A container port area planning method integrating AIS data

Abstract

The present invention discloses a container port area planning method integrating AIS data, comprising the following steps: constructing a container port area site selection double-layer planning model with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on each port, and constructing a container port area site selection double-layer planning model with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on the replaceable ports of each port; obtaining a port as a container port area site selection by the container port area site selection double-layer planning model, and screening the replaceable ports corresponding to the container port area site selection to obtain the replaceable site selection of the container port area site selection. The present invention realizes the rapid temporary replacement of the port container port area site selection, so that the port collection and distribution maintains stability while maintaining the goal of the lowest collection and distribution cost and the highest collection and distribution container carrying capacity.

Description

Technical Field

[0001] The present invention relates to the technical field of port planning, and in particular to a container port area planning method integrating AIS data. Background Art

[0002] With the continuous expansion of China's international trade, port services play an increasingly important role. In recent years, there have been certain research results on port collection and distribution networks and related issues. Pan Jingjing and others created a linear integer programming model with the operating capacity of the transshipment nodes and the line transportation capacity in the network as constraints and the goal of minimizing the total network transportation cost, and studied the reasonable allocation of container cargo flow in the seaport collection and distribution network; WANG and others considered the time window constraint when establishing the cargo flow allocation model, so that the model can better optimize the road and rail transportation problems of containers.

[0003] Existing port planning technologies are all based on optimizing the design of port collection and distribution networks from the perspective of port operators. When selecting the site for the port container port area, the stability of port collection and distribution is ignored, resulting in instability in collection and distribution. Summary of the invention

[0004] The purpose of the present invention is to provide a container port area planning method integrating AIS data to solve the technical problem that in the prior art, the stability of port collection and distribution is neglected in the site selection of the port container port area after a failure, resulting in instability of collection and distribution.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

[0006] A container port area planning method integrating AIS data includes the following steps:

[0007] Step S1: Count all ports in the planned area and obtain AIS data and container traffic flow of each port;

[0008] Step S2: quantify the substitutability of each port in the planning area in turn based on AIS data and container traffic flow to obtain alternative ports for each port;

[0009] Step S3, constructing a double-layer planning model for container port site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on each port, and constructing a double-layer planning model for container port site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on the replaceable ports of each port;

[0010] Step S4, using the double-layer planning model for container port site selection to obtain a port as the container port site selection, and screening the replaceable ports corresponding to the container port site selection to obtain the replaceable site selection for the container port site selection, so as to improve the replaceability of the container port area and reduce the instability of collection and distribution caused by port failure.

[0011] As a preferred solution of the present invention, the acquisition of container traffic flow includes:

[0012] Obtain the container carrying capacity of each port within a time series to obtain the container carrying capacity time series data;

[0013] The container carrying capacity time series data is rearranged from small to large according to the container carrying capacity to obtain the container traffic flow, and the container traffic flow is used to characterize the incremental trend of the container carrying capacity at the port.

[0014] As a preferred solution of the present invention, the method of quantifying the substitutability of each port in the planning area in turn based on AIS data and container traffic flow to obtain the replaceable ports of each port includes:

[0015] Set the substitutability weights of AIS data and container traffic flow, and apply the substitutability weights to AIS data and container traffic flow;

[0016] Based on the weighted AIS data and container traffic flow, the similarities of any two ports are quantified in turn as the substitutability of any two ports. The quantitative formula of the substitutability is:

[0017] I ij =|W1*D AIS,i -W1*D AIS,j |+|W2*D trend,i -W2*D trend,j |;

[0018] In the formula, I ij is the substitutability of port i and port j, D AIS,i is the AIS data of port i, D AIS,j is the AIS data of port j, D trend,i is the container traffic volume at port i, D trend,j is the container traffic flow of port j, W1 is the replaceable weight of AIS data, W2 is the replaceable weight of container traffic flow, |W1*D AIS,i -W2*D AIS,j | is W1*D AIS,i and W2*D AIS,j Euclidean distance, |W1*D trend,i -W2*D trend,j | is W1*D trend,iand W2*D trend,j The Euclidean distance of , i, j are port count variables;

[0019] Set the selection threshold of alternatives, where

[0020] When the substitutability between two ports is greater than or equal to the selection threshold, a connection edge is set between the two ports;

[0021] When the substitutability between two ports is less than the selection threshold, no connection edge is set between the two ports;

[0022] The ports are taken as network nodes, and the network nodes are connected according to the connection edges to obtain the substitutability network. The community analysis of the substitutability network is performed to obtain multiple substitutability clusters.

[0023] The ports corresponding to the nodes in each replaceable cluster are all interchangeable ports.

[0024] As a preferred solution of the present invention, the construction of the double-layer planning model for container port site selection includes:

[0025] Based on the lowest collection and distribution cost and the highest collection and distribution container carrying capacity of each port, the first-level planning model of the container port area location double-level planning model is constructed. The model expression of the first-level planning model is:

[0026] minF=F1+F2+F3;

[0027]

[0028]

[0029] In the formula, minF is the minimum collection and distribution cost, F1 is the economic cost of collection and distribution, F2 is the time cost of collection and distribution, and P k is the operating cost of port k selected as the container port area, O k is the construction cost of port k selected as the container port area, C a , C b and C c are the unit transportation costs of water, rail and road from port j to port k selected as the container port area, V a 、V b and V c are the unit transport speeds of water, rail and road from port j to port k selected as the container port area, L kj , l kj and h kjare the water, rail and road transport distances from port j to port k selected as the container port area, m is the total number of ports, n is the total number of ports selected as container port areas, k and j are counting variables of ports;

[0030]

[0031] In the formula, maxS is the maximum container load of the distribution transport, ML kj 、Ml kj and Mh kj are the container transport volumes from port j to port k selected as the container port area by water, rail and road respectively;

[0032] Based on the lowest collection and distribution cost and the highest collection and distribution container carrying capacity of each port's alternative ports, the second-level planning model in the container port area location double-level planning model is constructed. The model expression of the second-level planning model is:

[0033] minG=G1+G2+G3;

[0034]

[0035]

[0036] In the formula, minG is the minimum collection and distribution cost of the alternative port, G1 is the economic cost of the collection and distribution of the alternative port, G2 is the time cost of the collection and distribution of the alternative port, and P ky is the operating cost of port y, which is an alternative to port k as the container port site, O ky is the construction cost of alternative port y to port k selected as the container port area, C A , C B and C C are the unit transportation costs of water, rail and road from port j to alternative port y for port k as the container port site, V A 、V B and V C are the unit transport speeds of water, rail and road from port j to alternative port y as the container port site, L kyj , l kyj and h kyj are the water, rail and road transport distances from port j to port k as the container port area, m is the total number of ports, ny is the total number of alternative ports for port k as the container port area, ky is the alternative port y for port k as the container port area, k, y, j are port counting variables;

[0037]

[0038] Where maxZ is the maximum container handling capacity of the replaceable port, ML kyj 、Ml kyj and Mh kyj The container carrying capacity by water, rail and road from port j to alternative port y as the site of port k selected as the container port area.

[0039] As a preferred solution of the present invention, the determination of the location of the container port area includes:

[0040] Taking all ports in the area to be planned as the solution space, the genetic algorithm is used to search and solve the first-level planning model and the second-level planning model, and the ports obtained by the solution are used as the site selection of the container port area.

[0041] As a preferred solution of the present invention, the determination of the alternative site selection of the container port area includes:

[0042] Screening the alternative ports corresponding to the container port area site selection to obtain the alternative site selection for the container port area site selection;

[0043] Obtaining the port throughput time series data of the container port area site selection, and the port throughput time series data of the alternative port corresponding to the container port area site selection, wherein the port throughput time series data of the alternative port lags behind the port throughput time series data of the container port area site selection by a preset time series;

[0044] The failure similarity is measured by comparing the port throughput time series data of the container port area selection with the port throughput time series data of each alternative port corresponding to the container port area selection. The function expression of the failure similarity is:

[0045] J ky =|D tun,k -D tun,y |;

[0046] In the formula, J ky is the failure similarity between port k as the container port site and port y, which is an alternative to port k as the container port site, D tun,k is the port throughput time series data of port k selected as the container port area, D tun,y is the port throughput time series data of port y, which is an alternative to port k selected as the container port area, |D tun,k -D tun,y | for D tun,k and D tun,y The Euclidean distance of

[0047] At each container port site, the alternative port corresponding to the highest failure similarity is selected as the alternative site for each container port site.

[0048] As a preferred solution of the present invention, the entropy weight method is used to set the interchangeability weights of AIS data and container traffic flow.

[0049] As a preferred solution of the present invention, the AIS data and container traffic flow are normalized before the substitutability quantification calculation.

[0050] As a preferred solution of the present invention, the replaceable cluster includes at least one port.

[0051] As a preferred solution of the present invention, when constructing the double-layer planning model for container port site selection, the collection and distribution time cost, the collection and distribution economic cost, and the collection and distribution container carrying capacity are normalized.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention constructs a double-layer planning model for container port area site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on each port, and constructs a double-layer planning model for container port area site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on the replaceable ports of each port. The port is obtained as the container port area site selection by the double-layer planning model, and the replaceable ports corresponding to the container port area site selection are screened to obtain the replaceable site selection of the container port area site selection, thereby realizing rapid temporary replacement of the port container port area site selection, so that the port collection and distribution maintains stability while maintaining the goals of lowest collection and distribution cost and highest collection and distribution container carrying capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0055] Figure 1 A flow chart of a method for planning a port container area provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Existing port planning technologies are all based on the optimization design of port collection and distribution networks from the perspective of port operators. After the port container port area site selection fails, the stability of port collection and distribution is ignored, resulting in instability in collection and distribution. The present invention provides a container port area planning method that integrates AIS data, constructs a two-layer planning model for container port area site selection, and can determine replaceable sites for container port area site selection to ensure that after the container port area site selection fails (when the collection and distribution network deteriorates due to strong winds, heavy fog, earthquakes or some man-made disasters, it will cause the paralysis of the container port area site selection), the port container port area site selection can be quickly replaced temporarily, so that the port collection and distribution maintains stability while maintaining the goals of minimum collection and distribution cost and maximum collection and distribution container carrying capacity.

[0058] like Figure 1 As shown, the present invention provides a container port area planning method integrating AIS data, comprising the following steps:

[0059] Step S1: Count all ports in the planned area and obtain AIS data and container traffic flow of each port;

[0060] Step S2: quantify the substitutability of each port in the planning area in turn based on AIS data and container traffic flow to obtain alternative ports for each port;

[0061] Step S3, constructing a double-layer planning model for container port site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on each port, and constructing a double-layer planning model for container port site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on the replaceable ports of each port;

[0062] Step S4, using the double-layer planning model for container port site selection to obtain a port as the container port site selection, and screening the replaceable ports corresponding to the container port site selection to obtain the replaceable site selection for the container port site selection, so as to improve the replaceability of the container port area and reduce the instability of collection and distribution caused by port failure.

[0063] Substitutability is quantified to select a replacement port for each port, so that in the event of a port failure, the port can be replaced to quickly restore the stability of the collection and distribution network. In addition, when constructing a two-layer planning model for container port site selection, a two-layer planning model is used, in which the first-layer planning model is constructed based on the lowest collection and distribution cost and the highest collection and distribution container carrying capacity of each port itself, and the second-layer planning model is constructed based on the lowest collection and distribution cost and the highest collection and distribution container carrying capacity of the replaceable port of each port. As a result, the container port site selection obtained by the constructed two-layer planning model can achieve the lowest collection and distribution cost and the highest collection and distribution container carrying capacity, and at the same time, the replaceable port of the container port site selection can also achieve the lowest collection and distribution cost and the highest collection and distribution container carrying capacity, realizing rapid temporary replacement of the port container port site selection, so that the port collection and distribution maintains stability while maintaining the goal of the lowest collection and distribution cost and the highest collection and distribution container carrying capacity, that is, the collection and distribution cost can be minimized and the collection and distribution container carrying capacity can be maximized before and after the failure.

[0064] The acquisition of container traffic flow includes:

[0065] Obtain the container carrying capacity of each port within a time series to obtain the container carrying capacity time series data;

[0066] The container traffic flow is obtained by rearranging the container carrying capacity time series data from small to large according to the container carrying capacity. The container traffic flow is used to characterize the incremental trend of the container carrying capacity at the port.

[0067] The present invention can obtain the overall incremental trend of container carrying volume at the port from the time series trend of container carrying volume by rearranging the time series data of container carrying volume. Compared with the traditional time series data trend, the present invention uses container traffic flow to express the overall incremental trend of container carrying volume at the port, while expressing the integrity, avoiding the trend field limitation caused by the time series sequence, so that the subsequent quantification of interchangeability can avoid the influence of the trend field limitation of the time series sequence, thereby improving the accuracy of determining the replaceable ports.

[0068] Based on AIS data and container traffic flow, the substitutability of each port in the planning area is quantified in turn to obtain the alternative ports for each port, including:

[0069] Set the substitutability weights of AIS data and container traffic flow, and apply the substitutability weights to AIS data and container traffic flow;

[0070] Based on the weighted AIS data and container traffic flow, the similarities of any two ports are quantified in turn as the substitutability of any two ports. The quantitative formula for substitutability is:

[0071] I ij =|W1*D AIS,i -W1*D AIS,j |+|W2*D trend,i -W2*D trend,j |;

[0072] In the formula, I ij is the substitutability of port i and port j, D AIS,i is the AIS data of port i, D AIS,j is the AIS data of port j, D trend,i is the container traffic volume at port i, D trend,j is the container traffic flow of port j, W1 is the replaceable weight of AIS data, W2 is the replaceable weight of container traffic flow, |W1*D AIS,i -W2*D AIS,j | is W1*D AIS,i and W2*D AIS,j Euclidean distance, |W1*D trend,i -W2*D trend,j | is W1*D trend,i and W2*D trend,j The Euclidean distance of , i, j are port count variables;

[0073] Set the selection threshold of alternatives, where

[0074] When the substitutability between two ports is greater than or equal to the selection threshold, a connecting edge is set between the two ports;

[0075] When the substitutability between two ports is less than the selection threshold, no connection edge is set between the two ports;

[0076] The ports are taken as network nodes, and the network nodes are connected according to the connection edges to obtain the substitutability network. The community analysis of the substitutability network is performed to obtain multiple substitutability clusters.

[0077] The ports corresponding to the nodes in each replaceable cluster are all interchangeable ports.

[0078] The present invention utilizes AIS data and container traffic flow to quantify the interchangeability between ports. AIS data indicates the similarity of geographical attributes between ports, that is, any two interchangeable ports have similar geographical attributes, for example: the two interchangeable ports are close in distance, and the basic settings of the ports (berth quantity setting, traffic throughput setting, and traffic speed setting) are similar. Among them, the close distance can ensure that when replacing each other, the speed is fast and the container migration distance is short. The similar basic settings of the ports can make the changes to the ports small and the reuse rate high when replacing each other, and the container traffic flow indicates the similarity of the overall incremental trend of the container carrying capacity between ports, that is, any two interchangeable ports have similar overall incremental trends of the container carrying capacity, that is, when the two interchangeable ports replace each other, the container carrying capacity that can be carried is similar, and the operation state of the original collection and distribution network can be maintained when replacing each other.

[0079] In summary, the use of AIS data and container traffic flow to quantify the interchangeability between ports can make the calculated interchangeable ports have the advantages of high speed and high reusability when replacing each other, and enable the port collection and distribution to maintain high stability.

[0080] Compared with the container port area site selection planning model constructed by only using the port's own lowest collection and distribution cost and highest collection and distribution container carrying capacity, the present invention constructs a double-layer planning model for container port area site selection, which can ensure that the obtained container port area site selection has the lowest collection and distribution cost and the highest collection and distribution container carrying capacity, and after the container port area site selection fails, the enabled replaceable site selection also has the lowest collection and distribution cost and the highest collection and distribution container carrying capacity, so that the collection and distribution network can maintain the same advantages of the lowest collection and distribution cost and the highest collection and distribution container carrying capacity after the container port area site selection fails, thereby ensuring the stability of the operating state of the port collection and distribution network after the container port area site selection fails.

[0081] The construction of the two-layer planning model for container port site selection includes:

[0082] Based on the lowest collection and distribution cost and the highest collection and distribution container carrying capacity of each port, the first-level planning model of the container port area location two-level planning model is constructed. The model expression of the first-level planning model is:

[0083] minF=F1+F2+F3;

[0084]

[0085]

[0086] In the formula, minF is the minimum collection and distribution cost, F1 is the economic cost of collection and distribution, F2 is the time cost of collection and distribution, and Pk is the operating cost of port k selected as the container port area, O k is the construction cost of port k selected as the container port area, C a , C b and C c are the unit transportation costs of water, rail and road from port j to port k selected as the container port area, V a 、V b and V c are the unit transport speeds of water, rail and road from port j to port k selected as the container port area, L kj , l kj and h kj are the water, rail and road transport distances from port j to port k selected as the container port area, m is the total number of ports, n is the total number of ports selected as container port areas, k and j are counting variables of ports;

[0087]

[0088] In the formula, maxS is the maximum container load of the distribution transport, ML kj 、Ml kj and Mh kj are the container transport volumes from port j to port k selected as the container port area by water, rail and road respectively;

[0089] Based on the lowest collection and distribution cost of each port's alternative ports and the highest collection and distribution container carrying capacity, the second-level planning model of the container port site selection double-level planning model is constructed. The model expression of the second-level planning model is:

[0090] minG=G1+G2+G3;

[0091]

[0092]

[0093] In the formula, minG is the minimum collection and distribution cost of the alternative port, G1 is the economic cost of the collection and distribution of the alternative port, G2 is the time cost of the collection and distribution of the alternative port, and P ky is the operating cost of port y, which is an alternative to port k as the container port site, O ky is the construction cost of alternative port y to port k selected as the container port area, C A , C B and C C are the unit transportation costs of water, rail and road from port j to alternative port y for port k as the container port site, V A 、VB and V C are the unit transport speeds of water, rail and road from port j to alternative port y as the container port site, L kyj , l kyj and h kyj are the water, rail and road transport distances from port j to port k as the container port area, m is the total number of ports, ny is the total number of alternative ports for port k as the container port area, ky is the alternative port y for port k as the container port area, k, y, j are port counting variables;

[0094]

[0095] Where maxZ is the maximum container handling capacity of the replaceable port, ML kyj 、Ml kyj and Mh kyj The container carrying capacity by water, rail and road from port j to alternative port y as the site of port k selected as the container port area.

[0096] The determination of container port site selection includes:

[0097] Taking all ports in the planned area as the solution space, the genetic algorithm is used to search and solve the first-level planning model and the second-level planning model, and the ports obtained by the solution are used as the site selection of the container port area.

[0098] When constructing a two-layer planning model for container port site selection, a two-layer planning model is used, in which the first-layer planning model is constructed based on the lowest collection and distribution cost and the highest collection and distribution container capacity of each port itself, and the second-layer planning model is constructed based on the lowest collection and distribution cost and the highest collection and distribution container capacity of the alternative ports of each port. As a result, the container port site selection obtained by the constructed two-layer planning model can achieve the lowest collection and distribution cost and the highest collection and distribution container capacity, and at the same time, the alternative ports of the container port site selection can also achieve the lowest collection and distribution cost and the highest collection and distribution container capacity, realizing rapid temporary replacement of the port container port site selection, so that the port collection and distribution maintains stability while maintaining the goal of the lowest collection and distribution cost and the highest collection and distribution container capacity, that is, the collection and distribution cost can be minimized and the collection and distribution container capacity can be maximized before and after the failure.

[0099] The present invention utilizes the port throughput time series data to screen the alternative ports corresponding to the container port area site selection, and quantifies the failure similarity between the container port area site selection and the alternative ports. The port throughput time series data of the alternative ports lags behind the port throughput time series data of the container port area site selection by a preset time series. The failure similarity between the container port area site selection and the alternative ports indicates the failure correlation between the container port area site selection and the alternative ports, that is, whether the failure of the container port area site selection will affect the alternative ports. The alternative ports with the least impact are screened out as the alternative site selection, which can avoid being affected by the failure of the container port area site selection, and further ensure that the alternative site selection can realize the rapid temporary replacement of the port container port area site selection, so that the port collection and distribution maintains stability while maintaining the goals of minimum collection and distribution cost and maximum collection and distribution container carrying capacity.

[0100] Determination of alternative locations for container port sites, including:

[0101] Screening the alternative ports corresponding to the container port area site selection to obtain the alternative site selection for the container port area site selection;

[0102] Obtaining the port throughput time series data of the container port area site selection, and the port throughput time series data of the alternative port corresponding to the container port area site selection, wherein the port throughput time series data of the alternative port lags behind the port throughput time series data of the container port area site selection by a preset time series;

[0103] The failure similarity is measured by comparing the port throughput time series data of the container port area with the port throughput time series data of each alternative port corresponding to the container port area. The function expression of the failure similarity is:

[0104] J ky =|D tun,k -D tun,y |;

[0105] In the formula, J ky is the failure similarity between port k as the container port site and port y, which is an alternative to port k as the container port site, D tun,k is the port throughput time series data of port k selected as the container port area, D tun,y is the port throughput time series data of port y, which is an alternative to port k selected as the container port area, |D tun,k -D tun,y | for D tun,k and D tun,y The Euclidean distance of

[0106] At each container port site, the alternative port corresponding to the highest failure similarity is selected as the alternative site for each container port site.

[0107] The entropy weight method is used to set the substitutability weights of AIS data and container traffic flow.

[0108] AIS data and container traffic flow are normalized before quantitative calculation of substitutability.

[0109] An alternative cluster contains at least one port.

[0110] When constructing the two-layer planning model for container port site selection, the time cost, economic cost and container carrying capacity of collection and distribution are normalized.

[0111] The present invention constructs a double-layer planning model for container port area site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on each port, and constructs a double-layer planning model for container port area site selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on the replaceable ports of each port. The port is obtained as the container port area site selection by the double-layer planning model, and the replaceable ports corresponding to the container port area site selection are screened to obtain the replaceable site selection of the container port area site selection, thereby realizing rapid temporary replacement of the port container port area site selection, so that the port collection and distribution maintains stability while maintaining the goals of lowest collection and distribution cost and highest collection and distribution container carrying capacity.

[0112] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A container port area planning method integrating AIS data, characterized by: The following steps are involved: Step S1: Count all ports in the planned area and obtain AIS data and container traffic flow of each port; Step S2: quantify the substitutability of each port in the planning area in turn based on AIS data and container traffic flow to obtain alternative ports for each port; Step S3, constructing a double-layer planning model for container port location selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on each port, and constructing a double-layer planning model for container port location selection with the lowest collection and distribution cost and the highest collection and distribution container carrying capacity based on the replaceable ports of each port; Step S4: Obtain a port as the container port site selection by using the double-layer planning model, and screen the replaceable ports corresponding to the container port site selection to obtain the replaceable site selection of the container port site selection, so as to improve the replaceability of the container port area and reduce the instability of collection and distribution caused by port failure; The acquisition of container traffic flow includes: Obtain the container carrying capacity of each port within a time series to obtain the container carrying capacity time series data; The container carrying capacity time series data is rearranged from small to large according to the container carrying capacity to obtain the container traffic flow, and the container traffic flow is used to characterize the incremental trend of the container carrying capacity at the port; The method of quantifying the substitutability of each port in the planning area in turn based on AIS data and container traffic flow to obtain the alternative ports for each port includes: Set the substitutability weights of AIS data and container traffic flow, and apply the substitutability weights to AIS data and container traffic flow; Based on the weighted AIS data and container traffic flow, the similarities of any two ports are quantified in turn as the substitutability of any two ports. The quantitative formula of the substitutability is: I ij =|W1*D AIS,i -W1*D AIS,j |+|W2*D trend,i -W2*D trend,j |; In the formula, I ij is the substitutability of port i and port j, D AIS,i is the AIS data of port i, D AIS,j is the AIS data of port j, D trend,i is the container traffic volume at port i, D trend,j is the container traffic flow of port j, W1 is the replaceable weight of AIS data, W2 is the replaceable weight of container traffic flow, |W1*D AIS,i -W2*D AIS,j | is W1*D AIS,i and W2*D AIS,j Euclidean distance, |W1*D trend,i -W2*D trend,j | is W1*D trend,i and W2*D trend,j The Euclidean distance of , i, j are port count variables; Set the selection threshold of alternatives, where When the substitutability between two ports is greater than or equal to the selection threshold, a connection edge is set between the two ports; When the substitutability between two ports is less than the selection threshold, no connection edge is set between the two ports; The ports are taken as network nodes, and the network nodes are connected according to the connection edges to obtain the substitutability network. The community analysis of the substitutability network is performed to obtain multiple substitutability clusters. Each port corresponding to each node in each replaceable cluster is regarded as a replaceable port; The construction of the two-layer planning model for container port site selection includes: Based on the lowest collection and distribution cost and the highest collection and distribution container carrying capacity of each port, the first-level planning model of the container port area location double-level planning model is constructed. The model expression of the first-level planning model is: minF=F1+F2; In the formula, minF is the minimum collection and distribution cost, F1 is the economic cost of collection and distribution, F2 is the time cost of collection and distribution, and P k is the operating cost of port k selected as the container port area, O k is the construction cost of port k selected as the container port area, C a , C b and C c are the unit transportation costs of water, rail and road from port j to port k selected as the container port area, V a 、V b and V c are the unit transport speeds of water, rail and road from port j to port k selected as the container port area, L kj , l kj and h kj are the water, rail and road transport distances from port j to port k selected as the container port area, m is the total number of ports, n is the total number of ports selected as container port areas, k and j are counting variables of ports; In the formula, maxS is the maximum container load of the distribution transport, ML kj 、Ml kj and Mh kj are the container transport volumes from port j to port k selected as the container port area by water, rail and road respectively; Based on the lowest collection and distribution cost and the highest collection and distribution container carrying capacity of each port's alternative ports, the second-level planning model in the container port area location double-level planning model is constructed. The model expression of the second-level planning model is: minG=G1+G2; In the formula, minG is the minimum collection and distribution cost of the alternative port, G1 is the economic cost of the collection and distribution of the alternative port, G2 is the time cost of the collection and distribution of the alternative port, and P ky is the operating cost of port y, which is an alternative to port k as the container port site, O ky is the construction cost of alternative port y to port k selected as the container port area, C A , C B and C C are the unit transportation costs of water, rail and road from port j to alternative port y for port k as the container port site, V A 、V B and V C are the unit transport speeds of water, rail and road from port j to alternative port y as the container port site, L kyj , l kyj and h kyj are the water, rail and road transport distances from port j to port k as the container port area, m is the total number of ports, ny is the total number of alternative ports for port k as the container port area, ky is the alternative port y for port k as the container port area, k, y, j are port counting variables; Where maxZ is the maximum container handling capacity of the replaceable port, ML kyj 、Ml kyj and Mh kyj are the container carrying capacity of water, rail and road from port j to alternative port y of port k as the site of container port area; The determination of the location of the container port area includes: Taking all ports in the planned area as the solution space, the first-level planning model and the second-level planning model are searched and solved by using a genetic algorithm, and the ports obtained by the solution are used as the location of the container port area; The determination of alternative locations for the container port site selection includes: Screening the alternative ports corresponding to the container port area site selection to obtain the alternative site selection for the container port area site selection; Obtaining the port throughput time series data of the container port area site selection, and the port throughput time series data of the alternative port corresponding to the container port area site selection, wherein the port throughput time series data of the alternative port lags behind the port throughput time series data of the container port area site selection by a preset time series; The failure similarity is measured by comparing the port throughput time series data of the container port area selection with the port throughput time series data of each alternative port corresponding to the container port area selection. The function expression of the failure similarity is: I ky =|D tun,k -D tun,y |; In the formula, J ky is the failure similarity between port k as the container port site and port y, which is an alternative to port k as the container port site, D tun,k is the port throughput time series data of port k selected as the container port area, D tun,y is the port throughput time series data of port y, which is an alternative to port k selected as the container port area, |D tun,k -D tun,y | for D tun,k and D tun,y The Euclidean distance of At each container port site, the alternative port corresponding to the highest failure similarity is selected as the alternative site for each container port site.

2. A container port area planning method integrating AIS data according to claim 1, characterized in that: The entropy weight method is used to set the substitutability weights of AIS data and container traffic flow.

3. The container port area planning method integrating AIS data according to claim 1 is characterized in that: AIS data and container traffic flow are normalized before quantitative calculation of substitutability.

4. The container port area planning method integrating AIS data according to claim 1 is characterized in that: The alternative cluster includes at least one port.

5. The container port area planning method integrating AIS data according to claim 1 is characterized in that: When constructing the double-layer planning model for container port site selection, the collection and distribution time cost, the collection and distribution economic cost, and the collection and distribution container carrying capacity are normalized.

Images