A water vessel traffic flow complexity calculation method, device, equipment and medium

Abstract

The application discloses a water ship traffic flow complexity calculation method, device, equipment and medium, and the method comprises the steps of obtaining ship AIS data of a target water area; determining ship clustering clusters in the target water area according to the ship AIS data by using an improved DBSCAN algorithm; performing ship state feature clustering on the ship clustering clusters to obtain state feature probability distribution of the ship clustering clusters; and determining ship traffic flow complexity of the target water area based on information entropy according to the state feature probability distribution. The improved DBSCAN algorithm is innovatively obtained based on a ship field model, so that the algorithm is more suitable for navigation practice; the uncertainty of the water traffic flow state is described by information entropy according to the state feature probability, the method for measuring the complexity of the water ship traffic flow in the field of water traffic engineering is expanded, and the application has important theoretical and practical significance for promoting the informatization of maritime safety supervision.

Description

Technical Field

[0001] This invention relates to the field of maritime traffic safety technology, specifically to a method, apparatus, electronic device, and computer-readable storage medium for calculating the complexity of maritime vessel traffic flow. Background Technology

[0002] Water transport carries more than 90% of the world's cargo trade volume and is an important part of the transportation system. With the continuous development of the shipping industry, the number of ships continues to grow, and the flow of ships on water is gradually becoming faster and larger, and its composition is becoming more complex, which in turn leads to a significant increase in the difficulty of ship traffic management.

[0003] Currently, maritime traffic management departments primarily rely on equipment such as AIS and radar to collect static and dynamic information about vessels for monitoring and management. However, the ever-increasing number of vessels results in an enormous volume of this data, which is insufficient to clearly indicate the maritime traffic situation. This makes it difficult for traffic management personnel to identify areas with complex situations in the managed waters in a timely and effective manner, while also increasing the workload of management personnel and bringing certain difficulties and challenges to maritime traffic management.

[0004] Therefore, it is necessary to propose a method for calculating the complexity of waterway traffic flow, in order to solve the technical problem that existing traffic system complexity measurement data cannot intuitively describe and analyze the complexity of waterway traffic flow due to the increasing amount of waterway traffic flow data. This method can provide a reference for maritime safety supervision and improve the safety of waterways. Summary of the Invention

[0005] In view of this, it is necessary to provide a method for calculating the complexity of waterway traffic flow, so as to solve the technical problem that the existing traffic system complexity measurement data is too large and cannot intuitively describe and analyze the complexity of waterway traffic flow.

[0006] To address the above problems, this invention provides a method for calculating the complexity of maritime vessel traffic flow, comprising:

[0007] Obtain AIS data of vessels in the target waters;

[0008] The improved DBSCAN algorithm is used to determine the ship clusters in the target waters based on the ship AIS data;

[0009] The ship clusters are clustered by ship state features to obtain the probability distribution of the ship cluster state features;

[0010] Based on the probability distribution of the state characteristics, the complexity of ship traffic flow in the target waterway is determined.

[0011] Furthermore, the improved DBSCAN algorithm is used to determine ship clusters in the target waters based on the ship AIS data, including:

[0012] A sample set of ships in the target waters is obtained based on the ship AIS data.

[0013] Iterate through the relative positions of any ship in the ship sample set with other ships;

[0014] The vessel territory of the target waterway is obtained based on the relative position;

[0015] The core targets are identified based on the aforementioned shipbuilding sector;

[0016] Based on the core object, determine the ship clusters in the target waters.

[0017] Furthermore, determining the vessel domain of the target waters based on the relative position includes:

[0018] The relative positions of any ship in the ship sample set with other ships at different times are superimposed to obtain superimposed position data;

[0019] By fitting the superimposed position data using the general equation of an ellipse, the vessel domain of each vessel in the target water area is obtained.

[0020] Furthermore, based on the aforementioned shipbuilding field, the core objects are identified, including:

[0021] The search scope is defined as the domain of any vessel in the target waters. When other vessels are located within the search scope, the vessel is identified as the core object.

[0022] Furthermore, determining the ship clusters in the target waters based on the core object includes:

[0023] Identify the target vessel within the shipping sector of the core object;

[0024] Target ships with the same core object are merged to obtain objects within the cluster;

[0025] Based on the core object and the objects within the cluster, the ship clusters in the target waters are determined.

[0026] Furthermore, the ship's state characteristics include ship speed and heading;

[0027] The ship clusters are then subjected to ship state feature clustering to obtain the state feature probability distribution of the ship clusters, including:

[0028] Determine the set of ship speeds and headings for the ship clusters;

[0029] The DBSCAN algorithm is used to cluster the set of ship speeds and headings to obtain the probability distribution of speed and heading clusters for each cluster.

[0030] Furthermore, based on the state characteristic probability distribution, the complexity of vessel traffic flow in the target waterway is determined using information entropy, including:

[0031] The complexity of each cluster is determined based on the probability distribution of the speed and heading of each cluster.

[0032] The traffic flow complexity of the target water area is obtained by summing the complexities of all clusters in the target water area.

[0033] The present invention also provides a device for calculating the complexity of maritime traffic flow, comprising:

[0034] The data acquisition module is used to acquire AIS data of vessels in the target waters;

[0035] A clustering module is used to determine ship clusters in the target waters based on the ship AIS data using an improved DBSCAN algorithm.

[0036] The probability distribution calculation module is used to perform ship state feature clustering on the ship clusters to obtain the state feature probability distribution of the ship clusters;

[0037] The complexity calculation module is used to determine the complexity of ship traffic flow in the target waterway based on the information entropy according to the probability distribution of the state characteristics.

[0038] The present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements a method for calculating the complexity of waterway traffic flow as described in any of the above technical solutions.

[0039] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for calculating the complexity of maritime traffic flow as described in any of the above technical solutions.

[0040] Compared with existing technologies, the beneficial effects of this invention include: First, acquiring AIS data of vessels in the target waterway and using an improved DBSCAN algorithm to determine vessel clusters in the target waterway based on the AIS data; second, performing vessel state feature clustering on the vessel clusters to obtain the state feature probability distribution of the vessel clusters; and finally, determining the vessel traffic flow complexity in the target waterway based on information entropy according to the state feature probability distribution. This invention innovatively obtains an improved DBSCAN algorithm based on a vessel domain model, making the algorithm more closely aligned with maritime practice; it describes the uncertainty of waterway traffic flow states using information entropy based on state feature probabilities, expanding the method for measuring the complexity of waterway vessel traffic flow in the field of maritime transportation engineering, and has significant theoretical and practical implications for promoting the informatization of maritime safety supervision. Attached Figure Description

[0041] Figure 1 A flowchart illustrating an embodiment of the method for calculating the complexity of maritime traffic flow provided by the present invention;

[0042] Figure 2 A schematic diagram of the algorithm flow of an embodiment of the improved DBSCAN algorithm provided by the present invention;

[0043] Figure 3 A schematic diagram of the algorithm flow for determining ship clusters in the target water area based on the core object, provided by the present invention;

[0044] Figure 4 A schematic diagram of the algorithm flow for an embodiment of the ship traffic flow complexity of the target waterway provided by the present invention;

[0045] Figure 5 This is a schematic diagram of an embodiment of a device for calculating the complexity of waterborne vessel traffic flow provided by the present invention;

[0046] Figure 6 This is a schematic diagram of an embodiment of an electronic device provided by the present invention. Detailed Implementation

[0047] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0048] Before describing the embodiments, the relevant terms in this application will be explained first.

[0049] AIS data refers to vital information such as ship position, speed, course, name, and call sign obtained through data exchange between ships and shore or between ships via the Automatic Identification System (AIS). This data assists commanding officers on board in changing routes and / or speeds.

[0050] DBSCAN algorithm: Density-Based Spatial Clustering of Applications with Noise. This algorithm has two input parameters: neighborhood radius Eps and density threshold MinPts. These two parameters distinguish between high-density and low-density points. Data points whose neighborhood radius Eps exceeds the minimum containment threshold MinPts are considered high-density points. These high-density data points are then clustered into a single cluster, and the final clustering result is output.

[0051] In existing technologies, maritime traffic management departments mainly rely on equipment such as AIS and radar to collect static and dynamic information about vessels for supervision and management. However, the ever-increasing number of vessels results in an extremely large amount of data, which cannot intuitively reflect the maritime traffic situation and cannot effectively identify areas with complex situations in the managed waters, thus bringing difficulties and challenges to maritime traffic management.

[0052] This invention constructs an improved DBSCAN algorithm based on the ship domain model, building upon the existing DBSCAN algorithm. Furthermore, it performs clustering processing on AIS data, statistically analyzes the distribution probability of different clusters, and, by incorporating the concept of information entropy, obtains a method for measuring the complexity of waterway traffic flow. This method can intuitively indicate waterway traffic conditions and effectively identify the complexity of waterway traffic flow.

[0053] This invention provides a method for calculating the complexity of maritime traffic flow, such as... Figure 1 As shown, Figure 1 This is a flowchart illustrating the method for calculating the complexity of maritime vessel traffic flow, including:

[0054] Step S101: Obtain AIS data of vessels in the target waters;

[0055] Step S102: Use the improved DBSCAN algorithm to determine the ship clusters in the target waters based on the ship AIS data;

[0056] Step S103: Perform ship state feature clustering on the ship clusters to obtain the state feature probability distribution of the ship clusters;

[0057] Step S104: Determine the complexity of ship traffic flow in the target waterway based on the information entropy according to the probability distribution of the state features.

[0058] The method for calculating the complexity of maritime vessel traffic flow provided in this embodiment first acquires AIS data of vessels in the target waterway and uses an improved DBSCAN algorithm to determine vessel clusters in the target waterway based on the AIS data. Second, it performs vessel state feature clustering on the vessel clusters to obtain the state feature probability distribution of the vessel clusters. Finally, based on the state feature probability distribution, it determines the complexity of the vessel traffic flow in the target waterway using information entropy. This embodiment innovatively obtains an improved DBSCAN algorithm based on a vessel domain model, making the algorithm more closely aligned with maritime practice. By describing the uncertainty of maritime traffic flow states through information entropy based on state feature probabilities, it expands the methods for measuring the complexity of maritime vessel traffic flow in the field of maritime transportation engineering, and has significant theoretical and practical implications for promoting the informatization of maritime safety supervision.

[0059] In a preferred embodiment, step S102 involves using an improved DBSCAN algorithm to determine ship clusters in the target waters based on the ship AIS data, including:

[0060] A sample set of ships in the target waters is obtained based on the ship AIS data.

[0061] Iterate through the relative positions of any ship in the ship sample set with other ships;

[0062] The vessel territory of the target waterway is obtained based on the relative position;

[0063] The core targets are identified based on the aforementioned shipbuilding sector;

[0064] Based on the core object, determine the ship clusters in the target waters.

[0065] As a preferred embodiment, determining the vessel domain of the target waterway based on the relative position includes:

[0066] The relative positions of any ship in the ship sample set with other ships at different times are superimposed to obtain superimposed position data;

[0067] By fitting the superimposed position data using the general equation of an ellipse, the vessel domain of each vessel in the target water area is obtained.

[0068] As a preferred embodiment, the core objects are determined according to the shipbuilding field, including:

[0069] The search scope is defined as the domain of any vessel in the target waters. When other vessels are located within the search scope, the vessel is identified as the core object.

[0070] As a preferred embodiment, determining the ship clusters in the target waterway based on the core object includes:

[0071] Identify the target vessel within the shipping sector of the core object;

[0072] Target ships with the same core object are merged to obtain objects within the cluster;

[0073] Based on the core object and the objects within the cluster, the ship clusters in the target waters are determined.

[0074] The following specific embodiment illustrates the process of determining ship clusters in the target waters using the improved DBSCAN algorithm based on the ship's AIS data, through formulas and algorithms. Figure 2 As shown, Figure 2 The detailed implementation process of the improved DBSCAN algorithm is demonstrated, including:

[0075] Step S201: Establish a vessel sample set D = (s1, s2, ..., s) in the target waters. m ), where s1, s2, ..., s m For vessels in the target waters.

[0076] Step S202: Determine the relative position of any vessel in the vessel sample set to other vessels based on AIS data. Specifically:

[0077] Taking the vessel to be analyzed as the "self" vessel, calculate the relative position of the self vessel with the surrounding vessels:

[0078] Δx AB =x B -x A (1)

[0079] Δy AB =y B -y A (2)

[0080]

[0081]

[0082] Q = C AB -HDG (5)

[0083]

[0084] xc =D AB sinθ AB (7)

[0085] y c =D AB cosθ AB (8)

[0086] Where, Δx AB It is the difference in longitude between the ship's position and the target ship; x A These are the longitude coordinates of the ship's position; y A This is the latitude coordinate of the ship's position; x B The longitude coordinates of the target ship's position; y B The latitude coordinates of the target ship's position; Δy AB D is the difference in latitude between the ship's position and the target ship; AB C is the relative distance between the ship and the target ship; AB The target ship's true bearing is given; Q is an intermediate variable; HDG is the ship's heading; θ is the target ship's true bearing. AB It is the relative bearing between the ship and the target ship; x c y is the x-coordinate of the target vessel's position relative to the current vessel; c The vertical coordinate of the target vessel's position relative to the current vessel.

[0087] It should be noted that since AIS data typically uses the ship's latitude and longitude coordinates, these coordinates need to be converted before determining the ship's relative position. The conversion formula is as follows:

[0088]

[0089]

[0090] x=λr0 (11)

[0091] y=qr0 (12)

[0092] Where r0 is the radius of the standard latitude parallel circle; a is the semi-major axis of the Earth ellipsoid; and e is the first eccentricity of the Earth ellipsoid. is the standard latitude in the Mercator projection; q is an intermediate variable; λ represents the latitude coordinate of the ship's position; λ represents the longitude coordinate of the ship's position; x represents the longitude of the ship's position in Cartesian coordinates; and y represents the latitude of the ship's position in Cartesian coordinates.

[0093] Step S203: Establish a ship domain model based on the relative positions of the ship and the target ship.

[0094] By superimposing the relative positions of the target ship at different times and fitting the data using the general equation of an ellipse, a ship domain model is obtained:

[0095] a+bx+cy+dxy+ex 2 +fy 2 =0 (13)

[0096] Where a, b, c, d, e, f are ellipse parameters.

[0097] Step S204: Identify the core objects.

[0098] The core object is defined as: a vessel whose search scope includes other vessels when the search scope is the vessel's own domain.

[0099] Step S205: Determine the ship clusters in the target waterway based on the core object. For example... Figure 3 As shown, the specific algorithm flow is as follows:

[0100] Step S2051: Initialize the core object set Ω = φ, initialize the number of clusters k = 0, and set the cluster partition C = φ;

[0101] Step S2052: For a sample ship D = (s1, s2, ..., sm) containing m samples... m Given the target water area, let j = 1, 2, ..., m, and use formula (14) to obtain the s in the ship sample set D. j Other than those located in s j All ships in the shipping industry receive s j The subset N(s) j ).

[0102] a+bx+cy+dxy+ex j 2 +fy j 2 <0 (14)

[0103] Where, x j ,y j Ships s j The x and y coordinates.

[0104] Step S2053: If the subset satisfies N(s) j If φ ≠ φ, then the sample s j Add to the core object set Ω=Ω∪{s j}, update the ship sample set D = Ω.

[0105] Step S2054: If the core object set Ω = φ, the algorithm ends; otherwise, proceed to step S2055.

[0106] Step S2055: In the core object set Ω, randomly select a core object O and initialize the current core object sequence Ω. c ={O}, initialize the cluster index k = k + 1, initialize the current cluster C k ={O}, for the current core object sequence Ω c The core object O in i According to step S2052, O is obtained. i The subset N(O) i ).

[0107] Step S2056: Update the current core object sequence Ω c =Ω c ∪N(O i -O, update the current cluster C k =C k ∪N(O i ).

[0108] Step S2057: If the current core object sequence Ω c =φ, proceed to step S2058; otherwise return to step S2055.

[0109] Step S2058: Current cluster C k Once generated, update the cluster partition C = {C1, C2, ..., C}. K}, and update the core object sequence Ω = Ω - C k ;

[0110] Step S2059: If the core object sequence Ω = φ, proceed to step S2060; otherwise, return to step S2054.

[0111] Step S2060: Partition the cluster C = {C1, C2, ..., C} K Clusters with the same core object in the array are merged to obtain C' = {C1, C2, ..., C}. k}

[0112] This embodiment improves upon the traditional DBSCAN algorithm based on a ship domain model, reducing the impact of two hyperparameters in traditional DBSCAN clustering—ε-neighborhood and MinPts—on the clustering results. By combining the ship domain model with DBSCAN, ship clustering is achieved based on the existence of mutual influencing factors among ships under hyperparameter-free conditions, resulting in clusters of mutually influencing ships. This provides a new theoretical foundation and solution for analyzing the complexity of waterway traffic flow.

[0113] In a preferred embodiment, the ship's state characteristics include ship speed and heading.

[0114] The ship clusters are then subjected to ship state feature clustering to obtain the state feature probability distribution of the ship clusters, including:

[0115] Determine the set of ship speeds and headings for the ship clusters;

[0116] The DBSCAN algorithm is used to cluster the set of ship speeds and headings to obtain the probability distribution of speed and heading clusters for each cluster.

[0117] As a preferred embodiment, determining the vessel traffic flow complexity of the target waterway based on information entropy according to the state feature probability distribution includes:

[0118] The complexity of each cluster is determined based on the probability distribution of the speed and heading of each cluster.

[0119] The traffic flow complexity of the target water area is obtained by summing the complexities of all clusters in the target water area.

[0120] As a specific example, the calculation of vessel traffic flow complexity in a target waterway is explained using formulas and a specific algorithm flow. For example... Figure 4 As shown, Figure 4 A flowchart of the algorithm is shown.

[0121] Step S401: Parse and process the AIS data. Standardize the parsed data using z-score based on its airspeed and heading data. The transformation formula is as follows:

[0122]

[0123] Where x represents the original data; σ is the mean of the original data; σ is the standard deviation of the original data.

[0124] Step S402: For each cluster C k ={s1,s2,...,s n Establish the set of ship speeds and headings; HV = {(h1,v1),(h2,v2),...,(h...} n ,v n )}, where h n ,v n s n The ship's heading and speed. The cluster is divided into C' = {C1, C2, ..., C...}. k The set of all ship speeds and directions HV = {(h1,v1),(h2,v2),...,(h...} n ,v nClustering is performed using the DBSCAN algorithm to obtain the probability distribution set P = {(p1, p2, ..., p}. j )1,(p1,p2,...,p j )2,...,(p1,p2,...,p j ) k}, where (p1,p2,...,p j ) is the probability distribution of speed and heading after clustering for each cluster.

[0125] Step S403: Calculate the complexity for each cluster based on the probability distribution of speed and heading. The calculation formula is as follows:

[0126]

[0127] Among them, H i For cluster C i The complexity of p; i For cluster C i The probability distribution of the corresponding speed and heading.

[0128] Step S404: Superimpose the cluster complexity of the target water area to obtain the complexity of the target water area. The calculation formula is as follows:

[0129]

[0130] Where H represents the complexity of vessel traffic flow in the target waterway.

[0131] Based on the ship clustering results, the above-mentioned complexity determination method uses information entropy as a basis and the probability distribution of ship speed and heading as data to obtain the complexity of each cluster. Then, by superimposing the data, the complexity of ship traffic flow in the water area can be obtained. This method can effectively provide maritime regulatory authorities with a quantifiable method for measuring the complexity of ship traffic flow in water areas, which helps to provide corresponding traffic services for water areas with different traffic flow complexities.

[0132] This invention also provides a device for calculating the complexity of maritime traffic flow, such as... Figure 5 As shown, the maritime vessel traffic flow complexity calculation device 500 includes:

[0133] Data acquisition module 501 is used to acquire AIS data of ships in the target waters;

[0134] Clustering module 502 is used to determine ship clusters in the target waters based on the ship AIS data using an improved DBSCAN algorithm;

[0135] The probability distribution calculation module 503 is used to perform ship state feature clustering on the ship clusters to obtain the state feature probability distribution of the ship clusters;

[0136] The complexity calculation module 504 is used to determine the complexity of ship traffic flow in the target water area based on the information entropy according to the probability distribution of the state characteristics.

[0137] like Figure 6 As shown in the above-described method for calculating the complexity of maritime traffic flow, this invention also provides an electronic device 600, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The electronic device includes a processor 601, a memory 602, and a display 603.

[0138] In some embodiments, memory 602 may be an internal storage unit of a computer device, such as a hard disk or memory. In other embodiments, memory 602 may be an external storage device of a computer device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, memory 602 may include both internal and external storage units of the computer device. Memory 602 is used to store application software and various types of data installed on the computer device, such as program code for installing the computer device. Memory 602 can also be used to temporarily store data that has been output or will be output. In one embodiment, memory 602 stores a program 604 for calculating the complexity of maritime traffic flow, which can be executed by processor 601 to implement a method for calculating the complexity of maritime traffic flow according to various embodiments of the present invention.

[0139] In some embodiments, processor 601 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 602 or process data, such as executing a program for calculating the complexity of waterway traffic flow.

[0140] In some embodiments, display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 603 is used to display information on the computer device and to display a visual user interface. Components 601-603 of the computer device communicate with each other via a system bus.

[0141] This embodiment also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the method for calculating the complexity of waterway traffic flow as described in any of the above technical solutions.

[0142] The computer-readable storage medium and computing device provided in the above embodiments of the present invention can be implemented with reference to the content specifically described in the present invention for implementing the method for calculating the complexity of waterway traffic flow as described above, and have similar beneficial effects as the method for calculating the complexity of waterway traffic flow as described above, which will not be repeated here.

[0143] This invention discloses a method for calculating the complexity of maritime vessel traffic flow. First, AIS data of vessels in a target waterway is acquired, and an improved DBSCAN algorithm is used to determine vessel clusters in the target waterway based on the AIS data. Second, vessel clusters are clustered by vessel state features to obtain the state feature probability distribution of the vessel clusters. Finally, based on the state feature probability distribution, the complexity of vessel traffic flow in the target waterway is determined based on information entropy.

[0144] This invention innovatively derives an improved DBSCAN algorithm based on a ship domain model, making the algorithm more closely aligned with maritime practice. It describes the uncertainty of waterway traffic flow states using information entropy based on state characteristic probabilities, expanding the methods for measuring the complexity of waterway ship traffic flow in the field of waterway transportation engineering. This has significant theoretical and practical implications for promoting the informatization of maritime safety supervision.

[0145] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for calculating the complexity of maritime vessel traffic flow, characterized in that, include: Obtain AIS data of vessels in the target waters; The improved DBSCAN algorithm is used to determine the ship clusters in the target waters based on the ship AIS data; Clustering the ship clusters by ship state features to obtain the probability distribution of the ship clusters' state features includes: determining the set of ship speeds and headings for the ship clusters; ,in They are respectively The ship's heading and speed; for clustering. Set of all ship speeds and headings Clustering was performed using the DBSCAN algorithm to obtain a set of probability distributions. ,in The probability distribution of speed and heading after clustering for each cluster; Based on the probability distribution of the state characteristics, the complexity of ship traffic flow in the target waterway is determined using information entropy, including: calculating the complexity for each cluster based on the probability distribution of speed and heading, using the following formula: ;in, For clusters The complexity; For clusters The probability distribution of the corresponding speed and heading; the complexity of the target water area is obtained by superimposing the cluster complexity of the target water area, and the calculation formula is: (17); among them, The complexity of vessel traffic flow in the target waterway.

2. The method for calculating the complexity of maritime traffic flow according to claim 1, characterized in that, The improved DBSCAN algorithm is used to determine ship clusters in the target waters based on the ship AIS data, including: A sample set of ships in the target waters is obtained based on the ship AIS data. Iterate through the relative positions of any ship in the ship sample set with other ships; The vessel territory of the target waterway is obtained based on the relative position; The core targets are identified based on the aforementioned shipbuilding sector; Based on the core object, determine the ship clusters in the target waters.

3. The method for calculating the complexity of maritime traffic flow according to claim 2, characterized in that, Determining the vessel domain of the target waters based on the relative position includes: The relative positions of any ship in the ship sample set with other ships at different times are superimposed to obtain superimposed position data; By fitting the superimposed position data using the general equation of an ellipse, the vessel domain of each vessel in the target water area is obtained.

4. The method for calculating the complexity of maritime traffic flow according to claim 2, characterized in that, Based on the aforementioned shipbuilding sector, the core targets are identified, including: The search scope is defined as the domain of any vessel in the target waters. When other vessels are located within the search scope, the vessel is identified as the core object.

5. The method for calculating the complexity of maritime traffic flow according to claim 2, characterized in that, Based on the core object, the ship clusters in the target waters are determined, including: Identify the target vessel within the shipping sector of the core object; Target ships with the same core object are merged to obtain objects within the cluster; Based on the core object and the objects within the cluster, the ship clusters in the target waters are determined.

6. A device for calculating the complexity of maritime vessel traffic flow, executing a method for calculating the complexity of maritime vessel traffic flow as described in any one of claims 1-5, characterized in that, include: The data acquisition module is used to acquire AIS data of vessels in the target waters; A clustering module is used to determine ship clusters in the target waters based on the ship AIS data using an improved DBSCAN algorithm. The probability distribution calculation module is used to perform ship state feature clustering on the ship clusters to obtain the state feature probability distribution of the ship clusters; The complexity calculation module is used to determine the complexity of ship traffic flow in the target waterway based on the information entropy according to the probability distribution of the state characteristics.

7. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements a method for calculating the complexity of waterway traffic flow as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for calculating the complexity of maritime traffic flow as described in any one of claims 1-5.

Images