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 freight transportation route optimization method and freight transportation method, but is not limited to the above forms.

[0025] 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.

[0026] 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 cargo 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 these embodiments be obtained.

[0027] Please see Figure 1 , Figure 1 This is an optional flowchart of the cargo 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.

[0028] Step S110: Obtain the target cargo attribute data and first transportation attribute data corresponding to the transportation task based on the city pair to be planned in the cargo transportation scenario, and obtain the second transportation attribute data of the transit network points associated with the city pair to be planned. The city pair to be planned includes the starting network point and the destination network point. Step S120: Based on the first transportation attribute data and the second transportation attribute data, a graph is constructed to obtain a global transportation network connectivity graph; Step S130: Obtain the node attribute data corresponding to each graph node and the node edge attribute data corresponding to each node edge. Step S140: Construct multi-dimensional route optimization constraints based on target cargo attribute data, node attribute data, and node edge attribute data; Step S150: Based on the global transportation network connectivity graph and the preset transportation mode constraints, determine the cargo transportation route optimization target corresponding to the transportation task. The transportation mode constraints are used to indicate that the generated target route optimization scheme should contain at least one sub-route transportation segment based on air transportation. Step S160: Based on the cargo transportation route optimization objective and the multi-dimensional route optimization constraints, perform route optimization to obtain the target route optimization scheme.

[0029] In step S110 of some embodiments, the cargo transportation route optimization method provided in this application is mainly aimed at the end-to-end transportation scenario of large air cargo. A cargo transportation scenario refers to an operational environment in a logistics network where a complete transportation route from the originating geographical point to the destination point needs to be planned for a batch of goods, with particular attention to multimodal transport routes involving air transport. The city pair to be planned refers to the combination of the originating city and the destination city for which a transportation route needs to be planned. In specific operation, the entity of the goods in the originating city is the "originating point" (e.g., the receiving branch), and the entity in the destination city to which the goods need to reach is the "destination point" (e.g., the delivery branch). For example, a transportation task is formulated by planning the route for large cargo (weight range 50~100KG) shipped from city A to city B. A transportation task refers to the transportation demand for a batch of specific goods in the city pair to be planned, which may include the physical attributes of the goods (e.g., weight, size) and business requirements (e.g., promised delivery time). Target cargo attribute data refers to data that describes the characteristics of the cargo itself in the transportation task, such as the weight range of the cargo (e.g., 50-100KG), volume, and whether it belongs to special cargo (e.g., dangerous goods, valuables).

[0030] In the above embodiments, this application can collect basic data required for planning (such as target cargo attribute data, first transportation attribute data, second transportation attribute data, etc.) through various means such as data warehouses (such as Hive tables), parameter configuration libraries, transportation management systems (TMS) and geographic information systems (GIS) platforms. For example, it can pull data such as all land transportation, all-cargo aircraft, and chartered flight schedules, cost tables, and representative network mapping relationships of cities A and B and related transit cities in the near future from the Hive data warehouse table. The first transportation attribute data refers to transportation resource and rule data directly related to the originating and destination network points. Examples include: information on receiving and dispatching schedules (i.e., the time-based schedules for receiving goods at the network point), dispatching schedules (i.e., the time-based schedules for dispatching goods at the network point), dispatching time (i.e., the delivery time required for each network point's schedule), cost data (such as unit transportation costs for all-cargo aircraft, general aviation, and land transport routes), geographical location information (such as distance tables between cities to reflect the distance relationships between network points), transportation capacity resource information (such as land transport route tables, which may include transit network points, departure / arrival times, latest arrival times, and schedules), flight route tables (which may include originating / destination network points, takeoff / arrival / pickup times, latest arrival times, and schedules), and auxiliary information (such as city-applicable airport tables, aviation resource databases, and mapping tables of representative network points in large / large network cities).

[0031] The second transportation attribute data, which is associated with transit points in the cities to be planned, refers to the transportation resource data corresponding to transit points (i.e., intermediate nodes) that may be passed through during the transportation of goods from the originating point to the destination point. The content of the second transportation attribute data can be found in the first transportation attribute data, and the second transportation attribute data may have a broader scope, such as including information on all possible land transportation routes in the entire network (e.g., schedules, departure times, latest arrival times, and stops along the way), air route information (e.g., flight numbers for all-cargo aircraft and general cargo flights, departure and arrival airports, departure / arrival / pickup times, and latest delivery times), as well as transportation cost data for each route, distances between cities, and time required to switch between different modes of transportation.

[0032] It should be noted that after obtaining the required data, this embodiment of the application can clean, filter, and transform the collected raw data to construct high-quality input data suitable for optimization algorithms. For example, the data processing module can be used to filter out all valid transportation schedules related to the next three days, serving as the data foundation for subsequent graph construction. In practical applications, different data processing methods can be adopted for data from different modes of transportation. For example, for processing air transport schedule data: the latest and valid all-cargo and general cargo flights can be filtered out to ensure the completeness of pick-up and drop-off point information, and deduplication can be performed on flights within a specific solution date range (e.g., for duplicate flights with the same date, flight number, origin, and destination, the flight with the earliest latest arrival time is retained). For processing land transport schedule data: valid land transport departures within a specific date range can be filtered, and the dispatch date can be calibrated based on whether the receiving flight spans multiple days. For initializing cost and time parameters: cost types such as general cargo flight costs and all-cargo flight costs can be standardized, and key parameters such as collection and distribution flight times and delivery durations can be initialized.

[0033] In step S120 of some embodiments, this application embodiment can construct a graph based on the first transportation attribute data and the second transportation attribute data to abstract the physical transportation network into a mathematical model, constructing a global transportation network connectivity graph composed of graph nodes and node edges. The graph structure of this global transportation network connectivity graph can be represented as G = (V, A), where V is the set of nodes and A is the set of edges for different transportation modes. Each "graph node" can represent a transportation network point in a different geographical location, which can be a starting point, destination point, or transit point, abstracting hundreds or thousands of specific business outlets into a more controllable number of city nodes, thereby simplifying the network topology and improving computational efficiency. Node edges are used to connect two graph nodes, representing the existence of available transportation services between these two points. It should be noted that, considering the characteristics of multimodal transport, there may be multiple parallel "node edges" (i, j, m) between any two nodes (i, j), where m represents the transport capacity (such as road, chartered flights, and all-cargo aircraft; even the same mode may have multiple forms). In this case, each edge can represent a specific mode of transport (such as road transport on a specific schedule or air transport on a specific flight), and even different schedules of the same mode of transport can be considered as different edges. For example, the specific starting point in city A can be mapped to city node Node_A, and the destination point in city B can be mapped to Node_B.

[0034] It should be noted that, considering the time-consuming process of repeatedly loading the graph structure when solving the routes for all cities, the system in practical applications can fully load the information of the entire network, such as routes, flights, and routing nodes, into the graph structure each time it starts. There may be multiple routes and flights between any two nodes, and the latest arrival time, departure time, and planned arrival time of different routes are different. Therefore, the embodiment of this application can innovatively extend the edge information in the graph into parallel edges of different routes / flights according to the characteristics of the problem.

[0035] In step S130 of some embodiments, after constructing the global transportation network connectivity graph, this application embodiment can obtain node attribute data corresponding to each graph node. The node attribute data describes the characteristics when operating at that node, and may specifically include: the fixed service time si (where i represents node i) required for loading and unloading goods at the network point, whether the network point has the equipment capacity to handle large goods, and whether there is a closing time window (such as no operation at night), etc. Simultaneously, this application embodiment can obtain node edge attribute data corresponding to each node edge. This data is the core parameter driving the optimization calculation and is used to quantitatively describe various aspects of using the edge for transportation. Node edge attribute data may specifically include: transportation cost data c. ijm (i.e., the cost of using this side to transport a unit of goods), transportation time data T ijm(i.e., the time spent transporting goods along this edge), arrival time window data [E] ijm , τ ijm [(This is a time interval, representing [the earliest allowed arrival time E]). ijm Latest allowed arrival time τ ijm For example, for a land transport route, goods must arrive at the next node within this time window to ensure a smooth connection; for an air transport route, its latest allowed arrival time is the cut-off time), and transport mode related parameters (which can identify whether the route belongs to road, general air transport, or all-cargo aircraft, and the transit waiting time required to switch from the previous transport mode to the current transport mode, i.e., capacity switching time). ).

[0036] In step S140 of some embodiments, this application embodiment can construct multi-dimensional route optimization constraints based on target cargo attribute data, node attribute data, and node edge attribute data to formalize various constraints in actual operation into a mathematical model. Through the constructed multi-dimensional route optimization constraints, more suitable path information can be selected in subsequent route search and route optimization.

[0037] Please refer to Figure 2 , Figure 2 This is a flowchart of step S140 provided in an embodiment of this application. In some embodiments, step S130 may specifically include, but is not limited to, steps S210 to S250, as described below. Figure 2 These five steps will be explained in detail.

[0038] Step S210: Extract cargo timeliness requirement data and cargo weight from target cargo attribute data, and extract transportation time data and arrival time window data from node edge attribute data; Step S220: Based on the cargo timeliness requirement data and transportation time data, obtain the transportation timeliness constraints; Step S230: Generate transport weight constraints based on cargo weight, and generate connection time constraints based on arrival time window data; Step S240: Extract node geographic location data from node attribute data, and generate node location constraints based on node geographic location data; Step S250: Construct multi-dimensional route optimization constraints based on transportation time constraints, transportation weight constraints, connection time constraints, and node location constraints.

[0039] In step S210 of some embodiments, when constructing multidimensional route optimization constraints, the embodiments of this application can extract cargo timeliness requirement data (i.e., the maximum transportation time specified by the customer or internally, such as 48 hours) and cargo weight from the target cargo attribute data, and extract the transportation time data and arrival time window data of each node edge from the node edge attribute data.

[0040] In step S220 of some embodiments, this application embodiment can construct a transportation timeliness constraint based on the cargo timeliness requirement data p, the transportation time data of each edge on the entire path, and the service time of each node. Its mathematical expression is: the sum of the transportation times of all edges on the path + the sum of the service times of all transit nodes ≤ the cargo timeliness requirement data. This constraint ensures that the entire transportation process is completed within the promised time.

[0041] In step S230 of some embodiments, this application embodiment can generate transportation weight constraints based on the weight of the goods. This requires that each selected transportation segment (i.e., the selected node edge) on the path must be capable of carrying the goods of that weight segment. In actual modeling, this may be reflected in only including node edges whose capacity is greater than the weight of the goods in the candidate network, or adding a weight feasibility judgment condition to each edge in the optimization model. Furthermore, this application embodiment can generate connection time constraints based on arrival time window data, which can ensure the smooth connection of the transportation chain. For example, for consecutive edges A (from node i to j) and B (from node j to k) on the path, the following must be satisfied: the arrival time of the goods at edge A (considering possible waiting) plus the service time at node j must fall within the "arrival time window" allowed by edge B, and cannot be later than the "latest arrival time" of edge B, ensuring that the goods can catch the next transportation segment (edge ​​B) after being unloaded at node j. In other words, the connection time of each sub-route transportation segment in the constructed transportation routing scheme must match, that is, satisfy the time window constraint.

[0042] In step S240 of some embodiments, this application embodiment can extract node geographic location data from node attribute data. Based on this, node location constraints (also represented as node number limit constraints) can be generated. For example, it can be stipulated that the number of transit nodes (cities) traversed on the constructed path, excluding the starting node and the destination node, cannot exceed an upper limit N (e.g., 2) to avoid uneconomical and unreasonable long-distance detours. This can be achieved by recording the number of visited nodes in the label (corresponding to the label algorithm mentioned later) and imposing restrictions during expansion.

[0043] In step S250 of some embodiments, the aforementioned transportation timeliness constraints, transportation weight constraints, connection time constraints, and node location constraints are further integrated to form complete multi-dimensional route optimization constraints. Through the combined effect of these conditions, it can be ensured that the planned route scheme is not only theoretically low-cost, but also highly feasible and operable in complex real-world operational networks.

[0044] Therefore, the key constraints included in the embodiments of this application may include: (1) Connectivity constraint: ensuring the connectivity of the routing path, allowing the algorithm to intelligently add necessary transportation routes on the basis of the existing network to seek a better solution. (2) Time constraint (corresponding to the above transportation time constraint): the total duration of the planned route must meet the maximum time requirement specified by the customer or internal regulations. (3) Time window constraint (corresponding to the above connection time constraint): the operation time of each link in the route (such as receiving, flight departure, land transportation departure, and delivery) must fall within its corresponding feasible time window. (4) Mandatory air route constraint (corresponding to the transportation mode constraint in the subsequent embodiments): to ensure the air attribute of the route, the path must contain at least one air transportation segment. (5) Node number limit constraint: limiting the number of transit nodes passed through in the path to avoid unreasonable detours. (6) No complete duplication of air routes constraint: avoiding planning a path that is exactly the same as the existing default route in order to explore alternatives with greater cost or time advantage.

[0045] In step S150 of some embodiments, since this application embodiment is for a scenario of static planning for large air cargo, before setting the optimization objective, this application embodiment can define a key transportation mode constraint, requiring that the final generated target route scheme must include at least one sub-route transportation segment based on air transportation. That is, the final generated target route optimization scheme must use air routes, allowing for connecting flights and transfers, and any segment can add routes based on historical cargo volume. This constraint ensures the aviation attributes of the scheme and conforms to the business positioning of large air cargo transportation. Further, this application embodiment can determine the cargo transportation route optimization objective corresponding to the transportation task based on the global transportation network connectivity graph and the above-mentioned preset transportation mode constraint. The cargo transportation route optimization objective is to minimize the end-to-end total transportation cost. The total cost at this time is the sum of the costs of all selected optimized sub-route transportation segments on the path, and the objective function corresponding to the cargo transportation route optimization objective can be expressed as minimizing this total cost. Of course, the objective can also be a dual objective, such as simultaneously considering cost and timeliness, seeking the Pareto optimal solution set, which can be flexibly adjusted according to actual needs.

[0046] Please refer to Figure 3 , Figure 3This 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 S310 to S340, as described below. Figure 3 These four steps will be explained in detail.

[0047] Step S310: Based on the global transportation network connectivity graph and preset transportation mode constraints, perform path search to determine the candidate transportation route schemes corresponding to the transportation task; Step S320: Extract capacity switching parameters based on candidate transportation route schemes to obtain capacity switching parameters; Step S330: Based on the node edge attribute data, node attribute data and capacity switching parameters, the candidate transportation route scheme is pruned to obtain the optimized transportation route scheme; Step S340: For the transportation task, determine the cargo transportation route optimization target corresponding to the optimized transportation route scheme based on the node edge attribute data.

[0048] In step S310 of some embodiments, this application embodiment can perform path search based on the global transportation network connectivity graph and preset transportation mode constraints (which must include air segments) to determine at least one candidate transportation route scheme corresponding to the transportation task. This path search can be a systematic exploration, such as using graph search algorithms (e.g., variants of Dijkstra's algorithm) or labeling algorithms to generate a large number of possible candidate transportation route schemes. These candidate schemes are all paths connecting the starting node and the destination node, and satisfy the basic requirement of including air segments, but may not yet satisfy all other constraints (such as timeliness), or may not be cost-optimal.

[0049] In step S320 of some embodiments, to avoid the additional costs caused by multiple capacity switching in the generated routing scheme and to improve the operational robustness of the generated routing scheme, this application embodiment can extract the corresponding capacity switching parameters from each candidate transportation routing scheme, such as the number of capacity switching times, to record the number of times the cargo transportation mode changes in a candidate transportation route. For example, if the path is "road → bulk shipping → road", then the corresponding number of capacity switching times is 2.

[0050] In step S330 of some embodiments, this application embodiment can prune a massive number of candidate transportation routing schemes based on node edge attribute data, node attribute data, and extracted capacity switching parameters. The purpose of pruning is to eliminate obviously inferior paths as early as possible without losing the global optimal solution, thereby greatly reducing the search space and improving algorithm efficiency. This application embodiment innovatively introduces a multi-dimensional domination rule that includes the number of capacity switching operations. Specifically, when comparing two partial paths (represented as "labels" in the label algorithm) that reach the same node, it is not enough to only consider their cumulative cost and current time; the number of capacity switching operations that have already occurred must also be considered. A path with lower cost and earlier arrival but more switching operations cannot simply "dominate" another path with slightly higher cost and later arrival but fewer switching operations, because the latter may be more flexible in subsequent path selection, and may ultimately combine to form a complete path with a lower total cost. Based on this multi-dimensional rule, the result is a simplified set of optimized transportation routing schemes.

[0051] In step S340 of some embodiments, for a transportation task, this application embodiment can determine the cargo transportation route optimization objective corresponding to the optimized transportation route scheme based on node edge attribute data. For example, the total cost of each optimized path is calculated, and minimizing the total cost is used as an explicit mathematical objective function to guide subsequent precise solutions or further screening.

[0052] Please refer to Figure 4 , Figure 4 This is a flowchart of step S330 provided in an embodiment of this application. In some embodiments, step S330 may specifically include, but is not limited to, steps S410 to S440, as described below. Figure 4 These four steps will be explained in detail.

[0053] Step S410: Generate pruning constraints based on transportation cost data, transportation time data, arrival time window data, and transportation mode related parameters; Step S420: For each candidate route node in the candidate transportation routing scheme, generate a first label based on the candidate route node to be processed, determine the associated route node connected to the candidate route node according to the candidate transportation routing scheme, and generate a second label based on the associated route node. Step S430: Optimize the first and second labels according to the pruning constraints to determine the target label; Step S440: Optimize the candidate transportation route schemes based on the target label to obtain the optimized transportation route scheme.

[0054] In step S410 of some embodiments, the present application embodiments may use a labeling algorithm to solve the shortest route problem with resource constraints. Specifically, the present application embodiments may first generate pruning constraints based on transportation cost data, transportation time data, arrival time window data, and transportation mode association parameters.

[0055] In step S420 of some embodiments, since the present application embodiments can use the label algorithm to solve the shortest route problem with resource constraints, the node corresponding to the starting point can be initialized for the city to be planned. For example, an initial label Ls is generated at the node s corresponding to the starting point, and c(Ls)=0, t(Ls)=t0, V(Ls)={s}. , Let k(Ls) = 0, t(Ls) represent the time corresponding to the initial label Ls, c(Ls) represent the cumulative cost corresponding to the initial label Ls, V(Ls) represent the node set corresponding to the initial label Ls, m(Ls) represent the capacity data corresponding to the initial label Ls, pred(Ls) represent the label of the previous node corresponding to the initial label Ls, and k(Ls) represent the cumulative number of capacity switching times corresponding to the initial label Ls. Then, for each candidate route node i (which can correspond to label L), its mathematical expression can be represented as: the predicted arrival time t of the goods. arr = Node's current time t (L) + Node's service / loading / unloading time (si) + Power switching time +Driving time T ijm Early permitted arrival time E ijm That is, it is allowed to wait until E ijm Assume the actual arrival time of the goods is t' = max(E ijm , t arr Then t'≤τ is required. ijm If t' ≤ p, then the corresponding transport segment is not feasible. For a transport segment that meets the requirements, the cost corresponding to several labels L can be further updated, i.e., the cost c' corresponding to the next label L' is c' = c(L) + c ijm Label L' is placed on node j, and c(L') = c', t(L') = t', V(L') = V(L) ∪ {j}, pred(L') = L, and m(L') = m are updated. Furthermore, in the static programming scenario, the above parameters are treated as deterministic constants.

[0056] The pruning operation is performed dynamically during the generation of candidate transportation routes. The algorithm creates a label for each explored path state, which is attached to a graph node and records key state information of a portion of the path leading to that node. For a candidate route node to be processed during the exploration of candidate transportation routes, the algorithm generates a first label based on the path state leading to that node. Then, based on the network connectivity graph, it finds the "associated route nodes" directly connected to the candidate route node. When attempting to extend from the current node to an associated node through an edge (a certain transportation method), a "second label" (corresponding to the associated node) representing the new path state is generated according to the extension rules.

[0057] In step S430 of some embodiments, label optimization is performed on the first and second labels according to pruning constraints to determine target labels. Label optimization involves comparing and filtering labels using pruning constraints. For two labels residing on the same graph node (such as a first label and another previously arrived label on the same node, or two second labels to be compared), comparison is required from multiple dimensions. These dimensions include at least: cumulative cost, the current time of arrival at the node, the number of capacity switching events that have occurred, and the set of visited nodes (to prevent loops). According to the dominance rules defined in the embodiments of this application, label A is considered to dominate label B only if label A's value in all these dimensions is no worse than (less than or equal to) label B, and is strictly better than (less than) label B in at least one dimension. A dominated label (such as a second label) can be safely discarded (pruned) because the path it represents is unlikely to eventually develop into a complete path that is better than the path represented by the label that dominates it. Through this comparison, at least one target label that does not dominate each other is ultimately retained for each node, and these labels represent all non-dominated path states to that node.

[0058] For example, on the same transport m at the same node j, suppose there are two labels L1 and L2. If the following conditions are met: Cost non-inferior: c(L1) ≤ c(L2); Time non-inferior: t(L1) ≤ t(L2) (or more generally, subsequent arrival feasibility is not inferior, for example, earlier arrival time windows have greater margin); Resource non-inferior: k(L1) ≤ k(L2) on all controlled dimensions (such as optional resources like "number of transport mode switching"); Element-wise memory non-inferior: If at least one of them is strictly better, then L1 is considered to dominate L2, and L2 can be deleted to reduce the solution space.

[0059] In step S440 of some embodiments, the optimization of candidate transportation routes based on target labels is essentially a continuous process of label expansion and pruning. Only path expansions that generate non-dominated target labels are retained and continue to participate in subsequent searches. When the algorithm terminates (e.g., when the destination node is found and the priority queue is empty), backtracking from the target labels of the destination node yields the final optimized transportation route. These routes are all Pareto optimal solutions that satisfy all hard constraints (verified during the expansion process) and are non-dominated.

[0060] It should be noted that, to enhance the pruning effect, the embodiments of this application may also employ near-basic memory (ng) The route maintains access information only in the neighborhood N(i) of each node, and only performs inclusion relationship judgment on V(L)∩N(i,m) during dominance comparison, thus significantly reducing the number of candidate sets. Embodiments of this application can use algorithms suitable for large-scale combinatorial optimization (such as genetic algorithms, tabu search, linear programming / integer programming solvers, etc.) to solve the model, outputting one or more Pareto optimal static routing schemes.

[0061] Please refer to Figure 5 , Figure 5 This is a flowchart of step S340 provided in an embodiment of this application. In some embodiments, step S340 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.

[0062] Step S510: For the transportation task, determine the sub-route transportation cost corresponding to each optimized sub-route transportation segment based on the node edge attribute data. Step S520: Construct a cargo transportation route optimization target based on the transportation costs of all sub-routes corresponding to the optimized transportation route scheme.

[0063] In step S510 of some embodiments, this application embodiment clarifies how to extract specific optimization objectives from the optimized routing scheme. The optimized transportation routing scheme consists of several optimized sub-routes connected sequentially, each sub-route corresponding to a node edge (i.e., a specific transportation trip) in the global transportation network connectivity graph. For each transportation task, the sub-route transportation cost corresponding to each optimized sub-route can be determined based on the transportation cost data in the node edge attribute data. For example, the cost of a nighttime ferries from city H to city K is Chk; the cost of an afternoon land transport trip from city A to city H is Cah.

[0064] In step S520 of some embodiments, this application embodiment can sum the costs of all sub-route transportation segments included in the optimized transportation route scheme, and construct the freight transportation route optimization objective by calculating the total cost of the scheme. Based on this, constructing the freight transportation route optimization objective means explicitly defining the optimization objective function as minimizing this total cost. In the mathematical model, this objective function guides the optimization algorithm to find the path combination that minimizes this sum under the constraints. In this way, the global, end-to-end cost optimization concept is implemented as a specific, computable mathematical model objective.

[0065] In step S160 of some embodiments, embodiments of this application can perform route optimization on the global transportation network connectivity graph based on the determined cargo transportation route optimization objective and the constructed multi-dimensional route optimization constraints (such as timeliness constraints, time window constraints, mandatory air segment constraints, node number constraints, etc.). This process essentially uses operations research optimization algorithms (such as the improved label-based algorithm detailed later in this invention) to search the vast path combination space for one or more paths that simultaneously satisfy all constraints and make the objective function optimal (or nearly optimal) as the target route optimization scheme. This target route optimization scheme explicitly provides the specific walking path from the starting point to the destination point (which nodes are passed through), and which specific edge (i.e., which transport mode of which shift) is selected between each pair of nodes to complete the transportation.

[0066] Please refer to Figure 6 , Figure 6 This is another optional flowchart of the freight transportation route optimization method provided in the embodiments of this application. In some embodiments, after step S160, the freight transportation route optimization method provided in the embodiments of this application may further include, but is not limited to, steps S610 to S620, as described below. Figure 6 These two steps will be explained in detail.

[0067] Step S610: When at least two target route optimization schemes are selected, obtain the total route cost corresponding to each target route optimization scheme; Step S620: Sort all target route optimization schemes based on the total route cost to obtain a route optimization scheme sequence.

[0068] In steps S610 and S620 of some embodiments, since the optimization algorithm (especially when seeking the Pareto optimal set) may output more than one target route optimization scheme, these schemes may have different advantages and disadvantages in terms of cost, timeliness, and number of handovers. When at least two target route optimization schemes that satisfy all constraints are selected, the total route cost corresponding to each scheme can be obtained, that is, the cost of all transport segments included in each scheme is summed and sorted in ascending order according to the summation result. That is, when the priority queue is empty, or when enough feasible solutions have been found, the algorithm terminates, outputs all paths from the starting point s to the target d that satisfy the constraints, and sorts them by cost. In particular, by retaining the labels that were not pruned during the expansion process, the algorithm can naturally output a set of all feasible routes that meet the timeliness requirements and include different air route segments, rather than just a shortest path. For example, taking the planning of a route for large cargo (weight range 50~100KG) from city A to city B as an example, the algorithm may calculate the optimal path (i.e., the target route optimization scheme) which may include: (1) Node_A → (land transport, afternoon flight) → hub H → (dispersed air transport, night flight) → hub K → (land transport, next morning flight) → Node_B. (2) Node_A → (land transport, afternoon flight) → hub G → (dispersed air transport, morning flight) → hub M → (land transport, next morning flight) → Node_B. These two paths make full use of low-priced dispersed air transport resources in multiple regions, and the land transport connection is smooth. The total cost and timeliness are better than the traditional direct route to the core hub. Moreover, when the cargo volume is large, resources can be distributed to avoid warehouse overload. Furthermore, the two paths A→H→K→B and A→G→M→B can be used as the recommended static routes for the city pair and written into the routing table (i.e., the route optimization scheme sequence) for use by the ordering and scheduling system.

[0069] Understandably, this routing optimization scheme sequence provides operational decision-makers with a clear reference for decision-making, with the lowest-cost solution usually being the first choice. Simultaneously, decision-makers can also view other solutions in the sequence, which may have different advantages in terms of timeliness or operational complexity (such as the number of switching operations). These can serve as alternative solutions or contingency plans in special circumstances (such as the temporary cancellation of a segment of capacity on the preferred solution). This sorting and presentation process makes the automated planning results of this application embodiment more practical and facilitates final manual review and selection.

[0070] Please refer to Figure 7 , Figure 7 This is a flowchart of a cargo transportation method provided in an embodiment of this application. In some embodiments, the cargo transportation method provided in this application may specifically include, but is not limited to, steps S710 to S720, which are described below in conjunction with... Figure 7 These two steps will be explained in detail.

[0071] Step S710: Obtain the target route optimization scheme corresponding to the transportation task based on the city pair to be planned in the cargo transportation scenario. The target route optimization scheme is constructed based on the cargo transportation route optimization method. The target route optimization scheme is used to indicate the combination scheme of transportation path and transportation mode adopted to perform the transportation task. Step S720: Execute the transportation task based on the target route optimization scheme.

[0072] In steps S710 and S720 of some embodiments, this application embodiment can apply the cargo transportation route optimization method to actual cargo transportation operations, forming a new cargo transportation method. This method can first obtain a target route optimization scheme for the current transportation task. This scheme is not an abstract plan, but specifically specifies the "transportation route" (which cities / outlets to pass through) and the "combination scheme of transportation modes" (which road transport schedule, flight number, etc. to use on each segment of the route). After obtaining this precise route scheme, the transportation execution system or operators can execute the transportation task based on the target route optimization scheme. This means that dispatchers can arrange pickup vehicles according to the schedules and times indicated in the scheme, so that goods can be transported to the designated airport and board the designated flight according to the planned route. After arriving at the destination airport, they can be transferred to the final destination outlet according to the land transport schedule arranged in the scheme. The entire execution process strictly follows the planning scheme, thereby ensuring a high degree of consistency between the actual transportation route, cost, and timeliness and the planned expectations, realizing a closed loop from intelligent planning to efficient execution.

[0073] It should be noted that the technical difficulties that this application embodiment can solve include: (1) The network used in this application embodiment is time-varying and multimodal. There are multiple parallel edges (land transport, air transport, and cargo aircraft) between the same node pair, and each edge has its own independent cost and time attributes, which directly increases the complexity of the network by several orders of magnitude. Time-varying (time-dependent): The feasibility of an edge depends on the time of arrival at the starting node, which means that the "optimal path" is not absolute and depends on when the goods arrive at the transit node. This completely changes the nature of the problem, making it change from a simple spatial search to a more complex spatiotemporal joint search. Based on this, this application embodiment can accurately abstract the physical network into a spatiotemporal multimodal transport network model, in which the weight of the edge is no longer a scalar, but a tuple containing cost, departure time, arrival time, and latest arrival time. This is the basis for all subsequent algorithm designs. (2) Due to the introduction of a new optimization dimension of the number of transport mode switching, the traditional two-dimensional (cost-time) domination rule is no longer safe. This application embodiment can successfully define and prove the effectiveness of a three-dimensional domination rule containing the "number of transport mode switching". That is, L1 can only be determined to dominate L2 when label L1 is not worse than L2 in the three dimensions of cost, time, and number of switching. The discovery and verification of this rule is the key to whether the algorithm can work correctly. It requires a solid foundation in operations research theory to ensure a balance between pruning efficiency and solution correctness. (3) The three-dimensional domination rule above is the most important weapon to control the number of labels. The embodiments of this application can combine the use of priority queues (min-heaps) to always prioritize expanding the path with the lowest current cost. This guides the algorithm to quickly search the promising area and is expected to find the optimal solution as soon as possible, thereby using the domination rule to prune more high-cost paths. When expanding, hard constraints such as "latest arrival time" are checked immediately to directly reject infeasible expansion and avoid generating invalid labels. Therefore, the embodiments of this application can combine multi-dimensional domination rules with the best priority search strategy to form an efficient and stable solution framework, ensuring the feasibility of this method on large-scale industrial problems.

[0074] The cargo transportation route optimization method provided in this application is equivalent to providing an automated solution method for static route planning of end-to-end multimodal transport of large cargo in air. The resulting technical effects can include: (1) Global optima: This application embodiment performs global planning from a strategic level, breaking the limitation of point-to-point "city-to-city" and achieving end-to-end cost optimization from the originating point to the destination point by integrating the land and air transport resources of the entire network, thus avoiding the overall inefficiency caused by local optima. (2) Efficient resource allocation: This application embodiment automatically weighs the transport capacity cost and timeliness of different regions through algorithms, guides the reasonable allocation of waybills, effectively alleviates the transport capacity pressure of core hubs, fully activates and utilizes the cheap transport capacity of surrounding areas, and improves the overall network resource utilization rate. (3) Intelligence and automation: This application embodiment can transform the manual experience of front-line personnel into systematic algorithm rules, reduce the subjectivity and arbitrariness of human intervention, make route planning more scientific and efficient, and can quickly respond to network changes. (4) Multiple constraints are in line with reality: The target model constructed in this application embodiment can comprehensively consider various realistic constraints such as timeliness, time window, and number of nodes, so that the planned route scheme is not only low in cost, but also highly feasible and operable, which greatly improves the efficiency of subsequent scheduling and operation. (5) Promote the utilization of high-quality transportation capacity: Through global optimization, this application embodiment can aggregate scattered cargo volumes and create conditions for opening routes for transportation capacity resources with low unit price and good timeliness, thereby reducing the overall cost and further improving transportation timeliness. Based on this, this application embodiment can guide the rational allocation of transportation capacity resources, improve the flexibility of the planned transportation route scheme, and better cope with complex actual transportation needs and emergencies. Therefore, the cargo transportation route optimization method provided by this application embodiment can improve the accuracy of cargo transportation route optimization.

[0075] Please see Figure 8 This application embodiment also provides a cargo transportation route optimization device, the cargo transportation route optimization device 800 includes: The first acquisition module 810 is used to acquire the target cargo attribute data and the first transportation attribute data corresponding to the transportation task based on the city pair to be planned in the cargo transportation scenario, and to acquire the second transportation attribute data of the transit network associated with the city pair to be planned. The city pair to be planned includes the starting network and the destination network. The graph construction module 820 is used to construct a graph based on the first transportation attribute data and the second transportation attribute data to obtain a global transportation network connectivity graph. The global transportation network connectivity graph includes multiple graph nodes and multiple node edges. Each graph node is used to represent a transportation network point in a different geographical location. The transportation network point can be a starting point, a destination point, or a transit point. The second acquisition module 830 is used to acquire node attribute data corresponding to each graph node and node edge attribute data corresponding to each node edge. The node edge attribute data is used to indicate the relevant data of cargo transportation between two corresponding graph nodes based on different transportation methods. The constraint construction module 840 is used to construct multidimensional route optimization constraints based on the target cargo attribute data, node attribute data, and node edge attribute data. The target determination module 850 is used to determine the cargo transportation route optimization target corresponding to the transportation task based on the global transportation network connectivity graph and the preset transportation mode constraints. The transportation mode constraints are used to indicate that the generated target route optimization scheme should include at least one sub-route transportation segment based on air transportation. The route optimization module 860 is used to optimize routes based on the objective of cargo transportation route optimization and multi-dimensional route optimization constraints, and obtain the target route optimization scheme.

[0076] It should be noted that the cargo transportation route optimization device provided in this application embodiment is used to implement the cargo transportation route optimization method provided in the above embodiment, and the specific implementation process corresponds to the cargo transportation route optimization method in the above embodiment. It can be referred to the aforementioned cargo transportation route optimization method, and will not be repeated here.

[0077] 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 when the processor executes the computer program, it can implement any of the cargo transportation route optimization methods and cargo transportation methods described in the above embodiments. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0078] Please see Figure 9 , Figure 9 This illustration shows the hardware structure of an electronic device according to another embodiment, the electronic device comprising: The processor 910 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 920 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 920 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 920 and is called and executed by the processor 910 to execute the cargo transportation route optimization method and cargo transportation method of the embodiments of this application. The input / output interface 930 is used to implement information input and output; The communication interface 940 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 950 transmits information between various components of the device (e.g., processor 910, memory 920, input / output interface 930, and communication interface 940); The processor 910, memory 920, input / output interface 930 and communication interface 940 are connected to each other within the device via bus 950.

[0079] This application also provides a computer-readable storage medium storing a computer program for causing a computer to execute the cargo transportation route optimization method and cargo transportation method described in the above embodiments.

[0080] 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.

[0081] This invention also provides a computer program product that stores program instructions, which, when executed by a computer, cause the computer to implement the cargo transportation route optimization method described in any of the above embodiments.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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 cargo transportation routes, characterized in that, The method includes: In a cargo transportation scenario, target cargo attribute data and first transportation attribute data corresponding to transportation tasks based on city pairs to be planned are obtained, and second transportation attribute data of transit points associated with city pairs to be planned are obtained, wherein the city pairs to be planned include originating points and destination points. Based on the first transportation attribute data and the second transportation attribute data, a graph is constructed to obtain a global transportation network connectivity graph. The global transportation network connectivity graph includes multiple graph nodes and multiple node edges. Each graph node is used to represent a transportation network point in a different geographical location. The transportation network point can be a starting point, a destination point, or a transit point. Obtain the node attribute data corresponding to each graph node and the node edge attribute data corresponding to each node edge. The node edge attribute data is used to indicate the relevant data of cargo transportation between two corresponding graph nodes based on different transportation methods. Based on the target cargo attribute data, the node attribute data, and the node edge attribute data, construct multidimensional routing optimization constraints. Based on the global transportation network connectivity graph and the preset transportation mode constraints, the cargo transportation route optimization target corresponding to the transportation task is determined. The transportation mode constraints are used to indicate that the generated target route optimization scheme should include at least one sub-route transportation segment based on air transportation. Based on the cargo transportation route optimization objective and the multi-dimensional route optimization constraints, route optimization is performed to obtain the target route optimization scheme.

2. The method according to claim 1, characterized in that, The step of determining the cargo transportation route optimization objective corresponding to the transportation task based on the global transportation network connectivity graph and preset transportation mode constraints includes: Based on the global transportation network connectivity graph and preset transportation mode constraints, a path search is performed to determine the candidate transportation route schemes corresponding to the transportation task. Based on the candidate transportation route scheme, capacity switching parameters are extracted to obtain the capacity switching parameters; Based on the node edge attribute data, the node attribute data, and the capacity switching parameters, the candidate transportation route schemes are pruned to obtain an optimized transportation route scheme. For the transportation task, the cargo transportation route optimization target corresponding to the optimized transportation route scheme is determined based on the node edge attribute data.

3. The method according to claim 2, characterized in that, The node edge attribute data includes transportation cost data, transportation time data, arrival time window data, and transportation mode association parameters; the step of pruning the candidate transportation route schemes based on the node edge attribute data, the node attribute data, and the capacity switching parameters to obtain an optimized transportation route scheme includes: Based on the transportation cost data, the transportation time data, the arrival time window data, and the transportation mode association parameters, pruning constraints are generated. For each candidate route node in the candidate transportation routing scheme, a first label is generated based on the candidate route node to be processed, an associated route node connected to the candidate route node is determined based on the candidate transportation routing scheme, and a second label is generated based on the associated route node; Based on the pruning constraints, the first label and the second label are optimized to determine the target label; The candidate transportation route schemes are optimized based on the target label to obtain an optimized transportation route scheme.

4. The method according to claim 2, characterized in that, The optimized transportation routing scheme includes optimizing sub-routes for transportation segments. For the transportation task, determining the cargo transportation route optimization objective corresponding to the optimized transportation routing scheme based on the node edge attribute data includes: For the transportation task, the sub-route transportation cost corresponding to each optimized sub-route transportation segment is determined based on the node edge attribute data; The cargo transportation route optimization objective is constructed based on the transportation costs of all sub-routes corresponding to the optimized transportation route scheme.

5. The method according to claim 1, characterized in that, The step of constructing multidimensional route optimization constraints based on the target cargo attribute data, the node attribute data, and the node edge attribute data includes: Extract cargo timeliness requirements and cargo weight from the target cargo attribute data, and extract transportation time data and arrival time window data from the node edge attribute data; Based on the cargo timeliness requirement data and the transportation timeliness data, the transportation timeliness constraints are obtained; Based on the cargo weight, a transport weight constraint is generated, and based on the arrival time window data, a connection time constraint is generated. Extract node geographic location data from the node attribute data, and generate node location constraints based on the node geographic location data; Based on the transportation time constraints, transportation weight constraints, connection time constraints, and node location constraints, multidimensional route optimization constraints are constructed.

6. The method according to claim 1, characterized in that, After performing route optimization based on the cargo transportation route optimization objective and the multi-dimensional route optimization constraints to obtain the target route optimization scheme, the method further includes: Once at least two target route optimization schemes are selected, the total route cost corresponding to each target route optimization scheme is obtained. Based on the total routing cost, all the target route optimization schemes are sorted to obtain a route optimization scheme sequence.

7. A method for transporting goods, characterized in that, The method includes: Obtain the target route optimization scheme corresponding to the transportation task based on the city pair to be planned in the cargo transportation scenario. The target route optimization scheme is constructed based on the cargo transportation route optimization method according to any one of claims 1 to 6. The target route optimization scheme is used to indicate the combination scheme of transportation path and transportation mode adopted to perform the transportation task. The transportation task is executed based on the target route optimization scheme.

8. A cargo transportation route optimization device, characterized in that, The device includes: The first acquisition module is used to acquire target cargo attribute data and first transportation attribute data corresponding to transportation tasks based on the city pair to be planned in the cargo transportation scenario, and to acquire second transportation attribute data of transit points associated with the city pair to be planned, wherein the city pair to be planned includes a starting point and a destination point. The graph construction module is used to construct a graph based on the first transportation attribute data and the second transportation attribute data to obtain a global transportation network connectivity graph. The global transportation network connectivity graph includes multiple graph nodes and multiple node edges. Each graph node is used to represent a transportation network point in a different geographical location. The transportation network point is a starting point, a destination point, or a transit point. The second acquisition module is used to acquire node attribute data corresponding to each graph node and node edge attribute data corresponding to each node edge. The node edge attribute data is used to indicate relevant data on cargo transportation between two corresponding graph nodes based on different transportation methods. The constraint construction module is used to construct multidimensional route optimization constraints based on the target cargo attribute data, the node attribute data, and the node edge attribute data. The target determination module is used to determine the cargo transportation route optimization target corresponding to the transportation task based on the global transportation network connectivity graph and the preset transportation mode constraints. The transportation mode constraints are used to indicate that the generated target route optimization scheme should include at least one sub-route transportation segment based on air transportation. The route optimization module is used to optimize the route based on the cargo transportation route optimization objective and the multi-dimensional route optimization constraints to obtain the target route optimization scheme.

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