Ship route optimization method and device based on AIS data

Abstract

The invention relates to the technical field of air route design, in particular to a ship air route optimization method and device based on AIS data, and the method comprises the following steps: extracting a ship air route network based on historical AIS data; obtaining network structure node similarity and comprehensive node similarity between the ship route intersection nodes based on the position relation between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes; community division is carried out on the ship route intersection nodes based on the network structure node similarity and the comprehensive node similarity between the ship route intersection nodes; and merging the movable ship route intersection node with the minimum importance degree to the nearest ship route intersection node until a set merging termination condition is met. The problems that in the prior art, subjective experience and qualitative analysis of experts and maritime affair managers are relied on, then optimization is conducted, and objective basis and scientificity are lacked can be solved.

Description

Technical Field

[0001] The present application relates to the technical field of route design, and in particular to a method and device for optimizing a ship route based on AIS data. Background Art

[0002] With the rapid development of port construction and maritime transportation, the traffic volume and density of ships in coastal port waters have gradually increased, various types of ships have encountered more and more frequently, and the risk of water traffic safety has continued to increase. In order to ensure the safety of ships in coastal port waters, improve the efficiency of ships in waters, and sort out the traffic situation in waters to facilitate water traffic supervision, ship route optimization is usually used to re-plan the spatial and temporal layout of water routes to achieve the purpose of reducing navigation risks and improving navigation efficiency.

[0003] The existing main methods of route optimization include comprehensive management of navigable waters, sorting out traffic flows and planning of ship routing. This paper mainly constructs a set of evaluation indicators for routing and a comprehensive evaluation model for water traffic conditions by qualitatively analyzing the relevant factors of water ship routing, the inner and outer rings of ships, traffic rules and various behaviors of ships in real situations. By evaluating and selecting the routing schemes proposed by experts, an optimal scheme is selected to guide the navigation of ships in the waters.

[0004] Existing research on ship route optimization mainly focuses on the formulation of ship traffic rules and ship traffic control. However, most of the methods are based on the subjective experience and qualitative analysis of experts and maritime management personnel, and the optimization methods lack objective basis and scientificity. Summary of the invention

[0005] The present application provides a method and device for optimizing ship routes based on AIS data, which can solve the problem that the prior art relies on the subjective experience and qualitative analysis of experts and maritime management personnel to perform optimization, but lacks objective basis and scientificity.

[0006] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0007] In one aspect, the present invention provides a method for optimizing a ship route based on AIS data, comprising the following steps:

[0008] Extract ship route network based on historical AIS data;

[0009] Based on the positional relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes, the network structure node similarity and comprehensive node similarity between the ship route intersection nodes are obtained;

[0010] Based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes, the ship route intersection nodes are divided into communities;

[0011] The movable ship route intersection node with the least importance is merged to the nearest ship route intersection node until the set merging termination condition is reached.

[0012] In some optional solutions, the community division of the ship route intersection nodes based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes includes:

[0013] Based on the similarity of network structure nodes between ship route intersection nodes, the ship route intersection nodes are divided into initial communities according to hierarchical clustering and evaluated to obtain the initial division results.

[0014] Based on the initial division results and the comprehensive node similarity between the ship route intersection nodes, the ship route intersection nodes are divided into secondary communities according to hierarchical clustering;

[0015] Based on the modularity evaluation function, the secondary community division is evaluated to determine the optimal community division.

[0016] In some alternative schemes, according to the modularity evaluation function Evaluate primary and secondary community divisions;

[0017] Among them, Sim i,j The value represents the similarity between the ship route intersection nodes i and j; S i represents the sum of similarities between the ship route intersection node i and all adjacent ship route intersection nodes; AS is the sum of similarities of all ship route intersection nodes in the ship route network, C i Indicates the community number to which the ship route intersection node i belongs, Indicates that the ship route intersection nodes i and j belong to the same community, Indicates that nodes i and j belong to different communities.

[0018] In some optional schemes, based on the positional relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes, the network structure node similarity between the ship route intersection nodes is obtained, including:

[0019] According to the number of adjacent nodes between the ship route intersection nodes, the similarity of adjacent points between the ship route intersection nodes is determined;

[0020] According to the flow between the ship route intersection nodes and the flow on the ship route intersection nodes, the flow weight similarity between the ship route intersection nodes is determined;

[0021] Combining the traffic weight similarity and neighbor point similarity, the network structure node similarity is obtained.

[0022] In some alternative schemes, according to the formula Determine the similarity R of adjacent points between ship route intersection nodes ij , where │L i ∩L j │ represents the number of common adjacent nodes between nodes i and j, L i is the number of neighboring nodes of node i, L j is the number of neighboring nodes of node j;

[0023] According to the formula Determine the flow weight similarity W between the ship route intersection nodes ij , where w ij represents the traffic between nodes i and j, w i With w j Represent the traffic of each node respectively;

[0024] According to the formula Get the network structure node similarity S between the ship route intersection nodes ij , where a+b=1, a and b are weight coefficients.

[0025] In some optional schemes, the comprehensive node similarity between the ship route intersection nodes is obtained, including:

[0026] According to the spatial distance between the intersection nodes of the ship routes, the spatial distance node similarity is determined;

[0027] According to the similarity of network structure nodes, the ship route intersection nodes are divided into communities for the first time, and then evaluated to obtain the initial division results;

[0028] Based on the initial community division results, the comprehensive node similarity is obtained according to the network structure node similarity and spatial distance node similarity.

[0029] In some alternative schemes, according to the formula Determine the spatial distance node similarity D between the ship route intersection nodes ij , where d ij represents the temporal and spatial distance between node i and node j, d min and d max They represent the minimum and maximum time-space distances between all nodes in the ship route network respectively;

[0030] According to the formula The comprehensive node similarity between the ship route intersection nodes is obtained, where Z ijrepresents the comprehensive similarity between nodes i and j, c+d=1, D ij ` represents the normalized spatial distance node similarity between nodes i and j, S ij ` represents the normalized network structure node similarity between nodes i and j, lables i Indicates the community number to which node i belongs in the initial community division.

[0031] In some optional solutions, merging the least important movable ship route intersection node to the nearest ship route intersection node until a set merging termination condition is reached includes:

[0032] Rank the importance of the ship route intersection nodes in the community;

[0033] Merge the least important movable ship route intersection node to the nearest ship route intersection node;

[0034] Assess the collision risk of the merged ship route network. If the collision risk is reduced compared to the initial route network, continue to merge the movable ship route intersection nodes with the least importance among the remaining ship route intersection nodes until the collision risk is greater than the collision risk of the initial route network.

[0035] In some alternative schemes, according to the formula Determine the importance of the ship route intersection node C DC (v i ), where C Dout (v i ) represents the output strength of node i, C Din (v i ) represents the input strength of node i.

[0036] In a second aspect, the present invention provides a ship route optimization device based on AIS data, comprising:

[0037] The route network extraction module is used to extract the ship route network based on historical AIS data;

[0038] A similarity solving module is used to obtain the network structure node similarity and comprehensive node similarity between the ship route intersection nodes based on the position relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes;

[0039] A community division module is used to divide the ship route intersection nodes into communities based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes;

[0040] The optimization module is used to merge the movable ship route intersection node with the least importance into the nearest ship route intersection node until the set merging termination condition is reached.

[0041] Compared with the prior art, the advantages of the present invention are as follows: based on the positional relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes, the network structure node similarity and comprehensive node similarity between the ship route intersection nodes are obtained; based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes, the ship route intersection nodes are divided into communities; the intersection nodes that are closely related and affect each other are grouped together, and then the intersection nodes in the group are optimized, which can greatly reduce the calculation pressure in the optimization process. The movable ship route intersection node with the least importance is merged to the nearest ship route intersection node, and such a merger is more objective and scientific. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 Flow chart of a method for optimizing a ship route based on AIS data in an embodiment of the present invention;

[0044] Figure 2 This is a diagram showing the evaluation results of the community division effect in an embodiment of the present invention;

[0045] Figure 3 This is a community division result diagram in an embodiment of the present invention;

[0046] Figure 4 This is a diagram of the ship route optimization process in an embodiment of the present invention;

[0047] Figure 5 This is a comparison diagram before and after ship route optimization in an embodiment of the present invention;

[0048] Figure 6 This is a diagram showing the complexity and risk changes of the optimization process in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] like Figure 1 As shown, on the one hand, the present invention provides a ship route optimization method based on AIS data, comprising the following steps:

[0051] S1: Extract ship route network based on historical AIS data.

[0052] Ships frequently meet in the hybrid confluence waters, and the main intersection points of ships are unclear. In order to accurately extract the intersection points of ship routes, the main routes in the waters are obtained by trajectory clustering, and the intersection points between routes are extracted by image processing methods. At the same time, the ship traffic flow of each route is obtained based on the clustering results, which provides a basis for the subsequent construction of the ship traffic network. The extraction process includes ship trajectory clustering, ship route extraction, and ship route network extraction.

[0053] Firstly, the AIS data is preprocessed and trajectory compressed. The SSPD* (symmetrized segment·-path shor) model is used to calculate the trajectory similarity, and the HDBSCAN algorithm is used to cluster the trajectories to obtain the main ship traffic flows in the waters.

[0054] Secondly, based on the main ship traffic flows in the acquired waters, the traffic flow data are converted from vector data to raster data by rasterizing the entire waters, and the ship routes corresponding to each ship traffic flow are obtained using the improved Zhang-Suen fast thinning algorithm.

[0055] Finally, by referring to the tracking method in raster data vectorization, a route intersection recognition model is established to complete the extraction of the ship route network in the entire water area.

[0056] S2: Based on the positional relationship between ship route intersection nodes in the ship route network and the ship traffic flow between ship traffic network nodes, the network structure node similarity and comprehensive node similarity between ship route intersection nodes are obtained.

[0057] The main characteristics of complex confluence waters are that there are many ship routes and a large number of route intersections. Therefore, the main purpose of route optimization in complex confluence waters is to reduce route intersections as much as possible without affecting the safety of ship navigation and reduce the complexity of water traffic situation.

[0058] If all route intersections in the water area are optimized sequentially, each optimization will inevitably lead to changes in the traffic network structure, resulting in a large amount of calculation in the entire optimization process. At the same time, the optimization of a certain intersection does not lead to changes in the topological relationship of all intersections in the network, so this method will lead to computational redundancy in use. Therefore, the intersections in the traffic network can be grouped, and the intersections that are closely related and affect each other can be grouped together, and then the intersections in the group can be optimized, which can greatly reduce the calculation pressure during the optimization process.

[0059] Preferably, obtaining the network structure node similarity between the ship route intersection nodes includes:

[0060] S21: Determine the similarity of adjacent points between the ship route intersection nodes according to the number of adjacent nodes between the ship route intersection nodes.

[0061] According to the formula Determine the similarity R of adjacent points between ship route intersection nodes ij , where │L i ∩L j │ represents the number of common adjacent nodes between nodes i and j. The more common adjacent nodes two nodes have, the higher the similarity between the nodes. L i is the number of neighboring nodes of node i, L j is the number of neighboring nodes of node j.

[0062] The number of adjacent nodes is obtained based on the positional relationship between ship route intersection nodes and the ship traffic flow between ship traffic network nodes.

[0063] S22: Determine the similarity of flow weights between the ship route intersection nodes according to the flow between the ship route intersection nodes and the flow on the ship route intersection nodes.

[0064] According to the formula Determine the flow weight similarity W between the ship route intersection nodes ij , where w ij represents the ship traffic flow between nodes i and j, w i With w j Represents the traffic of each node, that is, w i is the ship traffic flow at the ship route intersection node i, w j is the ship traffic flow at the ship route intersection node j. The higher the proportion of the ship traffic flow between two nodes in the ship traffic flow of the two nodes, the higher the similarity of the two nodes.

[0065] S23: Combine the traffic weight similarity and the neighboring point similarity to obtain the network structure node similarity.

[0066] According to the formula Get the network structure node similarity S between the ship route intersection nodes ij , where a+b=1, a and b are weight coefficients.

[0067] Obtain the comprehensive node similarity between the ship route intersection nodes, including:

[0068] S24: Determine spatial distance node similarity according to the spatial distance between the ship route intersection nodes.

[0069] According to the formula Determine the spatial distance node similarity D ij , where d ij represents the temporal and spatial distance between node i and node j, d min and d max They represent the minimum and maximum time-space distances between all nodes in the ship route network.

[0070] The spatial distance between the ship route intersection nodes is obtained according to the positional relationship between the ship route intersection nodes.

[0071] S25: Based on the similarity of the network structure nodes, the ship route intersection nodes are initially divided into communities and evaluated to obtain the initial division results.

[0072] According to the similarity R between the adjacent points of the ship route intersection nodes ij , construct the adjacency similarity matrix between nodes, and calculate the flow weight similarity W between the ship route intersection nodes ij , construct the traffic weight similarity matrix between nodes, and the network structure node similarity S between the ship route intersection nodes ij , a network structure node similarity matrix between nodes is constructed, and the initial community division of ship route intersection nodes is carried out according to hierarchical clustering.

[0073] Here, the following modularity evaluation function is also used to evaluate the initial community division. In this example, when a is 0.6, the community division result is the best. If there is no common adjacent node between nodes i and j, the similarity of the nodes is completely determined by the similarity of ship traffic flow, otherwise the node similarity is determined by the adjacent nodes and ship traffic flow.

[0074] In other embodiments, the comprehensive node similarity may also be calculated directly based on the network structure node similarity and the spatial distance node similarity.

[0075] S26: Based on the initial community division results, the comprehensive node similarity is obtained according to the network structure node similarity and the spatial distance node similarity.

[0076] Based on the initial community division results, the spatial distance factor is incorporated into the original node network structure relationship.

[0077] According to the formula Get the comprehensive node similarity Z between the ship route intersection nodes ij , where Z ij represents the comprehensive similarity between nodes i and j, c and d are weight coefficients, c+d=1, D ij ` represents the normalized spatial distance node similarity between nodes i and j, S ij ` represents the normalized network structure node similarity between nodes i and j, lables i Indicates the community number to which node i belongs in the initial community division, lables j Indicates the community number to which node j belongs in the initial community division.

[0078] S3: Based on the network structure node similarity and comprehensive node similarity between ship route intersection nodes, the ship route intersection nodes are divided into communities.

[0079] In some optional solutions, step S3 includes:

[0080] S31: Based on the similarity of the network structure nodes between the ship route intersection nodes, the ship route intersection nodes are initially divided into communities according to hierarchical clustering, and evaluated to obtain the initial division results.

[0081] The division method is consistent with the method of performing the initial community division of the ship route intersection nodes according to the similarity of the network structure nodes in step S25, and will not be described in detail here.

[0082] S32: Based on the comprehensive node similarity between ship route intersection nodes, the ship route intersection nodes are divided into secondary communities according to hierarchical clustering.

[0083] Based on the initial community division results, the comprehensive node similarity is obtained by integrating indicators with the node similarity based on spatial distance, and the network and similarity matrix are constructed.

[0084] The final number of community divisions is determined based on the optimal number of communities in the initial division and the actual situation of the water area, and a hierarchical clustering algorithm is used to perform secondary community division on all nodes.

[0085] S33: Based on the modularity evaluation function, the secondary community division is evaluated to determine the optimal community division.

[0086] Preferably, according to the modularity evaluation function The primary and secondary community divisions were evaluated.

[0087] Among them, Sim i,j The value represents the similarity between the ship route intersection nodes i and j; S i represents the sum of similarities between the ship route intersection node i and all adjacent ship route intersection nodes; AS is the sum of similarities of all ship route intersection nodes in the ship route network, C i Indicates the community number to which the ship route intersection node i belongs, Indicates that the ship route intersection nodes i and j belong to the same community, Indicates that nodes i and j belong to different communities.

[0088] In practical applications, based on what similarity, the community division of ship route intersection nodes is carried out through hierarchical clustering. i,j The value is the corresponding similarity.

[0089] In this example, the community division with the largest modularity evaluation function value is selected as the optimal community division result.

[0090] S4: Merge the movable ship route intersection node with the least importance to the nearest ship route intersection node until the set merging termination condition is reached.

[0091] Preferably, step S4 comprises the following steps:

[0092] S41: Sort the importance of the ship route intersection nodes in the community.

[0093] The optimization of ship routes by merging ship traffic network nodes (i.e., intersection points) must follow certain rules. Therefore, it is proposed to sort the importance of all nodes in the network and merge two nodes to retain the node with greater importance.

[0094] Considering that the ship traffic network is a directed weighted network with traffic flows in both positive and negative directions, the traditional method of evaluating node importance using the node centrality model only considers the size of the node degree and is not suitable for the ship traffic network. It is necessary to divide the node degree into input intensity and output intensity to comprehensively calculate the node importance. The input intensity is the flow from other nodes into the node, and the output intensity is the flow from the node to other nodes.

[0095] According to the formula Determine the importance of the ship route intersection node C DC (v i ), where C Dout (v i ) represents the output strength of node i, C Din (v i ) represents the input strength of node i.

[0096] S42: Merge the movable ship route intersection node with the least importance into the nearest ship route intersection node.

[0097] Before merging the movable ship route intersection node with the least importance to the nearest ship route intersection node, it is determined whether the ship route intersection node is a non-movable node according to whether the routes at the location of the ship route intersection node must intersect.

[0098] S43: Evaluate the collision risk of the merged ship route network. If the collision risk is reduced compared to the initial route network, continue to merge the movable ship route intersection nodes with the least importance among the remaining ship route intersection nodes until the collision risk is greater than the collision risk of the initial route network.

[0099] In other embodiments, other merging termination conditions may also be set, for example, the merging process may be terminated when the collision risk no longer decreases; a set number of merging times may also be set, and the optimal solution among all merging times may be selected, for example, the solution with the lowest collision risk.

[0100] A more specific embodiment is given below, in which the ship route intersection node is referred to as a node or intersection point:

[0101] Select the AIS data of the set water area and set time period as the data set.

[0102] Through AIS data preprocessing, trajectory compression, trajectory clustering and other algorithms, the main ship traffic flow in the outbound waters is obtained, and the ship route network in the outbound waters is extracted based on this.

[0103] Through the initial network division, the network community is divided from three perspectives: based on the similarity of adjacent points, based on the similarity of traffic weights, and based on the similarity of network structure nodes. The model based on the network structure similarity is used as the experimental group, and the other two are used as the control group. At the same time, the modularity evaluation function is used for evaluation, such as Figure 2 As shown in the figure, by comparing the three community division methods, it can be found that the community division based on the similarity of network structure nodes is the best, and the optimal number of communities is 4.

[0104] According to the optimal number of communities being 4, the results of dividing the community of the ship traffic network in the study area using the network structure node similarity and node comprehensive similarity are as follows: Figure 3 As shown, Figure 3 a is the comprehensive similarity division of nodes, Figure 3 b is the similarity division of network structure nodes.

[0105] It is found that the final community division results of the two algorithms are relatively close. However, compared with the node similarity based on network structure, the node comprehensive similarity increases the consideration of the temporal and spatial distance between nodes, which changes the community belonging of some nodes and makes the distance between nodes in the community closer. In actual situations, it is easier to merge and optimize the intersection of routes close to each other, and the modularity evaluation function is the largest. The division result corresponding to the node comprehensive similarity is selected.

[0106] Based on maritime needs and actual conditions, it was finally determined that only routes of Community 1 and Community 2 needed to be optimized.

[0107] According to the steps of S4, the routes of community 1 and community 2 are optimized. The optimization process is as follows: Figure 4 As shown in the figure, in the first optimization iteration, P37 is the node with the least importance, and is optimized and merged into the nearest P3 node. In the second optimization, P7 is the node with the least importance, and is optimized and merged into the nearest P6 node. And so on, after 9 iterations, the original network with 12 nodes and 18 edges is simplified to a network with 4 nodes and 4 edges, and its structure and complexity are greatly simplified.

[0108] After optimizing the routes of the two main community-covered waters in the ship traffic network through the above route optimization method, the traffic conditions in the waters have been improved to a certain extent, including the following aspects:

[0109] ① Changes in the number of ship intersections in the waters: Figure 5 As shown in Figures 5a and 5c, there are 13 route intersections in the original ship route network corresponding to community 1, and the number of route intersections is reduced to 4 after route optimization.

[0110] ② Reduce the complexity and risk of water vessel traffic network: Figure 6 As shown in Figures 6a and 6b, the average degree of network nodes, network radius and average path length in the network complexity index decreased by about 50% during the whole simplification process compared with before optimization, while the network efficiency and clustering coefficient increased by 40%, which means that the complexity of the traffic network structure decreased, the traffic correlation between the intersection points of the routes in the water area decreased, and the traffic situation was gradually simplified. At the same time, the risk level in the network after optimization decreased by 30% compared with before optimization, indicating that the navigation of ships in the water area is safer after the route optimization.

[0111] ③ The area of ​​waters that the maritime regulatory authorities need to supervise becomes smaller: Figure 5 b and Figure 5 d, where the yellow dotted box represents the waters where the intersections are concentrated. It can be seen that after the optimization, in addition to the reduction in the number of intersections, the area of ​​the waters occupied by the intersections has also been significantly reduced, which will significantly reduce the regulatory pressure on the maritime regulatory authorities.

[0112] In a second aspect, the present invention further provides a ship route optimization device based on AIS data, comprising:

[0113] The route network extraction module is used to extract the ship route network based on historical AIS data;

[0114] A similarity solving module is used to obtain the network structure node similarity and comprehensive node similarity between the ship route intersection nodes based on the position relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes;

[0115] A community division module is used to divide the ship route intersection nodes into communities based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes;

[0116] The optimization module is used to merge the movable ship route intersection node with the least importance into the nearest ship route intersection node until the set merging termination condition is reached.

[0117] Among them, the functional implementation of each module in the above-mentioned ship route optimization device based on AIS data corresponds to the various steps in the above-mentioned ship route optimization method embodiment based on AIS data, and its functions and implementation processes will not be repeated here one by one.

[0118] In a third aspect, an embodiment of the present application provides a ship route optimization device based on AIS data. The ship route optimization device based on AIS data can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0119] In an embodiment of the present application, a ship route optimization device based on AIS data may include a processor, a memory, a communication interface, and a communication bus.

[0120] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0121] The communication interface includes an input / output (I / O) interface, a physical interface, and a logical interface, which are used to interconnect the devices inside the ship route optimization device based on AIS data, and an interface used to interconnect the ship route optimization device based on AIS data with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0122] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0123] The processor may be a general-purpose processor, which may call a ship route optimization program based on AIS data stored in a memory and execute a ship route optimization method based on AIS data provided in an embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the AAAA program is called may refer to the various embodiments of the ship route optimization method based on AIS data of the present application, which will not be described in detail here.

[0124] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0125] The computer-readable storage medium of the present application stores a ship route optimization program based on AIS data, wherein when the ship route optimization program based on AIS data is executed by a processor, the steps of the ship route optimization method based on AIS data as described above are implemented.

[0126] Among them, the method implemented when the ship route optimization program based on AIS data is executed can refer to the various embodiments of the ship route optimization method based on AIS data in this application, and will not be repeated here.

[0127] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0128] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0129] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0130] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or. For example, A / B can mean A or B. The “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0131] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0133] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A ship route optimization method based on AIS data, characterized in that: The following steps are involved: Extract ship route network based on historical AIS data; Based on the positional relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes, the network structure node similarity and comprehensive node similarity between the ship route intersection nodes are obtained; Based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes, the ship route intersection nodes are divided into communities; The movable ship route intersection node with the least importance is merged to the nearest ship route intersection node until the set merging termination condition is reached.

2. The ship route optimization method based on AIS data according to claim 1, characterized in that: The community division of the ship route intersection nodes based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes includes: Based on the similarity of network structure nodes between ship route intersection nodes, the ship route intersection nodes are divided into initial communities according to hierarchical clustering and evaluated to obtain the initial division results. Based on the initial division results and the comprehensive node similarity between the ship route intersection nodes, the ship route intersection nodes are divided into secondary communities according to hierarchical clustering; Based on the modularity evaluation function, the secondary community division is evaluated to determine the optimal community division.

3. The ship route optimization method based on AIS data as claimed in claim 2, characterized in that: According to the modularity evaluation function Evaluate primary and secondary community divisions; Among them, Sim i,j The value represents the similarity between the ship route intersection nodes i and j; S i represents the sum of similarities between the ship route intersection node i and all adjacent ship route intersection nodes; AS is the sum of similarities of all ship route intersection nodes in the ship route network, C i Indicates the community number to which the ship route intersection node i belongs, Indicates that the ship route intersection nodes i and j belong to the same community, Indicates that nodes i and j belong to different communities.

4. The ship route optimization method based on AIS data according to claim 1, characterized in that: Based on the positional relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes, the network structure node similarity between the ship route intersection nodes is obtained, including: According to the number of adjacent nodes between the ship route intersection nodes, the similarity of adjacent points between the ship route intersection nodes is determined; According to the flow between the ship route intersection nodes and the flow on the ship route intersection nodes, the flow weight similarity between the ship route intersection nodes is determined; Combining the traffic weight similarity and neighbor point similarity, the network structure node similarity is obtained.

5. The ship route optimization method based on AIS data as claimed in claim 4, characterized in that: According to the formula Determine the similarity R of adjacent points between ship route intersection nodes ij , where │L i ∩L j │ represents the number of common adjacent nodes between nodes i and j, L i is the number of neighboring nodes of node i, L j is the number of neighboring nodes of node j; According to the formula Determine the flow weight similarity W between the ship route intersection nodes ij , where w ij represents the traffic between nodes i and j, w i With w j Represent the traffic of each node respectively; According to the formula Get the network structure node similarity S between the ship route intersection nodes ij , where a+b=1, a and b are weight coefficients.

6. The ship route optimization method based on AIS data according to claim 4, characterized in that: Obtain the comprehensive node similarity between the ship route intersection nodes, including: According to the spatial distance between the intersection nodes of the ship routes, the spatial distance node similarity is determined; According to the similarity of network structure nodes, the ship route intersection nodes are divided into communities for the first time, and then evaluated to obtain the initial division results; Based on the initial community division results, the comprehensive node similarity is obtained according to the network structure node similarity and spatial distance node similarity.

7. The ship route optimization method based on AIS data according to claim 6, characterized in that: According to the formula Determine the spatial distance node similarity D between the ship route intersection nodes ij , where d ij represents the temporal and spatial distance between node i and node j, d min and d max They represent the minimum and maximum time-space distances between all nodes in the ship route network respectively; According to the formula The comprehensive node similarity between the ship route intersection nodes is obtained, where Z ij represents the comprehensive similarity between nodes i and j, c and d are weights, c+d=1, D ij ` represents the normalized spatial distance node similarity between nodes i and j, S ij ` represents the normalized network structure node similarity between nodes i and j, lables i Indicates the community number to which node i belongs in the initial community division, lables j Indicates the community number to which node j belongs in the initial community division.

8. The ship route optimization method based on AIS data according to claim 1, characterized in that: The step of merging the least important movable ship route intersection node to the nearest ship route intersection node until the set merging termination condition is reached includes: Rank the importance of the ship route intersection nodes in the community; Merge the least important movable ship route intersection node to the nearest ship route intersection node; Assess the collision risk of the merged ship route network. If the collision risk is reduced compared to the initial route network, continue to merge the movable ship route intersection nodes with the least importance among the remaining ship route intersection nodes until the collision risk is greater than the collision risk of the initial route network.

9. The ship route optimization method based on AIS data according to claim 8, characterized in that: According to the formula Determine the importance of the ship route intersection node C DC (v i ), where C Dout (v i ) represents the output strength of node i, C Din (v i ) represents the input strength of node i.

10. A ship route optimization device based on AIS data, characterized in that: include: The route network extraction module is used to extract the ship route network based on historical AIS data; A similarity solving module is used to obtain the network structure node similarity and comprehensive node similarity between the ship route intersection nodes based on the position relationship between the ship route intersection nodes in the ship route network and the ship traffic flow between the ship traffic network nodes; A community division module is used to divide the ship route intersection nodes into communities based on the network structure node similarity and comprehensive node similarity between the ship route intersection nodes; The optimization module is used to merge the movable ship route intersection node with the least importance into the nearest ship route intersection node until the set merging termination condition is reached.

Images