Method and device for determining ship formation, storage medium and electronic equipment

Abstract

The application discloses a kind of ship formation determination method, device, storage medium and electronic equipment, wherein the method comprises: determining the first driving trajectory point of target ship based on ship automatic identification system data;Determine the envelope of target ship based on each first driving trajectory point, obtain multiple envelopes;Determine the target envelope included in multiple envelopes, wherein the target envelope includes second driving trajectory point, and the second driving trajectory point is the trajectory point of ship except target ship;Determine the ship formation of target ship based on first driving trajectory point and second driving trajectory point. Through the present application, the problem that ship formation cannot be determined in real time in the related art is solved, and the effect of determining ship formation in real time and accurately is achieved.

Description

Technical Field

[0001] This application relates to the field of maritime safety protection technology, and more specifically, to a method, apparatus, storage medium, and electronic device for determining ship formations. Background Technology

[0002] In related technologies, ship formations are usually determined by radar, cameras, etc. However, in open seas, the visibility range of ships is limited, and relying on monitoring methods (such as radar and cameras) is difficult to cover large areas of sea, which limits the ability to monitor ship formations in real time.

[0003] This indicates that the relevant technologies have the problem of being unable to determine ship formations in real time.

[0004] There is currently no effective solution to the aforementioned problems in the relevant technologies. Summary of the Invention

[0005] This application provides a method, apparatus, storage medium, and electronic device for determining ship formations, so as to at least solve the technical problem of the inability to determine ship formations in real time in related technologies.

[0006] According to one aspect of the embodiments of this application, a method for determining a ship formation is provided, comprising: determining a first travel trajectory point of a target ship based on data from an Automatic Identification System (AIS); determining an envelope of the target ship based on each of the first travel trajectory points to obtain a plurality of envelopes; determining a target envelope included in the plurality of envelopes, wherein the target envelope includes a second travel trajectory point, the second travel trajectory point being a trajectory point of a ship other than the target ship; and determining a ship formation of the target ship based on the first travel trajectory point and the second travel trajectory point.

[0007] In an exemplary embodiment, determining the vessel formation of the target vessel based on the first and second travel trajectory points includes: determining a first trajectory of the target vessel based on the first travel trajectory point; determining a third travel trajectory point belonging to the same other vessel included in the second travel trajectory point; determining a second trajectory of the other vessel based on the third travel trajectory point; determining the trajectory similarity between the first and second trajectories; and determining the vessel formation based on the trajectory similarity.

[0008] In an exemplary embodiment, determining the trajectory similarity between the first trajectory and the second trajectory includes: determining the target sub-envelope in which the third travel trajectory point is located, wherein the target envelope includes the target sub-envelope; determining the fourth travel trajectory point included in the first trajectory and located within the target sub-envelope; determining the spatiotemporal similarity of each of the third travel trajectory points and each of the fourth travel trajectory points; determining the velocity similarity between a first velocity and a second velocity, wherein the first velocity is the velocity of the target vessel in the first trajectory, and the second velocity is the velocity of the other vessel in the second trajectory; and determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity.

[0009] In an exemplary embodiment, determining the spatiotemporal similarity of each third driving trajectory point and each fourth driving trajectory point includes: performing a target operation for each third driving trajectory point to determine the trajectory point similarity between the third driving trajectory point and the fourth driving trajectory point; and determining the spatiotemporal similarity as the product of the trajectory point similarity and the spatiotemporal weight; wherein the target operation includes: determining a first driving time corresponding to the third driving trajectory point; determining a second driving time for each fourth driving trajectory point; determining a time difference between the first driving time and each second driving time; determining a longitude difference between the third driving trajectory point and each fourth driving trajectory point; determining a latitude difference between the third driving trajectory point and each fourth driving trajectory point; determining a first squared value for each longitude difference and a second squared value for each latitude difference; determining a first product of each first squared value and the time difference corresponding to the first squared value; determining a second product of each second squared value and the time difference corresponding to the second squared value; and determining a first sum of the first product and the second product as the trajectory point similarity.

[0010] In an exemplary embodiment, determining the speed similarity between a first speed and a second speed includes: determining the absolute value of the difference between the first speed and the second speed; and determining the speed similarity by multiplying the absolute value by a speed distance weight.

[0011] In an exemplary embodiment, determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity includes: determining the sum of the similarity of each trajectory point included in the spatiotemporal similarity and the velocity similarity to obtain a plurality of second sums; constructing a target matrix based on the plurality of second sums; determining the minimum distance between the first trajectory and the second trajectory based on the target matrix; and determining the minimum distance as the trajectory similarity.

[0012] In an exemplary embodiment, determining the first travel trajectory point of a target vessel based on Automatic Identification System (AIS) data includes: determining the actual trajectory point of the target vessel based on the AIS data; determining the time interval between the generation times of two adjacent actual trajectory points; if the time interval is greater than a preset threshold, interpolating the two adjacent actual trajectory points to obtain an interpolated trajectory point; and determining the actual trajectory point and the interpolated trajectory point as the first travel trajectory point.

[0013] In an exemplary embodiment, determining the envelope of the target vessel based on each first travel trajectory point to obtain multiple target envelopes includes: determining the envelope size of the envelope; and constructing the target envelope according to the envelope size, using each first travel trajectory point as the target point of the envelope.

[0014] According to another aspect of the embodiments of this application, a device for determining a ship formation is also provided, comprising: a first determining module, configured to determine a first travel trajectory point of a target ship based on data from an Automatic Identification System (AIS); a second determining module, configured to determine an envelope of the target ship based on each of the first travel trajectory points, thereby obtaining a plurality of envelopes; a third determining module, configured to determine a target envelope included in the plurality of envelopes, wherein the target envelope includes a second travel trajectory point, the second travel trajectory point being a trajectory point of a ship other than the target ship; and a fourth determining module, configured to determine the ship formation of the target ship based on the first travel trajectory point and the second travel trajectory point.

[0015] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed by a processor.

[0016] According to another aspect of the embodiments of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform the steps in any of the method embodiments described above.

[0017] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to perform the steps of any of the above method embodiments through the computer program.

[0018] This application enables the determination of a target vessel's first trajectory point based on Automatic Identification System (AIS) data; the determination of the target vessel's envelope based on each first trajectory point, resulting in multiple envelopes; the determination of target envelopes included within these multiple envelopes, wherein the target envelopes include second trajectory points of vessels other than the target vessel; and the determination of the target vessel's formation based on the first and second trajectory points. Because the search range can be limited to the second trajectory points of other vessels within the constructed target vessel's target envelope, the trajectories of vessels accompanying the target vessel can be accurately captured, thus avoiding the influence of external interference points. By strictly limiting the search range, the accuracy of formation identification is effectively improved, ensuring the accurate identification of the trajectories of accompanying vessels. Furthermore, AIS data can be acquired in real time, thus solving the problem of not being able to determine vessel formations in real time in related technologies, achieving the effect of accurate real-time determination of vessel formations. Attached Figure Description

[0019] Figure 1 This is a schematic diagram illustrating an application scenario of a method for determining a ship formation according to an embodiment of this application;

[0020] Figure 2 This is a flowchart illustrating an optional method for determining a ship formation according to an embodiment of this application;

[0021] Figure 3 This is an optional ship escort diagram according to an embodiment of this application;

[0022] Figure 4 These are schematic diagrams of the first and second trajectories according to embodiments of this application;

[0023] Figure 5 This is a schematic diagram of the first trajectory portion according to an embodiment of this application;

[0024] Figure 6 This is a schematic diagram of the spatiotemporal envelope of a ship trajectory according to an embodiment of this application;

[0025] Figure 7 This is a structural diagram of a ship formation determination system according to an embodiment of this application;

[0026] Figure 8 This is a schematic diagram of the trajectory of accompanying vessels within a target time period according to an embodiment of this application;

[0027] Figure 9 This is a structural block diagram of an optional ship formation determination device according to an embodiment of this application;

[0028] Figure 10 A computer system architecture block diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] According to one aspect of the embodiments of this application, a method for determining a ship formation is provided. Optionally, in this embodiment, the above-described method for determining a ship formation may be applied, but is not limited to, to applications such as... Figure 1 The hardware environment shown includes terminal device 102 and server 104. Server 104 can be connected to terminal device 102 via a network and can be used to provide services (e.g., application services, etc.) to terminal device 102 or clients installed on terminal device 102. A database can be set up on server 104 or independently of server 104 to provide data storage services for server 104.

[0032] The aforementioned network may include, but is not limited to, at least one of the following: wired network and wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network (WAN), metropolitan area network (MAN), and local area network (LAN). The aforementioned wireless network may include, but is not limited to, at least one of the following: Wireless Fidelity (WIFI) and Bluetooth. Terminal device 102 may be, but is not limited to, a personal computer (PC), mobile phone, tablet computer, etc. Server 104 may be, but is not limited to, a cloud server, server cluster, or other server types.

[0033] The method for determining ship formations in this application embodiment can be executed by server 104, terminal device 102, or jointly by server 104 and terminal device 102. Alternatively, the method for determining ship formations in this application embodiment can be executed by a client installed on terminal device 102.

[0034] Taking the method for determining the ship formation in this embodiment, executed by terminal device 102 (server 104), as an example, Figure 2 This is a flowchart illustrating an optional method for determining a ship formation according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include the following steps:

[0035] Step S202: Determine the first trajectory point of the target vessel based on data from the Automatic Identification System (AIS).

[0036] Step S204: Determine the envelope of the target vessel based on each of the first travel trajectory points to obtain multiple envelopes;

[0037] Step S206: Determine the target envelope included in the plurality of envelopes, wherein the target envelope includes a second travel trajectory point, and the second travel trajectory point is the trajectory point of a vessel other than the target vessel;

[0038] Step S208: Determine the ship formation of the target ship based on the first travel trajectory point and the second travel trajectory point.

[0039] The method for determining ship formations in this embodiment can be applied to key areas such as optimizing ship navigation planning, enhancing maritime emergency response capabilities, and improving maritime safety protection efficiency. It is applied to scenarios involving identifying accompanying vessels at sea and determining ship formations. This can effectively promote the rational allocation and utilization of marine resources, reduce the risk of maritime accidents, and lay a solid technical foundation for building a safe, efficient, and green maritime transportation system.

[0040] The complex marine environment and the influence of weather, currents, and tides on ships during their operation result in highly variable navigation conditions, increasing the difficulty of formation identification. In open waters, the limited visibility of ships and the inability of traditional monitoring methods (such as radar and cameras) to cover large areas limit the real-time monitoring capabilities of ship formations. Busy maritime traffic and the dynamic changes in ship formations can lead to collision risks and other safety hazards, necessitating efficient formation identification technology to improve maritime safety management. With the rapid development of maritime trade, the efficiency of ship formation management directly impacts the operating costs of shipping companies and ports, requiring intelligent technologies to improve the efficiency of ship formation identification and management. Furthermore, intelligent ship formation identification can provide data support for maritime law enforcement, rescue operations, and resource allocation, improving response capabilities and decision-making in the face of emergencies. Given the limitations of traditional ship formation identification methods in dealing with the dynamic nature of complex marine environments, diverse shipping demands, and real-time requirements, their accuracy, timeliness, and reliability fail to meet the high standards of modern maritime management, becoming a bottleneck restricting the intelligent development of maritime traffic.

[0041] To at least partially address the aforementioned technical problems, this embodiment can receive a target instruction for determining a ship formation. This instruction may include a target time period for the ship formation to be determined. AIS data for the target time period is acquired, and based on the Automatic Identification System (AIS) data, the first trajectory points of the target ships are determined. Multiple first trajectory points may be included. A target envelope of the target ship can be constructed based on each first trajectory point. The target envelope can be constructed according to a pre-defined envelope size, or the envelope size can be determined based on the received construction instruction. The envelope size may include Δx, Δy, and Δt, representing length, width, and time, respectively. The dimensions of the spatiotemporal envelope, Δx, Δy, and Δt, can be dynamically adjusted according to different scenarios or the specific motion characteristics of the ships, enhancing the system's adaptability.

[0042] In this embodiment, the target envelope includes a second trajectory point, and the ship formation can be determined based on the first and second trajectory points. The ship formation may include ships exhibiting escort behavior within the same time period. Escort behavior refers to the phenomenon where the trajectories of other ships closely match the target ship in both space and time within a specific time period, exhibiting synchronized navigation characteristics. Multiple ships exhibiting escort behavior can be defined as a ship formation. A schematic diagram of ship escort behavior can be found in the appendix. Figure 3For all vessels located within the spatiotemporal envelope of the target vessel, their complete trajectories can be fused in chronological order. The trajectory similarity between the target vessel and other vessels is calculated to determine whether these vessels form a highly escorting formation with the target vessel. Vessels meeting the escort criteria are selected based on trajectory similarity, and the time they spend escorting the target vessel is further calculated. The analysis results can be presented through the output module. The final output includes the MMSI of all eligible escorting vessels in the formation, as well as the shared sailing time between these vessels and the target vessel. This output provides important information for subsequent analysis, decision-making, or monitoring.

[0043] In this embodiment, determining the vessel formation of the target vessel based on the first and second travel trajectory points may include determining a first trajectory based on the first travel trajectory point, determining a second trajectory belonging to the same vessel based on the second travel trajectory point, determining the similarity between the first and second trajectories, and determining that the target vessel and the vessel corresponding to the second trajectory belong to the same vessel formation when the similarity is greater than a set threshold. When the similarity is less than or equal to the set threshold, determining that the target vessel and the vessel corresponding to the second trajectory do not belong to the same vessel formation.

[0044] This application enables the determination of a target vessel's first trajectory point based on Automatic Identification System (AIS) data; the determination of the target vessel's envelope based on each first trajectory point, resulting in multiple envelopes; the determination of target envelopes included within these multiple envelopes, wherein the target envelopes include second trajectory points of vessels other than the target vessel; and the determination of the target vessel's formation based on the first and second trajectory points. Because the search range can be limited to the second trajectory points of other vessels within the constructed target vessel's target envelope, the trajectories of vessels accompanying the target vessel can be accurately captured, thus avoiding the influence of external interference points. By strictly limiting the search range, the accuracy of formation identification is effectively improved, ensuring the accurate identification of the trajectories of accompanying vessels. Furthermore, AIS data can be acquired in real time, thus solving the problem of not being able to determine vessel formations in real time in related technologies, achieving the effect of accurate real-time determination of vessel formations.

[0045] In an exemplary embodiment, determining the vessel formation of the target vessel based on the first and second travel trajectory points includes: determining a first trajectory of the target vessel based on the first travel trajectory point; determining a third travel trajectory point belonging to the same other vessel included in the second travel trajectory point; determining a second trajectory of the other vessel based on the third travel trajectory point; determining the trajectory similarity between the first and second trajectories; and determining the vessel formation based on the trajectory similarity. In this embodiment, trajectory points located within the same spatiotemporal envelope of vessel trajectories can be integrated by vessel to generate a complete trajectory for each vessel, i.e., the second trajectory. By classifying trajectory points by vessel, a third travel trajectory point is obtained, and fused according to spatiotemporal information to ensure the continuity and integrity of the trajectory.

[0046] In this embodiment, a fusion operation was performed on trajectory points located within the spatiotemporal envelope of the ship's trajectory to extract representative trajectory information. Schematic diagrams of the first and second trajectories can be found in the appendix. Figure 4 ,like Figure 4 As shown, P1, P2, P3, P4, L1, L2, L3, L4, and L5 constitute the first trajectory. Within the spatiotemporal envelope of the target ship's trajectory, the trajectories of the four ships are fused to form trajectory 1, trajectory 2, trajectory 3, and trajectory 4. That is, trajectory 1, trajectory 2, trajectory 3, and trajectory 4 are the second trajectory, thus more effectively reflecting the motion characteristics of these ships.

[0047] In this embodiment, within the constructed spatiotemporal envelope, the search range is limited to the trajectory points of other vessels within the envelope. This allows for the accurate capture of the trajectories of vessels accompanying the target vessel, thereby avoiding the influence of external interference points. This method, by strictly limiting the search range, effectively improves the accuracy of formation identification, ensuring the precise identification of the trajectories of accompanying vessels. By searching only within the spatiotemporal envelope for potential accompanying vessels, the search range is significantly reduced. This method effectively reduces computational load, improves the overall system's processing efficiency and real-time response capabilities, and demonstrates significant advantages, especially when dealing with large-scale vessel data.

[0048] In an exemplary embodiment, determining the trajectory similarity between the first trajectory and the second trajectory includes: determining the target sub-envelope where the third trajectory point is located, wherein the target envelope includes the target sub-envelope; determining the fourth trajectory point included in the first trajectory and located within the target sub-envelope; determining the spatiotemporal similarity of each of the third and fourth trajectory points; determining the velocity similarity between a first velocity and a second velocity, wherein the first velocity is the velocity of the target vessel in the first trajectory, and the second velocity is the velocity of the other vessels in the second trajectory; and determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity. In this embodiment, when calculating the trajectory similarity between the target vessel and each search vessel, the calculation efficiency and accuracy can be improved by limiting the trajectory range of the target vessel. The similarity calculation is only for a portion of the target vessel's trajectory points, not the global trajectory points. A partial schematic diagram of the first trajectory can be found in the appendix. Figure 5 ,like Figure 5 As shown, the trajectory points included in the first trajectory may include (P1, P2, P3, P4). For the ship S existing within the spatiotemporal envelope of the target ship's trajectory points (P1, P2, P3, P4), its trajectory is S1-S2-S3. When calculating the trajectory similarity between ship S and the target ship, the trajectory points of the target ship within the corresponding spatiotemporal envelope of the ship's trajectory, i.e., P1-P2, can be considered for similarity evaluation. That is, when the target sub-envelope is an envelope including P1, the fourth travel trajectory point is P1, and the third travel trajectory points are S1 and S2. Therefore, the spatiotemporal similarity between S1 and P1, and between S2 and P1, can be calculated. The velocity similarity between the second velocity in trajectory S1-S2 and the first velocity in trajectory P1 is calculated. The trajectory similarity is determined based on the spatiotemporal similarity and velocity similarity.

[0049] In this embodiment, a speed-weighted dynamic time warping (DTW) algorithm can be used to evaluate the similarity between each fused ship trajectory and the target ship trajectory, comprehensively considering the influence of factors such as speed, time, and spatial position. This algorithm pays particular attention to the alignment in the spatiotemporal dimensions. By introducing a speed factor into the overall similarity calculation, the similarity formula becomes:

[0050] Overall Similarity = γ·Spatiotemporal Similarity+δ·SpeedSimilarity (1)

[0051] In formula (1), γ and δ represent the weighting coefficients of spatiotemporal and velocity, respectively, thereby enhancing the accuracy of companion vessel identification when time synchronization is critical. Overall Similarity represents the overall similarity, i.e., trajectory similarity, Spatiotemporal Similarity represents spatiotemporal similarity, and Speed ​​Similarity represents velocity similarity.

[0052] In this embodiment, by fusing multiple trajectory data and combining a similarity algorithm that comprehensively considers time, speed, and spatial location, accompanying vessels that highly match the trajectory of the target vessel are accurately selected.

[0053] In an exemplary embodiment, determining the spatiotemporal similarity of each third driving trajectory point and each fourth driving trajectory point includes: performing a target operation for each third driving trajectory point to determine the trajectory point similarity between the third driving trajectory point and the fourth driving trajectory point; and determining the spatiotemporal similarity as the product of the trajectory point similarity and a spatiotemporal weight. The target operation includes: determining a first driving time corresponding to each third driving trajectory point; determining a second driving time for each fourth driving trajectory point; determining a time difference between the first driving time and each second driving time; determining a longitude difference between the third driving trajectory point and each fourth driving trajectory point; determining a latitude difference between the third driving trajectory point and each fourth driving trajectory point; determining a first squared value for each longitude difference and a second squared value for each latitude difference; determining a first product of each first squared value and the corresponding time difference; determining a second product of each second squared value and the corresponding time difference; and determining a first sum of the first product and the second product as the trajectory point similarity. In this embodiment, trajectory point similarity can be represented as... Among them, t i Indicates the first travel time, t j Indicates the second travel time, x i The longitude of the third travel trajectory point is represented by y. i Indicates the latitude of the third driving trajectory point. x j The longitude of the fourth travel trajectory point is represented by y. j This represents the latitude of the fourth driving trajectory point. Spatiotemporal similarity can be represented as... Where γ represents the spatiotemporal weight. It should be noted that the time difference represents the time interval and is a positive number.

[0054] In an exemplary embodiment, determining the velocity similarity between a first velocity and a second velocity includes: determining the absolute value of the difference between the first velocity and the second velocity; and determining the velocity similarity as the product of the absolute value and a velocity distance weight. In this embodiment, the velocity similarity can be expressed as δ|v i -v j |, where v i Indicates the second velocity, v j δ represents the first velocity, and δ represents the velocity weight.

[0055] In an exemplary embodiment, determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity includes: determining the sum of the spatiotemporal similarity and the velocity similarity as the trajectory similarity.

[0056] In an exemplary embodiment, determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity includes: determining the sum of the similarity of each trajectory point included in the spatiotemporal similarity and the velocity similarity, obtaining multiple second sums; constructing a target matrix based on the multiple second sums; determining the minimum distance between the first trajectory and the second trajectory based on the target matrix; and determining the minimum distance as the trajectory similarity. In this embodiment, the similarity between each ship trajectory and the target ship trajectory can be calculated using the Speed-Weighted Dynamic Time Warping (SWT) algorithm, filtering out ships that are highly adjacent to the target ship. Compared with traditional algorithms, this algorithm comprehensively considers information from multiple dimensions such as spatiotemporal position and velocity, improving the accuracy and reliability of similarity assessment. When calculating trajectory similarity, it is only necessary to focus on the spatiotemporal envelope of the ship trajectory where the merged trajectory of the search ship is located. Specifically, the spatiotemporal envelope of the ship trajectory where the merged trajectory points of the search ship are located should be identified, and the target ship trajectory points within these envelopes should be extracted. The extracted target ship trajectory points constitute the main trajectory, and similarity calculation is performed with the merged trajectory of the search ship. The specific calculation logic is as follows:

[0057] The distance between two trajectory points can be defined as the sum of the trajectory point similarity and the velocity similarity. Among them, S i It is the search vessel, that is, the trajectory point of other vessels after merging, Q j The trajectory point (P) of the target vessel j ) and interpolation point (L j The equation is composed of: v represents the average speed of the search vessel and the target vessel within that trajectory segment when calculating similarity. γ and δ are the spatiotemporal weights and velocity weights, respectively. A dynamic programming matrix, i.e., the target matrix, is constructed based on the second sum.

[0058] The matrix is ​​initialized as follows:

[0059] D[0,0]=d(S0,Q0) (2)

[0060] D[i,0]=D[i-1,0]+d(S i (3) (i = 1, 2, ..., N)

[0061] D[0,j]=D[0,j-1]+d(S0,Q j (j=1,2,...,N) (4)

[0062] Recurrence relation:

[0063] D[i,j]=d(S i Q j )+min(D[i-1,j],D[i,j-1],D[i-1,j-1]) (5)

[0064] This means taking the minimum cumulative distance from the three directions (left, top, and top right) and adding it to the distance of the current point. The D[i,j] determined by the value in the lower right corner of this matrix is ​​the similarity value (or alignment index), i.e., the trajectory similarity.

[0065] In this embodiment, the Speed-Weighted Dynamic Time Warping (DTW) algorithm evaluates the similarity between each fused ship trajectory and the target ship trajectory, comprehensively considering the influence of factors such as speed, time, and spatial position. This algorithm pays particular attention to the alignment in the spatiotemporal dimensions, ensuring that the search ship and the target ship are highly aligned by introducing a speed factor into the overall similarity calculation.

[0066] In the above embodiments, based on AIS data input, a spatiotemporal envelope of ship trajectories is constructed to deeply mine the spatiotemporal correlation features in ship motion trajectories. Combined with trajectory similarity and speed evaluation rules, high-precision identification of ship formations is achieved. Furthermore, data can be acquired more readily, as AIS data is widely available, eliminating the need for additional image acquisition equipment and reducing system deployment costs. By employing a ship trajectory spatiotemporal envelope, ships closely related to the target ship in both time and space can be efficiently filtered out, significantly reducing data processing volume and computational costs. By constructing an accurate ship trajectory spatiotemporal envelope, only ship trajectories highly correlated with the target ship in time and space are analyzed. Combined with trajectory similarity and speed matching rules, the false positive rate is greatly reduced, ensuring that identified ships accurately belong to the same formation. AIS data is updated in real time, rapidly reflecting dynamic changes in ships and supporting real-time identification and decision-making. Unaffected by weather, lighting, or other natural factors, the stability and reliability of identification are improved. Through a spatiotemporal analysis and identification method based on AIS data, ultra-precise identification of ship formations is achieved, providing strong technical support for maritime traffic management, safety monitoring, and other fields.

[0067] In an exemplary embodiment, determining the first trajectory point of a target vessel based on Automatic Identification System (AIS) data includes: determining the actual trajectory point of the target vessel based on the AIS data; determining the time interval between the generation times of two adjacent actual trajectory points; if the time interval is greater than a preset threshold, interpolating the two adjacent actual trajectory points to obtain interpolated trajectory points; and determining the actual trajectory point and the interpolated trajectory point as the first trajectory point. In this embodiment, the AIS trajectory points of each target vessel, i.e., the actual trajectory point data, are processed. In particular, when the time interval between adjacent trajectory points is too large, a new trajectory point, i.e., the interpolated trajectory point, is generated through an interpolation algorithm. The purpose of interpolation is to ensure that sufficiently continuous and accurate trajectory information can be obtained in subsequent analysis, avoiding trajectory discontinuity or analysis result deviation due to excessive time intervals. After the trajectory point interpolation is completed, the system constructs a spatiotemporal envelope for the target vessel based on the original trajectory points and the interpolated trajectory points. This model defines the possible navigation space range of the target vessel in each time period, ensuring that subsequent spatiotemporal analysis can be carried out within a precise spatiotemporal framework. The purpose of spatiotemporal analysis is to screen out other vessels that have a strict escort relationship with the target vessel.

[0068] In an exemplary embodiment, determining the envelope of the target vessel based on each first trajectory point to obtain multiple target envelopes includes: determining the envelope size of the envelope; and constructing the target envelope according to the envelope size, using each first trajectory point as the target point of the envelope. In this embodiment, each target vessel trajectory point, i.e., the actual trajectory point P, can be...i =(x i ,y i ,t i ) and interpolation trajectory point L i =(x i ,y i ,t i And construct a spatiotemporal envelope model with side lengths Δx, Δy and Δt to capture the relative motion range of the target ship in time and space.

[0069] In this embodiment, in order to find the ship formation that is strictly accompanying the target ship, it is necessary to analyze the trajectory point P of the target ship. i =(x i ,y i ,t i Interpolation point L i =(x i ,y i ,t i Spatiotemporal analysis is performed. A schematic diagram of the spatiotemporal envelope of the ship's trajectory can be found in the appendix. Figure 6 ,like Figure 6 As shown, the trajectory point P of the target ship can be... i and interpolation point L i A regular rectangular spatiotemporal envelope is constructed, with side lengths Δx, Δy, and Δt. Only ships whose trajectory points lie within this spatiotemporal envelope can be identified as accompanying vessels and included as members of the formation. This method improves the accuracy and efficiency of accompanying vessel identification by strictly limiting the spatiotemporal range.

[0070] In this embodiment, the envelope size can be dynamically adjusted. The dimensions Δx, Δy, and Δt of the spatiotemporal envelope of the ship trajectory can be dynamically adjusted according to different scenarios or the specific motion characteristics of the ship, thereby enhancing the adaptability of the system.

[0071] The above method for determining ship formations can be executed within a ship formation determination system. A diagram of the ship formation determination system can be found in the appendix. Figure 7 ,like Figure 7 As shown, the system includes an input module, a detection module, and an output module. These three modules together complete the task of high-precision identification of ship formations.

[0072] The input module primarily receives Automatic Identification System (AIS) data from vessels, specifically their Maritime Mobility Service Identifier (MMSI) and target detection time. The MMSI uniquely identifies a specific vessel, while the detection time determines the time period to be analyzed.

[0073] The detection module performs a series of trajectory analyses and accompanying vessel detection operations based on the input vessel MMSI and detection time data. The specific steps are described below:

[0074] 1. Trajectory Point Interpolation. First, the AIS trajectory point data for each target vessel is processed, especially when the time interval between adjacent trajectory points is too large. New trajectory points are generated using an interpolation algorithm. The purpose of interpolation is to ensure sufficiently continuous and accurate trajectory information in subsequent analysis, avoiding trajectory inconsistencies or biased analysis results due to excessive time intervals.

[0075] 2. Constructing the Spatiotemporal Envelope of the Ship's Trajectory. After trajectory point interpolation, the system constructs a spatiotemporal envelope for the target ship based on the original and interpolated trajectory points. This model defines the possible navigation space range of the target ship within each time period, ensuring that subsequent spatiotemporal analysis can be conducted within a precise spatiotemporal framework. The purpose of the spatiotemporal analysis is to identify other ships that have a strict escort relationship with the target ship. Escort behavior refers to the phenomenon where, within a specific time period, the trajectories of other ships closely match those of the target ship in both space and time, exhibiting synchronous navigation characteristics.

[0076] 3. Trajectory Fusion. For all ships located within the spatiotemporal envelope of the target ship, their complete trajectories need to be fused in chronological order.

[0077] 4. Similarity Calculation. The trajectory similarity between the target ship and other vessels is calculated to determine whether these vessels form a formation closely following the target ship. Vessels meeting the escort criteria are selected based on trajectory similarity, and the time they spend accompanying the target ship is further calculated.

[0078] Third is the output module. This module presents the analysis results. The final output includes the MMSI of all eligible accompanying vessels in the formation, as well as the co-travel time between these vessels and the target vessel. This output provides crucial information for subsequent analysis, decision-making, or monitoring.

[0079] For example, a ship formation identification system can find the ship formation of a target ship (MMSI 412695650, target time period from XXXX-XX-XX 00:00:00 to XXXX-XX-XX 23:59:59).

[0080] Track point interpolation. For the ship's trajectory within this time period, interpolation is performed for trajectories between adjacent points that are more than 10 minutes apart.

[0081] Construct the spatiotemporal envelope of the target vessel's trajectory. Set Δx and Δy to 5 km and Δt to 5 minutes, and strictly control accompanying vessels.

[0082] Point fusion within the spatiotemporal envelope of a ship's trajectory. For ships located within the spatiotemporal envelope of their trajectories, their trajectory points are fused into a single trajectory.

[0083] An improved speed-weighted dynamic time warping (DTW) algorithm is used to calculate the similarity between the target ship's trajectory and the trajectories of the searched ships, and ships with trajectory similarity greater than a threshold are selected.

[0084] Calculate and output the common navigation time between each vessel and the target vessel. A schematic diagram of the accompanying vessel trajectories during the target time period can be found in the appendix. Figure 8 .

[0085] In the aforementioned embodiments, constructing a spatiotemporal envelope of ship trajectories based on interpolated trajectory points allows for precise analysis of ship spatiotemporal behavior and improves search accuracy. Within the constructed spatiotemporal envelope, limiting the search range to other ship trajectory points within the envelope enables accurate capture of ship trajectories accompanying the target ship, thereby avoiding the influence of external interference points. This method effectively improves the accuracy of formation identification by strictly limiting the search range, ensuring accurate identification of the trajectories of accompanying ships. Constructing a spatiotemporal envelope of ship trajectories based on interpolated trajectory points also narrows the search range and improves search efficiency, requiring only the search of potential accompanying ships within the spatiotemporal envelope, significantly reducing the search scope. This method effectively reduces computational load, improves the overall system's processing efficiency and real-time response capability, and shows significant advantages, especially when dealing with large-scale ship data. Furthermore, using the Speed-Weighted Dynamic Time Warping (DTW) algorithm for trajectory similarity calculation enables the application of distance metrics to determine trajectory similarity.

[0086] In the foregoing embodiments, for the target ship trajectory points after cubic spline interpolation, this invention constructs a positive rectangular spatiotemporal envelope surrounding these trajectory points and the interpolated trajectory points. The presence of accompanying ships is determined by detecting other ship trajectory points located within this spatiotemporal envelope. The innovation of this method lies in using a spatiotemporal envelope to capture the spatiotemporal relationships between ships, thereby achieving accurate identification of ship formations.

[0087] Compared to methods in related technologies, this application demonstrates more efficient data dependency. Accurate identification of ship formations can be achieved solely relying on AIS data, without needing to depend on real-time imagery or radar data, thus reducing the complexity of data requirements. The focus of this application is on identifying which ships belong to the same formation, rather than being limited to analyzing the formations of known formations, thereby providing more flexible formation identification capabilities. This application uses a ship trajectory spatiotemporal envelope model and a speed-weighted dynamic time warping (DTW) algorithm to identify ships strictly accompanying the target ship, achieving efficient discovery and identification of ship formations, significantly improving the accuracy and reliability of formation identification.

[0088] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0089] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0090] According to another aspect of the embodiments of this application, a vessel formation determination apparatus is also provided. This vessel formation determination apparatus can be used to implement the vessel formation determination method provided in the above embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0091] Figure 9 This is a structural block diagram of an optional ship formation determination device according to an embodiment of this application, such as... Figure 9 As shown, the device for determining the ship formation includes:

[0092] The first determining module 92 is used to determine the first trajectory point of the target vessel based on data from the Automatic Identification System (AIS).

[0093] The second determining module 94 is used to determine the envelope of the target vessel based on each of the first driving trajectory points, thereby obtaining a plurality of the envelopes;

[0094] The third determining module 96 is used to determine the target envelope included in the plurality of envelopes, wherein the target envelope includes a second travel trajectory point, and the second travel trajectory point is the trajectory point of a vessel other than the target vessel;

[0095] The fourth determining module 98 is used to determine the ship formation of the target ship based on the first driving trajectory point and the second driving trajectory point.

[0096] It should be noted that the first determining module 92 in this embodiment can be used to execute the above step S202, the second determining module 94 in this embodiment can be used to execute the above step S204, the third determining module 96 in this embodiment can be used to execute the above step S206, and the fourth determining module 98 in this embodiment can be used to execute the above step S208.

[0097] In an exemplary embodiment, the fourth determining module 98 can determine the ship formation of the target ship based on the first travel trajectory point and the second travel trajectory point in the following manner: determining the first trajectory of the target ship based on the first travel trajectory point; determining the third travel trajectory point of the second travel trajectory point that belongs to the same other ship; determining the second trajectory of the other ship based on the third travel trajectory point; determining the trajectory similarity between the first trajectory and the second trajectory; and determining the ship formation based on the trajectory similarity.

[0098] In an exemplary embodiment, the fourth determining module 98 may determine the trajectory similarity between the first trajectory and the second trajectory in the following manner: determining the target sub-envelope in which the third driving trajectory point is located, wherein the target envelope includes the target sub-envelope; determining the fourth driving trajectory point included in the first trajectory and located within the target sub-envelope; determining the spatiotemporal similarity of each of the third driving trajectory points and each of the fourth driving trajectory points; determining the velocity similarity between a first velocity and a second velocity, wherein the first velocity is the velocity of the target vessel in the first trajectory, and the second velocity is the velocity of the other vessel in the second trajectory; and determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity.

[0099] In an exemplary embodiment, the fourth determining module 98 can determine the spatiotemporal similarity of each of the third driving trajectory points and each of the fourth driving trajectory points in the following manner: performing a target operation for each of the third driving trajectory points to determine the trajectory point similarity between the third driving trajectory point and the fourth driving point; determining the spatiotemporal similarity as the product of the trajectory point similarity and the spatiotemporal weight; wherein, the target operation includes: determining the first driving time corresponding to the third driving trajectory point; determining the second driving time of each of the fourth driving trajectory points; determining the time difference between the first driving time and each of the second driving time; determining the longitude difference between the third driving trajectory point and each of the fourth driving trajectory points; determining the latitude difference between the third driving trajectory point and each of the fourth driving trajectory points; determining the first square value of each of the longitude differences and determining the second square value of each of the latitude differences; determining the first product of each of the first square values ​​and the time difference corresponding to the first square value; determining the second product of each of the second square values ​​and the time difference corresponding to the second square value; and determining the first sum of the first product and the second product as the trajectory point similarity.

[0100] In an exemplary embodiment, the fourth determining module 98 can determine the speed similarity between the first speed and the second speed by: determining the absolute value of the difference between the first speed and the second speed; and determining the speed similarity by multiplying the absolute value by the speed distance weight.

[0101] In an exemplary embodiment, the fourth determining module 98 can determine the trajectory similarity based on the spatiotemporal similarity and the velocity similarity in the following manner: determining the sum of the similarity of each trajectory point included in the spatiotemporal similarity and the velocity similarity to obtain a plurality of second sums; constructing a target matrix based on the plurality of second sums; determining the minimum distance between the first trajectory and the second trajectory based on the target matrix; and determining the minimum distance as the trajectory similarity.

[0102] In an exemplary embodiment, the first determining module 92 can determine the first travel trajectory point of the target vessel based on the Automatic Identification System (AIS) data in the following manner: determining the actual trajectory point of the target vessel based on the AIS data; determining the time interval between the generation times of two adjacent actual trajectory points; if the time interval is greater than a preset threshold, interpolating the two adjacent actual trajectory points to obtain an interpolated trajectory point; and determining the actual trajectory point and the interpolated trajectory point as the first travel trajectory point.

[0103] In an exemplary embodiment, the second determining module 94 can determine the envelope of the target vessel based on each of the first travel trajectory points to obtain multiple target envelopes in the following manner: determining the envelope size of the envelope; using each of the first travel trajectory points as the target points of the envelope, and constructing the target envelope according to the envelope size.

[0104] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0105] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program executes the steps in any of the above method embodiments when it is run.

[0106] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0107] According to another aspect of the embodiments of this application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor is configured to perform the steps of any of the method embodiments described above via the computer program. In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0108] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0109] According to another aspect of the embodiments of this application, a computer program product is also provided, comprising a computer program / instructions containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit 1001, it performs various functions provided in the embodiments of this application. The sequence numbers of the embodiments of this application above are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0110] Figure 10 A schematic block diagram of a computer system architecture for implementing embodiments of the present application is shown. Figure 10As shown, the computer system 1000 includes a Central Processing Unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in ROM 1002 or programs loaded into RAM 1003 from storage section 1008. Random access memory 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004.

[0111] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a local area network card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. Drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.

[0112] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit 1001, it performs various functions defined in the system of this application.

[0113] It should be noted that, Figure 10 The computer system 1000 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0114] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0115] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining a ship formation, characterized in that, include: The first trajectory point of the target vessel is determined based on data from the Automatic Identification System (AIS). The envelope of the target vessel is determined based on each of the first travel trajectory points, resulting in multiple envelopes; A target envelope is identified among a plurality of said envelopes, wherein the target envelope includes a second travel trajectory point, the second travel trajectory point being the trajectory point of a vessel other than the target vessel within the target envelope; The ship formation of the target vessel is determined based on the first and second travel trajectory points; Determining the envelope of the target vessel based on each of the first travel trajectory points, and obtaining multiple envelopes, includes: determining the envelope size of the envelope; using each of the first travel trajectory points as the target point of the envelope, and constructing the envelope according to the envelope size; Determining the vessel formation of the target vessel based on the first and second travel trajectory points includes: determining a first trajectory of the target vessel based on the first travel trajectory point; determining a third travel trajectory point belonging to the same other vessel included in the second travel trajectory point; determining a second trajectory of the other vessel based on the third travel trajectory point; determining the trajectory similarity between the first and second trajectories; and determining the vessel formation based on the trajectory similarity. Determining the trajectory similarity between the first trajectory and the second trajectory includes: determining the target sub-envelope where the third trajectory point is located, wherein the target envelope includes the target sub-envelope; determining the fourth trajectory point included in the first trajectory and located within the target sub-envelope; determining the spatiotemporal similarity of each third trajectory point and each fourth trajectory point; determining the velocity similarity between a first velocity and a second velocity, wherein the first velocity is the velocity of the target vessel in the first trajectory, and the second velocity is the velocity of the other vessels in the second trajectory; and determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity.

2. The method according to claim 1, characterized in that, Determining the spatiotemporal similarity of each of the third and fourth driving trajectory points includes: For each of the third driving trajectory points, a target operation is performed to determine the trajectory point similarity between the third driving trajectory point and the fourth driving trajectory point; The product of the trajectory point similarity and the spatiotemporal weight is determined as the spatiotemporal similarity. The target operation includes: Determine the first travel time corresponding to the third travel trajectory point; Determine the second travel time for each fourth travel trajectory point; Determine the time difference between the first travel time and each of the second travel times; Determine the longitude difference between the third driving trajectory point and each of the fourth driving trajectory points; Determine the latitude difference between the third driving trajectory point and each of the fourth driving trajectory points; Determine a first squared value for each of the longitude differences, and determine a second squared value for each of the latitude differences; Determine the first product of each first squared value and the time difference corresponding to the first squared value; Determine the second product of each second squared value and the time difference corresponding to the second squared value; The first sum of the first product and the second product is determined as the similarity of the trajectory points.

3. The method according to claim 1, characterized in that, Determining the velocity similarity between the first velocity and the second velocity includes: Determine the absolute value of the difference between the first speed and the second speed; The product of the absolute value and the speed distance weight is determined as the speed similarity.

4. The method according to claim 1, characterized in that, Determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity includes: The sum of the similarity of each trajectory point included in the spatiotemporal similarity and the velocity similarity is determined to obtain multiple second sums; Construct the target matrix based on multiple second sums; The minimum distance between the first trajectory and the second trajectory is determined based on the target matrix; The minimum distance is determined as the trajectory similarity.

5. The method according to claim 1, characterized in that, The first trajectory point of the target vessel determined based on data from the Automatic Identification System (AIS) includes: The actual trajectory points of the target vessel are determined based on the data from the Automatic Identification System (AIS). Determine the time interval between the generation times of two adjacent actual trajectory points; If the time interval is greater than a preset threshold, interpolation is performed on two adjacent actual trajectory points to obtain interpolated trajectory points; The actual trajectory point and the interpolated trajectory point are determined as the first driving trajectory point.

6. A device for determining ship formations, characterized in that, include: The first determination module is used to determine the first trajectory point of the target vessel based on data from the Automatic Identification System (AIS). The second determining module is used to determine the envelope of the target vessel based on each of the first travel trajectory points, thereby obtaining multiple envelopes; The third determining module is used to determine the target envelope included in the plurality of envelopes, wherein the target envelope includes a second travel trajectory point, and the second travel trajectory point is the trajectory point of a vessel other than the target vessel within the target envelope; The fourth determining module is used to determine the ship formation of the target ship based on the first driving trajectory point and the second driving trajectory point; The second determining module determines the envelope of the target vessel based on each of the first travel trajectory points in the following manner, resulting in multiple envelopes: determining the envelope size of the envelope; using each of the first travel trajectory points as the target point of the envelope, and constructing the envelope according to the envelope size; The fourth determining module determines the vessel formation of the target vessel based on the first and second travel trajectory points in the following manner: determining the first trajectory of the target vessel based on the first travel trajectory point; determining the third travel trajectory point belonging to the same other vessel included in the second travel trajectory point; determining the second trajectory of the other vessel based on the third travel trajectory point; determining the trajectory similarity between the first and second trajectories; and determining the vessel formation based on the trajectory similarity. The fourth determining module determines the trajectory similarity between the first trajectory and the second trajectory in the following ways: determining the target sub-envelope where the third travel trajectory point is located, wherein the target envelope includes the target sub-envelope; determining the fourth travel trajectory point included in the first trajectory and located within the target sub-envelope; determining the spatiotemporal similarity of each third travel trajectory point and each fourth travel trajectory point; determining the velocity similarity between a first velocity and a second velocity, wherein the first velocity is the velocity of the target vessel in the first trajectory, and the second velocity is the velocity of the other vessels in the second trajectory; and determining the trajectory similarity based on the spatiotemporal similarity and the velocity similarity.

7. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

Images