Marine traffic network construction method and device, electronic equipment and readable storage medium

Abstract

The invention provides a marine traffic network construction method and device, electronic equipment and a readable storage medium, and the method comprises the steps: carrying out the preprocessing of AIS data, including the filtering of abnormal data in a specified research range, the screening of ship AIS data, the segment processing of a journey, and the calculation of a complementation SOG value; analyzing the track set, extracting static and dynamic feature points, identifying a main category cluster through a clustering algorithm, and calculating a convex hull to determine a region boundary; and projecting the feature points into a grid for filtering, retaining important feature points, constructing a flow direction, and finally forming a complete maritime traffic network. According to the invention, through AIS data preprocessing, feature point extraction, clustering analysis, region division and flow direction construction, an accurate maritime traffic network is generated, and decision support is provided for maritime affair management.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and readable storage medium for constructing a maritime transportation network. Background Art

[0002] As an important part of international trade and the global economy, maritime transport carries more than 80% of the international trade volume. Maritime transport not only supports the flow of a large amount of goods in international trade, but also plays a vital role in the efficient operation of the global supply chain. Due to its large volume, diverse routes, and wide coverage, maritime transport has a lower cost advantage than other modes of transportation, especially in the long-distance transportation of bulk goods, which can save more costs. It also has high security and flexibility to adapt to transportation needs of different scales. However, with the growth of global trade and the expansion of international markets, maritime transport faces more and more challenges, such as environmental protection, shipping safety, and congestion of waterways and ports. The extraction of maritime traffic networks is not only related to the optimization of routes, but also to maritime safety and environmental protection. Through high-precision extraction of maritime traffic networks, ship routes can be effectively planned and navigation paths can be optimized, thereby reducing sailing time and fuel consumption, reducing transportation costs and environmental pollution. In addition, accurate route information can also help ships avoid entering environmentally sensitive or navigationally dangerous areas, such as coral reef areas and narrow straits, thereby reducing potential threats to marine ecology and significantly improving navigation safety.

[0003] At present, my country is vigorously developing smart maritime affairs, and at the same time strengthening the construction of the Maritime Silk Road internationally. Strengthening the construction of maritime transportation is of great significance to my country's construction into a maritime power and a transportation power. In recent years, the development of digital and automation technologies has brought new opportunities for the development of maritime transportation. According to the regulations of the International Maritime Organization (IMO), ships with a deadweight of more than 300 tons and all passenger ships are required to install a ship automatic identification system (AIS). The application of AIS and other navigation safety technologies has improved the safety and efficiency of ship navigation. AIS data includes: current time, maritime mobile service identity (MMSI), longitude and latitude, actual speed of the ship (or ship) relative to the ground (SOG, Speed ​​Over Ground), heading angle (COG), navigation status and other information. The extraction of maritime traffic network based on AIS data can better understand the flow mode of maritime traffic. This process is crucial to shipping safety, maritime traffic management, environmental monitoring and shipping logistics.

[0004] At present, the methods for extracting maritime traffic networks are mainly divided into: (1) vision-based methods, which visualize AIS data and identify waypoints in the visualized trajectory through computer image processing technology; (2) vector-based methods, which identify maritime traffic networks by extracting representative waypoints and waterways, usually by calculating the trajectory change angle to identify waterway points; (3) grid-based methods, which divide the sea area into spatial grids and analyze the traffic characteristics within each cell to establish a maritime traffic flow map.

[0005] As mentioned above, the existing maritime traffic network extraction methods do not mention too many data preprocessing techniques. At the same time, their fixed-size area division of maritime traffic network nodes cannot adapt well to the spatial heterogeneity unique to maritime traffic. Summary of the invention

[0006] The main technical problem solved by the present invention is to provide a method, device, electronic device and readable storage medium for constructing a maritime traffic network, which effectively solves the technical problems of the existing methods lacking in-depth data preprocessing when processing AIS data and being inflexible in the regional division of maritime traffic network nodes, thereby achieving a technical effect of more accurately reflecting the spatial heterogeneity and dynamic characteristics of maritime traffic, thereby improving the accuracy and efficiency of maritime traffic management and analysis.

[0007] In order to solve the above technical problems, a technical solution adopted by the present invention is: to provide a method for constructing a maritime transportation network, the method comprising: obtaining AIS data, preprocessing data within a specified research range of the AIS data to obtain a preprocessed ship trajectory set; analyzing the preprocessed ship trajectory set to extract feature points, clustering and region dividing the feature points to identify and group important feature points to form regional boundaries, and establishing the spatial boundaries of the maritime transportation network; wherein the feature points include static feature points and dynamic feature points; analyzing the preprocessed ship trajectory set to extract feature points of ship trajectories, identifying and recording the order in which ships pass through the feature points to form edges of the transportation network, and constructing the flow direction of the maritime transportation network according to the edges of the transportation network; and It is constructed according to the spatial boundaries of the maritime transportation network and the flow direction of the maritime transportation network.

[0008] Among them, obtaining AIS data and preprocessing data within a specified research range of the AIS data specifically include: obtaining AIS data, filtering abnormal data in the AIS data through the specified research range, and filtering ship AIS data from the AIS data through ship identity recognition to obtain ship AIS data after data cleaning; determining that the AIS data between two consecutive recording points in the ship AIS data after data cleaning is an AIS data segment with missing data based on the time interval between the two consecutive recording points exceeding the maximum segmentation time threshold, and performing trip segmentation processing on the AIS data segment with missing data to obtain a segmented data set; calculating SOG for continuous AIS data points in each segment in the segmented data set, and completing the calculated SOG value to the corresponding AIS data point to obtain the AIS data point with speed information; and filtering the drift points in the AIS data point with speed information.

[0009] The drift points include independent drift points and continuous drift points; filtering the drift points in the AIS data points with speed information specifically includes: filtering independent drift points according to the SOG in the AIS data points with speed information being less than the SOG threshold; and clustering the AIS data points in each segment in the segmented data set to form clusters by adjusting the neighborhood radius and the minimum number of samples parameters, identifying and retaining the cluster with the largest number as the main category cluster, and filtering out the data points that do not belong to any main category cluster as noise or outliers to filter out the continuous drift points.

[0010] The AIS data points in each segment of the segmented data set are clustered to form clusters by adjusting the neighborhood radius and the minimum number of samples parameters, the largest number of clusters are identified and retained as the preprocessed ship trajectory set, and the data points that do not belong to any preprocessed ship trajectory set are regarded as noise or outliers and filtered out to filter out continuous drift points, specifically including: obtaining a segmented data set, and setting the neighborhood radius and the minimum number of samples; traversing all data points in the segmented data set; selecting any unlabeled object in the segmented data set p , and the object p Mark as visited; mark the object as visited p If the number of data points within the neighborhood radius of the center is less than the minimum number of samples, the object will be marked as visited. p Mark as noise point, and re-traverse all data points in the segmented data set; mark as noise point p The number of data points within the neighborhood radius as the center is not less than the minimum number of samples, and the object marked as a noise point is executed. p Join a new cluster C , and all objects marked as noise pointsp The points within the neighborhood radius form a neighborhood sub-dataset; traverse all data points in the neighborhood sub-dataset; select any unlabeled object from the neighborhood sub-dataset q , and the object q Mark as visited; mark the object as visited q If the number of data points within the neighborhood radius as the center is less than the minimum number of samples, all data points in the neighborhood sub-dataset are traversed; and objects are marked as visited. q The number of data points within the neighborhood radius of the center is not less than the minimum number of samples, and the object marked as visited is executed. q All objects within the neighborhood radius of are added to the neighborhood sub-dataset, and objects that are not classified into any cluster are q Join the cluster C ; Traverse all data points in the neighborhood sub-dataset to obtain clustering results, calculate the number of data points in different clusters in the clustering results, retain the cluster with the largest number as the preprocessed ship trajectory set, and treat data points that do not belong to any preprocessed ship trajectory set as noise or outliers and filter them out to filter out continuous drift points.

[0011] The method comprises: analyzing the preprocessed ship trajectory set to extract feature points, clustering and region dividing the feature points to identify and group important feature points to form regional boundaries, and establishing the spatial boundaries of the maritime transportation network, specifically comprising: analyzing the preprocessed ship trajectory set, and marking the data points as static feature points according to their SOG values ​​being less than a first threshold; randomly sampling a subset from the preprocessed ship trajectory set, processing each ship trajectory in the subset according to a maximum deviation threshold, extracting key dynamic feature points by checking the influence of the data points forming the ship trajectory on the shape of the ship trajectory, so as to obtain a dynamic feature point set; wherein the ship trajectory comprises a plurality of trajectory segments, and the maximum deviation threshold defines the maximum allowable deviation between the data point and the corresponding trajectory segment; analyzing the local density of each feature point in the dynamic feature point set to construct a clustering hierarchy, and according to the The clustering results are extracted based on the stability of the clustering hierarchy, and the static feature points and the dynamic feature points are clustered and grouped according to the clustering results to obtain the important feature points contained in the clustering grouping with high stability; the feature points of the preprocessed ship trajectory set are divided into different grids according to the geographical location for clustering and regional division, and the static feature points and dynamic feature points of the clustering grouping are projected onto the grid, and the grid is filtered to retain the grid containing important feature points and remove the grid containing noise or insignificant feature points; wherein each grid is assigned a corresponding category according to the category label of its internal feature point; from the filtered grid, according to the category label of the feature point in the grid, the feature points belonging to the same category are compiled into a feature point set; the convex hull of the feature point set of each category is calculated to obtain a polygon, and a boundary is provided for the feature point area of ​​each category to form the spatial boundary of the maritime transportation network.

[0012] Among them, analyzing the preprocessed ship trajectory set, identifying and recording the order in which ships pass through feature points to form the edges of the transportation network, and constructing the flow direction of the maritime transportation network according to the edges of the transportation network, specifically includes: analyzing the preprocessed ship trajectory set, traversing each ship trajectory, identifying and extracting the feature points of the ship trajectory; determining and recording the order in which each ship passes through the feature points, connecting the transportation nodes in sequence to form the edges in the maritime transportation network diagram, and constructing the flow direction of the maritime transportation network.

[0013] In order to solve the above technical problems, another technical solution adopted by the present invention is: to provide a maritime transportation network construction device, the device comprising: a data preprocessing unit, used to obtain AIS data, preprocess the data of the specified research range of the AIS data to obtain a preprocessed ship trajectory set; a node establishment unit, used to analyze the preprocessed ship trajectory set to extract feature points, cluster and divide the feature points into regions to identify and group important feature points to form regional boundaries, and establish the spatial boundaries of the maritime transportation network; wherein the feature points include static feature points and dynamic feature points, which are used to represent nodes in the maritime transportation network; a transportation network construction unit, used to: analyze the preprocessed ship trajectory set to extract feature points of ship trajectories, identify and record the order in which ships pass through the feature points to form the edges of the transportation network, and construct the flow direction of the maritime transportation network according to the edges of the transportation network; and construct the maritime transportation network according to the spatial boundaries of the maritime transportation network and the flow direction of the maritime transportation network.

[0014] The data preprocessing unit includes: a data cleaning module for acquiring AIS data, filtering abnormal data in the AIS data by specifying a research range, and filtering ship AIS data from the AIS data by ship identity recognition to obtain ship AIS data after data cleaning; a trajectory segmentation module for determining that the AIS data between two consecutive recording points in the ship AIS data after data cleaning is an AIS data segment with missing data according to the time interval between the two consecutive recording points exceeding the maximum segmentation time threshold, and performing trip segmentation processing on the AIS data segment with missing data to obtain a segmented data set; a data completion module for calculating SOG for continuous AIS data points in each segment in the segmented data set, and completing the calculated SOG value to the corresponding AIS data point to obtain an AIS data point with speed information; a drift point filtering module for filtering drift points in the AIS data points with speed information; wherein the drift points include independent drift points and continuous drift points.

[0015] The drift point filtering module includes: an independent drift point filtering submodule, which is used to filter independent drift points according to the SOG in the AIS data points with speed information being less than the SOG threshold; a continuous drift point filtering submodule, which is used to cluster the AIS data points in each segment in the segmented data set to form clusters by adjusting the neighborhood radius and the minimum number of samples parameters, identify and retain the cluster with the largest number as the preprocessed ship trajectory set, and treat the data points that do not belong to any preprocessed ship trajectory set as noise or outliers for filtering, so as to filter the continuous drift points.

[0016] The continuous drift point filtering submodule is specifically used to: obtain the segmented data set, and set the neighborhood radius and the minimum number of samples; traverse all data points in the segmented data set; select any unlabeled object in the segmented data set; p , and the object p Mark as visited; mark the object as visited p If the number of data points within the neighborhood radius centered is less than the minimum number of samples, the object marked as visited will be executed. p Mark as noise point, and re-execute the traversal of all data points in the segmented data set; mark as noise point object p If the number of data points within the neighborhood radius centered is not less than the minimum number of samples, the execution will mark it as a noise point object p Join a new cluster C , and all objects marked as noise points p The points within the neighborhood radius form a neighborhood sub-dataset; traverse all data points in the neighborhood sub-dataset; select any unlabeled object in the neighborhood sub-dataset q , and the object q Mark as visited; mark the object as visited q If the number of data points within the neighborhood radius centered is less than the minimum number of samples, all points in the neighborhood sub-dataset are traversed; and objects are marked as visited. q If the number of data points within the neighborhood radius of the center is not less than the minimum number of samples, the object will be marked as visited. q All objects within the neighborhood radius of are added to the neighborhood sub-dataset, and objects that are not classified into any cluster are q Join the cluster C , execute traversal of all data points in the neighborhood sub-dataset; traverse all data points in the neighborhood sub-dataset to obtain clustering results, calculate the number of data points in different clusters, retain the cluster with the largest number as the preprocessed ship trajectory set, and treat data points that do not belong to any preprocessed ship trajectory set as noise or outliers to filter out continuous drift points.

[0017] The static feature point extraction module is used to analyze the pre-processed ship trajectory set and mark the data point as a static feature point according to the SOG value of the data point being less than the first threshold; the dynamic feature point extraction module is used to randomly sample a subset from the pre-processed ship trajectory set, process each ship trajectory in the subset according to the maximum deviation threshold, extract key dynamic feature points by checking the influence of the data points forming the ship trajectory on the shape of the ship trajectory, so as to obtain a dynamic feature point set; wherein the ship trajectory includes multiple trajectory segments, and the maximum deviation threshold defines the maximum deviation allowed between the data point and the corresponding trajectory segment; the feature point clustering module is used to analyze the local density of each feature point in the dynamic feature point set to construct a clustering hierarchy, extract clustering results according to the stability of the clustering hierarchy, and cluster the static feature points and the dynamic feature points. The feature points are clustered and grouped according to the clustering results to obtain important feature points contained in the clustering groups with high stability; the feature point area division module is used to: divide the feature points of the pre-processed ship trajectory set into different grids according to the geographical location for clustering and area division, and project the static feature points and dynamic feature points of the clustering groups onto the grids, filter the grids, retain the grids containing important feature points, and remove the grids containing noise or insignificant feature points; wherein each grid is assigned a corresponding category according to the majority category labels of its internal feature points; from the filtered grids, according to the category labels of the feature points in the grids, the feature points belonging to the same category are compiled into a feature point set; and the convex hull of the feature point set of each category is calculated to obtain a polygon, providing a boundary for the feature point area of ​​each category to form the spatial boundary of the maritime transportation network.

[0018] Among them, the transportation network construction unit is specifically used to: analyze the preprocessed ship trajectory set, traverse each ship trajectory, identify and extract the characteristic points of the ship trajectory; and determine and record the order in which each ship passes through the characteristic points, connect the transportation nodes in sequence to form edges in the maritime transportation network diagram, and construct the flow direction of the maritime transportation network.

[0019] To solve the above technical problems, another technical solution adopted by the present invention is: to provide an electronic device, including: a processor and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the electronic device executes the steps of the maritime transportation network construction method as described above.

[0020] In order to solve the above technical problems, another technical solution adopted by the present invention is: providing a readable storage medium, in which a computer program is stored, and the computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the steps of the maritime transportation network construction method as described above.

[0021] The present invention provides a method, device, electronic device and readable storage medium for constructing a maritime traffic network. The method filters abnormal data by specifying a research range, screens ship AIS data, performs itinerary segmentation processing, and calculates and completes SOG values, thereby ensuring the quality and accuracy of the data. The method extracts static feature points by analyzing SOG values, and extracts dynamic feature points based on a maximum deviation threshold, thereby accurately identifying key nodes and routes of maritime traffic, and providing important spatial information for network construction. The method clusters feature points by a density-based clustering algorithm, effectively identifies and retains the main category clusters, and filters out noise and outliers. The method also determines the regional boundaries by calculating the convex hull of a feature point set, thereby adapting to different scales. The feature point areas of small and large shapes can represent the maritime traffic node areas in more detail; further, by projecting the feature points into different grids and filtering them, the grids containing important feature points are retained, the impact of noise is reduced, and the adaptation to spatial heterogeneity is enhanced; by identifying and recording the order in which ships pass through the feature points, the flow direction of the maritime traffic network is constructed, and the complete maritime traffic network is constructed by combining the spatial boundary and flow direction information; according to the original AIS trajectory generated during the ship's navigation, the end-to-end generation of the maritime traffic network is for subsequent maritime traffic flow prediction and trajectory prediction, which helps to understand the complexity of maritime traffic and also provides a powerful tool for maritime management, route planning and safety monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a method for constructing a marine transportation network in an embodiment of the present invention; Figure 2 yes Figure 1 A flowchart of a specific implementation method of step S10; Figure 3 yes Figure 2 A flowchart of a specific implementation method of step S102; Figure 4 yes Figure 2 A flowchart of a specific method of step S103; Figure 5 This is the effect diagram of the improved DBSCAN algorithm for filtering trajectory noise points; Figure 6 yes Figure 1 A flowchart of a specific implementation method of step S11; Figure 7 is a schematic diagram of clustering static feature points and dynamic feature points in the study area through step S112; Figure 8 is a schematic diagram of a maritime transportation network in a part of Denmark established by a maritime transportation network construction method in an embodiment of the present invention; Fig. 9 is a functional structure diagram of a marine transportation network construction device in an embodiment of the present invention; Fig.10 yes Fig. 9 The functional structure diagram of the data preprocessing unit shown; Fig.11 yes Fig.10 The functional structure diagram of the data completion module shown; Fig.12 yes Fig.10 The functional structure diagram of the drift point filtering module shown; Fig.13 yes Fig. 9 The functional structure diagram of the node establishment unit shown; Fig.14 It is a schematic diagram of the hardware structure of an electronic device in an embodiment of the present invention.

[0023] The reference numerals in the above drawings are described as follows: 30. Maritime transportation network construction device; 31. Data preprocessing unit; 310. Data cleaning module; 311. Trajectory segmentation module; 312. Data completion module; 3120. SOG calculation submodule; 3121. Information completion submodule; 313. Drift point filtering module; 3130. Independent drift point filtering submodule; 3131. Continuous drift point filtering submodule; 32. Node establishment unit; 320. Static feature point extraction module; 321. Dynamic feature point extraction module; 322. Feature point clustering module; 323. Feature point area division module; 33. Transportation network construction unit; 4. Electronic device; 41. Processor; 42. Memory; 43. Input device; 44. Output device; 45. Computer program; DETAILED DESCRIPTION

[0024] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0025] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0026] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0027] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0028] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0029] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0030] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0031] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0032] The efficiency and safety of maritime transport have a significant impact on the stable operation of the global supply chain. In an embodiment of the present invention, a method for constructing a maritime traffic network is provided, which can cope with various noise point situations in the trajectory, accept feature point areas of different sizes, and better adapt to complex maritime scenes. A method for constructing a maritime traffic network provided in an embodiment of the present invention is used to generate an end-to-end maritime traffic network based on the original AIS trajectory generated during the ship's travel, laying the foundation for subsequent maritime traffic flow prediction, trajectory prediction, maritime safety area identification and other tasks, and promoting the development of smart maritime.

[0033] So, see Figure 1 , is a flow chart of a method for constructing a marine transportation network in an embodiment of the present invention. The method comprises: Step S10, acquiring AIS data, and preprocessing the data in a specified research range of the AIS data to obtain a preprocessed ship trajectory set.

[0034] AIS data is usually generated automatically by equipment and reported manually. There are often abnormal data in the data transmission process, so data preprocessing is required before analyzing AIS data. Specifically, AIS data preprocessing tasks include: data cleaning, trajectory segmentation, data completion, and abnormal point filtering algorithm.

[0035] Please also see Figure 2 , step S10, obtaining AIS data, and preprocessing the data in the specified research range of the AIS data, specifically including: Step S100, obtaining AIS data, filtering abnormal data in the AIS data by specifying a research range, and filtering ship AIS data from the AIS data by ship identity recognition to obtain ship AIS data after data cleaning.

[0036] The designated research scope is a scope divided according to designated longitude and latitude.

[0037] AIS data may contain abnormal situations such as erroneous data, null values, and duplicate data during the reporting and transmission process. For such abnormal data, the method of dividing the research scope is adopted to filter the data within the specified longitude and latitude range, that is, to remove data with too many abnormal data items within the specified research scope, and to delete duplicate data.

[0038] In this embodiment, the “filtering the ship AIS data from the AIS data by ship identity identification to obtain the ship AIS data after data cleaning” is specifically: filtering the ship AIS data from the AIS data by using the MMSI coding rule to obtain the ship AIS data after data cleaning.

[0039] Since some aircraft, coastal stations, navigation aids, etc. are also equipped with fixed identification systems and report AIS data, this will interfere with the research of ship AIS data. MMSI is the maritime mobile server identifier in AIS data. It is a set of nine-digit codes used to uniquely identify ship radio communication equipment. According to the MMSI encoding rules, the first digits 2-7 are assigned to ships of different countries; therefore, ship AIS data can be filtered and retained by this identifier.

[0040] Step S101, according to the time interval between two consecutive recording points in the ship AIS data after data cleaning exceeding the maximum segmentation time threshold, it is determined that the AIS data between the two consecutive recording points is an AIS data segment with data missing, and the AIS data segment with data missing is processed by itinerary segmentation to obtain a segmented data set.

[0041] Each segment contains a series of continuous AIS data points with no time interval exceeding the maximum segment time threshold. The recording point is the time point at which the ship's position information is recorded in the AIS data, and the time point at least includes the ship's latitude and longitude coordinates, timestamp, speed, and heading information.

[0042] In this implementation, the maximum segment time threshold is 30 minutes.

[0043] The AIS data reported by the same ship may be missing due to weak signals and other reasons. For AIS data segments with missing data, the maximum segmentation time threshold is applied to segment. If the interval between two consecutive points exceeds this threshold, the trip is segmented between the two points. Based on experience, the time threshold used in this method is half an hour.

[0044] Step S102, calculating the SOG for the continuous AIS data points in each segment in the segmented data set, and completing the calculated SOG value into the corresponding AIS data point to obtain the AIS data point with speed information.

[0045] Please also see Figure 3 , the “calculating SOG for continuous AIS data points in each segment of the segmented data set” specifically includes: Step S1020, for each continuous AIS data point in each segment of the segmented data set, determining the longitude and latitude coordinates between every two AIS data points; Step S1021, calculating the great circle distance between the two AIS data points (i.e., the shortest path distance between two points on the surface of the earth); Step S1022, determining the time difference between the two AIS data points (i.e., the difference in timestamps); Step S1023, dividing the great circle distance between the two points by the time difference between the observations of the two points to obtain SOG.

[0046] Specifically, as described in formula (1): SOG = Great Circle Distance / Time Difference Formula (1) Furthermore, the "completing the calculated SOG value into the corresponding AIS data point to obtain an AIS data point with speed information" specifically includes: analyzing the AIS data points in each segment of the segmented data set to determine the missing attribute information, obtaining the corresponding ship information from the ship database through ship identification, and extracting the missing attribute information from the ship database, and completing it into the corresponding AIS data point to obtain an AIS data point with complete attribute information. The attribute information at least includes ship type, width, and length information.

[0047] Among them, the MMSI code in the AIS data is used as a unique identifier, and the MMSI code is matched with the ship database to obtain the corresponding ship information.

[0048] Some AIS data are missing speed values. For the segmented track, SOG (Speed ​​Over Ground, the actual speed of the ship on the sea surface, not affected by external factors such as water current and wind speed) is calculated based on the longitude and latitude and time difference between each two points, and the data is completed. At the same time, in the AIS data reporting process, there are missing data such as ship type, width, length, etc. As described in step S102, the cross data completion method is used to match the MMSI of the AIS data with the ship database, and the type, size and other data are completed.

[0049] Step S103: filtering the drift points in the AIS data points having speed information.

[0050] Wherein, the drift points include independent drift points and continuous drift points.

[0051] The noise data in AIS data mainly manifests as drift points on the track. Drift points include independent drift points and continuous drift points. Independent drift points will appear as speed anomalies between two adjacent points in the data, and continuous drift points will appear as outliers on the track during visualization.

[0052] Step S103, i.e., filtering the drift points in the AIS data points with speed information, specifically comprises: filtering the independent drift points according to the SOG in the AIS data points with speed information being less than the SOG threshold; and filtering the independent drift points by adjusting the neighborhood radius ε and the minimum number of samples. MinPts The parameters are used to cluster the AIS data points in each segment of the segmented data set to form clusters, identify and retain the cluster with the largest number as the preprocessed ship track set, and filter out the data points that do not belong to any preprocessed ship track set as noise or outliers to filter out continuous drift points.

[0053] In this embodiment, the SOG threshold is 40 nautical miles per hour.

[0054] In this embodiment, the DBSCAN algorithm is applied to the AIS data points in each segment of the segmented data set (ie, each segmented ship track) to filter the continuous drift points.

[0055] Specifically, ships j The trajectory of the observation sequence Definition, where the data points Defined by formula (2): Formula (2) In formula (2), i is a total of m The index of the point. MMSI j Represented as a ship j of MMSI , , and Respectively represent ships j SOG, COG (Course Over Ground, the direction of the ship on the sea) and navigation status, and Ships j In time The latitude and longitude position of the .

[0056] The DBSCAN algorithm is a density-based clustering algorithm that divides data points into different clusters (categories) based on their distance and density. A cluster is defined as the maximum set of samples connected by the maximum density derived from the density-reachable relationship. ε and the minimum number of samples in the neighborhood MinPts , identify all high-density data sets, and then find clustering results of arbitrary shapes. By definition, the data set D Center and data points X The distance is no greater than ε The sub-dataset of N ε(xj) , calculated by formula (3): Formula (3) Different neighborhood sub-datasets N are classified into different clusters, and other points that are not counted into any cluster are classified as outliers, that is, noise points.

[0057] In DBSCAN, a cluster is defined as a set of maximum density samples connected to each other by density-reachable relationships, that is, there are enough points in the neighborhood of a data point (according to MinPts Determined), these points and the points in their neighborhood can be classified into the same cluster. The density can be specifically: if point A is within the neighborhood radius of point B ε and there are enough points (at least MinPts Point A is considered to be reachable to point B through density. If point B is also reachable to point C through density, and point C is within the neighborhood radius of point A ε If the neighborhood radius is within , then point A and point C are also considered to be connected by density. ε Defined in ε How many points must there be in a neighborhood to be considered high-density and thus form the core of a cluster. A high-density data set refers to a data set with a neighborhood radius of ε At least MinPts A set of data points of size , which are considered to be part of a cluster.

[0058] Please also see Figure 4 , the "by adjusting the neighborhood radius ε and the minimum number of samples MinPts The parameters cluster the AIS data points in each segment of the segmented data set to form clusters, identify and retain the largest number of clusters as the pre-processed ship track set, and filter out the data points that do not belong to any pre-processed ship track set as noise or outliers to filter out continuous drift points", specifically including: Step S200, obtaining the segmented data set D , and set the neighborhood radius ε and minimum number of samples MinPts ; Step S201, traverse the segmented data set D All data points in ; Step S202, determining the segmented data set D Is there an unmarked object? If yes, proceed to step S203; otherwise, proceed to step S212; Among them, labeling refers to accessing, classifying or identifying data points.

[0059] Step S203, selecting the segmented data set D Any unlabeled object in p , and the object p Mark as visited; Step S204, check the objects marked as visited p The neighborhood radius is the center ε Is the number of data points in the range less than the minimum number of samples? MinPts ; If yes, proceed to step S205; otherwise proceed to step S206; Step S205: mark the object as visited p Mark as a noise point, and then return to step S201; Step S206: mark the object as a noise point p Join a new cluster C , and all objects marked as noise points p Neighborhood radius ε Points within the range form a neighborhood sub-dataset N ; Step S207, traverse the neighborhood sub-dataset N All data points in ; Step S208, determining the neighborhood sub-dataset N Is there an unmarked object? If yes, proceed to step S209; otherwise, return to step S201; Step S209: from the neighborhood sub-dataset N Select any unlabeled object q , and the object q Mark as visited; Step S210, checking the objects marked as visited q The neighborhood radius is the center ε Is the number of data points in the range less than the minimum number of samples? MinPts ; If yes, return to step S207; otherwise, go to step S211; Step S211: mark the object as visited q Neighborhood radius ε All objects within the range are added to the neighborhood sub-dataset N , and objects that are not assigned to any clusterq Join the cluster C ; Then, go to step S212.

[0060] It should be noted that if the object q was not previously classified into any of the identified clusters and is now identified by the object p Neighborhood sub-dataset N is taken into account, then the object q Will be added to the cluster currently being built C middle: (1) Target q The neighborhood set of the object q The distance is not greater than the neighborhood radius ε The number of data points in the set of data points in the range is not less than the minimum number of samples MinPts , which indicates that the object q It is a core point or boundary point, not a noise point.

[0061] (2) Target q Relationships and clusters through density C Connected, that is, object p Already a cluster C part of the object q In the object p within the neighborhood.

[0062] Step S212, determining the neighborhood sub-dataset N Whether all data points in have been traversed; if so, go to step S213; otherwise, return to step S207.

[0063] Step S213, obtain the clustering result ( C 1, C 2,……, C k ), calculate the number of data points in different clusters, retain the cluster with the largest number as the preprocessed ship trajectory set, and filter out the data points that do not belong to any preprocessed ship trajectory set as noise or outliers to filter out continuous drift points.

[0064] Specifically, the number of data points in different clusters is calculated according to formula (4), and the argmax c | C |The cluster with the largest number of data points is identified and the identified cluster is retained as the preprocessed set of ship trajectories, which is considered to represent the normal trajectory pattern; the data points in other clusters are considered as noise or outliers and are filtered out from the dataset.

[0065] Formula (4) in, lat j , lon j Respectively represent j The latitude and longitude coordinates of the data points, C i is the cluster obtained after clustering, with a total of k different clusters; for each cluster C i , calculate the number of data points inside it, i.e. | C i |.

[0066] Please also see Figure 5 ,The effect diagram of the improved DBSCAN algorithm for filtering trajectory noise points. The left side is the visualization of the original data, and the right side is the visualization of the data after filtering using the algorithm. It can be seen that this algorithm handles the noise points in the trajectory very well.

[0067] Most of the existing ship AIS data preprocessing methods are based on speed filtering, that is, setting a threshold to remove noise points, and calculating the average speed by the distance and time difference between two adjacent data points. If the average speed is greater than the threshold, it means that the subsequent point is a noise point and is filtered. However, this method has defects: (1) When the initial point of the trajectory is a noise point, all subsequent normal points will be filtered out and the noise point will be retained, resulting in errors; (2) If there are continuous drift points, only the first noise point can be filtered out, and the subsequent noise points will not be filtered out due to the speed threshold because they are closer to the first noise point. The processing of noise points is not perfect.

[0068] The data preprocessing method described in steps S200 to S213, the DBSCAN algorithm used to filter trajectory noise points can deal with the two situations where the above-mentioned existing methods are insufficient, and has good robustness in dealing with multiple noise points in the trajectory. Through this method, abnormal points in the trajectory data can be cleaned up, including continuous outliers, so as to obtain a cleaner and more accurate trajectory data set, which is convenient for subsequent data analysis.

[0069] Step S11, analyzing the pre-processed ship trajectory set to extract feature points, clustering and region dividing the feature points to identify and group important feature points to form region boundaries, and establishing the spatial boundaries of the maritime transportation network.

[0070] The feature points include static feature points and dynamic feature points, which are used to represent nodes in the maritime transportation network.

[0071] Static feature points are areas where vessels may be paused for various reasons, including in port, waiting for a berth to become available, conducting customs inspections, or anchoring due to adverse weather conditions.

[0072] During the course of a ship's journey, there will be a place on the planned route where the ship is scheduled to change its course. When the ship reaches this place, it will often slow down and change its course. Such nodes are dynamic feature points. Subsequent ships need to slow down in advance before reaching the dynamic feature points to avoid collisions. Therefore, it is necessary to extract dynamic feature points in the process of establishing a maritime transportation network.

[0073] Please also see Figure 6 Step S11, i.e., analyzing the pre-processed ship trajectory set to extract feature points, clustering and region dividing the feature points to identify and group important feature points to form region boundaries, and establishing the spatial boundaries of the maritime transportation network, specifically includes: Step S110, analyzing the preprocessed ship trajectory set, and marking the data point as a static feature point according to the SOG value of the data point being less than a first threshold.

[0074] In this embodiment, the first threshold is 0.2 knots, that is, data points with SOG<0.2 knots / hour are marked as static feature points.

[0075] Step S111, randomly sampling a subset from the preprocessed ship trajectory set, and performing a multi-step analysis on each ship trajectory in the subset according to a maximum deviation threshold. T j Processing, forming ship tracks through inspection T j The data points for the ship trajectory T j The key dynamic feature points are extracted based on the shape of the dynamic feature point to obtain a dynamic feature point set. FP j .

[0076] The ship trajectory T j It includes multiple trajectory segments, and the maximum deviation threshold defines the maximum deviation allowed between the data point and the corresponding trajectory segment.

[0077] The AIS data points of each ship constitute the corresponding trajectory set T j , the trajectory set T j contains a series of longitude and latitude coordinate pairs, representing the position of the ship at different time points, as described in formula (5).

[0078] Formula (5) Processing trajectories through the RDP algorithm T j, as described in formula (6), the key dynamic feature points are extracted, which include the starting point, the end point of the trajectory, and the key points of changing the course during navigation. The extracted dynamic feature point set is expressed as FP j , contains the key points on the trajectory after simplification and feature extraction.

[0079] Formula (6) Since the amount of AIS data is huge, a subset is randomly sampled from the full amount of AIS data. In this implementation, 5 days of data are evenly sampled every month as the dynamic feature point extraction set.

[0080] The RDP algorithm is a polyline simplification algorithm that can reduce the number of intermediate points while maintaining the basic shape of the polyline. The maximum deviation threshold defines the maximum deviation allowed during the simplification process. If the distance from the intermediate point to the simplified polyline segment does not exceed the first parameter value, the point can be removed.

[0081] In step S10, after the AIS data is preprocessed, each ship track has been properly segmented so that the start and end of the trip are static feature points corresponding to potential docking areas. As described in step S111, the ship track is processed by the RDP algorithm, which effectively reduces the number of points in the broken line segment while retaining its basic shape, helping to identify the start point, end point, and turning point of the track, that is, the dynamic feature point.

[0082] Step S112: Analyze the dynamic feature point set FP j A clustering hierarchy is constructed based on the local density of each feature point in the cluster, a clustering result is extracted according to the stability of the clustering hierarchy, and the static feature points and the dynamic feature points are grouped according to the clustering result to obtain cluster-grouped feature points.

[0083] In this embodiment, the HDBSCAN clustering algorithm is applied to effectively identify and group the static feature points and dynamic feature points.

[0084] HDBSCAN is an extension of the DBSCAN algorithm. It is a density-based hierarchical clustering method that can identify clustering areas of different densities in the same data set. Without pre-specifying the number of clusters, it automatically identifies and extracts stable clustering structures, thereby connecting data points according to density to form different clusters. This is particularly important for maritime traffic analysis, because the distribution and behavior of ships may have different density characteristics in different areas.

[0085] HDBSCAN forms different clusters by constructing a clustering hierarchy, connecting data points according to density. In this hierarchy, the interrelationships and stability between clusters can be observed. HDBSCAN uses stability metrics to evaluate the reliability of the clustering structure. Clusters with high stability mean that their representation in the data is significant, which is of great significance for subsequent analysis and decision-making. Taking static feature points (such as ports, anchorages, etc.) and dynamic feature points (such as turning points on the route) as input, the HDBSCAN algorithm can identify the clusters to which these feature points belong, so as to identify and distinguish different maritime traffic patterns and behavior patterns, providing strong data support and insights for maritime management, route planning and safety analysis.

[0086] Please also see Figure 7 , is a schematic diagram of clustering static feature points and dynamic feature points in the study area through step S112. Figure 7 As shown, each cluster is represented by different grayscale, indicating its category label.

[0087] Step S113, the feature points of the preprocessed ship trajectory set are divided into different grids according to the geographical location for clustering and regional division, and the static feature points and dynamic feature points of the clustered groups are projected onto the grids, the grids are filtered, the grids containing important feature points are retained, and the grids containing noise or insignificant feature points are removed.

[0088] Among them, each grid is assigned a corresponding category according to the majority category labels of its internal feature points.

[0089] Specifically, the study area is spatially partitioned by geohash coding, and the study area is recursively divided into smaller grids, thereby improving the geographic resolution. In this embodiment, a 6-bit precision geohash coding is used, that is, the study area is recursively divided into 4 equal parts 6 times to obtain a geographic resolution of 0.1° latitude and 0.2° longitude.

[0090] Among them, the important feature points are representative and significant points extracted from the pre-processed AIS data, such as static feature points such as ports and anchorages, and dynamic feature points such as turning points on the route. After being processed by the clustering algorithm (such as HDBSCAN) of step S112, these points are identified and attributed to clusters with high stability, indicating that they are of great significance in data analysis. The noise-containing or insignificant feature points appear in the data set due to data errors, transmission problems or other non-representative factors, and do not represent the main maritime traffic patterns or behaviors. During the clustering process of step S112, these points may not be classified into any stable clusters, or may be identified as outliers, indicating that they are not important in the current analysis and regional division.

[0091] Step S114, from the filtered grid, according to the category labels of the feature points in the grid, the feature points belonging to the same category are compiled into a feature point set; the convex hull of the feature point set of each category is calculated to obtain a polygon, and a boundary is provided for the feature point area of ​​each category to form the spatial boundary of the maritime transportation network.

[0092] Among them, the feature point area V i It is expressed as: V i =( C i , lat i , lon i , H i ), C i is the category label, lat i is the latitude of the region centroid, lon i is the longitude of the region centroid, H i is the convex hull.

[0093] After extracting nodes, existing methods for extracting maritime traffic networks often use a method of selecting feature point regions by demarcating a specified size area based on the center of the feature point. This method cannot adapt to the spatial heterogeneity unique to maritime traffic. As a representative static feature point region, ports are divided into large ports and small ports, and dynamic feature point regions often have waypoint regions of different sizes due to the different sizes and numbers of ships passing through them.

[0094] The feature point region division algorithm described in step S114 obtains the polygon corresponding to the feature region by calculating the convex hull of the feature point set. This method represents the maritime traffic node region in a more detailed manner, adapts to the inherent spatial heterogeneity of such data, and can accommodate feature point regions of different sizes. Compared with fixed feature point regions, it is more in line with the actual situation and can better adapt to complex maritime scenes.

[0095] Step S12, analyzing the preprocessed ship trajectory set to extract feature points of the ship trajectory, identifying and recording the order in which the ships pass through the feature points to form the edges of the transportation network, and constructing the flow direction of the maritime transportation network according to the edges of the transportation network.

[0096] The edges of the transportation network are given additional attribute information. In this embodiment, the additional attribute information includes: Passing times: Records the frequency with which a ship passes each edge.

[0097] Maximum width: Record the maximum width of a vessel passing this side.

[0098] Maximum length: record the maximum length of the ship passing through this side.

[0099] Maximum draught: record the maximum draught of the vessel passing this side.

[0100] The attribute information described above provides additional contextual information for each edge, which helps to analyze the ship size distribution, traffic flow and navigation conditions, and is of great significance to maritime management, route planning and safety monitoring.

[0101] The "analyzing the preprocessed ship trajectory set to extract characteristic points of the ship trajectory, identifying and recording the order in which the ships pass through the characteristic points to form the edges of the transportation network, and constructing the flow direction of the maritime transportation network according to the edges of the transportation network" specifically includes: analyzing the preprocessed ship trajectory set, traversing each ship trajectory, identifying and extracting characteristic points of the ship trajectory; determining and recording the order in which each ship passes through the characteristic points, connecting the transportation nodes in sequence to form the edges in the maritime transportation network diagram, and constructing the flow direction of the maritime transportation network.

[0102] The traffic nodes represent ports, waterway intersections or other important maritime traffic locations, and the edges represent actual maritime traffic routes.

[0103] While traversing and building edges, additional attribute information is collected on each edge.

[0104] Recording the order in which each ship passes through traffic nodes helps to understand the ship's navigation path and traffic flow patterns.

[0105] Step S13, constructing a maritime transportation network according to the spatial boundary of the maritime transportation network and the flow direction of the maritime transportation network.

[0106] Among them, nodes and edges jointly reflect the actual layout and dynamic characteristics of maritime traffic.

[0107] Please also see Figure 8 , which is a schematic diagram of a maritime transportation network for a part of Denmark established by a maritime transportation network construction method in an embodiment of the present invention.

[0108] As described above, the method for constructing a maritime traffic network in the embodiment of the present invention has the following technical effects: by specifying a research scope to filter abnormal data, screening ship AIS data, performing itinerary segmentation processing, and calculating and completing SOG values, the quality and accuracy of the data are ensured; by analyzing the SOG value to extract static feature points, and extracting dynamic feature points based on the maximum deviation threshold, the key nodes and routes of maritime traffic can be accurately identified, providing important spatial information for network construction; by clustering the feature points through a density-based clustering algorithm, the main category clusters are effectively identified and retained, while filtering out noise and outliers, and the regional boundaries are determined by calculating the convex hull of the feature point set, adapting to different sizes The feature point areas of different shapes and shapes can represent the maritime traffic node areas in more detail; further, by projecting the feature points into different grids and filtering them, the grids containing important feature points are retained, the impact of noise is reduced, and the adaptation to spatial heterogeneity is enhanced; by identifying and recording the order in which ships pass through the feature points, the flow direction of the maritime traffic network is constructed, and the complete maritime traffic network is constructed by combining the spatial boundaries and flow direction information; according to the original AIS trajectory generated during the ship's navigation, the end-to-end generation of the maritime traffic network is for subsequent maritime traffic flow prediction and trajectory prediction, which helps to understand the complexity of maritime traffic and also provides a powerful tool for maritime management, route planning and safety monitoring.

[0109] See also Fig. 9 Corresponding to the above-mentioned method for constructing a maritime transportation network, an embodiment of the present invention further provides a maritime transportation network construction device 30, comprising: The data preprocessing unit 31 is used to obtain AIS data and preprocess the data in a specified research range of the AIS data to obtain a preprocessed ship track set.

[0110] The node establishment unit 32 is used to analyze the pre-processed ship trajectory set to extract feature points, cluster and divide the feature points into regions to identify and group important feature points to form region boundaries, and establish the spatial boundaries of the marine transportation network. The feature points include static feature points and dynamic feature points, which are used to represent nodes in the marine transportation network.

[0111] The traffic network construction unit 33 is used for: Analyzing the preprocessed ship trajectory set to extract characteristic points of the ship trajectory, identifying and recording the order in which the ships pass through the characteristic points to form edges of a transportation network, and constructing the flow direction of the marine transportation network according to the edges of the transportation network; and Construct a maritime transportation network based on its spatial boundaries and the flow direction of the maritime transportation network.

[0112] The edges in the maritime transportation network are given additional attribute information. In this embodiment, the additional attribute information includes: Passing times: Records the frequency with which a ship passes each edge.

[0113] Maximum width: Record the maximum width of a vessel passing this side.

[0114] Maximum length: record the maximum length of the ship passing through this side.

[0115] Maximum draught: record the maximum draught of the vessel passing this side.

[0116] The traffic network construction unit 33 is specifically used for: Analyzing the preprocessed ship trajectory set, traversing each ship trajectory, identifying and extracting feature points of the ship trajectory; and The order in which each ship passes through the characteristic points is determined and recorded, the traffic nodes are sequentially connected to form edges in the marine traffic network graph, and the flow direction of the marine traffic network is constructed.

[0117] Please also see Fig.10 Specifically, the data preprocessing unit 31 includes: a data cleaning module 310, a trajectory segmentation module 311, a data completion module 312, and a drift point filtering module 313.

[0118] The data cleaning module 310 is used to obtain AIS data, filter abnormal data in the AIS data by specifying a research range, and filter ship AIS data from the AIS data by ship identification to obtain ship AIS data after data cleaning. The specified research range is a range divided according to specified longitude and latitude.

[0119] In this embodiment, the data cleaning module 310 is used to filter the ship AIS data from the AIS data by using the MMSI coding rule to obtain the ship AIS data after data cleaning.

[0120] The trajectory segmentation module 311 is used to determine that the AIS data between two consecutive recording points in the ship AIS data after data cleaning is an AIS data segment with missing data based on the time interval between the two consecutive recording points exceeding the maximum segmentation time threshold, and perform itinerary segmentation processing on the AIS data segment with missing data to obtain a segmented data set.

[0121] Each segment contains a series of continuous AIS data points with no time interval exceeding the maximum segment time threshold. The recording point is the time point at which the ship's position information is recorded in the AIS data, and the time point at least includes the ship's latitude and longitude coordinates, timestamp, speed, and heading information.

[0122] In this implementation, the maximum segment time threshold is 30 minutes.

[0123] The data completion module 312 is used to calculate the SOG for the continuous AIS data points in each segment of the segmented data set, and complete the calculated SOG value into the corresponding AIS data point to obtain the AIS data point with speed information.

[0124] Further, please also refer to Fig.11 , the data completion module 312 includes: The SOG calculation submodule 3120 is used to determine the longitude and latitude coordinates between each two AIS data points in each segment of the segmented data set, calculate the great circle distance between the two AIS data points and the time difference between the two AIS data points, and divide the great circle distance between the two points by the time difference between the two points to obtain the SOG. As described in formula (1): SOG = Great Circle Distance / Time Difference Formula (1) The information completion submodule 3121 is used to analyze the AIS data points in each segment of the segmented data set to determine the missing attribute information, obtain the corresponding ship information from the ship database through ship identification, and extract the missing attribute information from the ship database, and complete it to the corresponding AIS data point to obtain the AIS data point with complete attribute information. The attribute information at least includes ship type, width, and length information.

[0125] The drift point filtering module 313 is used to filter the drift points in the AIS data points with speed information, wherein the drift points include independent drift points and continuous drift points.

[0126] Please also see Fig.12 The drift point filtering module 313 comprises: The independent drift point filtering submodule 3130 is used to filter the independent drift points according to the SOG of the AIS data points with speed information being less than the SOG threshold.

[0127] The continuous drift point filtering submodule 3131 is used to adjust the neighborhood radius ε and the minimum number of samples. MinPts The parameters are used to cluster the AIS data points in each segment of the segmented data set to form clusters, identify and retain the cluster with the largest number as the preprocessed ship track set, and filter out the data points that do not belong to any preprocessed ship track set as noise or outliers to filter out continuous drift points.

[0128] In this embodiment, the SOG threshold is 40 nautical miles per hour.

[0129] In this embodiment, the drift point filtering module 313 applies the DBSCAN algorithm to the AIS data points in each segment of the segmented data set (ie, each segmented ship track) to filter the continuous drift points.

[0130] Ships j The trajectory of the observation sequence Definition, where the data points Defined by formula (2): Formula (2) In formula (2), i is a total of m The index of the point. MMSI j Represented as a ship j of MMSI , , and Respectively represent ships j SOG, COG and navigation status, and Ships j In time The latitude and longitude position of the .

[0131] Dataset D Center and data points X The distance is no greater than ε The sub-dataset of N ε(xj) , calculated by formula (3): Formula (3) The continuous drift point filtering submodule 3131 is specifically used for: Get the segmented dataset D , and set the neighborhood radius ε and minimum number of samples MinPts ; Traverse the segmented dataset D All data points in ; Select the segmented dataset D Any unlabeled object in p , and mark the object p marked as visited as visited; The radius of the neighborhood centered on the object p marked as visited ε The number of data points in the range is less than the minimum number of samples MinPts, then the object p marked as visited is marked as a noise point, and the segmented data set is traversed again D All data points in ; the neighborhood radius centered on the object p marked as visited ε The number of data points in the range is not less than the minimum number of samples MinPts , then the object p marked as visited is added to a new cluster C , and all objects in the neighborhood radius of the object p marked as visited ε Points within the range form a neighborhood sub-dataset N ; Traverse the neighborhood sub-datasets N All data points in ; Select the neighborhood subdataset N Any unlabeled object in q , and mark the object p marked as visited as visited; The radius of the neighborhood centered on the object p marked as visited ε The number of data points in the range is less than the minimum number of samples MinPts , then execute the traversal of the neighborhood sub-dataset N All points in; the neighborhood radius centered on the object p marked as visited ε The number of data points in the range is not less than the minimum number of samples MinPts , then the neighborhood radius of the object p that will be marked as visited is ε All objects within the range are added to the neighborhood sub-dataset N , add the object p marked as visited that is not included in any cluster to the cluster C , execute the traversal of the neighborhood sub-dataset N All data points in ; Traverse the neighborhood sub-datasets N All data points in the clustering result are obtained ( C 1, C 2,……, C k ), calculate the number of data points in different clusters, retain the cluster with the largest number as the preprocessed ship trajectory set, and filter out the data points that do not belong to any preprocessed ship trajectory set as noise or outliers to filter out continuous drift points.

[0132] Specifically, the continuous drift point filtering submodule 3131 calculates the number of data points in different clusters according to formula (4), and uses argmax c | C|The cluster with the largest number of data points is identified and the identified cluster is retained as the preprocessed set of ship trajectories, which is considered to represent the normal trajectory pattern; the data points in other clusters are considered as noise or outliers and are filtered out from the dataset.

[0133] Formula (4) in, Respectively represent j The latitude and longitude coordinates of the data points, C i is the cluster obtained after clustering, with a total of k different clusters; for each cluster C i , calculate the number of data points inside it, i.e. | C i |.

[0134] Please also see Fig.13 The node establishment unit 32 includes: a static feature point extraction module 320, a dynamic feature point extraction module 321, a feature point clustering module 322, and a feature point area division module 323.

[0135] The static feature point extraction module 320 is used to analyze the pre-processed ship trajectory set and mark the data point as a static feature point if its SOG value is less than a first threshold.

[0136] In this embodiment, the first threshold is 0.2 knots.

[0137] The dynamic feature point extraction module 321 is used to randomly sample a subset from the pre-processed ship trajectory set, and extract each ship trajectory in the subset according to the maximum deviation threshold. T j Processing, forming ship tracks through inspection T j The data points for the ship trajectory T j The key dynamic feature points are extracted based on the shape of the dynamic feature point to obtain a dynamic feature point set. FP j .

[0138] In this embodiment, the dynamic feature point extraction module 321 extracts each track in the subset by using the RDP algorithm. T j Extract key dynamic feature points to obtain a set of dynamic feature points FP j .

[0139] The AIS data points of each ship constitute the corresponding trajectory set T j , the trajectory set T j contains a series of longitude and latitude coordinate pairs, representing the position of the ship at different time points, as described in formula (5).

[0140] Formula (5) Processing trajectories through the RDP algorithm T j , as described in formula (6), the key dynamic feature points are extracted, which include the starting point, the end point of the trajectory, and the key points of changing the course during navigation. The extracted dynamic feature point set is expressed as FP j , contains the key points on the trajectory after simplification and feature extraction.

[0141] Formula (6) In this embodiment, data of 5 days are uniformly sampled every month as the dynamic feature point extraction set.

[0142] The feature point clustering module 322 is used to analyze the dynamic feature point set FP j A clustering hierarchy is constructed based on the local density of each feature point in the cluster, a clustering result is extracted according to the stability of the clustering hierarchy, and the static feature points and the dynamic feature points are grouped according to the clustering result to obtain cluster-grouped feature points.

[0143] In this embodiment, the feature point clustering module 322 uses the HDBSCAN clustering algorithm to effectively identify and group the static feature points and dynamic feature points.

[0144] The feature point region division module 323 is used to: The feature points of the preprocessed ship trajectory set are divided into different grids according to their geographical locations for clustering and regional division, and the static feature points and dynamic feature points of the clustered groups are projected onto the grids, and the grids are filtered to retain grids containing important feature points and remove grids containing noise or insignificant feature points; wherein each grid is assigned a corresponding category according to the majority category labels of its internal feature points; From the filtered grid, according to the category labels of the feature points in the grid, the feature points belonging to the same category are compiled into a feature point set; and The convex hull is calculated for the feature point set of each category to obtain a polygon, which provides a boundary for the feature point area of ​​each category and forms the spatial boundary of the maritime transportation network.

[0145] Among them, the feature point area V i It is expressed as: V i =( C i , lat i , lon i , H i ),in, C i is the category label, lat i is the latitude of the region centroid, lon i is the longitude of the region centroid, H i is the convex hull.

[0146] Specifically, the feature point region division module 323 spatially partitions the study area through geohash coding, and recursively divides the study area into smaller grids. In this embodiment, a 6-bit precision geohash coding is used, that is, the study area is recursively divided into 4 equal parts 6 times to obtain a geographic resolution of 0.1° latitude and 0.2° longitude.

[0147] The advantages and beneficial effects of a method for constructing a maritime transportation network have been explained above and will not be repeated here. Moreover, since a device for constructing a maritime transportation network is applied to a method for constructing a maritime transportation network, it satisfies the method for constructing a maritime transportation network and has the same advantages and beneficial effects.

[0148] One of the embodiments of the present invention also provides a readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the steps of the method for constructing a maritime transportation network as described in any of the above embodiments.

[0149] One of the embodiments of the present invention also provides an electronic device, including: a processor and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the electronic device executes the steps of the maritime transportation network construction method described in any of the above embodiments.

[0150] See also Fig.14 , is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention.

[0151] The electronic device 4 includes a processor 41, a memory 42, an input device 43, and an output device 44. The processor 41, the memory 42, the input device 43, and the output device 44 are coupled via a connector, and the connector includes various interfaces, transmission lines, or buses, etc., which are not limited in the embodiments of the present invention. It should be understood that in various embodiments of the present invention, coupling refers to mutual connection in a specific manner, including direct connection or indirect connection through other devices, for example, through various interfaces, transmission lines, buses, etc.

[0152] The processor 41 described in the embodiment of the present application can be implemented by hardware, firmware, software or a combination thereof, and can use a circuit, a single or multiple application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processor, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, at least one of a microprocessor, and also includes other physical, biological or chemical structures that can achieve similar or equivalent functions to the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of the present application, or any combination of the steps mentioned therein. In the electronic device 4 in this embodiment, the processor 41 can be a single processor or a combination of two or more processors in terms of physical entity, such as a combination of a CPU and a GPU, a combination of a CPU and an FPGA, a combination of a CPU and an ASIC, a combination of a CPU and a coprocessor, and a combination of a CPU and a DSP, etc. In the embodiments, these combinations are collectively referred to as processors like a single processor.

[0153] The computer program 45 involved in the embodiment can be stored in a computer device readable storage medium, which includes but is not limited to a disk, a tape, a magnetic card, a floppy disk, a flash memory, an optical disk, an optical card, a read-only memory (ROM), a random access memory (RAM), an erasable programmable ROM (EPROM) and an electrically erasable programmable ROM (EEPROM), etc., and also includes other biological, physical or chemical structures that can achieve similar or equivalent functions to the storage media listed above, such as DNA, RNA, protein and other units with information storage capabilities. In a specific embodiment, the storage medium involved can be one of the above-mentioned media types, or a combination of the above-mentioned media types. In different embodiments, the computer program involved in the embodiment can be stored in a single medium in a centralized manner, or can be stored in multiple media in a distributed manner.

[0154] The memory 42 containing a computer device readable storage medium may be a non-volatile memory or a random access memory. These computer device readable storage media may be built into the device, or may be connected to the device involved in the embodiment as an external device or part of an external device. In some embodiments, the memory with a computer device readable storage medium is deployed locally; in other embodiments, a scheme of deploying the memory away from the processor may also be adopted, such as a network attached memory accessed via an RF circuit or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), etc., or a suitable combination thereof, as long as the computer device can access the memory. In addition, the computer program involved in the embodiment may be stored in plaintext / ciphertext form, or may be designed as training data, which may be integrated and reorganized by model training and implicitly stored in the parameter state of a deep neural network or other machine learning model.

[0155] like Fig.14 In the illustrated embodiment, the computer program 45 is stored in the memory 42 of the electronic device 4, but the reader should be aware that other solutions that can enable the processor to execute the computer program are feasible.

[0156] The input device 43 is used to input data and / or signals, and the output device 44 is used to output data and / or signals. The output device 44 and the input device 43 may be independent devices or an integrated device.

[0157] It is understandable that in the implementation manner of the present invention, the memory 42 is not only used to store related instructions, and the implementation manner of the present invention does not limit the specific data stored in the memory.

[0158] Understandably, Fig.14Only a simplified design of an electronic device is shown. In practical applications, the electronic device may also include other necessary components, including but not limited to any number of input / output devices, processors, memories, etc., and all methods for constructing a marine transportation network that can implement the embodiments of the present invention are within the protection scope of the present invention.

[0159] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical or other forms.

[0160] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0161] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0162] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of the present invention can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a management server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: read-only memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

[0163] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A method for constructing a marine transportation network, characterized in that: The method comprises: Acquire AIS data, and preprocess the data in a specified research range of the AIS data to obtain a preprocessed ship trajectory set; Analyze the preprocessed ship trajectory set to extract feature points, cluster and divide the feature points into regions to identify and group important feature points to form regional boundaries, and establish the spatial boundaries of the maritime transportation network; wherein the feature points include static feature points and dynamic feature points; Analyzing the preprocessed ship trajectory set to extract characteristic points of the ship trajectory, identifying and recording the order in which the ships pass through the characteristic points to form edges of a transportation network, and constructing the flow direction of the marine transportation network according to the edges of the transportation network; and Construct a maritime transportation network based on its spatial boundaries and the flow direction of the maritime transportation network.

2. The method for constructing a marine transportation network according to claim 1, characterized in that: Obtain AIS data and preprocess the data in the specified research range of AIS data, including: Acquire AIS data, filter abnormal data in the AIS data by specifying a research range, and filter ship AIS data from the AIS data by ship identity recognition to obtain cleaned ship AIS data; According to the time interval between two consecutive recording points in the ship AIS data after data cleaning exceeding the maximum segmentation time threshold, the AIS data between the two consecutive recording points is determined to be an AIS data segment with data missing, and the AIS data segment with data missing is processed by itinerary segmentation to obtain a segmented data set; Calculating SOG for continuous AIS data points in each segment of the segmented data set, and completing the calculated SOG value into the corresponding AIS data point to obtain the AIS data point with speed information; and The drifting points among the AIS data points with speed information are filtered.

3. The method for constructing a marine transportation network according to claim 2, characterized in that: in, The drift points include independent drift points and continuous drift points; Filtering the drift points in the AIS data points with speed information specifically includes: Filtering independent drift points according to the SOG of the AIS data points with speed information being less than the SOG threshold; as well as The AIS data points in each segment of the segmented data set are clustered to form clusters by adjusting the neighborhood radius and the minimum number of samples parameters, the cluster with the largest number is identified and retained as the main category cluster, and the data points that do not belong to any main category cluster are regarded as noise or outliers and filtered out to filter out continuous drift points.

4. The method for constructing a marine transportation network according to claim 3, characterized in that: The AIS data points in each segment of the segmented data set are clustered by adjusting the neighborhood radius and the minimum number of samples parameters to form clusters, the largest number of clusters are identified and retained as the pre-processed ship track set, and the data points that do not belong to any pre-processed ship track set are regarded as noise or outliers and filtered out to filter out continuous drift points, specifically including: Get the segmented data set and set the neighborhood radius and minimum number of samples; Iterate over all data points in the segmented data set; Select any unlabeled object in the segmented dataset p , and the object p Mark as visited; To mark an object as visited p If the number of data points within the neighborhood radius of the center is less than the minimum number of samples, the object will be marked as visited. p Mark as noise point, and re-traverse all data points in the segmented data set; mark as noise point p The number of data points within the neighborhood radius as the center is not less than the minimum number of samples, and the object marked as a noise point is executed. p Join a new cluster C , and all objects marked as noise points p The points within the neighborhood radius form a neighborhood sub-dataset; Traverse all data points in the neighborhood sub-dataset; Select any unlabeled object from the neighborhood sub-dataset q , and the object q Mark as visited; To mark an object as visited q If the number of data points within the neighborhood radius as the center is less than the minimum number of samples, all data points in the neighborhood sub-dataset are traversed; and objects are marked as visited. q The number of data points within the neighborhood radius of the center is not less than the minimum number of samples, and the object marked as visited is executed. q All objects within the neighborhood radius of are added to the neighborhood sub-dataset, and objects that are not classified into any cluster are q Join the cluster C ; All data points in the neighborhood sub-dataset are traversed to obtain clustering results, the number of data points in different clusters in the clustering results is calculated, the cluster with the largest number is retained as the preprocessed ship trajectory set, and the data points that do not belong to any preprocessed ship trajectory set are regarded as noise or outliers and filtered out to filter out continuous drift points.

5. The method for constructing a marine transportation network according to claim 1, characterized in that: Analyzing the preprocessed ship trajectory set to extract feature points, clustering and regionalizing the feature points to identify and group important feature points to form regional boundaries, and establishing the spatial boundaries of the maritime transportation network, specifically including: Analyzing the preprocessed ship trajectory set, and marking the data point as a static feature point according to the SOG value of the data point being less than a first threshold; A subset is obtained by randomly sampling from the preprocessed ship trajectory set, each ship trajectory in the subset is processed according to a maximum deviation threshold, and key dynamic feature points are extracted by checking the influence of the data points forming the ship trajectory on the shape of the ship trajectory to obtain a dynamic feature point set; wherein the ship trajectory includes a plurality of trajectory segments, and the maximum deviation threshold is used to define the maximum deviation allowed between the data point and the corresponding trajectory segment; Analyzing the local density of each feature point in the dynamic feature point set to construct a clustering hierarchy, extracting clustering results according to the stability of the clustering hierarchy, and clustering the static feature points and the dynamic feature points according to the clustering results to obtain important feature points contained in clustering groups with high stability; The feature points of the preprocessed ship trajectory set are divided into different grids according to their geographical locations for clustering and regional division, and the static feature points and dynamic feature points of the clustered groups are projected onto the grids, and the grids are filtered to retain grids containing important feature points and remove grids containing noise or insignificant feature points; wherein each grid is assigned a corresponding category according to the category labels of its internal feature points; From the filtered grid, feature points belonging to the same category are compiled into a feature point set according to the category labels of the feature points in the grid; The convex hull is calculated for the feature point set of each category to obtain a polygon, which provides a boundary for the feature point area of ​​each category and forms the spatial boundary of the maritime transportation network.

6. The method for constructing a marine transportation network according to claim 1, characterized in that: Analyzing the preprocessed ship trajectory set, identifying and recording the order in which the ships pass through the feature points to form the edges of the transportation network, and constructing the flow direction of the marine transportation network according to the edges of the transportation network, specifically includes: Analyzing the preprocessed ship trajectory set, traversing each ship trajectory, identifying and extracting feature points of the ship trajectory; Determine and record the order in which each ship passes through the characteristic points, connect the traffic nodes in sequence to form edges in the maritime traffic network diagram, and construct the flow direction of the maritime traffic network; wherein the traffic nodes represent ports, waterway intersections or other important maritime traffic locations; and the edges represent actual maritime traffic routes.

7. A marine transportation network construction device, characterized in that: The device comprises: A data preprocessing unit, used for acquiring AIS data, and preprocessing data in a specified research range of the AIS data to obtain a preprocessed ship trajectory set; A node establishment unit, used for analyzing the pre-processed ship trajectory set to extract feature points, clustering and region dividing the feature points to identify and group important feature points to form region boundaries, and establishing the spatial boundaries of the maritime transportation network; wherein the feature points include static feature points and dynamic feature points, which are used to represent nodes in the maritime transportation network; Traffic network building blocks for: Analyzing the preprocessed ship trajectory set to extract characteristic points of the ship trajectory, identifying and recording the order in which the ships pass through the characteristic points to form edges of a transportation network, and constructing the flow direction of the marine transportation network according to the edges of the transportation network; and Construct a maritime transportation network based on its spatial boundaries and the flow direction of the maritime transportation network.

8. The marine transportation network construction device according to claim 7, characterized in that: The data preprocessing unit comprises: A data cleaning module is used to obtain AIS data, filter abnormal data in the AIS data by specifying a research range, and filter ship AIS data from the AIS data by ship identity recognition to obtain ship AIS data after data cleaning; A trajectory segmentation module is used to determine that the time interval between two consecutive recording points in the ship AIS data after data cleaning exceeds the maximum segmentation time threshold, and the AIS data between the two consecutive recording points is an AIS data segment with missing data, and the AIS data segment with missing data is segmented to obtain a segmented data set; A data completion module, used to calculate SOG for continuous AIS data points in each segment of the segmented data set, and complete the calculated SOG value to the corresponding AIS data point to obtain the AIS data point with speed information; A drift point filtering module is used to filter the drift points in the AIS data points with speed information; wherein the drift points include independent drift points and continuous drift points.

9. The marine transportation network construction device according to claim 8, characterized in that: The drift point filtering module comprises: An independent drift point filtering submodule, used to filter independent drift points according to the SOG of the AIS data points with speed information being less than the SOG threshold; The continuous drift point filtering submodule is used to cluster the AIS data points in each segment of the segmented data set to form clusters by adjusting the neighborhood radius and the minimum number of samples parameters, identify and retain the cluster with the largest number as the preprocessed ship trajectory set, and treat the data points that do not belong to any preprocessed ship trajectory set as noise or outliers and filter them out to filter the continuous drift points.

10. The marine transportation network construction device according to claim 9, characterized in that: The continuous drift point filtering submodule is specifically used for: Obtain the segmented data set, and set the neighborhood radius and the minimum number of samples; Iterate over all data points in the segmented data set; Select any unlabeled object in the segmented dataset p , and the object p Mark as visited; To mark an object as visited p If the number of data points within the neighborhood radius centered is less than the minimum number of samples, the object marked as visited will be executed. p Mark as noise point, and re-execute the traversal of all data points in the segmented data set; mark as noise point object p If the number of data points within the neighborhood radius centered is not less than the minimum number of samples, the execution will mark it as a noise point object p Join a new cluster C , and all objects marked as noise points p The points within the neighborhood radius form a neighborhood sub-dataset; Traverse all data points in the neighborhood sub-dataset; Select any unlabeled object in the neighborhood sub-dataset q , and the object q Mark as visited; To mark an object as visited q If the number of data points within the neighborhood radius centered is less than the minimum number of samples, all points in the neighborhood sub-dataset are traversed; and objects are marked as visited. q If the number of data points within the neighborhood radius of the center is not less than the minimum number of samples, the object marked as visited will be executed. q All objects within the neighborhood radius of are added to the neighborhood sub-dataset, and objects that are not classified into any cluster are q Join the cluster C , execute traversal of all data points in the neighborhood sub-dataset; All data points in the neighborhood sub-dataset are traversed to obtain clustering results, the number of data points in different clusters is calculated, the cluster with the largest number is retained as the preprocessed ship trajectory set, and the data points that do not belong to any preprocessed ship trajectory set are regarded as noise or outliers and filtered out to filter out continuous drift points.

11. The marine transportation network construction device according to claim 7, characterized in that: The node establishment unit comprises: A static feature point extraction module, used for analyzing the pre-processed ship trajectory set, and marking a data point as a static feature point according to a SOG value less than a first threshold; A dynamic feature point extraction module, used for randomly sampling from the pre-processed ship trajectory set to obtain a subset, processing each ship trajectory in the subset according to a maximum deviation threshold, extracting key dynamic feature points by checking the influence of the data points forming the ship trajectory on the shape of the ship trajectory, so as to obtain a dynamic feature point set; wherein the ship trajectory includes a plurality of trajectory segments, and the maximum deviation threshold is used to define the maximum deviation allowed between the data point and the corresponding trajectory segment; A feature point clustering module, used for analyzing the local density of each feature point in the dynamic feature point set to construct a clustering hierarchy, extracting clustering results according to the stability of the clustering hierarchy, and clustering and grouping the static feature points and the dynamic feature points according to the clustering results to obtain important feature points contained in clustering groups with high stability; Feature point area division module, used for: The feature points of the preprocessed ship trajectory set are divided into different grids according to their geographical locations for clustering and regional division, and the static feature points and dynamic feature points of the clustered groups are projected onto the grids, and the grids are filtered to retain grids containing important feature points and remove grids containing noise or insignificant feature points; wherein each grid is assigned a corresponding category according to the majority category labels of its internal feature points; From the filtered grid, according to the category labels of the feature points in the grid, the feature points belonging to the same category are compiled into a feature point set; and The convex hull is calculated for the feature point set of each category to obtain a polygon, which provides a boundary for the feature point area of ​​each category and forms the spatial boundary of the maritime transportation network.

12. The marine transportation network construction device according to claim 7, characterized in that: The traffic network construction unit is specifically used for: Analyzing the preprocessed ship trajectory set, traversing each ship trajectory, identifying and extracting feature points of the ship trajectory; and Determine and record the order in which each ship passes through the characteristic points, connect the traffic nodes in sequence to form edges in the maritime traffic network diagram, and construct the flow direction of the maritime traffic network; wherein the traffic nodes represent ports, waterway intersections or other important maritime traffic locations; and the edges represent actual maritime traffic routes.

13. An electronic device comprising: A processor and a memory, characterized in that the memory is used to store computer program codes, the computer program codes include computer instructions, and when the processor executes the computer instructions, the electronic device executes the steps of the method for constructing a maritime transportation network as described in any one of claims 1 to 6.

14. A readable storage medium having a computer program stored therein, characterized in that: The computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the steps of the marine transportation network construction method as described in any one of claims 1 to 6.

Images