Method and apparatus for managing a logistics network

Abstract

The application discloses a method and device for logistics network management, and relates to the technical field of logistics management. A specific embodiment of the method comprises the following steps: determining the correlation degree between different city nodes in a logistics network based on cargo volume information, and obtaining a correlation degree matrix between the different city nodes in the logistics network; taking the correlation degree matrix between the different city nodes in the logistics network as a weighted value of a link relationship between the different city nodes in the logistics network, and constructing an initial adjacency matrix of the logistics network; and performing clustering processing on the initial adjacency matrix by using a graph theory algorithm, and obtaining a community clustering result of each city node in the logistics network and core nodes of each community. The embodiment can give a scientific logistics hub node selection method under the premise of comprehensively considering the cargo volume and the transportation network between the city nodes, and the finally obtained community structure is consistent with the hub-and-spoke structure in the logistics network, and has good practical value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of logistics management, and in particular to a logistics network management method and device. BACKGROUND

[0002] The commonly used methods for selecting a city as a logistics center include the gravity method, the combination prediction method, the analytic hierarchy process method, etc. The gravity method only considers the influence of geographical location, and has great limitations. The selected location often needs to be adjusted for many times. The combination prediction method can predict the future economic development trend of a city or region in the economic dimension, but the considered factors are also single, and the feasibility of the obtained conclusion is also limited. The analytic hierarchy process method can consider various qualitative analysis factors such as politics, economy, and geographical location, but it strongly depends on expert scoring in the actual execution process, and has certain subjectivity and cannot be eliminated. Therefore, the applicability of the above methods is poor. SUMMARY

[0003] Therefore, the embodiments of the present application provide a logistics network management method and device, which can give a scientific logistics hub node selection method under the premise of comprehensively considering the freight volume and transportation network between city nodes, and the obtained community structure 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 an aspect of the embodiments of the present application, a logistics network management method is provided, comprising:

[0005] determining the correlation degree between different city nodes in the logistics network based on the freight volume information, to obtain a correlation degree matrix between different city nodes in the logistics network;

[0006] taking the correlation 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;

[0007] performing clustering processing on the initial adjacency matrix by using a graph theory algorithm, to obtain the community clustering result of each city node in the logistics network and the core node of each community.

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

[0009] Optionally, the discrete probability distribution of the local network of each city node in the logistics network is determined according to the cargo volume information, including:

[0010] The cargo flow output capacity of each city node in the local network is determined; the cargo flow output capacity is used to indicate the ability of the corresponding city node to output cargo to the city node directly adjacent thereto;

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

[0012] The discrete probability of each city node in the local network is determined according to the comprehensive cargo flow input capacity of the local network and the cargo flow output capacity of each city node in the local network.

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

[0014] Optionally, the correlation degree between any two city nodes in the logistics network is determined according to the discrete probability distribution corresponding to the any two city nodes, including: determining the relative entropy of the discrete probability distribution corresponding to the any two city nodes in the logistics network, and determining the correlation degree between the 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 degree between different city nodes in the logistics network based on the cargo volume information, the method further includes: determining the cargo volume information between different city nodes in the logistics network according to the number of routes and the route transportation volume between different city nodes in the logistics network.

[0017] Optionally, after obtaining the community clustering result of each city node in the logistics network and the core node of each community, the method further includes: screening the hub node of the logistics network from the core node of each community; taking the network formed by connecting each hub node as the trunk network of the logistics network, and taking the network formed by connecting the hub node and other city nodes in the community where the hub node is located as the branch network of the logistics network, to obtain the logistics network with a hub-and-spoke structure.

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

[0019] The correlation degree determination module determines the correlation degrees between different city nodes in the logistics network based on the freight volume information, to obtain a correlation degree matrix between different city nodes in the logistics network.

[0020] The adjacency matrix determination module takes the correlation degree matrix between different city nodes in the logistics network as a weighted value of a link relationship between different city nodes in the logistics network, and constructs an initial adjacency matrix of the logistics network.

[0021] The node clustering module performs clustering processing on the initial adjacency matrix by using a graph theory algorithm, to obtain a social community clustering result of each city node in the logistics network and a core node of each social community.

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

[0023] Optionally, the correlation degree determination module determines the discrete probability distribution of the local network of each city node in the logistics network according to the freight volume information, including:

[0024] determining a freight flow output capacity of each city node in the local network; the freight flow output capacity is used to indicate an ability of the corresponding city node to output freight to a directly adjacent city node;

[0025] determining a freight flow input capacity of each city node in the local network, and determining a comprehensive freight flow input capacity of the local network according to the freight flow input capacities of each city node in the local network; the freight flow input capacity is used to indicate an ability of the corresponding city node to receive input of freight from a directly adjacent city node;

[0026] determining a discrete probability of each city node in the local network according to the comprehensive freight flow input capacity of the local network and the freight flow output capacities of each city node in the local network;

[0027] determining the discrete probability distribution of the local network according to the discrete probabilities of each city node in the local network.

[0028] Optionally, the correlation degree determination module determines the correlation degrees between any two city nodes in the logistics network according to the discrete probability distributions corresponding to the any two city nodes, including: determining a relative entropy of the discrete probability distributions corresponding to any two city nodes in the logistics network, and determining the correlation degrees between the any two city nodes according to the relative entropy.

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

[0030] Optionally, the apparatus further comprises an information acquisition module configured to: before determining the correlation degree between different city nodes in the logistics network based on the freight volume information, determine the freight volume information between different city nodes in the logistics network according to the number of routes and the route transportation volume between different city nodes in the logistics network.

[0031] Optionally, the apparatus further comprises a network construction acquisition module configured 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; take the network formed by each hub node as the trunk network of the logistics network, and take the network formed by the hub nodes and other city nodes in the community as the branch network of the logistics network, to obtain the logistics network with a hub-and-spoke structure.

[0032] According to a third aspect of the embodiments of the present application, an electronic device for logistics network management is provided, comprising:

[0033] one or more processors;

[0034] a storage device configured to store 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 by the first aspect of the embodiments of the present application.

[0036] According to a fourth aspect of the embodiments of the present application, a computer readable medium is provided, which stores a computer program, and the program is executed by a processor to implement the method provided by the first aspect of the embodiments of the present application.

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

[0038] Further effects of the above non-conventional optional mode will be described in the following in conjunction with the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0039] The accompanying drawings are used to better understand the application and do not constitute undue limitations on the application. Among them:

[0040] Figure 1 is a schematic diagram of the main process of the logistics network management method of the embodiment of the application;

[0041] Figure 2 is a structural schematic diagram of a local network of a city node in an optional embodiment of the application;

[0042] Figure 3 is a schematic diagram of the main modules of the logistics network management device of the embodiment of the application;

[0043] Figure 4 is an exemplary system architecture diagram to which the embodiment of the application can be applied;

[0044] Figure 5 is a structural schematic diagram of a computer system of a terminal device or a server suitable for implementing the embodiment of the application. DETAILED DESCRIPTION

[0045] The exemplary embodiments of this application are described herein with reference to the accompanying drawings, which are meant to be exemplary. Therefore, various changes and modifications can be made to the embodiments described herein without departing from the spirit and scope of this application. For clarity and conciseness, descriptions of well-known functions and constructions are omitted.

[0046] According to an aspect of the embodiments of the present application, there is provided a method for logistics network management.

[0047] Figure 1 is a schematic diagram of the main flow of the method for logistics network management according to the embodiments of the present application. As shown in Figure 1 The method for logistics network management comprises steps S101, S102 and S103.

[0048] In step S101, the correlation between different city nodes in the logistics network is determined based on cargo volume information, to obtain a correlation matrix between different city nodes in the logistics network.

[0049] The cargo volume information refers to the information of cargo transmission volume between city nodes, such as the information of cargo output volume and / or cargo inflow volume. In actual application, the cargo volume information can be determined according to historical data before determining the correlation between different city nodes in the logistics network based on the cargo volume information, such as determining the above cargo volume information according to the monthly average cargo transmission volume in the past half year or one year. In optional embodiments, 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 before determining the correlation between different city nodes in the logistics network based on the cargo volume information. Exemplarily, the logistics network comprises city node 1 and city node 2, and the cargo volume information between city node 1 and city node 2 is determined according to the number of routes between city node 1 and city node 2 and the route transportation volume of each route.

[0050] The more the cargo transmission volume between two city nodes, the closer the cargo flow relationship between them, and the higher the corresponding correlation. In some optional embodiments, the correlation between two city nodes is directly determined according to the cargo volume information between them, such as making the correlation between them positively correlated with the cargo volume information between them.

[0051] In other optional embodiments, determining the correlation between different city nodes in the logistics network based on the cargo volume information comprises: 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 two city nodes.

[0052] For any one 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, as shown in the following figure. Figure 2 The embodiment of the present application splits the logistics network into a network structure with a city node as the hub and a radius of 1, where the radius refers to the number of times of transfer needed to reach another city node from a city node. The smallest network structure that can be obtained by splitting a logistics network is the 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. That is, 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 in the local area network. The more the 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 degree, and the denser the local area network. The less the 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 degree, and the more discrete the local area network.

[0053] The embodiment can more accurately reflect the correlation degree between different city nodes by considering the cargo volume and transportation network between city nodes, by determining the correlation degree between any two city nodes according to the discrete probability distribution of the local area network of each city node and the discrete probability distribution corresponding to the two city nodes.

[0054] For any one 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 can include:

[0055] determining 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 ability of the corresponding city node to receive cargo input from city nodes directly adjacent to it. It should be noted that when determining the cargo flow input capacity of city node j in the local area network of city node i , the above "city nodes directly adjacent to it" can only refer to city nodes directly adjacent to it within the local area network of city node i, or can include city nodes directly connected to it within the local area network of city node i and city nodes directly adjacent to it outside the local area network of city node i. For example, Figure 2For example, in the schematic diagram in FIG. 1, the central city node is connected with 5 other city nodes, and the theoretical freight flow input capacity of the central city node is the sum of the freight volumes output from the 5 other city nodes to the central city node. According to the freight flow input capacity of each city node j in the local network of city node i The comprehensive freight flow input capacity D of the local network of city node i is determined i The comprehensive freight flow input capacity D i is positively correlated with the freight flow input capacity of each city node j For example:

[0056] The freight flow output capacity of each city node j in the local network is determined The freight flow output capacity is used to indicate the capacity of the corresponding city node to output freight to the city nodes directly adjacent thereto. It should be noted that when determining the freight flow output capacity of city node j in the local network of city node i , the “city nodes directly adjacent thereto” can refer only to the city nodes directly adjacent thereto within the local network of city node i, or can refer to both the city nodes directly adjacent thereto within the local network of city node i and the city nodes directly adjacent thereto outside the local network of city node i. For example, Figure 2 in the schematic diagram in FIG. 1, the central city node is connected with 5 other city nodes, and the theoretical freight flow output capacity of the central city node is the sum of the freight volumes output from the central city node to the 5 other city nodes adjacent thereto;

[0057] The comprehensive freight flow input capacity D of the local network of city node i i , and the freight flow output capacity of each city node j in the local network The discrete probability p of each city node in the local network is determined i (j); p i (j) is calculated according to the following formula:

[0058] According to the discrete probability of each city node in the local network, the discrete probability distribution P of the local 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 network, the discrete probability of each city node in the local network can also be sorted, for example, in descending order or in ascending order.

[0059] The method used in this embodiment to determine the discrete probability distribution of the local area network 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 urban commercial flow relationship and logistics links.

[0060] While the above example provides a specific implementation 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 reflects the discrete distribution of the local area network. This embodiment of the invention does not limit the specific implementation for determining the discrete probability distribution. For example, in the aforementioned example of determining the discrete probability distribution of a local area network:

[0061] The comprehensive freight input capacity D of the local area network of city node i is not based on the city node i. i and the cargo flow output capability 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 rather based on the freight output capacity of each city node j in the local area network of city node i. Determine the comprehensive freight output capacity D of the local area network of city node i. i ′ Comprehensive cargo flow output capacity D i ′ The cargo flow output capacity of each city node j Positive correlation, for example: Then, based on the comprehensive freight output capacity D of the local area network of city node i... i ′ And the cargo flow input capability 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 formula for calculating (j) is:

[0062] In this embodiment of the invention, in order to facilitate the analysis of the degree of correlation 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 can be further standardized.

[0063] In the embodiment of the present application, the manner of determining the correlation degree between any two city nodes can be selectively set, as long as the close degree of the freight flow relationship between the two can be reflected, and the specific implementation manner of determining the correlation degree is not limited in the embodiment of the present application. Alternatively, the correlation degree between any two city nodes in the logistics network is determined according to the discrete probability distribution corresponding to the two city nodes, comprising: 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 degree between the two city nodes according to the Shannon entropy or relative entropy. The relative entropy, also known as the KL divergence, is an important method of information theory and one of the important extensions of the Shannon entropy. The greater the Shannon entropy or relative entropy, the higher the correlation degree of the two city nodes in the logistics network.

[0064] In step S102, the initial adjacency matrix of the logistics network is constructed by taking the correlation degree matrix between different city nodes in the logistics network as the weighted value of the link relationship between the different city nodes.

[0065] The element in the adjacency matrix refers to the link relationship between the row and column city nodes, and the correlation degree between adjacent city nodes in the logistics network is taken as the weight on the corresponding edge in the adjacency matrix to construct the initial adjacency matrix between the city nodes. By performing the correlation degree calculation between the city nodes based on the freight information in advance when constructing the initial adjacency matrix, the conclusion obtained by using the graph algorithm for clustering processing can better reflect the actual freight flow situation between the city nodes, instead of only considering whether the city nodes are connected to each other, so that the method can be used to better select the hub nodes of the logistics network.

[0066] In step S103, the initial adjacency matrix is clustered by using a graph algorithm to obtain the community clustering result of each city node in the logistics network and the core node of each community.

[0067] The graph algorithm includes various algorithms, which can be selected by a person skilled in the art according to the actual situation. For example, the graph algorithm is a Markov clustering algorithm or a minimum spanning tree algorithm. The Markov clustering algorithm (MCL) is one of the graph algorithms. The core of the MCL algorithm is to simulate the process of continuous iteration and continuous random walk of random flow in a complex network, and its theoretical basis is that, when randomly walking in a network G, if the walk reaches a dense subgraph, the walk will not go out of the subgraph unless most of the nodes in the subgraph have been visited. The MCL algorithm simulates the random flow of random flow in a network, that is, a random walk of random flow in a network graph G is a process of starting from a certain node, jumping to the next adjacent node according to a certain probability, and stopping until jumping to a node.

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

[0069] According to the initial adjacency matrix E, the expansion coefficient k (adaptively set), the inflation coefficient γ (adaptively set), the MCL clustering algorithm is used to process as follows:

[0070] 1. Column standardization operation is performed on the initial adjacency matrix E to obtain matrix T 2k ;

[0071] 2. Expansion operation is performed on matrix T 2k to obtain matrix The expansion process is adjacency matrix multiplication, which is used to simulate the random walk process of random flow in the network, so that the adjacency matrix has homogeneity. After the column standardization operation of the adjacency matrix, the power operation of the matrix can be performed, E exp = M k , where the value of k represents the expansion coefficient. When the expansion coefficient k = 2, it represents the probability of E(i,j) reaching node j from node i through 1 step. When the expansion coefficient k = 3, it represents the probability of E(i,j) reaching node j from node i through 2 steps. When the expansion coefficient k is larger, the number of steps through is larger, which will make the probability of E(i,j) leaving the current cluster and entering another cluster larger. As can be seen, with the increase of the expansion coefficient k, the tightness between the same clusters will become weaker.

[0072] 3. Inflation operation is performed on matrix to obtain matrix The inflation process is the power operation of each element in the matrix, and 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 process of inflation operation is to perform matrix point multiplication, and then perform column normalization operation. The inflation coefficient γ represents the number of point multiplications, and the larger the inflation coefficient γ, the smaller the granularity of the obtained clustering result;

[0073] 4. Column standardization operation is performed on matrix to obtain matrix T 2k+1 ;

[0074] 5. The Euclidean distance between matrix T 2k+1 and matrix T 2k is calculated. If the distance is not 0, matrix T 2k+1 is taken as the new matrix T 2kSteps 2, 3 and 4 are repeated for multiple iterations until the Euclidean distance calculated in step 5 is 0, and the matrix converges. In actual application, to speed up the convergence of the matrix, a correction value can be set, and when the Euclidean distance calculated in step 5 is less than the correction value, the matrix is processed, and the elements in the matrix that are already very small are modified to 0.

[0075] 6. Output the community clustering result of each city node and the core node of each community, and the core node is the city node recommended as the hub node in the logistics network.

[0076] The commonly used methods for selecting a city as a hub node of logistics network include the gravity method, the combination prediction method, the analytic hierarchy process and the like. The gravity method only considers the influence of geographical position, and has great limitations, and the finally selected position often needs to be adjusted for multiple times. The combination prediction method can predict the future economic development trend of a city or region in the economic dimension, but the considered factors are also single, and the feasibility of the obtained conclusion is also limited. Although the analytic hierarchy process can consider various qualitative analysis factors such as politics, economy and geographical position, it strongly depends on expert scoring in actual execution process, and has certain subjectivity and cannot be eliminated. Moreover, the analytic hierarchy process, the gravity method and the combination prediction method do not analyze the network structure, but directly give the recommended city node, and the conclusion obtained by these methods cannot reflect what the relationship of the city node in the logistics network is like, and the community structure cannot be obtained. In addition, since there are many selectable cities for the hub node in the international logistics business scenario, it is difficult to keep using a unified standard and comprehensively consider various factors to compare each city, and the logistics center selected by the above existing technologies is also difficult to scientifically explain the radiation range of the surrounding cities, and the applicability in the international scenario 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 center node. Based on this, the embodiment of the present application proposes a logistics site selection scheme based on graph theory algorithm, which mainly includes two steps: the first step is to calculate the correlation degree of the discrete probability distribution between any two city nodes in the logistics network using the cargo volume information between the city nodes in the logistics network, and the greater the correlation degree, the higher the correlation degree of the two city nodes in the logistics network, and the correlation degree is used as the initial adjacency matrix of the graph theory algorithm, and the initial transition probability matrix is obtained by performing column standardization operation on the initial adjacency matrix, and then the subsequent calculation is completed using the graph theory algorithm, so that the community classification result of the city group can be obtained, and the city nodes in the same community represent that the cargo flow relationship between these cities is close.

[0078] In the embodiments of the present application, 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 be screened from the core nodes of each community, for example, taking the core nodes of each community as hub nodes respectively, or taking the core nodes of part of the communities as hub nodes, then taking the network formed by connecting each hub node as the trunk network of the logistics network, and taking the network formed by connecting the hub nodes with other city nodes of the community where the hub nodes are located as the branch network of the logistics network, to obtain the logistics network with hub-and-spoke structure. When only part of the communities obtained by clustering and their core nodes are taken as the branch network and the hub nodes, each city node in the unselected community can be included in the branch network to which the city node directly adjacent to is included, and if there is a city node in the unselected community which 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. Exemplarily, when cross-border goods are transported, no matter from which city in G1 country the goods are originated, the goods will be first collected to a city g1 in G1 country, and the city g1 is the hub node of the logistics network in G1 country. The goods are not directly transported from the city g1 to each city in G2 country, but are first transported from the city g1 to a city g2 in G2 country, and then are distributed from the city g2 to the specific destination city, which is the hub-and-spoke network, and the cities g1 and g2 are the core nodes or hub nodes of the logistics network. The present application analyzes the community effect of the existing logistics network through the existing logistics routes and the cargo volume between cities, identifies the city nodes in the logistics network as a local network structure with core nodes as the center, and the core node in the community composed of several city nodes is the candidate logistics hub node identified based on the present application. The present application can give a scientific hub node selection method under the premise of comprehensively considering the cargo volume and transportation network between cities, and the finally obtained community structure is consistent with the hub-and-spoke structure of the logistics network, and has good practical value.

[0080] In the embodiments of the present application, the cargo volume information between each city node is used to determine the correlation degree between the city nodes, and the initial adjacency matrix is generated by taking the correlation degree as the weighted value of the logistics link relationship between each city node in the logistics network, and the city group clustering result based on the real city commodity flow relationship and the logistics link can be obtained by processing the initial adjacency matrix through the graph theory algorithm, and has good practical value.

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

[0082] Figure 3 is a schematic diagram of main modules of the device for logistics network management according to an embodiment of the present application. As shown in Figure 3 the device for logistics network management 300 comprises:

[0083] a correlation degree determination module 301 configured to determine the correlation degrees between different city nodes in the logistics network based on the freight volume information, and obtain a correlation degree matrix between different city nodes in the logistics network;

[0084] a neighborhood matrix determination module 302 configured to take the correlation degree matrix between different city nodes in the logistics network as a weighted value of a link relationship between different city nodes in the logistics network, and construct an initial neighborhood matrix of the logistics network;

[0085] a node clustering module 303 configured to perform clustering processing on the initial neighborhood matrix by using a graph theory algorithm, and obtain a social community clustering result of each city node in the logistics network and a core node of each social community.

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

[0087] Optionally, the correlation degree determination module determines the discrete probability distribution of the local network of each city node in the logistics network according to the freight volume information, including:

[0088] determining a freight flow output capacity of each city node in the local network; the freight flow output capacity is used to indicate an ability of the corresponding city node to output freight to a directly adjacent city node;

[0089] determining a freight flow input capacity of each city node in the local network, and determining a comprehensive freight flow input capacity of the local network according to the freight flow input capacities of each city node in the local network; the freight flow input capacity is used to indicate an ability of the corresponding city node to receive input of freight from a directly adjacent city node;

[0090] determining a discrete probability of each city node in the local network according to the comprehensive freight flow input capacity of the local network and the freight flow output capacities of each city node in the local network;

[0091] determining a discrete probability distribution of the local network according to the discrete probabilities of each city node in the local network.

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

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

[0094] Optionally, the apparatus further comprises an information acquisition module configured to: before determining the correlation degree between different city nodes in the logistics network based on the cargo volume information, determine the cargo volume information between different city nodes in the logistics network according to the number of routes and the route transportation volume between different city nodes in the logistics network.

[0095] Optionally, the apparatus further comprises a network construction acquisition module configured 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; take the network formed by connecting each hub node as the trunk network of the logistics network, and take the network formed by connecting the hub node and other city nodes in the community as the branch network of the logistics network, to obtain the logistics network with a hub-and-spoke structure.

[0096] According to a third aspect of the embodiments of the present application, an electronic device for logistics network management is provided, comprising:

[0097] one or more processors;

[0098] a storage device configured to store 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 by the first aspect of the embodiments of the present application.

[0100] According to a fourth aspect of the embodiments of the present application, a computer readable medium is provided, which stores a computer program, and the program is executed by a processor to implement the method provided by the first aspect of the embodiments of the present application.

[0101] Figure 4 An exemplary system architecture 400 is shown, which can apply the method for logistics network management or the apparatus for logistics network management according to the embodiments of the present application.

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

[0103] The users can use the terminal devices 401, 402, 403 to interact with the server 405 through the network 404 to receive or send messages, etc. Various communication client applications can be installed on the 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, 403 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers and desktop computers, etc.

[0105] The server 405 can be a server providing various services, such as a background management server supporting shopping websites browsed by users using the terminal devices 401, 402, 403 (only as an example). The background management server can analyze and process received product information query requests and other data, and feed back the processing results (such as target push information, product information - only as examples) to the terminal devices.

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

[0107] It should be understood that the number of terminal devices, networks and servers in the system architecture 400 is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks and servers. Figure 4

[0108] The following refers to Figure 5 which shows a structural schematic diagram of a computer system 500 of a terminal device suitable for implementing the embodiments of the present application. Figure 5 The terminal device shown is only an example and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0109] As Figure 5 ​As shown, the computer system 500 includes a central processing unit (CPU) 501 which can perform various appropriate actions and processes in accordance with programs stored in a read only memory (ROM) 502 or loaded from a storage section 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 through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0110] Connected to the I / O interface 505 are an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a display such as 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 necessary. A removable recording medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 510 as necessary, so that a computer program read therefrom is installed into the storage section 508 as necessary.

[0111] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with the embodiments disclosed herein. For example, the embodiments disclosed herein include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 509 and / or installed from the removable recording medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-described functions defined in the system of the present application are performed.

[0112] It should be noted that the computer-readable medium shown in the present application can 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, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, 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, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component. In the present application, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or component. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0113] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code containing one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different order than that shown in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0114] The modules described in the embodiments of the present application can be implemented in the form of software or hardware. The modules described can also be arranged in a processor, for example, a processor can be described as including a correlation degree determining module, an adjacency matrix determining module and a node clustering module. In some cases, the names of the modules do not constitute a limitation on the modules themselves, for example, the correlation degree determining module can also be described as a module that performs clustering processing on the initial adjacency matrix using a graph theory algorithm.

[0115] As another aspect, the present application also provides a computer readable medium, which can be included in the device described in the above embodiments or exist independently without being assembled into the device. The computer readable medium carries one or more programs, which, when executed by the device, cause the device to include: determining correlations between different city nodes in a logistics network based on freight volume information to obtain a correlation matrix between different city nodes in the logistics network; constructing an initial adjacency matrix of the logistics network by taking the correlation matrix between different city nodes in the logistics network as a weighted value of a link relationship between the different city nodes in the logistics network; and performing clustering processing on the initial adjacency matrix using a graph theory algorithm to obtain a community clustering result of the city nodes in the logistics network and core nodes of each community.

[0116] According to the technical solution of the embodiments of the present application, the correlations between different city nodes in a logistics network are determined based on freight volume information to obtain a correlation matrix between different city nodes in the logistics network, an initial adjacency matrix of the logistics network is constructed by taking the correlation matrix between different city nodes in the logistics network as a weighted value of a link relationship between the different city nodes in the logistics network, clustering processing is performed on the initial adjacency matrix using a graph theory algorithm to obtain a community clustering result of the city nodes in the logistics network and core nodes of each community. The embodiments of the present application analyze the community effect of an existing logistics network according to the existing logistics routes and freight volume information between the city nodes, identify the logistics network nodes as a number of local network structures centered on core nodes, can give a scientific logistics hub node selection method under the premise of comprehensively considering the freight volume and transportation network between the city nodes, and the finally obtained community structure is consistent with the hub-and-spoke structure in the logistics network, which has good practical value.

[0117] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made depending on design requirements and other factors. Any modification, equivalent replacement and improvement made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for logistics network management, characterized in that, include: Based on cargo volume information, the correlation degree between different city nodes in the logistics network is determined, and the correlation degree matrix between different city nodes in the logistics network is obtained. The initial adjacency matrix of the logistics network is constructed by using the correlation degree matrix between different city nodes in the logistics network as the weighting value of the link relationship between different city nodes in the logistics network. 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.

2. The method as described in claim 1, characterized in that, Determining the correlation between different city nodes in the logistics network based on cargo volume information includes: Based on the cargo volume information, determine the discrete probability distribution of the local area network of each city node in the logistics network; The degree of correlation between any two city nodes is determined based on the discrete probability distributions corresponding to any two city nodes in the logistics network.

3. The method as described in claim 2, characterized in that, Determining the discrete probability distribution of the local area network of each city node in the logistics network based on the cargo volume information includes: Determine the cargo output capacity of each city node in the local area network; the cargo output capacity is used to indicate the ability of the corresponding city node to output cargo to its directly adjacent city nodes; The freight input capacity of each city node in the local area network is determined, and the overall freight input capacity of the local area network is determined based on the freight input capacity of each city node in the local area network; the freight input capacity is used to indicate the ability of the corresponding city node to receive freight input from its directly adjacent city nodes; Based on 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 of each city node in the local area network is determined. The discrete probability distribution of the local area network is determined based on the discrete probability of each city node in the local area network.

4. The method as described in claim 2, characterized in that, Based on the discrete probability distributions corresponding to any two city nodes in the logistics network, the correlation degree between any two city nodes is determined, including: Determine the relative entropy of the discrete probability distributions corresponding to any two city nodes in the logistics network, and determine the correlation degree between the two city nodes based on the relative entropy.

5. The method as described in claim 1, characterized in that, The graph theory algorithm mentioned is the Markov clustering algorithm.

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

7. The method according to any one of claims 1-6, 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: Select hub nodes for the logistics network from the core nodes of each community; The logistics network is formed by connecting various hub nodes as the trunk network and by connecting the hub nodes with other city nodes in their respective communities as the branch network, thus obtaining a hub-and-spoke logistics network.

8. A device for logistics network management, characterized in that, include: The correlation determination module determines the correlation between different city nodes in the logistics network based on cargo volume information, and obtains the correlation matrix between different city nodes in the logistics network. The adjacency matrix determination module uses the correlation 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 the initial adjacency matrix of the logistics network. The node clustering module uses graph theory algorithms to cluster the initial adjacency matrix, obtaining 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; 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 as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images