Transportation network optimization method and device

Abstract

The invention discloses a transportation network optimization method and device, and relates to the technical field of big data. A specific embodiment of the method comprises the following steps: determining an adjustment route corresponding to an existing route in an existing route set from an adjustment route set; wherein the existing route and the adjusting route comprise at least one route, the starting point and the terminal point of the existing route are consistent with those of the corresponding adjusting route, and the existing route and the corresponding adjusting route form a pair of route groups; determining a cargo volume change result of a line in an existing route of the route group according to the route group, and determining a coupling relationship between the existing route and the adjustment route in the route group based on the cargo volume change result of the line in the existing route; based on the adjustment route in each pair of route group and the coupling relationship between the existing route and the adjustment route in each pair of route group, adjusting and optimizing the line in the transportation network; the mutual influence degree of the transportation network can be determined, the optimization cost of the transportation network is reduced, and the timeliness of transportation adjustment is improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method and device for optimizing a transportation network. Background Art

[0002] With the annual growth of customer order volume and the continuous change of order structure, the transportation network structure should also change accordingly. Currently, most logistics companies often use the method of forced splitting based on manual experience to make adjustments and formulate global network adjustment and optimization plans. This global network adjustment and optimization plan is very complex and has intricate influence relationships. As the complexity of the transportation network increases, this mutual influence will become more serious.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the related art:

[0004] The inability to control the degree of mutual influence of the transportation network results in high costs and poor timeliness in adjusting and optimizing the transportation network. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method and device for optimizing a transportation network, which can describe and control the degree of mutual influence of the transportation network, reduce the adjustment and optimization cost of the transportation network, and improve the timeliness of transportation adjustment.

[0006] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for optimizing a transportation network is provided, comprising:

[0007] Determine an adjusted route corresponding to an existing route in the existing route set from the adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups;

[0008] Determine the cargo volume change result of the route in the existing route of the route group according to the route group, and determine the coupling relationship between the existing route and the adjusted route in the route group based on the cargo volume change result of the route in the existing route;

[0009] Based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups, the routes in the transportation network are adjusted and optimized.

[0010] Optionally, based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups, adjusting and optimizing the routes in the transportation network includes:

[0011] Determine an optimal network adjustment plan based on the adjusted routes in each pair of routing groups and the coupling relationship between the existing routes and the adjusted routes in each pair of routing groups; wherein the optimal network adjustment plan is the network adjustment plan with the lowest cost or the network adjustment plan with the shortest effectiveness;

[0012] Adjust and optimize the routes in the transportation network based on the optimal network adjustment plan.

[0013] Optionally, adjusting and optimizing the routes in the transportation network based on the optimal network adjustment solution includes:

[0014] The optimal network adjustment scheme is traversed by using the breadth-first search algorithm to obtain multiple connected components;

[0015] Splitting the optimal network adjustment scheme into multiple sub-schemes based on multiple connected components;

[0016] Routes in the transport network are adjusted according to multiple sub-schemes.

[0017] Optionally, before adjusting the routes in the transportation network according to the plurality of sub-schemes, the method further includes:

[0018] Evaluate each sub-scheme based on the simulation calculation strategy to obtain the evaluation result of each sub-scheme;

[0019] The evaluation results of each sub-scheme are ranked to adjust the routes in the transportation network based on the ranking results.

[0020] Optionally, determining a cargo volume change result of a route in an existing route of the route group according to the route group includes:

[0021] The existing routes and the adjusted routes in the route group are intersected, and the cargo volume change results of the routes in the existing routes in the intersection are determined as unchanged cargo volume;

[0022] The results of the volume changes for the routes in the existing routes that exist only in the existing routes are determined as volume increases;

[0023] The cargo volume change results of the lines in the existing routes that exist only in the adjusted routes are determined as cargo volume reduction.

[0024] Optionally, determining the coupling relationship between the existing route and the adjusted route in the route group based on the cargo volume change result of the line in the existing route includes:

[0025] According to the cargo volume change results of the lines in the existing routes and the corresponding lines in the adjusted routes, a bipartite graph is constructed, and the coupling relationship between the existing routes and the adjusted routes in the routing group is analyzed based on the bipartite graph.

[0026] According to a second aspect of an embodiment of the present invention, there is provided a transport network optimization device, characterized in that it comprises:

[0027] A route determination module, configured to determine an adjusted route corresponding to an existing route in the existing route set from the adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups;

[0028] A relationship determination module, used to determine the cargo volume change result of the route in the existing route of the route group according to the route group, and determine the coupling relationship between the existing route and the adjusted route in the route group based on the cargo volume change result of the route in the existing route;

[0029] The adjustment and optimization module is used to adjust and optimize the routes in the transportation network based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups.

[0030] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0031] one or more processors;

[0032] a memory for storing one or more programs,

[0033] When one or more programs are executed by one or more processors, the one or more processors are enabled to implement the method of any of the above embodiments.

[0034] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method of any of the above embodiments is implemented.

[0035] According to a fifth aspect of an embodiment of the present invention, there is provided a computer program product, including a computer program, which implements the method of any of the above embodiments when the computer program is executed by a processor.

[0036] An embodiment of the above invention has the following advantages or beneficial effects: by determining an adjusted route corresponding to an existing route in an existing route set from an adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups; determining the cargo volume change result of the route in the existing route of the route group according to the route group, and determining the coupling relationship between the existing route and the adjusted route in the route group based on the cargo volume change result of the route in the existing route; adjusting and optimizing the routes in the transportation network based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups; thereby describing and controlling the mutual influence of the transportation network, reducing the adjustment and optimization cost of the transportation network, and improving the timeliness of transportation adjustment.

[0037] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific implementation examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0039] Figure 1 is a schematic diagram of the main process of the method for optimizing a transportation network according to an embodiment of the present invention;

[0040] Figure 2 It is a schematic diagram of the main flow of a method for optimizing a transportation network according to a preferred embodiment of the present invention;

[0041] Figure 3 is a schematic diagram of the structure of a bipartite graph according to a preferred embodiment of the present invention;

[0042] Figure 4 is a schematic diagram of main modules of a transportation network optimization device according to an embodiment of the present invention;

[0043] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0044] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0046] It should be noted that the acquisition, storage and application of personal information etc. involved in the embodiments of the present invention are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0047] As customer orders grow year by year and order structures continue to change, the transportation network structure should also change accordingly. Currently, most logistics companies often use artificial experience to forcibly split and make adjustments to formulate global network adjustment and optimization plans. This global network adjustment and optimization plan is very complex and has intricate influence relationships. As the complexity of the transportation network increases, this mutual influence will become more serious. The current optimization method cannot control the degree of mutual influence of the transportation network, resulting in high adjustment and optimization costs for the transportation network and poor timeliness.

[0048] In view of this, according to one aspect of an embodiment of the present invention, a method for optimizing a transportation network is provided.

[0049] Figure 1 FIG. 1 is a schematic diagram of the main process of the method for optimizing a transportation network according to an embodiment of the present invention. Figure 1 As shown, the method for optimizing a transportation network according to an embodiment of the present invention includes the following steps S101 to S103.

[0050] Step S101, determining an adjusted route corresponding to an existing route in the existing route set from the adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups.

[0051] In transportation network optimization, the existing route set and the adjusted route set refer to a set of route paths before and after the transportation network is adjusted. The adjustment of the transportation network can be to add, close or reconfigure certain routes to optimize transportation efficiency and resource allocation. The existing route set refers to all route paths or route sets that already exist or are in operation in the transportation network before the adjustment. Each existing route represents a specific transportation route at present, defining the transportation path of goods from a fixed starting point to a fixed end point and related transportation parameters, such as departure time, travel time and arrival time. In contrast, the adjusted route set is a new route path set formed after the transportation network is adjusted. The network can be replanned according to the latest transportation demand, resource allocation strategy or external factors. In the adjusted route set, each adjusted route describes a new path corresponding to the corresponding existing route, that is, when the starting point and end point are consistent, different travel routes, time arrangements or vehicle configurations are designed to better match the expected operation goals. By matching the starting point and end point of the existing route and the adjusted route, the relationship between the existing route and the corresponding adjusted route can be identified, and they can be regarded as a pair of route groups. For example, if the existing route connects city A and city B, and the route adjustment provides a new path (such as through different intermediate stations) to optimize transportation efficiency, the starting point and end point between the two lines remain unchanged before and after the adjustment, but the detailed path may change.

[0052] In the specific implementation process, the path comparison method based on the route matching rule can be used to first analyze the starting point and end point information of each existing route in the existing route set, and match it with the starting point and end point of each adjusted route in the adjusted route set. For the adjusted route with the same starting point and end point, it is regarded as the adjusted route corresponding to the existing route. Such path comparison can control the strictness of the match by setting a threshold, for example, allowing a certain error range to consider the line deviation, so that only those adjusted routes with overlapping key nodes or resource sharing on the path are selected to ensure that the adjusted path maintains business consistency with the original path. In addition, the similarity calculation method based on multi-dimensional feature analysis can also be used to first select an existing route from the existing route set, and then select candidate routes that meet the same starting point and end point from the adjusted route set; then, by calculating the similarity between the multi-dimensional features of these candidate adjusted routes and the existing routes, the one with the highest similarity is determined as the final corresponding adjustment route, for example, using feature vectors to represent information such as transportation time and frequency, and using cosine similarity or Euclidean distance to quantify the similarity.

[0053] Step S102, determining the cargo volume change result of the line in the existing route of the routing group according to the routing group, and determining the coupling relationship between the existing route and the adjusted route in the routing group based on the cargo volume change result of the line in the existing route.

[0054] Among them, the lines in the existing route can be understood as the existing lines; the lines in the adjusted route can be understood as the adjusted lines, such as opening new lines or closing lines; the coupling relationship refers to the mutual influence relationship between different lines in the transportation network due to line adjustments (such as the opening of new lines or the closure of old lines). In logistics and transportation networks, when the opening, closure or change of a line causes changes in the cargo volume, flow direction or capacity of another line, these lines are considered to have a coupling relationship. The strength of the coupling relationship depends on factors such as the shared nodes between the lines (such as the starting point or the end point), the degree of overlap of the cargo flow direction, and the similarity of the transportation time. For example, when the opening of a new line reduces the cargo volume of the original line, this indicates that there is a negative coupling relationship between the two lines; if the opening of a new line increases the cargo volume of another line, it indicates that there is a positive coupling relationship.

[0055] Specifically, a direct comparison method can be used based on the difference in cargo volume changes. By obtaining the cargo volume data of the existing routes and the corresponding routes of the adjusted routes in each pair of route groups, the changes in cargo volume before and after the adjustment can be compared. For example, for a route in an existing route, analyze whether its cargo volume increases or decreases significantly after the corresponding adjusted route is opened or closed. The increase or decrease in cargo volume directly reflects the coupling relationship between the existing route and the adjusted route. If the addition of the new route leads to a decrease in the cargo volume of the old route, it indicates that there is a negative coupling relationship between the two; if the cargo volume increases, it indicates a positive coupling relationship. It is also possible to collect the trend of cargo volume changes of existing routes over a period of time for each pair of route groups based on the statistical analysis method of cargo volume fluctuations and time periods, and compare it with the implementation time of the adjusted routes. Statistical analysis is performed to determine whether the cargo volume of existing routes has obvious fluctuations before and after the adjusted routes, so as to judge the coupling relationship. For example, if the cargo volume of the existing routes changes significantly within the time window after the adjusted routes are opened or shut down, it can be considered that there is a strong coupling relationship between the existing routes and the adjusted routes. On the contrary, if the cargo volume fluctuations are small, the coupling relationship is weak. By comparing the time periods, the actual impact of the adjustments on the existing routes can be more comprehensively identified.

[0056] Step S103: Based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups, the routes in the transportation network are adjusted and optimized.

[0057] According to the adjusted routes in each pair of identified route groups and their coupling relationship with the existing routes, the transportation network can be adjusted and optimized more accurately. Specifically, by analyzing the coupling relationship between the existing routes and the adjusted routes in each pair of route groups, it is possible to determine the impact of changes in each adjusted route on the existing routes or which adjusted routes affect each existing route, such as the increase or decrease in cargo volume, changes in transportation efficiency, and route priority adjustments.

[0058] Specifically, based on the coupling relationship within each pair of route groups, it is possible to identify which existing routes may be directly or indirectly affected by the adjusted routes. For example, if the addition of an adjusted route significantly reduces the cargo flow of an existing route, it is possible to consider merging or reducing the frequency of the existing route to optimize resource utilization; and if the cargo volume of an existing route is significantly increased due to the impact of the adjusted route, it is possible to consider increasing the departure frequency of the route or expanding the capacity support to meet the new demand changes. Through the adjustment decision guided by this coupling relationship, the various routes in the network can form a more coordinated relationship, thereby reducing resource waste, improving overall transportation efficiency, and reducing unnecessary cost expenditures. In addition, the overall network performance can also be taken into account during adjustment and optimization. Not only the changes in cargo volume of a single existing route are concerned, but also the coupling conduction effects of these changes on other routes in the overall network are analyzed. For example, when adjusting some highly coupled routes, it may be necessary to gradually test their collateral effects on the entire network to avoid local optimization leading to global performance degradation. Through this adjustment and optimization based on coupling relationships, the transportation network can achieve dynamic optimization of routes while ensuring network stability, thereby adapting to changing transportation needs and environments.

[0059] Optionally, based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups, the routes in the transportation network are adjusted and optimized, including: based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups, an optimal network adjustment plan is determined; wherein the optimal network adjustment plan is a network adjustment plan with the lowest cost or a network adjustment plan with the shortest effectiveness; and based on the optimal network adjustment plan, the routes in the transportation network are adjusted and optimized.

[0060] The coupling relationship between the adjusted route and the existing route in each pair of route groups reflects the impact of the adjusted route on the existing route, and contains key information such as cargo volume changes, path utilization, and departure frequency. Based on these coupling relationships, a variety of network adjustment plans can be generated, and the optimal network adjustment plan can be determined through quantitative analysis to ensure that the network optimization direction meets specific operational goals.

[0061] First, according to the coupling relationship between the existing routes and the adjusted routes in each pair of route groups, the changes in the volume of cargo and path resources of each adjusted route on the existing routes can be analyzed and identified, so as to deduce the impact of different adjustment schemes on the overall transportation network. In this process, the pros and cons of the schemes can be set as the lowest cost or the shortest time according to the operation objectives. If the goal is the lowest cost network adjustment scheme, the system will give priority to the schemes that reduce resource consumption and reduce operating costs, such as reducing empty routes and merging low-flow routes. If the goal is the network adjustment scheme with the shortest time, the system will give priority to optimizing the transmission efficiency between routes, so as to maximize the transportation efficiency of high-demand routes and improve the overall time response. After determining the optimal network adjustment scheme, the execution of the scheme can adjust the actual configuration of the route based on the network adjustment strategy in the simulation optimization results, and gradually implement optimization and adjustment measures for each affected existing route, such as increasing capacity, adjusting departure time, optimizing terminal routes, etc., to achieve the expected cargo volume distribution and route efficiency. At the same time, during the execution process, in order to ensure the effectiveness of the optimal network adjustment plan, the system can simultaneously monitor and feedback, and adjust or optimize the configuration of each line in real time. In this way, the final adjustment can not only meet the set goals in terms of cost and timeliness, but also achieve higher resource utilization and service responsiveness in the transportation network.

[0062] Optionally, the routes in the transportation network are adjusted and optimized based on the optimal network adjustment plan, including: using a breadth-first search algorithm to traverse the graph of the optimal network adjustment plan to obtain multiple connected components; splitting the optimal network adjustment plan into multiple sub-plans based on the multiple connected components; and adjusting the routes in the transportation network according to the multiple sub-plans.

[0063] Based on the line coupling relationship in the optimal network adjustment scheme, the complex scheme can be split by graph theory method to gradually optimize the lines of the transportation network. Specifically, in order to effectively manage and execute the line optimization in the network adjustment scheme, the breadth-first search (BFS) algorithm is first used to traverse the graph structure of the scheme. BFS is a graph traversal method that can gradually identify each connected area in the network in a breadth-first hierarchical manner. During the BFS process, the system identifies the mutually coupled lines in the optimal network adjustment scheme as a connected component. By traversing these connected components, the complex line adjustment scheme can be decomposed into several independent sub-schemes. Splitting the optimal network adjustment scheme into multiple sub-schemes helps to simplify the actual operation and reduce the risk in the adjustment process. Each sub-scheme represents a group of interconnected lines. There is no mutual influence between the sub-schemes, so they can be adjusted one by one without destroying the overall network structure. For each sub-scheme formed by a connected component, the system can implement independent optimization adjustments to the relevant lines according to the actual situation, such as adjusting the departure frequency, modifying the line end point, increasing or decreasing the capacity, etc., so as to ensure that the interference to the network is minimized.

[0064] In addition to splitting based on the BFS graph traversal method, it is also possible to optimize the core nodes first by analyzing the importance of each line node. For example, line subsets can be divided according to flow density and connection centrality, and high-flow and core nodes can be adjusted independently first, and the peripheral or secondary connected lines can be grouped and optimized again. The peripheral lines can be gradually optimized while maintaining the core transportation efficiency, which can not only flexibly respond to the personalized adjustment needs of each sub-plan, but also better match the resource allocation and priority in actual operation, thereby achieving refined line optimization effects.

[0065] Optionally, before adjusting the routes in the transportation network according to multiple sub-plans, the method also includes: evaluating each sub-plan based on a simulation measurement strategy to obtain an evaluation result of each sub-plan; and sorting the evaluation result of each sub-plan to adjust the routes in the transportation network based on the sorting result.

[0066] The simulation calculation strategy is used to simulate the effect of each sub-scheme in actual application, so as to quantify its impact on the transportation network. Specifically, by establishing a model of the transportation network, each sub-scheme is calculated and estimated in terms of different time nodes, traffic flow and cost, and a set of evaluation indicators reflecting each sub-scheme is generated, such as improved transportation efficiency, reduced operating costs, improved timeliness, etc. The simulation calculation process can be based on a variety of parameter settings, such as traffic conditions during specific peak hours, changes in freight demand in different seasons, etc., so that the calculation results meet the actual operation needs. After the simulation calculation, the evaluation results of each sub-scheme are compared and sorted. The sorting basis can give priority to key factors such as the degree of improvement in transportation network efficiency, the reduction in operating costs, and the adaptability to the overall network. After sorting, the priority execution order of each sub-scheme can be clarified, and the routes of the transportation network can be gradually adjusted from the optimal scheme to the scheme with the least impact, to ensure a smooth transition of network optimization and efficient use of resources.

[0067] In addition to the evaluation method based on simulation calculation strategy, it is also possible to use a combination of expert evaluation and historical data analysis to evaluate the feasibility and expected effect of each sub-scheme through the professional judgment of senior transportation management personnel and historical operation data. For example, referring to the effect of similar schemes in similar routes in the past, the advantages and disadvantages of each sub-scheme are analyzed by combining qualitative and quantitative methods, and then the evaluation results are sorted. It can combine experience judgment with data support, further improve the accuracy of the adjustment plan, and make the priority order consistent with the long-term development goals of the transportation network.

[0068] Optionally, determining the cargo volume change results of the lines in the existing routes of the route group according to the route group includes: taking the intersection of the existing routes and the adjusted routes in the route group, and determining the cargo volume change results of the lines in the existing routes that exist in the intersection as unchanged cargo volume; determining the cargo volume change results of the lines in the existing routes that only exist in the existing routes as increased cargo volume; and determining the cargo volume change results of the lines in the existing routes that only exist in the adjusted routes as decreased cargo volume.

[0069] When determining the results of the volume change of the lines in the existing routes in the route group, the volume change of each line can be clarified by analyzing the intersection of the existing routes and the adjusted routes. First, the line sets contained in the existing routes and the adjusted routes are compared. For the lines that appear in the intersection, since the lines remain before and after the adjustment, it can be inferred that their volume will not change significantly after the adjustment. Therefore, the volume change result of the line is determined as unchanged. On these lines where the volume does not change, the stability of the cargo flow is high, which is convenient for maintaining the smooth operation of the transportation network. At the same time, if a line only exists in the existing route and does not appear in the adjusted route, it means that the line needs to bear more cargo flow or coverage in the existing network. The volume change result of such lines is determined as an increase in cargo volume, indicating that it may face higher transportation demand in the future. Accordingly, this result can be used to configure more transportation resources in advance to avoid line overload problems caused by a sudden increase in cargo volume. For routes that only appear in the adjusted routes, since there are no corresponding routes in the existing routes, it can be considered that these routes will undertake fewer cargo transportation tasks, resulting in a decrease in cargo volume. In this way, resource allocation can be appropriately reduced to improve the overall operational efficiency of the network.

[0070] In addition, the forecasting algorithm can be used to directly measure the changes in cargo volume on each route. For example, by comparing historical data with the adjustment plan, the forecasting model can be used to estimate the changes in cargo volume on each route after adjustment. The increase or decrease in cargo volume can be quantified more accurately, rather than simply judging the increase or decrease, which is conducive to adjusting the allocation of transportation resources at a finer granularity.

[0071] Optionally, the coupling relationship between the existing routes and the adjusted routes in the routing group is determined based on the cargo volume change results of the routes in the existing routes, including: constructing a bipartite graph according to the cargo volume change results of the routes in the existing routes and the corresponding routes in the adjusted routes, and analyzing the coupling relationship between the existing routes and the adjusted routes in the routing group based on the bipartite graph.

[0072] A bipartite graph is a special graph structure with two different types of nodes, and the connecting edges only exist between these two types of nodes. In this scenario, the lines in the existing route can be regarded as one type of node, and the lines in the corresponding adjusted route can be regarded as another type of node. The connection relationship between these nodes is determined according to the results of cargo volume changes, thereby constructing a bipartite graph. Through the constructed bipartite graph, the association between the existing route and the adjusted route is analyzed. When a line in an existing route has a connection relationship with lines in multiple adjusted routes, it indicates that the cargo volume change of this existing route will affect multiple adjusted routes, which is a part with strong coupling; and when only a single existing route is connected to the corresponding adjusted route, it indicates that its impact on the adjusted route is small or local. Based on this analysis, it is possible to identify which lines are more closely related, thereby effectively quantifying and representing the coupling relationship between different lines, which has a guiding role in subsequent network optimization, making the adjustment plan more targeted and avoiding the chain reaction caused by excessive coupling.

[0073] The statistical results of cargo volume changes can also be used to establish a coupling relationship matrix between existing routes and adjusted routes in a matrix manner. In the matrix, rows represent routes in existing routes, and columns represent routes in adjusted routes. The element values ​​of the matrix are filled according to the value of cargo volume changes to reflect the coupling strength between each pair of routes. Quantifying the coupling relationship into a data matrix makes it easier to analyze the matrix through algorithms, obtain accurate coupling relationship distribution, and further optimize the adjustment plan.

[0074] Figure 2 FIG. 1 is a schematic diagram of the main flow of a method for optimizing a transportation network according to a preferred embodiment of the present invention; Figure 2 As shown, in the transportation network, the indicator describing the degree of mutual influence of the network is defined as coupling degree, and the line coupling degree is defined in detail as the number of lines that need to be adjusted that any existing line is affected by. The complexity of network changes can be defined as: max{any existing line is affected by the number of lines that need to be adjusted}. Taking the newly opened line as an example (the same applies to closing a line or both opening and closing a line), the coupling degree of an existing line is 2, which means that the line and the other two newly opened lines will affect each other. For such complex network changes, this embodiment proposes a method for optimizing the transportation network to effectively identify and optimize the line coupling relationship.

[0075] First, in the input data preparation stage, complex scheme data is sorted. The main data includes adjusted route data and existing route data, which record the route's starting point, end point, departure time, arrival time, and adjustment actions (such as new opening or closure). In addition, route data needs to be sorted, including the starting point, end point, and route information before and after adjustment.

[0076] In the stage of identifying the coupling relationship of lines, the coupling relationship of lines is analyzed, identified and established. The coupling relationship of lines is mainly generated by routing. In the existing routes and adjusted routes of the same flow direction, the cargo volume of the existing routes that only appear in the adjusted routes but not in the existing routes will increase; the cargo volume of the existing routes that only appear in the existing routes but not in the adjusted routes will decrease; the cargo volume of the existing routes that appear in both the adjusted routes and the existing routes remains unchanged, and the routing adjustment has no effect on them. According to the coupling relationship between different lines, a bipartite graph of the entire network can be constructed. In this graph, a newly opened line may affect multiple existing lines at the same time, resulting in an increase or decrease in their cargo volume. In order to accurately construct the coupling relationship of the entire network, it is necessary to generate the line association relationship corresponding to all starting points and end points, and integrate this information into an adjacency matrix for subsequent analysis. Specifically, Figure 3 shown.

[0077] In the coupling formula expression and constraint construction stage, for each existing route, the adjustment route that affects its cargo volume is identified and the coupling variable is defined. , coupling variable is a 0-1 variable, indicating the coupling relationship between the existing line i and the adjustment line j. In addition, a coupling degree constraint is set, including a coupling degree description constraint and a coupling degree limit constraint; the coupling degree description constraint is all the adjustment routes related to the existing line i and the adjustment line j, that is, The coupling degree constraint is related to any existing line i ; Among them, M in the coupling degree description constraint is a large number; A 0-1 variable representing whether route k is selected; Represents all new routes related to old line i and new line j; in the coupling degree constraint The coupling degree is manually specified, usually set to 1 or 2. The coupling degree is controlled by the value of to limit the degree of change of the network. This method is highly independent and can be integrated with any path model to achieve effective network adjustment.

[0078] The algorithm implementation scheme splitting uses a heuristic algorithm that combines breadth-first search (BFS) and taboo table, aiming to output all sub-schemes without coupling relationships. BFS stands for Breadth First Search, and its Chinese name is breadth-first search, also known as breadth-first search. The so-called breadth-first means that each time you try to visit the nodes of the same layer, if the same layer has been visited, then visit the next layer, the result is that the path found by the BFS algorithm is the shortest legal path from the starting point. In other words, this path contains the smallest number of edges. At the end of BFS, each node is visited by the shortest path from the starting point to the point. The algorithm process can be regarded as the process of flame propagation: at the beginning, only the starting point is on fire. At each moment, the node with fire spreads the flame to all its adjacent nodes. Specifically, a queue Q is used to record the nodes to be processed, and then a Boolean array vis[] is opened to mark whether a node has been visited. At the beginning, the vis value of all nodes is set to 0, indicating that it has not been visited; then the starting point s is put into the queue Q and vis[s] is set to 1. After that, each time the node u at the head of the queue is taken out from the queue Q, all nodes v adjacent to u are marked as visited and put into the queue Q. The loop continues until the queue Q is empty, indicating the end of a round of BFS. At the end of each round of the BFS algorithm, a result that can be independently implemented in a sub-scheme can be obtained. Then, by looking for the next scheme to affect the main line, and using the taboo table to skip the scheme that has been visited to affect the main line, the next round of BFS search is carried out until all line adjustment schemes are traversed, and the search is finally ended. The BFS algorithm visits nodes layer by layer to find the shortest path from the starting point to each node to ensure that a legal path is found. At the same time, the use of the taboo table can avoid repeated visits to processed schemes. Through this method, we can split complex adjustment schemes into multiple sub-schemes, simplify the implementation process, and reduce the difficulty of implementation.

[0079] Determine the order of implementation of each sub-plan, evaluate each sub-plan using simulation calculations, calculate the cost and time changes brought about by its implementation, sort each sub-plan according to the comprehensive score of cost and time improvement, and implement them in sequence from high to low to achieve efficient adjustment of the transportation network while minimizing the gap between implementation results and predictions.

[0080] According to a second aspect of an embodiment of the present invention, a device for optimizing a transportation network is provided.

[0081] Figure 4 Schematic diagram of main modules of a transportation network optimization device according to an embodiment of the present invention. Figure 4 As shown, a transportation network optimization device 400 includes:

[0082] The route determination module 401 is used to determine an adjusted route corresponding to an existing route in the existing route set from the adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups;

[0083] A relationship determination module 402 is used to determine the cargo volume change result of the route in the existing route of the route group according to the route group, and determine the coupling relationship between the existing route and the adjusted route in the route group based on the cargo volume change result of the route in the existing route;

[0084] The adjustment and optimization module 403 is used to adjust and optimize the routes in the transportation network based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups.

[0085] Optionally, the adjustment and optimization module 403 is further used for:

[0086] Determine an optimal network adjustment plan based on the adjusted routes in each pair of routing groups and the coupling relationship between the existing routes and the adjusted routes in each pair of routing groups; wherein the optimal network adjustment plan is the network adjustment plan with the lowest cost or the network adjustment plan with the shortest effectiveness;

[0087] Adjust and optimize the routes in the transportation network based on the optimal network adjustment plan.

[0088] Optionally, the adjustment and optimization module 403 is further used for:

[0089] The optimal network adjustment scheme is traversed by using the breadth-first search algorithm to obtain multiple connected components;

[0090] Splitting the optimal network adjustment scheme into multiple sub-schemes based on multiple connected components;

[0091] Routes in the transport network are adjusted according to multiple sub-schemes.

[0092] Optionally, the adjustment and optimization module 403 is further used for:

[0093] Evaluate each sub-scheme based on the simulation calculation strategy to obtain the evaluation result of each sub-scheme;

[0094] The evaluation results of each sub-scheme are ranked to adjust the routes in the transportation network based on the ranking results.

[0095] Optionally, the relationship determination module 402 is further configured to:

[0096] The existing routes and the adjusted routes in the route group are intersected, and the cargo volume change results of the routes in the existing routes in the intersection are determined as unchanged cargo volume;

[0097] The results of the volume changes for the routes in the existing routes that exist only in the existing routes are determined as volume increases;

[0098] The cargo volume change results of the lines in the existing routes that exist only in the adjusted routes are determined as cargo volume reduction.

[0099] Optionally, the relationship determination module 402 is further configured to:

[0100] According to the cargo volume change results of the lines in the existing routes and the corresponding lines in the adjusted routes, a bipartite graph is constructed, and the coupling relationship between the existing routes and the adjusted routes in the routing group is analyzed based on the bipartite graph.

[0101] It should be noted that the specific implementation content of the transportation network optimization device of the present invention has been described in detail in the above transportation network optimization method, so the repeated content will not be described again here.

[0102] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present invention.

[0103] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0104] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0105] Figure 5 An exemplary system architecture 500 is shown to which the transportation network optimization method or transportation network optimization device according to the embodiments of the present application can be applied.

[0106] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0107] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0108] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0109] The server 505 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 501, 502, and 503. The backend management server may analyze and process the received data such as the optimization request of the transportation network, and feed back the processing result (such as the optimization result - only an example) to the terminal device.

[0110] It should be noted that the transportation network optimization method provided in the embodiment of the present application is generally executed by the server 505 , and accordingly, the transportation network optimization device is generally set in the server 505 .

[0111] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0112] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present application. Figure 6 The terminal device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0113] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0114] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0115] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present application are executed.

[0116] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable storage media may include, for example, but are not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0117] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The units involved in the embodiments described in the present application may be implemented by software or by hardware. The units described may also be set in a processor, for example, may be described as: a processor includes a route determination module, a relationship determination module and an adjustment optimization module. Among them, the names of these modules do not constitute a limitation on the module itself under certain circumstances. For example, the adjustment optimization module may be described as "a module for adjusting and optimizing the routes in the transportation network based on the adjustment routes in each pair of route groups, and the coupling relationship between the existing routes and the adjustment routes in each pair of route groups".

[0119] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by one of the devices, the device includes: determining an adjusted route corresponding to an existing route in an existing route set from an adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route are a pair of route groups; determining the cargo volume change result of the route in the existing route of the route group according to the route group, and determining the coupling relationship between the existing route and the adjusted route in the route group based on the cargo volume change result of the route in the existing route; adjusting and optimizing the routes in the transportation network based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups.

[0120] The computer program product provided by the embodiment of the present invention includes a computer program. When the computer program is executed by a processor, the method for optimizing the transportation network in the embodiment of the present invention is implemented.

[0121] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by determining the adjusted routes corresponding to the existing routes in the existing route set from the adjusted route set; wherein the existing routes and the adjusted routes include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups; determining the cargo volume change result of the line in the existing route of the route group according to the route group, and determining the coupling relationship between the existing route and the adjusted route in the route group based on the cargo volume change result of the line in the existing route; adjusting and optimizing the routes in the transportation network based on the adjusted routes in each pair of route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of route groups; thereby describing and controlling the mutual influence degree of the transportation network, reducing the adjustment and optimization cost of the transportation network, and improving the timeliness of the transportation adjustment.

[0122] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

[0123] It should be noted that the acquisition, storage and application of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

Claims

1. A method for optimizing a transportation network, characterized in that: include: Determine an adjusted route corresponding to an existing route in the existing route set from the adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups; Determine, according to the routing group, a result of a change in the volume of goods of a route in an existing route of the routing group, and determine, based on the result of the change in the volume of goods of the route in the existing route, a coupling relationship between an existing route and an adjusted route in the routing group; Based on the adjusted routes in each pair of the route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of the route groups, the routes in the transportation network are adjusted and optimized.

2. The method according to claim 1, characterized in that Based on the adjusted routes in each pair of the route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of the route groups, the routes in the transportation network are adjusted and optimized, including: Determine an optimal network adjustment scheme based on the adjusted routes in each pair of the routing groups and the coupling relationship between the existing routes and the adjusted routes in each pair of the routing groups; wherein the optimal network adjustment scheme is the network adjustment scheme with the lowest cost or the network adjustment scheme with the shortest effectiveness; The routes in the transportation network are adjusted and optimized based on the optimal network adjustment plan.

3. The method according to claim 2, characterized in that Adjusting and optimizing the routes in the transportation network based on the optimal network adjustment scheme includes: Using a breadth-first search algorithm to perform graph traversal on the optimal network adjustment solution to obtain a plurality of connected components; Splitting the optimal network adjustment solution into a plurality of sub-solutions based on the plurality of connected components; Routes in the transportation network are adjusted according to the multiple sub-plans.

4. The method according to claim 3, characterized in that Before adjusting the routes in the transportation network according to the multiple sub-schemes, the method further includes: Evaluate each sub-scheme based on the simulation calculation strategy to obtain the evaluation result of each sub-scheme; The evaluation results of each sub-scheme are sorted to adjust the routes in the transportation network based on the sorting results.

5. The method according to claim 1, characterized in that Determining, according to the routing group, a cargo volume change result of a route in an existing route of the routing group, including: Taking the intersection of the existing routes and the adjusted routes in the route group, and determining the cargo volume change result of the route in the existing routes in the intersection as the cargo volume unchanged; The results of the volume changes for the routes in the existing routes that exist only in the existing routes are determined as volume increases; The cargo volume change results of the lines in the existing routes that exist only in the adjusted routes are determined as cargo volume reduction.

6. The method according to claim 1, characterized in that Determining the coupling relationship between the existing routes and the adjusted routes in the route group based on the cargo volume change result of the lines in the existing routes includes: A bipartite graph is constructed according to the cargo volume change results of the routes in the existing routes and the routes in the corresponding adjusted routes, and a coupling relationship between the existing routes and the adjusted routes in the route group is analyzed based on the bipartite graph.

7. A transportation network optimization device, characterized in that: include: A route determination module, configured to determine an adjusted route corresponding to an existing route in the existing route set from the adjusted route set; wherein the existing route and the adjusted route include at least one route, the starting point and the end point of the existing route and the corresponding adjusted route are consistent, and the existing route and the corresponding adjusted route form a pair of route groups; a relationship determination module, configured to determine, according to the routing group, a result of a change in the volume of goods of a route in an existing route of the routing group, and determine a coupling relationship between an existing route and an adjusted route in the routing group based on the result of a change in the volume of goods of a route in the existing route; The adjustment and optimization module is used to adjust and optimize the routes in the transportation network based on the adjusted routes in each pair of the route groups and the coupling relationship between the existing routes and the adjusted routes in each pair of the route groups.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images