A method and system for local path adaptive reconstruction in AIS cluster

Abstract

The application provides an AIS cluster local path adaptive reconstruction method and system, comprising the following steps: according to user input start and end points and expected speed, and based on an offline constructed maritime traffic network connectivity graph planning, a global route is generated, and through local path reconstruction on a cluster where a route turning point is located, global heading information of the global route is obtained; according to the global heading information and the expected speed, an optimal sub-cluster in the cluster where the route turning point is located is obtained; through an adaptive algorithm, a cluster entrance reference point and a cluster exit reference point in the optimal sub-cluster are obtained, the local path in the cluster is reconstructed according to the cluster entrance reference point and the cluster exit reference point, and the global heading information of the global route is updated. The application uses the global heading information and combines AIS trajectory points in the clustering cluster to guide adaptive reconstruction of the local path in the cluster, so that the centroid of the clustering cluster is no longer directly connected, the route planning is more in line with logic, and the authenticity and availability of the route planning are improved.

Description

Technical Field

[0001] This application belongs to the field of ship route planning technology, and in particular relates to a method and system for adaptive reconstruction of local paths within an AIS cluster. Background Technology

[0002] The maritime traffic network mined from AIS big data can not only plan routes that are more in line with ship navigation habits and actual navigation characteristics, but also greatly simplify the reliance on nautical chart data for route planning, thereby improving the accuracy and reliability of route planning.

[0003] There are still shortcomings in the current construction of route networks. For example, the following defects exist in the process of constructing route networks based on the HDBSCAN algorithm for clustering AIS trajectory points:

[0004] (1) Directly select the centroid of the cluster as the key turning point of the route network and connect the centroids directly to construct the route network. In this way, the route planning directly connects the centroids within the cluster, and the local paths within the cluster will lose the true route characteristics or not conform to the navigation habits.

[0005] (2) By constructing a route network through multi-dimensional clustering or hierarchical clustering of latitude, longitude, speed and heading features, although the authenticity of the route network and traffic flow are taken into account, it is difficult to determine the weight factors. At the same time, multi-dimensional clustering is computationally expensive, not easy to update and difficult to optimize parameters. Summary of the Invention

[0006] In view of this, this application aims to propose a method and system for adaptive local path reconstruction within an AIS cluster to solve at least one of the above-mentioned problems.

[0007] To achieve the above objectives, the technical solution of this application is implemented as follows:

[0008] In a first aspect, this application provides an adaptive local path reconstruction method within an AIS cluster, characterized by comprising:

[0009] Based on the user's input of the start and end points and desired speed, and based on the offline constructed maritime traffic network connectivity map, a global route is planned and generated. By reconstructing the local path of the cluster where the route turning point is located, the global heading information of the global route is obtained.

[0010] The optimal sub-cluster within the cluster containing the route turning point is obtained based on the global heading information and the desired speed.

[0011] The cluster ingress reference point and cluster egress reference point within the optimal sub-cluster are obtained through an adaptive algorithm. Based on the cluster ingress reference point and the cluster egress reference point, the local path within the cluster is reconstructed, and the global heading information of the global route is updated.

[0012] Secondly, based on the same inventive concept, this application also provides an AIS cluster local path adaptive reconstruction system, comprising:

[0013] The global route planning module is configured to generate a global route based on the user-input start and end points and desired speed, and on an offline-constructed maritime traffic network connectivity graph. The global heading information of the global route is obtained by reconstructing the local path of the cluster where the route turning point is located.

[0014] The optimal subcluster determination module is configured to determine the optimal subcluster within the cluster where the route turning point is located based on the global heading information and the desired speed.

[0015] The adaptive reconstruction module is configured to obtain the cluster inlet reference point and cluster outlet reference point within the optimal sub-cluster through an adaptive algorithm, and reconstruct the local path within the cluster based on the cluster inlet reference point and the cluster outlet reference point to update the global heading information of the global route.

[0016] Thirdly, based on the same inventive concept, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect.

[0017] Fourthly, based on the same inventive concept, this application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method as described in the first aspect.

[0018] Compared with existing technologies, the adaptive local path reconstruction method and system within an AIS cluster described in this application have the following advantages:

[0019] The adaptive reconstruction method for local paths within an AIS cluster described in this application uses historical AIS trajectory points as the data source, obtains global routes based on the maritime traffic network connectivity graph, and performs secondary clustering only on the clusters containing turning points involved in the global routes to improve the efficiency of secondary clustering. Based on global heading information and desired speed, the optimal subclass is found, and the AIS trajectory points in the optimal subclass are traversed. By calculating the distance, speed, and heading cost with adaptive weights weighted by inverse standard deviation, the in-cluster entry reference point and in-cluster exit reference point are obtained, and the local routes within the cluster are reconstructed, increasing the realism of the planned routes. Attached Figure Description

[0020] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0021] Figure 1 This is a flowchart of an AIS cluster local path adaptive reconstruction method according to an embodiment of this application;

[0022] Figure 2 This is a comparison diagram of the initial global route and the route after adaptive reconstruction of the local path as described in the embodiments of this application;

[0023] Figure 3 This refers to the initial global route and the local path reconstruction graph without adaptive weights as described in the embodiments of this application;

[0024] Figure 4 This refers to the initial global route and the local path reconstruction graph with adaptive weights as described in the embodiments of this application;

[0025] Figure 5 This is a schematic diagram of an AIS cluster local path adaptive reconstruction system structure according to an embodiment of this application;

[0026] Figure 6 This is a schematic diagram of the hardware structure of the electronic device described in an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0028] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0029] The embodiments of this application are described in detail below with reference to the accompanying drawings.

[0030] Please see Figure 1 As shown, this embodiment provides a method for adaptive reconstruction of local paths within an AIS cluster, specifically including the following steps:

[0031] Step S101: Based on the user's input of the starting and ending points and the desired speed, and based on the offline constructed maritime traffic network connectivity graph, a global route is planned and generated. By reconstructing the local path of the cluster where the route turning point is located, the global heading information of the global route is obtained.

[0032] Specifically, in this embodiment, the user inputs the departure point, destination, and desired speed, and a global route is generated based on the offline constructed maritime traffic network connectivity map. ,in, and These are the user-inputted origin and destination, and turning points. This includes latitude and longitude location, speed, and heading information, as well as cluster numbers obtained from latitude and longitude clustering. and It is the centroid location of the cluster, and may not be a real historical AIS trajectory point.

[0033] The offline-constructed maritime traffic network connectivity graph is an undirected graph obtained by preprocessing, cleaning, compressing, and clustering AIS data from around the world for a full year. The user-input origin and destination can be ports or any location. The shortest point in the maritime traffic network is automatically matched using a path planning algorithm (it should be noted that this algorithm is existing technology in this field, and this embodiment has not improved it, so it will not be described in detail). Then, a global route with the shortest distance is planned using Dijkstra's algorithm. The turning point of the global route is the node of the undirected graph, which is the centroid of the cluster.

[0034] Calculate the turning point of the current route respectively Turning point of the previous route Next turning point The angle between the line connecting the two directions and due north. and This serves as the current cluster's entry and departure reference headings. The formula for calculating the included angle is as follows:

[0035] ;

[0036] In the formula, and Turning point and Latitude and longitude, in radians.

[0037] Step S102: Obtain the optimal sub-cluster within the cluster where the route turning point is located based on the global heading information and the desired speed.

[0038] Specifically, in this embodiment, the purpose of this step is to find the nearest sub-cluster based on the global heading information of the global flight path and the user-inputted desired speed. The specific steps are as follows:

[0039] Based on the global route turning points planned in S101, all clusters included in the route are obtained. These clusters are obtained by clustering the historical trajectory points of AIS using their latitude and longitude features when generating the maritime traffic network.

[0040] Find all AIS historical trajectory points within a cluster based on the cluster number of the turning point.

[0041] , ;

[0042] Among them, the centroid The corresponding cluster is , For clusters The AIS track point set, each point includes attributes such as longitude, latitude, speed, and heading.

[0043] Determine the number of AIS trajectory points within a cluster. If the corresponding number of trajectory points within the cluster is... Greater than (In this embodiment, 20 is selected) When the cluster is selected, local path reconstruction is performed on the cluster; otherwise, the original turning point is maintained and the next cluster is determined.

[0044] The HDBSCAN algorithm is used to cluster the velocity and heading characteristics of AIS trajectory points within a cluster, resulting in sub-clusters. The velocity and heading centroids of these sub-clusters are then calculated. Since the heading ranges from 0° to 360°, it is transformed during clustering to avoid boundary error issues.

[0045] ;

[0046] in, This provides the heading information for trajectory points within a cluster, ensuring that turning points near 0° and near 360° are within the same sub-cluster. After clustering, the centroids of the sub-clusters are determined. It is the average of the velocity and heading of all trajectory points within the sub-cluster.

[0047] Traverse the centroids of the subclusters and calculate the minimum value of the difference between the current cluster's inbound reference heading and the current cluster's outbound reference heading and the centroid's heading, obtained in step S1. and If the minimum value is greater than (60° is selected in this embodiment), indicating that there is a significant difference between the main traffic flow direction and the reference heading of this cluster. In this case, adaptive reconstruction of the cluster is not performed; otherwise, proceed to the next step.

[0048] Traverse the subclusters, and calculate the subcluster with the smallest velocity difference and orientation difference as the optimal subcluster. The calculation formula is as follows:

[0049] ;

[0050] ;

[0051] ;

[0052] ;

[0053] ;

[0054] ;

[0055] in, This is the cluster number. The sub-cluster number is obtained by clustering the current cluster based on velocity and heading characteristics. and For the first The centroid velocity and heading of each sub-cluster The desired course entered by the user. and The difference between the center of mass and the desired velocity, and the maximum value of the difference. and The difference between the current cluster's entry reference heading and its center of mass, and the maximum value of this difference. and The difference between the current cluster's departure reference heading and its center of mass, and the maximum difference thereof. Let cost function be The sub-cluster where the cluster entrance reference point is located. This refers to the sub-cluster where the cluster exit reference point is located.

[0056] In step S102 of this embodiment, the global heading information of the global path guides the reconstruction of local paths within the cluster. Historical AIS trajectory points within the cluster that better match the speed and heading characteristics are selected as route turning points, avoiding the problem of losing the true route characteristics or not conforming to navigation habits due to direct connection of centroids within the cluster. At the same time, guided by the global path, it is only necessary to consider the secondary clustering problem of the clusters where a few turning points are located online, and it is not necessary to perform secondary clustering on all clusters to reconstruct the maritime traffic network map, which greatly reduces the computational consumption and improves the planning efficiency.

[0057] Step S103: Obtain the cluster inlet reference point and cluster outlet reference point within the optimal sub-cluster using an adaptive algorithm, and reconstruct the local path within the cluster based on the cluster inlet reference point and cluster outlet reference point.

[0058] Specifically, in this embodiment, based on the global flight path's turning point, global heading information, desired speed, and optimal subcluster, the "cluster entry reference point" and "cluster exit reference point" within the cluster are adaptively found. Connecting these two reference points replaces the direct connection of the cluster centroid, thus completing the local path reconstruction within the cluster. The specific steps are as follows:

[0059] Step S301: Traverse the optimal sub-clusters respectively and Historical AIS trajectory points, calculate the previous turning point and sub-cluster Calculate the distance, heading difference, velocity difference, variance, and adaptive weights of all trajectory points within the cluster, and then calculate the next turning point and subcluster. The total agency value is calculated by taking the distance, heading difference, velocity difference, variance, and adaptive weights of all trajectory points within the trajectory. and The specific formula is as follows:

[0060] ;

[0061] ;

[0062] ;

[0063] ;

[0064] in, , , , , , ;

[0065] In the formula, For the Earth's radius, and Clusters The optimal subcluster within and The trajectory point number within, and These are the previous turning point and the sub-cluster, respectively. Inner trajectory points Latitude and longitude, in radians. and sub-clusters Inner trajectory points The heading angle and speed; and Distance from the previous turning point to the sub-cluster interior point The distance and standard deviation, and The current cluster is entering the reference navigation. sub-clusters Inner trajectory points The heading difference and standard deviation, and It is the expected speed and sub-clusters Inner trajectory points The difference in speed and its standard deviation. , and Calculate the total agency value respectively Distance weight, heading difference weight, and speed weight at time; and Distance subcluster for the next turning point Inner trajectory points The distance and standard deviation, and The current cluster has departed from the reference navigation. sub-clusters Inner trajectory points The heading difference and standard deviation, and It is the expected speed and sub-clusters Inner trajectory points Speed ​​difference and standard deviation , and Calculate the total agency value respectively The weights for distance, heading difference, and speed are calculated.

[0066] Step S302: Calculate the optimal subcluster The point of least value in internal substitution This serves as the cluster inlet reference point, used to calculate the optimal sub-cluster. The point of least value in internal substitution The cost calculation formula for the cluster exit reference point is as follows:

[0067] ;

[0068] Step S303: Update the local path within the cluster, and change the cluster ingress reference point. Cluster exit reference point The line connecting them replaces the initial turning point. See Figure 2 Without adaptive weights, this embodiment selects all weights as 1, resulting in the following global flight path: Figure 3 As shown, the global flight path map with adaptive weights is as follows: Figure 4 As shown, the addition of adaptive weights to the route reduces the elements with large disturbances in AIS, and the planned local path avoids redundant detours and improves smoothness.

[0069] After step S103 is completed, proceed to step S101 to update the global heading information and reconstruct the next intra-cluster local path, that is, the exit reference point of the current cluster calculated in step S103 and... The angle between the line connecting the two points and due north is used as the reference heading for the next cluster's entry, and the reference heading for the next cluster's departure is used as the turning point. and The angle between the line and due north.

[0070] This invention uses historical AIS trajectory points as the data source. First, it obtains the global route based on the maritime traffic network connectivity map. Then, it performs secondary clustering only on the clusters containing the turning points involved in the global route to improve the efficiency of secondary clustering. Based on the global heading information and the expected speed, it finds the optimal subclass. It traverses the AIS trajectory points in the optimal subclass and calculates the distance, speed, and heading cost with adaptive weights that are inversely weighted by standard deviation to obtain the "intra-cluster entry reference point" and "intra-cluster exit reference point". This reconstructs the local route within the cluster and increases the authenticity of the planned route.

[0071] Based on the above method, the following embodiment is given:

[0072] This example selects a global route based on maritime transportation network planning. The latitude and longitude of the origin and destination, as well as the planned route, are shown in Table 1. The route after local path adaptive reconstruction is shown in Table 2. Comparison diagrams are shown below. Figure 2 The "shown" "The line represents the original global flight path," "The line represents the global flight path after local path reconstruction, with a desired speed of 10 knots."

[0073] Table 1 Global Flight Routes

[0074] lon lat 116.45857611548556 22.601627296587928 116.6084601449275 21.484239130434784 112.99985215053763 15.76937051971326 109.26498181818182 9.722139393939392 104.6635142711519 8.428376656472986

[0075] Table 2 Reconstructed flight routes

[0076] lon lat 116.45857611548556 22.601627296587928 116.75166666666668 21.74 116.605 21.23333333333333 113.69166666666666 17.04 112.07166666666669 14.178333333333333 109.49666666666668 10.151666666666667 108.89833333333333 9.375 104.6635142711519 8.428376656472986

[0077] Furthermore, to verify the effectiveness of the reconstructed route using this method, we define a validity evaluation criterion and a smoothness evaluation criterion:

[0078] ;

[0079] ;

[0080] in, The number of turning points is the actual historical AIS trajectory used in the reconstructed route. and For the speed and heading angle at the turning point, and For the desired velocity and intra-cluster reference heading, For the first The first turning point and the second The angle between the line connecting the turning points and true north. For the first The first turning point and the second The angle between the line connecting each turning point and true north. Since the turning points within the initial global route may not be the actual AIS track points, the speed and heading information of the AIS track point closest to the turning point are selected for calculation.

[0081] Table 3. Authenticity Indicators and Smoothing Indicators

[0082] Route Name Authenticity Indicators Smoothness index Original route 158.49 27.69° Reconstructed flight routes 52.99 17.79°

[0083] Therefore, it can be seen that the realism and smoothness of the reconstructed route based on this method are well optimized. Compared with the original route directly connecting the centroid of the cluster, this method adaptively reconstructs the local route within the cluster based on global heading information, making the route more in line with the real navigation characteristics, and improving the smoothness by 35.75%.

[0084] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] Based on the same inventive concept, and corresponding to the methods of any of the above embodiments, the embodiments of this application also provide an AIS cluster local path adaptive reconstruction system.

[0086] like Figure 5 As shown, the AIS cluster intra-local path adaptive reconstruction system includes:

[0087] The global route planning module 11 is configured to generate a global route based on the user-input start and end points and desired speed, and based on the offline constructed maritime traffic network connectivity graph. By reconstructing the local path of the cluster where the route turning point is located, the global heading information of the global route is obtained.

[0088] The optimal subcluster determination module 12 is configured to determine the optimal subcluster within the cluster where the route turning point is located based on global heading information and desired speed.

[0089] The adaptive reconstruction module 13 is configured to obtain the cluster inlet reference point and cluster outlet reference point within the optimal sub-cluster through an adaptive algorithm, and reconstruct the local path within the cluster based on the cluster inlet reference point and cluster outlet reference point to update the global heading information of the global route.

[0090] For ease of description, the above system is described by dividing it into various modules based on their functions. Of course, in implementing the embodiments of this application, the functions of each module can be implemented in one or more software and / or hardware.

[0091] The system described in the above embodiments is used to implement the corresponding method in any of the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0092] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the methods described in any of the above embodiments.

[0093] Figure 6 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0094] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0095] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0096] The input / output interface 1030 is used to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0097] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0098] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0099] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0100] The electronic devices described above are used to implement the corresponding methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0101] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to perform the methods described in any of the above embodiments.

[0102] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0103] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to perform the methods described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0104] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0105] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0106] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0107] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A method for local path adaptive reconfiguration in AIS cluster, characterized in that, The method comprises the following steps: According to the start and end points and the expected speed input by the user, a global route is generated based on the offline constructed maritime traffic network connectivity graph planning, and the global heading information of the global route is obtained by locally reconstructing the path in the cluster where the route turning point is located; According to the global heading information and the expected speed, the optimal sub-cluster in the cluster where the route turning point is located is obtained; The cluster entrance reference point and the cluster exit reference point in the optimal sub-cluster are obtained by an adaptive algorithm, the local path in the cluster is reconstructed according to the cluster entrance reference point and the cluster exit reference point, and the global heading information of the global route is updated; The specific method for obtaining the optimal sub-cluster in the cluster where the route turning point is located comprises: All AIS historical trajectory points in the cluster are obtained according to the cluster number of the route turning point; The speed and heading characteristics of the AIS historical trajectory points are clustered based on the HDBSCAN algorithm to obtain sub-clusters, and the speed and heading centroids of the sub-clusters are calculated; The route centroid of the sub-cluster is traversed, and the sub-cluster closest to the global heading information and the expected speed is obtained according to the entry reference heading and the exit reference heading respectively, so as to be taken as the optimal sub-cluster; The AIS trajectory points in the optimal sub-cluster are traversed, the cluster entrance reference point and the cluster exit reference point are obtained by calculating the distance, speed and heading cost values with adaptive weights inversely proportional to the standard deviation, and the local path in the cluster is reconstructed.

2. The method of claim 1, wherein, The local path reconstruction comprises: The angles between the lines connecting the current route turning point and the previous route turning point and the next route turning point and the north direction are calculated respectively, and are taken as the entry reference heading and the exit reference heading of the current cluster.

3. The method of claim 2, wherein: The historical AIS trajectory points in the first optimal sub-cluster and the second optimal sub-cluster are traversed respectively, the point with the minimum total cost value in the first optimal sub-cluster is taken as the cluster entrance reference point, and the point with the minimum total cost value in the second optimal sub-cluster is taken as the cluster exit reference point.

4. The method of claim 3, wherein, The adaptive algorithm comprises: The distance, heading difference and speed difference, variance and adaptive weight between the previous route turning point and all trajectory points in the first optimal sub-cluster, and the distance, heading difference and speed difference, variance and adaptive weight between the next turning point and all trajectory points in the second optimal sub-cluster are calculated by a cost calculation formula according to the historical AIS trajectory points in the first optimal sub-cluster and the second optimal sub-cluster, so as to obtain the first total cost value and the second total cost value respectively.

5. The method of claim 4, wherein, The cost calculation formula is as follows: ； wherein, represents the distance of the previous leg turning point from the trajectory point in the first optimal sub-cluster, represents the distance of the next leg turning point from the trajectory point in the second optimal sub-cluster, represents the heading difference of the current cluster’s inbound reference heading from the trajectory point in the first optimal sub-cluster, represents the heading difference of the current cluster’s outbound reference heading from the trajectory point in the second optimal sub-cluster, represents the speed difference of the desired speed from the trajectory point in the first optimal sub-cluster, represents the speed difference of the desired speed from the trajectory point in the second optimal sub-cluster, and are the distance weight, heading difference weight and speed weight respectively when calculating the total cost value and are the distance weight, heading difference weight and speed weight respectively when calculating the total cost value .​​​ 6. The method of claim 1, wherein, The reconstruction of the local path in the cluster comprises: The connection between the cluster entrance reference point and the cluster exit reference point is replaced to directly connect the cluster centroid, so as to complete the reconstruction of the local path in the cluster and update the global heading information for the reconstruction of the local path in the next cluster.

7. A system for local path adaptive reconfiguration in AIS clusters, characterized by, The method comprises the following steps: A global route planning module is configured to generate a global route according to the start and end points and the expected speed input by the user, and based on the offline constructed maritime traffic network connectivity graph planning, and to obtain the global heading information of the global route by locally reconstructing the path in the cluster where the route turning point is located; The optimal sub-cluster determination module is configured to obtain an optimal sub-cluster in a cluster where a route turning point is located according to the global heading information and the expected speed; The adaptive reconstruction module is configured to obtain a cluster entry reference point and a cluster exit reference point in the optimal sub-cluster by an adaptive algorithm, and reconstruct a local path in the cluster according to the cluster entry reference point and the cluster exit reference point, so as to update the global heading information of the global route; The specific method for obtaining the optimal sub-cluster in the cluster where the route turning point is located includes: obtaining all AIS historical trajectory points in the cluster according to the cluster number of the route turning point; performing clustering on the speed and heading features of the AIS historical trajectory points based on an HDBSCAN algorithm to obtain sub-clusters, and calculating the speed and heading centroids of the sub-clusters; traversing the route centroids of the sub-clusters, and obtaining a sub-cluster closest to the global heading information and the expected speed according to the entry reference heading and the exit reference heading respectively, so as to take the sub-cluster as the optimal sub-cluster; traversing the AIS trajectory points in the optimal sub-cluster, obtaining a cluster entry reference point and a cluster exit reference point by calculating the distance, speed and heading cost values with adaptive weights inversely proportional to the standard deviation, and reconstructing a local route in the cluster.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method according to any one of claims 1-6 when executing the program.

9. A non-transitory computer-readable storage medium, comprising: The non-transitory computer readable storage medium stores computer instructions for causing a computer to execute the method according to any one of claims 1-6. The non-transitory computer readable storage medium stores computer instructions for causing a computer to execute the method according to any one of claims 1-6.

Images