Logistics network management method and device

Abstract

The invention discloses a logistics network management method and device, and relates to the technical field of logistics management. A specific embodiment of the method comprises the following steps: determining association degrees among different city nodes in a logistics network based on cargo volume information, and obtaining an association degree matrix among the different city nodes in the logistics network; taking the correlation degree matrix among the different city nodes in the logistics network as a weighted value of a link relationship among the different city nodes in the logistics network, and constructing an initial adjacency matrix of the logistics network; and carrying out clustering processing on the initial adjacent matrix by adopting a graph theory algorithm to obtain a community clustering result of each city node in the logistics network and a core node of each community. According to the embodiment, a scientific logistics hub node selection method can be provided on the premise of comprehensively considering the cargo quantity and the transportation network among the urban nodes, and the finally obtained community structure is consistent with the axial-radial structure in the logistics network, so that the method has a relatively good practical value.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a method and device for logistics network management. Background Art

[0002] Commonly used methods for selecting a city as a logistics center include the center of gravity method, the combined prediction method, and the hierarchical analysis method. The center of gravity method only considers the impact of geographical location, which has great limitations, and the final selected location often needs to be adjusted many times. The combined prediction method can predict the future economic development trend of a city or region in the economic dimension, but the factors considered are also relatively single, and the feasibility of the conclusions drawn is also limited. Although the hierarchical analysis method can take into account a variety of qualitative analysis factors such as politics, economy, and geographical location, it relies heavily on expert scoring in the actual implementation process, and there is a certain degree of subjectivity that cannot be eliminated. Therefore, the applicability of the above methods is poor. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and device for logistics network management, which can provide a scientific logistics hub node selection method under the premise of comprehensively considering the cargo volume and transportation network between each city node, and the community structure finally obtained is consistent with the hub-and-spoke structure in the logistics network, and has good practical value.

[0004] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for logistics network management is provided, comprising:

[0005] Determine the correlation between different city nodes in the logistics network based on the cargo volume information, and obtain a correlation matrix between different city nodes in the logistics network;

[0006] Using the association degree matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network, constructing the initial adjacency matrix of the logistics network;

[0007] The initial adjacency matrix is ​​clustered using a graph theory algorithm to obtain community clustering results of each city node in the logistics network and the core nodes of each community.

[0008] Optionally, determining the correlation between different city nodes in the logistics network based on cargo volume information includes: determining the discrete probability distribution of the local network of each city node in the logistics network based on the cargo volume information; and determining the correlation between any two city nodes in the logistics network based on the discrete probability distribution corresponding to the any two city nodes.

[0009] Optionally, determining the discrete probability distribution of the local area network of each of the city nodes in the logistics network according to the cargo volume information includes:

[0010] Determine the cargo flow output capacity of each city node in the local area network; the cargo flow output capacity is used to indicate the capacity of the corresponding city node to output cargo to the city node directly adjacent to it;

[0011] Determine the cargo flow input capacity of each city node in the local area network, and determine the comprehensive cargo flow input capacity of the local area network according to the cargo flow input capacity of each city node in the local area network; the cargo flow input capacity is used to indicate the ability of the corresponding city node to receive cargo input from the city node directly adjacent to it;

[0012] Determine the discrete probability of each city node in the local area network according to the comprehensive cargo flow input capacity of the local area network and the cargo flow output capacity of each city node in the local area network;

[0013] The discrete probability distribution of the local area network is determined according to the discrete probability of each city node in the local area network.

[0014] Optionally, determining the correlation between any two city nodes according to the discrete probability distribution corresponding to any two city nodes in the logistics network includes: determining the relative entropy of the discrete probability distribution corresponding to any two city nodes in the logistics network, and determining the correlation between any two city nodes according to the relative entropy.

[0015] Optionally, the graph theory algorithm is a Markov clustering algorithm.

[0016] Optionally, before determining the correlation between different city nodes in the logistics network based on cargo volume information, the method further includes: determining the cargo volume information between different city nodes in the logistics network based on the number of routes and route transportation volume between different city nodes in the logistics network.

[0017] Optionally, after obtaining the community clustering results of each city node in the logistics network and the core nodes of each community, the method also includes: selecting the hub nodes of the logistics network from the core nodes of each community; using the network formed by connecting the hub nodes as the trunk network of the logistics network, and using the network formed by connecting the hub nodes and other city nodes in the community where they are located as the branch network of the logistics network, so as to obtain a logistics network with a hub-and-spoke structure.

[0018] According to a second aspect of an embodiment of the present invention, there is provided a device for logistics network management, including:

[0019] A correlation determination module, which determines the correlation between different city nodes in the logistics network based on the cargo volume information, and obtains a correlation matrix between different city nodes in the logistics network;

[0020] An adjacency matrix determination module, using the association matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network, to construct an initial adjacency matrix of the logistics network;

[0021] The node clustering module uses a graph theory algorithm to perform clustering processing on the initial adjacency matrix to obtain the community clustering results of each city node in the logistics network and the core nodes of each community.

[0022] Optionally, the correlation determination module determines the correlation between different city nodes in the logistics network based on cargo volume information, including: determining the discrete probability distribution of the local network of each city node in the logistics network according to the cargo volume information; and determining the correlation between any two city nodes in the logistics network according to the discrete probability distribution corresponding to the any two city nodes.

[0023] Optionally, the association determination module determines the discrete probability distribution of the local area network of each of the city nodes in the logistics network according to the cargo volume information, including:

[0024] Determine the cargo flow output capacity of each city node in the local area network; the cargo flow output capacity is used to indicate the capacity of the corresponding city node to output cargo to the city node directly adjacent to it;

[0025] Determine the cargo flow input capacity of each city node in the local area network, and determine the comprehensive cargo flow input capacity of the local area network according to the cargo flow input capacity of each city node in the local area network; the cargo flow input capacity is used to indicate the ability of the corresponding city node to receive cargo input from the city node directly adjacent to it;

[0026] Determine the discrete probability of each city node in the local area network according to the comprehensive cargo flow input capacity of the local area network and the cargo flow output capacity of each city node in the local area network;

[0027] The discrete probability distribution of the local area network is determined according to the discrete probability of each city node in the local area network.

[0028] Optionally, the correlation determination module determines the correlation between any two city nodes in the logistics network based on the discrete probability distribution corresponding to any two city nodes in the logistics network, including: determining the relative entropy of the discrete probability distribution corresponding to any two city nodes in the logistics network, and determining the correlation between the any two city nodes based on the relative entropy.

[0029] Optionally, the graph theory algorithm is a Markov clustering algorithm.

[0030] Optionally, the device also includes: an information acquisition module, which is used to: determine the cargo volume information between different city nodes in the logistics network according to the number of routes and route transportation volume between different city nodes in the logistics network before determining the correlation between different city nodes in the logistics network based on the cargo volume information.

[0031] Optionally, the device also includes: a network construction acquisition module, which is used to: after obtaining the community clustering results of each city node in the logistics network and the core nodes of each community, screen the hub nodes of the logistics network from the core nodes of each community; use the network formed by connecting each hub node as the trunk network of the logistics network, and use the network formed by connecting the hub node and other city nodes in the community where it is located as the branch network of the logistics network, so as to obtain a logistics network with a hub-and-spoke structure.

[0032] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for logistics network management, including:

[0033] one or more processors;

[0034] a storage device for storing one or more programs,

[0035] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0036] 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.

[0037] One embodiment of the above invention has the following advantages or beneficial effects: the embodiment of the present invention determines the correlation between different city nodes in the logistics network based on the cargo volume information, obtains the correlation matrix between different city nodes in the logistics network, takes the correlation matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network, constructs the initial adjacency matrix of the logistics network, and processes the initial adjacency matrix using a graph theory algorithm to obtain the community clustering results of each city node in the logistics network and the core nodes of each community. The embodiment of the present invention analyzes the community effect of the existing logistics network according to the existing logistics routes and cargo volume information between each city node, identifies the logistics network nodes as several local network structures centered on the core node, and can provide a scientific logistics hub node selection method under the premise of comprehensively considering the cargo volume and transportation network between each city node, and the community structure finally obtained is consistent with the hub-and-spoke structure in the logistics network, which has good practical value.

[0038] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0040] Figure 1 It is a schematic diagram of the main process of the method for logistics network management according to an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of the structure of a local area network of a city node in an optional embodiment of the present invention;

[0042] Figure 3 is a schematic diagram of main modules of a logistics network management device according to an embodiment of the present invention;

[0043] Figure 4 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0044] Figure 5 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] According to one aspect of an embodiment of the present invention, a method for managing a logistics network is provided.

[0047] Figure 1 FIG. 1 is a schematic diagram of the main process of the method for logistics network management according to an embodiment of the present invention. Figure 1 As shown, the method for logistics network management includes step S101, step S102 and step S103.

[0048] Step S101, determining the correlation between different city nodes in the logistics network based on cargo volume information, and obtaining a correlation matrix between different city nodes in the logistics network.

[0049] Cargo volume information refers to information about the volume of cargo transported between city nodes, such as information about cargo output and / or cargo inflow. In actual application, before determining the correlation between different city nodes in the logistics network based on cargo volume information, the cargo volume information can be determined based on historical data, such as determining the above cargo volume information based on the average monthly cargo transport volume in the past six months or a year. In an optional embodiment, before determining the correlation between different city nodes in the logistics network based on cargo volume information, the cargo volume information between different city nodes in the logistics network is determined based on the number of routes and route transportation volume between different city nodes in the logistics network. Exemplarily, the logistics network includes city node 1 and city node 2, and the cargo volume information between city node 1 and city node 2 is determined based on the number of routes between city node 1 and city node 2, and the route transportation volume of each route.

[0050] The more cargo transport volume there is between two city nodes, the closer the cargo flow relationship between the two is, and the higher the corresponding correlation is. In some optional embodiments, the correlation between the two city nodes is directly determined based on the cargo volume information between the two city nodes, for example, the correlation between the two city nodes is positively correlated with the cargo volume information between the two city nodes.

[0051] In other optional embodiments, the correlation between different city nodes in the logistics network is determined based on cargo volume information, including: determining the discrete probability distribution of the local network of each city node in the logistics network based on the cargo volume information; and determining the correlation between any two city nodes in the logistics network based on the discrete probability distribution corresponding to the any two city nodes.

[0052] For any city node, the local area network of the city node refers to the network structure formed by the city node and other city nodes directly connected to the city node, such as Figure 2 As shown. The embodiment of the present invention splits the logistics network into a network structure with a radius of 1 with a city node as the hub, where the radius refers to the number of transfers required to reach another city node from one city node. The smallest network structure that can be obtained after disassembling a logistics network is a network structure formed by a city node and other city nodes directly connected to the city node, and the radius of this structure is 1. In other words, the city node located at the core of the local area network only needs one transfer to reach other city nodes in the local area network. By dividing the logistics network into a network structure with a radius of 1, it is convenient to define the cargo link relationship between city nodes and city nodes in the local area network for calculating. The more cargo transmission volume between different city nodes in a local area network, the closer the cargo flow relationship between the two, the higher the corresponding correlation, and the denser the local area network; the less cargo transmission volume between different city nodes in a local area network, the weaker the cargo flow relationship between the two, the lower the corresponding correlation, and the more discrete the local area network.

[0053] This embodiment determines the correlation between any two city nodes based on the discrete probability distribution of the local network of each city node according to the cargo volume information, and determines the correlation between any two city nodes according to the discrete probability distribution corresponding to the any two city nodes. This can more accurately reflect the correlation between different city nodes under the premise of comprehensively considering the cargo volume and transportation network between city nodes.

[0054] For any city node, the discrete probability distribution of the local area network of the city node can be determined according to the cargo flow input capacity and cargo flow output capacity of each city node in the local area network. In some optional embodiments, determining the discrete probability distribution of the local area network of each city node in the logistics network according to the cargo volume information may include:

[0055] Determine the cargo flow input capacity of each city node j in the local area network of city node i The cargo flow input capacity is used to indicate the capacity of the corresponding city node to receive cargo input from the city nodes directly adjacent to it. It should be noted that in determining the cargo flow input capacity of city node j in the local area network of city node i, When the above “directly adjacent city nodes” refers only to the city nodes directly adjacent to city node i in the local area network of city node i, or includes both the city nodes directly connected to city node i in the local area network of city node i and the city nodes directly adjacent to city node i outside the local area network of city node i. Figure 2For example, the city node at the center is connected to five other city nodes. The theoretical cargo flow input capacity of the city node at the center is the sum of the cargo output from the five other adjacent city nodes to the city node at the center. According to the cargo flow input capacity of each city node j in the local area network of city node i, Determine the comprehensive cargo flow input capacity D of the local network of city node i i . Comprehensive cargo flow input capacity D i The cargo flow input capacity of each city node j Positive correlation, for example:

[0056] Determine the cargo flow output capacity of each city node j in the local area network The cargo flow output capacity is used to indicate the capacity of the corresponding city node to output cargo to the city node directly adjacent to it. It should be noted that in determining the cargo flow output capacity of city node j in the local area network of city node i, When the above “directly adjacent city nodes” refers only to the city nodes directly adjacent to city node i in the local area network of city node i, or includes both the city nodes directly connected to city node i in the local area network of city node i and the city nodes directly adjacent to city node i outside the local area network of city node i. Figure 2 For example, the city node at the center is connected to five other city nodes. The theoretical cargo flow output capacity of the city node at the center is the sum of the cargo output from the city node at the center to the five other adjacent city nodes.

[0057] According to the comprehensive cargo flow input capacity D of the local network of city node i i , and the cargo flow output capacity of each city node j in the local area network Determine the discrete probability p of each city node in the local area network i (j); p i The calculation formula of (j) is:

[0058] According to the discrete probability of each city node in the local area network, the discrete probability distribution P of the local area network is determined. i =(p i (1),p i (2),…,p i (k),…,p i (n)). In actual application, before determining the discrete probability distribution of the local area network, the discrete probability of each city node in the local area network may be sorted, for example, in order from large to small or from small to large.

[0059] The method of determining the discrete probability distribution of the local area network in this embodiment can comprehensively consider the cargo volume and transportation network between cities, so as to cluster the city nodes in the logistics network based on the real city business flow relationship and logistics links.

[0060] Although the above example provides a specific implementation method for determining the discrete probability distribution of a local area network, those skilled in the art should understand that the method for determining the discrete probability distribution of a local area network can be selectively set, as long as it can reflect the discrete distribution of the local area network, and the embodiment of the present invention does not limit the specific implementation method for determining the discrete probability distribution. For example, in the above example of determining the discrete probability distribution of a local area network:

[0061] The comprehensive cargo flow input capacity D of the local network of city node i is not based on i , and the cargo flow output capacity of each city node j in the local area network Determine the discrete probability p of each city node in the local area network i (j), but according to the cargo flow output capacity of each city node j in the local area network of city node i Determine the comprehensive cargo flow output capacity D of the local network of city node i i ′ , comprehensive cargo flow output capacity D i ′ The cargo output capacity of each city node j Positive correlation, for example: Then, according to the comprehensive cargo flow output capacity D of the local area network of city node i i ′ , and the cargo flow input capacity of each city node j in the local area network Determine the discrete probability p of each city node in the local area network i ′ (j); p i ′ The calculation formula of (j) is:

[0062] In the embodiment of the present invention, in order to analyze the degree of association between different city nodes, after determining the discrete probability distribution of the local area network, the discrete probability distribution of the local area network of each city node may be further standardized.

[0063] In an embodiment of the present invention, the method of determining the correlation between any two city nodes can be selectively set, as long as it can reflect the closeness of the cargo flow relationship between the two. The embodiment of the present invention does not limit the specific implementation method of determining the correlation. Optionally, according to the discrete probability distribution corresponding to any two city nodes in the logistics network, the correlation between the any two city nodes is determined, including: determining the Shannon entropy or relative entropy of the discrete probability distribution corresponding to any two city nodes in the logistics network, and determining the correlation between the any two city nodes according to the Shannon entropy or relative entropy. Relative entropy, also known as KL divergence, is an important method in information theory and one of the important extensions of Shannon entropy. The larger the Shannon entropy or relative entropy, the higher the correlation between the two city nodes in the logistics network.

[0064] Step S102, using the association degree matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network, to construct an initial adjacency matrix of the logistics network.

[0065] The elements in the adjacency matrix refer to the link relationship between the row and column city nodes. The embodiment of the present invention uses the correlation between adjacent city nodes in the logistics network as the weight of the corresponding edge in the adjacency matrix to construct the initial adjacency matrix between each city node. This application calculates the correlation between each city node based on the cargo information in advance when constructing the initial adjacency matrix, so that the conclusion of clustering processing using graph theory algorithms can better reflect the actual cargo flow between city nodes, rather than just considering whether the city nodes are connected to each other, so that this method can be used to better select the hub nodes of the logistics network.

[0066] Step S103, clustering the initial adjacency matrix using a graph theory algorithm to obtain community clustering results of each city node in the logistics network and the core nodes of each community.

[0067] Graph theory algorithms include a variety of algorithms, and those skilled in the art can choose according to actual conditions, for example, the graph theory algorithm is a Markov clustering algorithm or a minimum spanning tree algorithm. Markov Cluster Algorithm (MCL) is one of the graph theory algorithms. The core of the MCL algorithm is to imitate the process of random flow constantly iterating and randomly walking in a complex network. Its theoretical basis is, "When walking randomly in the network G, if you walk to a dense subgraph, then unless most of the nodes in the subgraph have been visited, you will not walk out of the subgraph." The MCL algorithm imitates the random flow of random flow in the network, that is, a random walk of the random flow in the network graph G starts from a certain node, jumps to the next adjacent node according to a certain probability, and stops at a certain node.

[0068] Taking the Markov clustering algorithm as an example, the specific process of clustering the initial adjacency matrix includes:

[0069] According to the initial adjacency matrix E, the expansion coefficient k (adaptively set), and the expansion coefficient γ (adaptively set), the MCL clustering algorithm is used to perform the following steps:

[0070] 1. Perform column normalization on the initial adjacency matrix E to obtain the matrix T 2k ;

[0071] 2. For the matrix T 2k Perform expansion operation to get the matrix The expansion process is to multiply the adjacency matrix, which is used to simulate the random flow in the network and make the adjacency matrix homogeneous. After the adjacency matrix column is standardized, the matrix power operation can be performed. exp =M k , where the k value represents the expansion coefficient. When the expansion coefficient k = 2, it represents the probability that E(i,j) reaches node j from node i in one step. When the expansion coefficient k = 3, it represents the probability that E(i,j) reaches node j from node i in two steps. The larger the expansion coefficient k, the more steps it takes, which increases the probability that E(i,j) will leave the current cluster and enter another cluster. It can be seen that as the expansion coefficient k increases, the closeness between the same clusters will weaken.

[0072] 3. Matrix Perform an inflation operation to obtain the matrix The expansion process is the process of performing power operations on each element in the matrix. The goal is to enhance the flow probability within the same cluster through this process, so that the random flow flows within the cluster and the probability of leaving the cluster becomes lower, thereby accelerating the clustering process in the network. The expansion operation process is to perform matrix dot multiplication and then column normalization. The expansion coefficient γ represents the number of dot multiplications. The larger the expansion coefficient γ, the smaller the granularity of the clustering result.

[0073] 4. Matrix Perform column standardization to obtain the matrix T 2k+1 ;

[0074] 5. Calculate the matrix T 2k+1 With the matrix T 2k If the distance is not 0, the matrix T 2k+1 As the new matrix T 2kRepeat steps 2, 3, and 4 for multiple iterations until the Euclidean distance calculated in step 5 is 0 and the matrix converges. In actual application, in order to speed up the convergence of the matrix, a correction value can be set. When the Euclidean distance calculated in step 5 is less than the correction value, the matrix is ​​processed and the elements with particularly small values ​​in the matrix are modified to 0.

[0075] 6. Output the community clustering results of each city node and the core nodes of each community. The core nodes are the city nodes recommended as hub nodes in the logistics network.

[0076] Commonly used methods for selecting a city as a hub node for logistics include the centroid method, combined prediction method, and hierarchical analysis method. The centroid method only considers the impact of geographical location, which has great limitations, and the location finally selected often needs to be adjusted many times. The combined prediction method can predict the future economic development trend of a city or region in the economic dimension, but the factors considered are also relatively single, and the feasibility of the conclusions drawn is also limited. Although the hierarchical analysis method can take into account a variety of qualitative analysis factors such as politics, economy, and geographical location, it relies heavily on expert scoring in the actual implementation process, and there is a certain degree of subjectivity that cannot be eliminated. In addition, the hierarchical analysis method, the centroid method, and the combined prediction method do not analyze the network structure, but directly give recommended city nodes. The conclusions drawn by these methods do not reflect the relationship between city nodes in the logistics network, nor can they derive the community structure. In addition, since there are many optional cities for hub nodes in international logistics business scenarios, it is difficult to maintain a unified caliber and comprehensively consider multiple factors to compare various cities, and the logistics centers selected by the above-mentioned existing technologies are also difficult to scientifically explain their radiation range to surrounding cities, and their applicability in international scenarios is poor.

[0077] Community identification is to rearrange the adjacency matrix of a complex network according to certain rules, so that the rearranged adjacency matrix is ​​partially dense, and the nodes contained in the dense part can be considered as a community, and the core node in the community is the central node. Based on this, an embodiment of the present invention proposes a logistics site selection scheme based on a graph theory algorithm. The method is mainly divided into two steps: the first step is to use the cargo volume information between the city nodes in the logistics network to calculate the correlation between the discrete probability distribution of any two city nodes in the logistics network. The greater the correlation, the higher the correlation between the two city nodes in the logistics network. This is used as the initial adjacency matrix of the graph theory algorithm, and the initial transfer probability matrix is ​​obtained by column normalization of the initial adjacency matrix. After that, the graph theory algorithm is used to complete the subsequent calculations, and the community classification results of the urban agglomeration can be obtained. The city nodes that are divided into a community represent that the cargo flow relationship between these cities is close.

[0078] In an embodiment of the present invention, after obtaining the community clustering results of each city node in the logistics network and the core nodes of each community, the hub nodes of the logistics network can also be screened from the core nodes of each community, for example, the core nodes of each community are used as hub nodes, or the core nodes of some communities are used as hub nodes, and then the network formed by connecting the hub nodes is used as the trunk network of the logistics network, and the network formed by connecting the hub nodes with other city nodes in the community where they are located is used as the branch network of the logistics network, so as to obtain a logistics network with a hub-and-spoke structure. When only the part of the communities obtained by clustering and their core nodes are used as the branch network and the hub node, for the unselected communities, each city node therein can be classified into the branch network to which the city node directly adjacent to it belongs. If there is a city node in the unselected community that is not directly adjacent to any city node in the branch network, the city node can be directly connected to a hub node.

[0079] The hub-and-spoke logistics network is a centralized transportation system based on a large logistics hub center station. For example, when cross-border goods are transported, no matter which city in country G1 the goods are shipped from, they will first be transported to a city g1 in country G1. City g1 is the hub node of the logistics network in country G1. The way of transporting goods from city g1 to various cities in the inland of country G2 is not to send them directly from city g1, but to transport them from city g1 to city g2 in country G2 first, and then divert them from city g2 to specific destination cities. This is the hub-and-spoke network, and cities g1 and g2 are the core nodes or hub nodes of the logistics network. This application analyzes the community effect of the existing logistics network through the existing logistics routes and cargo volumes between cities, and identifies the city nodes in the logistics network as several local network structures centered on the core nodes. The core nodes in the community composed of several city nodes are the candidate logistics hub nodes identified based on this application. This application can provide a scientific hub node selection method under the premise of comprehensively considering the cargo volume and transportation network between cities, and the final community structure is consistent with the hub-and-spoke structure in the logistics network, which has good practical value.

[0080] The embodiment of the present invention uses the cargo volume information between each city node to determine the correlation between the city nodes, and generates an initial adjacency matrix as the weighted value of the logistics link relationship between each city node in the logistics network. A graph theory algorithm is established to process the initial adjacency matrix to obtain the city clustering result based on the real city business flow relationship and logistics link, which has good practical value.

[0081] According to a second aspect of an embodiment of the present invention, a device for implementing the above method is provided.

[0082] Figure 3 FIG. 1 is a schematic diagram of the main modules of the device for logistics network management according to an embodiment of the present invention. Figure 3 As shown, the device 300 for logistics network management includes:

[0083] A correlation determination module 301 determines the correlation between different city nodes in the logistics network based on the cargo volume information, and obtains a correlation matrix between different city nodes in the logistics network;

[0084] The adjacency matrix determination module 302 constructs an initial adjacency matrix of the logistics network by using the association matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network;

[0085] The node clustering module 303 uses a graph theory algorithm to perform clustering processing on the initial adjacency matrix to obtain the community clustering results of each city node in the logistics network and the core nodes of each community.

[0086] Optionally, the correlation determination module determines the correlation between different city nodes in the logistics network based on cargo volume information, including: determining the discrete probability distribution of the local network of each city node in the logistics network according to the cargo volume information; and determining the correlation between any two city nodes in the logistics network according to the discrete probability distribution corresponding to the any two city nodes.

[0087] Optionally, the association determination module determines the discrete probability distribution of the local area network of each of the city nodes in the logistics network according to the cargo volume information, including:

[0088] Determine the cargo flow output capacity of each city node in the local area network; the cargo flow output capacity is used to indicate the capacity of the corresponding city node to output cargo to the city node directly adjacent to it;

[0089] Determine the cargo flow input capacity of each city node in the local area network, and determine the comprehensive cargo flow input capacity of the local area network according to the cargo flow input capacity of each city node in the local area network; the cargo flow input capacity is used to indicate the ability of the corresponding city node to receive cargo input from the city node directly adjacent to it;

[0090] Determine the discrete probability of each city node in the local area network according to the comprehensive cargo flow input capacity of the local area network and the cargo flow output capacity of each city node in the local area network;

[0091] The discrete probability distribution of the local area network is determined according to the discrete probability of each city node in the local area network.

[0092] Optionally, the correlation determination module determines the correlation between any two city nodes in the logistics network based on the discrete probability distribution corresponding to any two city nodes in the logistics network, including: determining the relative entropy of the discrete probability distribution corresponding to any two city nodes in the logistics network, and determining the correlation between the any two city nodes based on the relative entropy.

[0093] Optionally, the graph theory algorithm is a Markov clustering algorithm.

[0094] Optionally, the device also includes: an information acquisition module, which is used to: determine the cargo volume information between different city nodes in the logistics network according to the number of routes and route transportation volume between different city nodes in the logistics network before determining the correlation between different city nodes in the logistics network based on the cargo volume information.

[0095] Optionally, the device also includes: a network construction acquisition module, which is used to: after obtaining the community clustering results of each city node in the logistics network and the core nodes of each community, screen the hub nodes of the logistics network from the core nodes of each community; use the network formed by connecting each hub node as the trunk network of the logistics network, and use the network formed by connecting the hub node and other city nodes in the community where it is located as the branch network of the logistics network, so as to obtain a logistics network with a hub-and-spoke structure.

[0096] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for logistics network management, including:

[0097] one or more processors;

[0098] a storage device for storing one or more programs,

[0099] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0100] 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.

[0101] Figure 4 An exemplary system architecture 400 is shown to which the method or apparatus for logistics network management according to an embodiment of the present invention may be applied.

[0102] like Figure 4As shown, system architecture 400 may include terminal devices 401, 402, 403, network 404 and server 405. Network 404 is used to provide a medium for communication links between terminal devices 401, 402, 403 and server 405. Network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0103] Users can use terminal devices 401, 402, 403 to interact with server 405 through network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, 403, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0104] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0105] The server 405 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 401, 402, and 403. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0106] It should be noted that the method for logistics network management provided in the embodiment of the present invention is generally executed by the server 405 , and accordingly, the device for logistics network management is generally set in the server 405 .

[0107] It should be understood that Figure 4 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.

[0108] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of a terminal device suitable for implementing an embodiment of the present invention. Figure 5 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0109] like Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0110] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0111] In particular, according to the embodiments disclosed in the present invention, 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 invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a 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 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0112] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, 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 invention, 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 invention, 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.

[0113] 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 invention. 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.

[0114] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be arranged in a processor, for example, may be described as: a processor including: an association determination module, an adjacency matrix determination module and a node clustering module. The names of these modules do not constitute a limitation on the modules themselves in certain cases, for example, the association determination module may also be described as a "module for clustering the initial adjacency matrix using a graph theory algorithm".

[0115] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being 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 a device, the device includes: determining the correlation between different city nodes in the logistics network based on the cargo volume information, and obtaining the correlation matrix between different city nodes in the logistics network; using the correlation matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network, and constructing the initial adjacency matrix of the logistics network; clustering the initial adjacency matrix using a graph theory algorithm to obtain the community clustering results of each city node in the logistics network and the core nodes of each community.

[0116] According to the technical solution of the embodiment of the present invention, the correlation between different city nodes in the logistics network is determined based on the cargo volume information, and the correlation matrix between different city nodes in the logistics network is obtained. The correlation matrix between different city nodes in the logistics network is used as the weighted value of the link relationship between different city nodes in the logistics network to construct the initial adjacency matrix of the logistics network, and the initial adjacency matrix is ​​clustered using a graph theory algorithm to obtain the community clustering results of each city node in the logistics network and the core nodes of each community. The embodiment of the present invention analyzes the community effect of the existing logistics network based on the existing logistics routes and cargo volume information between each city node, and identifies the logistics network nodes as a number of local network structures centered on the core node. Under the premise of comprehensively considering the cargo volume and transportation network between each city node, a scientific logistics hub node selection method can be given, and the community structure finally obtained is consistent with the hub-and-spoke structure in the logistics network, which has good practical value.

[0117] The above specific implementations do not constitute a limitation on the protection scope of the present invention. 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 modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for logistics network management, characterized in that: include: Determine the correlation between different city nodes in the logistics network based on the cargo volume information, and obtain a correlation matrix between different city nodes in the logistics network; Using the association degree matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network, constructing the initial adjacency matrix of the logistics network; The initial adjacency matrix is ​​clustered using a graph theory algorithm to obtain community clustering results of each city node in the logistics network and the core nodes of each community.

2. The method according to claim 1, characterized in that Determine the correlation between different city nodes in the logistics network based on cargo volume information, including: Determine the discrete probability distribution of the local area network of each of the city nodes in the logistics network according to the cargo volume information; According to the discrete probability distribution corresponding to any two city nodes in the logistics network, the correlation degree between the any two city nodes is determined.

3. The method according to claim 1, characterized in that Determining the discrete probability distribution of the local area network of each of the city nodes in the logistics network according to the cargo volume information includes: Determine the cargo flow output capacity of each city node in the local area network; the cargo flow output capacity is used to indicate the capacity of the corresponding city node to output cargo to the city node directly adjacent to it; Determine the cargo flow input capacity of each city node in the local area network, and determine the comprehensive cargo flow input capacity of the local area network according to the cargo flow input capacity of each city node in the local area network; the cargo flow input capacity is used to indicate the ability of the corresponding city node to receive cargo input from the city node directly adjacent to it; Determine the discrete probability of each city node in the local area network according to the comprehensive cargo flow input capacity of the local area network and the cargo flow output capacity of each city node in the local area network; The discrete probability distribution of the local area network is determined according to the discrete probability of each city node in the local area network.

4. The method according to claim 2, characterized in that Determining the correlation between any two city nodes according to the discrete probability distribution corresponding to any two city nodes in the logistics network includes: The relative entropy of the discrete probability distribution corresponding to any two city nodes in the logistics network is determined, and the correlation between the any two city nodes is determined according to the relative entropy.

5. The method according to claim 1, characterized in that The graph theory algorithm is a Markov clustering algorithm.

6. The method according to claim 1, characterized in that Before determining the correlation between different city nodes in the logistics network based on the cargo volume information, the method further includes: The cargo volume information between different city nodes in the logistics network is determined according to the number of routes and the route transportation volume between different city nodes in the logistics network.

7. The method according to any one of claims 1 to 6, characterized in that: After obtaining the community clustering results of each city node in the logistics network and the core nodes of each community, the method further includes: Selecting the hub nodes of the logistics network from the core nodes of each community; The network formed by connecting various hub nodes is used as the trunk network of the logistics network, and the network formed by connecting the hub node with other city nodes in its community is used as the branch network of the logistics network, thus obtaining a logistics network with a hub-and-spoke structure.

8. A device for logistics network management, characterized in that: include: A correlation determination module, which determines the correlation between different city nodes in the logistics network based on the cargo volume information, and obtains a correlation matrix between different city nodes in the logistics network; An adjacency matrix determination module, using the association matrix between different city nodes in the logistics network as the weighted value of the link relationship between different city nodes in the logistics network, to construct an initial adjacency matrix of the logistics network; The node clustering module uses a graph theory algorithm to perform clustering processing on the initial adjacency matrix to obtain the community clustering results of each city node in the logistics network and the core nodes of each community.

9. An electronic device for logistics network management, 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 7.

10. 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 7 is implemented.

Images