Method for recognizing similar scenarios of multi-ship encounter based on topological graph sequence

Abstract

The application discloses a kind of based on topological graph sequence multi-ship encounter similar scene identification method, including the following steps: 1) multi-ship encounter scene information acquisition;2) multi-ship encounter scene extraction;Through the construction multi-ship encounter topological graph sequence, multi-ship encounter scene extraction is carried out;3) multi-ship encounter similar scene identification;4) the identification result queue obtained to the scene hierarchical identification has multiple graph sequences, arranges final result according to graph sequence similarity from small to big, completes the acquisition of multi-ship encounter scene similar scene.The application aims at the problem that multi-ship encounter scene is difficult to find similar scene by similarity measurement, proposes multi-ship encounter scene identification method based on topological graph sequence, and the research result can provide method reference for ship collision avoidance decision, encounter risk analysis related research.

Description

Technical Field

[0001] This invention relates to ship collision avoidance technology, and more particularly to a method for identifying similar multi-ship encounter scenarios based on topological graph sequences. Background Technology

[0002] In busy navigable waters, multiple vessels frequently encounter each other, and these complex encounter scenarios often present challenges for collision avoidance. To address this issue, an effective approach is to learn from good collision avoidance habits in similar historical scenarios. The core of this approach is the extraction of encounter scenarios and the identification of similar scenarios. By extracting encounter scenarios from AIS data and analyzing and comparing similar scenarios, vessels can learn from the experience and decisions of others and take appropriate collision avoidance measures.

[0003] Current research on ship encounter scenarios has received widespread attention. Ma Jie et al. proposed an improved support vector machine-based encounter situation identification model based on the relative distance and heading difference between two ships, effectively identifying ship encounter situations. Jiang Longhui et al. extracted ship encounter scenarios by calculating relative motion parameters of ships and based on collision avoidance rules and navigational experience. Rong et al. proposed an encounter scenario extraction method based on an improved sliding window algorithm, automatically identifying ship maneuvering behaviors based on ship trajectories. Zhang Jinfen et al. identified encounter scenarios based on ship trajectories and achieved real-time quantification of ship collision risks. Hwang T et al. proposed a data-driven navigation situation clustering model, classifying ship encounter situations into ordinary and special encounter scenarios. Zhang et al. constructed a ship encounter identification model based on ship encounter characteristics, designed a collision avoidance behavior extraction algorithm, and established a behavior knowledge base. Most of the above research focuses on the identification and extraction of encounter scenarios, with relatively little research on similarity measurement between encounter scenarios, making it difficult to formulate accurate and effective collision avoidance strategies. Therefore, exploring and developing similarity measurement methods for multi-ship encounter scenarios is essential. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method for identifying similar multi-ship encounters based on topological graph sequences, addressing the deficiencies in the prior art.

[0005] The technical solution adopted by this invention to solve its technical problem is: a method for identifying similar multi-ship encounter scenes based on topological graph sequences, comprising the following steps: 1) Information collection for multi-ship encounter scenarios; A multi-ship encounter situation is defined as follows: when three or more ships approach each other, and at any given moment any ship encounters at least one other ship, a multi-ship encounter situation is constituted. The multi-ship encounter scenario is defined as: a combination of consecutive multi-ship encounter situations in chronological order; Acquire information on multi-ship encounter scenarios, including ship type, number of ships, ship MMSI, and ship navigation information; 2) Extraction of multi-ship encounter scenarios; Multi-ship encounter scenarios are extracted by constructing a sequence of multi-ship encounter topology maps. Ship information and encounter relationships are used as node features and edge attributes of the topology graph, and this type of topology graph with spatiotemporal information is defined as a time sequence graph. Multiple time sequence graphs are combined in chronological order to characterize the dynamic changes of ship encounters in the scene and construct a multi-ship encounter topology graph sequence. 3) Identification of similar scenarios when multiple ships encounter each other; 3.1) Use graph convolutional neural networks for overall identification of similar scenes; By compressing the topological relationships of the scene graph sequence, a representative topological graph representing the entire scene is generated as input; The GCN model is used to classify the input representative topology graph. The category of the representative graph is determined based on the probability distribution of the output graph category, thereby measuring the similarity of the overall topological relationships in the scene. 3.2) Layered identification of similar scenes A graph-based hierarchical encounter scene identification method is used to identify the internal states of the scene: The graph sequence model is split into three layers according to the graph structure: graph unit, topological graph, and graph sequence. The similarity between dynamic graph models is measured layer by layer by calculating the similarity of the three layers of graph structure, so as to complete the hierarchical identification of similar scenes. 4) The queue of identification results obtained from scene layer identification contains multiple graph sequences. The graph sequences are sorted in ascending order of similarity to obtain the final result, thus completing the acquisition of similar scenes in multi-ship encounter scenarios.

[0006] According to the above scheme, in step 1), in the multi-ship encounter scenario, for the ships included in the earliest multi-ship encounter situation in the scenario, the time when they form an encounter is recorded as the start time of the multi-ship encounter scenario; for the ships included in the encounter situation at the start time... ship s If at any given moment at least one ship is not in contact with ship s If other ships in the scene encounter each other, this moment will be recorded as the end of the scene.

[0007] According to the above scheme, in step 2), the multi-ship encounter topology map sequence is constructed as follows: 2.1) Construction of edge relationships in the topological graph The encounter relationship between ships is determined using three encounter characteristic parameters: relative distance, DCPA, and TCPA. t At that moment, when i boat andj If all the encounter characteristic parameters between ships meet the threshold, then they are determined to have an encounter relationship at the current moment. 2.2) Node attribute definition MMSI and ship type are selected as node features of the topology graph, and the topology graph is represented by an undirected graph. Let X be the set of nodes in graph G, containing ship information and the number of ships currently in the graph; E is the set of edges, containing the encounter relationships between ships. 2.3) Scene graph sequence construction; The encounter scenario is determined by calculating the Jaccard coefficient: When the Jaccard coefficients of two graphs are greater than a threshold, it indicates that they exist in the same encounter scenario. Clustering topological graphs belonging to the same scene to construct a graph sequence model representing the complete scene. , where Y represents the graph sequence features of C, including the duration of the scene and the start time; S represents the number of time sequence graphs contained in C.

[0008] According to the above scheme, step 3.1) represents the process of generating the topology graph as follows: By aggregating the union of points and edges of all time-series graphs in the scene, a representative topological graph containing all graph structures within the scene is obtained. Feature information extraction: The encounter relationships between ships in the scene are extracted by extracting the adjacency matrix that represents the topological graph. For each node representing the topology graph Each has N features, denoted as MMSI and ship type are used as node feature inputs.

[0009] According to the above scheme, in step 3.2), the similarity graph unit is identified as follows: 3.2.1) Similarity graph unit identification; 3.2.1.1) Extract graph elements; A graph cell is a partial representation of the internal structure of a time series diagram; a graph cell... From the source node and multiple adjacent nodes Composition, using express; Node attributes Indicates the type of vessel; For timing diagrams , time sequence diagram Each node contained herein is used sequentially as a source node to extract graph units; 3.2.1.2) Calculate the similarity of graph elements; Node attributes and inter-node connectivity are selected as elements for calculating graph unit similarity. For two graph units... and The similarity of its graph units is defined as follows:

[0010] in, , They represent and The number of adjacent nodes; It is the number of adjacent nodes shared by the two graph units; This is the number of edges shared by the two graph units, calculated as follows:

[0011] It is the source node of the two graph units. , The similarity is calculated using the following formula:

[0012] 3.2.1.3) Similarity graph unit identification; By query graph cells Similarity is calculated and filtered among all graph units in the database to obtain a queue of graph units with the minimum distance, and then an adaptive evaluation score is applied. Remove queue members whose distance is less than The graph cells are used to filter graph cells in the database that may be similar to the query graph cell. According to the above scheme, in step 3.2), the similar time series diagram identification is as follows: 3.2.2) Identification of similar time series diagrams; 3.2.2.1) Time series diagram similarity; Each time series graph is an unordered set of graph units, and the similarity of time series graphs is calculated as the optimal allocation of two sets of graph units; 3.2.2.2) Identification of similar time series diagrams; For timing diagrams Each graph unit All of them are identified by graph unit identification to find their similar graph unit queues, denoted as Therefore Obtain a queue of M similar graph units; based on the elements in the queues, find the time series graphs containing the similar graph units from the database, thereby filtering out those that match the query graph. L time series diagrams that have similar relationships are used to form a graph association list. ; Will Similarity is calculated and filtered for each time series graph in the associated list, and then based on the evaluation score. Obtain a queue of similar graphs that meet the criteria. According to the above scheme, in step 3.2), the similarity graph unit is identified as follows: 3.2.3) Similar Graph Sequence Identification 3.2.3.1) Graph sequence similarity A graph sequence containing n graphs A graph sequence can be viewed as a time series composed of multiple time slices. Therefore, measuring the similarity of graph sequences is considered as a problem of calculating time series similarity. Hence, dynamic time warping is introduced to define the similarity between graph sequences. For two graph sequences... , The similarity of their graph sequences is calculated as follows:

[0013] 3.2.3.2) Similar graph sequence identification; For graph sequences First, a sequence graph identification algorithm is used to find n similar sequence graph queues. Then, a graph sequence association list is constructed based on the sequence graphs within each queue. Finally, [the algorithm is then used to...] Iterate through the associated list and based on the evaluation score Obtain a queue of similar graph sequences. The beneficial effects of this invention are: This invention addresses the problem that it is difficult to find similar scenarios in multi-ship encounters using similarity metrics. It proposes a multi-ship encounter scenario identification method based on topological graph sequences. The research results can provide a methodological reference for ship collision avoidance decision-making and encounter risk analysis. Attached Figure Description

[0014] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings: Figure 1 This is a flowchart of a method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the construction of a multi-ship encounter scene sequence according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a graph convolutional neural network according to an embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the generation of a scene representative image according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the accuracy curve of the GCN model in an embodiment of the present invention; Figure 6 This is a schematic diagram of the loss function curve of the GCN model in an embodiment of the present invention; Figure 7 This is a schematic diagram of the hierarchical identification of the encounter scene according to an embodiment of the present invention; Figure 8 This is a schematic diagram of graph unit extraction according to an embodiment of the present invention; Figure 9 This is a schematic diagram of graph similarity calculation according to an embodiment of the present invention; Figure 10 This is a schematic diagram of the weight matrix according to an embodiment of the present invention. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0016] This invention addresses the problem of difficulty in finding similar scenarios in multi-ship encounters using similarity metrics, proposing a multi-ship encounter scene identification method based on topological graph sequences. First, multi-ship encounter scenes are identified and extracted from AIS data and transformed into a graph sequence model. Then, a similarity algorithm is used to calculate the graph sequence similarity, identifying multi-ship encounter scenes similar to the original scenes. Experimental results show that the proposed method can identify encounter scenes with similar encounter evolution trends and can identify the encounter situations of corresponding ships within the scenes.

[0017] like Figure 1 As shown, a method for identifying similar multi-ship encounter scenes based on topological graph sequences includes the following steps: 1) Information collection for multi-ship encounter scenarios; A multi-ship encounter situation is defined as follows: when three or more ships approach each other, and at any given moment any ship encounters at least one other ship, a multi-ship encounter situation is constituted. The multi-ship encounter scenario is defined as: a combination of consecutive multi-ship encounter situations in chronological order; Acquire information on multi-ship encounter scenarios, including ship type, number of ships, ship MMSI, and ship navigation information; navigation information includes speed, heading, and position information; 2) Extraction of multi-ship encounter scenarios; Multi-ship encounter scenarios are extracted by constructing a sequence of multi-ship encounter topology maps. Ship information and encounter relationships are used as node features and edge attributes of the topology graph, and this type of topology graph with spatiotemporal information is defined as a temporal sequence graph. Multiple temporal sequence graphs are combined in chronological order to characterize the dynamic changes in ship encounters within the scene, constructing a multi-ship encounter topology graph sequence, such as... Figure 2 ; 2.1) Construction of edge relationships in the topological graph The encounter relationship between ships is determined using three encounter characteristic parameters: relative distance, DCPA, and TCPA. tAt that moment, when i boat and j If all the encounter characteristic parameters between ships meet the threshold, then they are determined to have an encounter relationship at the current moment. t Relative distance between ships at any time The calculation is as follows:

[0018] , , , They are i boat and j The ship is t Location information at any given time. Based on relative distance. The two ships can be calculated at... t Moment and :

[0019]

[0020] yes i boat and j The ship in time t relative velocity, It is the cosine of the angle between the line connecting the two ships and their relative velocities, and it is calculated as follows:

[0021]

[0022] in , They are t The two ships' course at that moment.

[0023] 2.2) Node attribute definition MMSI and ship type are selected as node features of the topology graph, and the topology graph is represented by an undirected graph. Let X be the set of nodes in graph G, containing ship information and the number of ships currently in the graph; E is the set of edges, containing the encounter relationships between ships.

[0024] 2.3) Scene Graph Sequence Construction The Jaccard similarity coefficient is used to determine the encounter scenario to which two images belong: when the Jaccard similarity coefficients of two images are greater than a threshold, it indicates that they exist in the same encounter scenario. The calculation formula is as follows: (6) in, , These are topology diagrams , The similarity between two topological graphs is calculated by determining the similarity of node features (MMSI, ship type) contained in the two node sets. The threshold is typically set between 0.4 and 0.8, and the specific threshold setting needs to be selected through experimental comparison and analysis.

[0025] Clustering topological graphs belonging to the same scene to construct a graph sequence model representing the complete scene. , where Y represents the graph sequence features of C, including the duration of the scene and the start time; S represents the number of time sequence graphs contained in C.

[0026] 3) Identification of similar scenarios when multiple ships encounter each other; 3.1) Use graph convolutional neural networks for overall recognition of similar scenes, such as... Figure 3 ; By compressing the topological relationships of the scene graph sequence, a representative topological graph representing the entire scene is generated as input; The GCN model is used to classify the input representative topology graph. The category of the representative graph is determined based on the probability distribution of the output graph category, thereby measuring the similarity of the overall topological relationships in the scene. 3.1.1) GCN Model Construction For the graph convolutional network model used It has the following hierarchical propagation rules: (7) Let h represent the output features of the h-th layer, and ,and It is a picture Input features; ,in yes The adjacency matrix, It is the identity matrix; It is the degree matrix of a graph in an undirected graph. It equals the number of edges connected to the vertex; It is the trainable weight matrix of layer h; This represents the activation function.

[0027] 3.1.2) Input Dataset Construction ① Represents topology graph generation The process of generating a scene-representative topology diagram is as follows: Figure 4 As shown.

[0028] Depend on Figure 4It can be seen that by aggregating the union of points and edges of all time-series graphs in the scene, a representative topological graph containing all graph structures in the scene can be obtained to summarize the changes in the entire scene.

[0029] ② Scene feature information extraction a. Graph Adjacency Matrix The encounter relationships between ships within a scene are extracted by extracting the adjacency matrix of the representative graph. Figure 4 Generated scene representation diagram C R -1, its adjacency matrix As shown below:

[0030] b. Graph node feature matrix For each node in the topology graph Each has N features, denoted as If MMSI and ship type are used as node feature inputs, then for Figure 4 The representative image of the scene, its node feature matrix As shown below:

[0031] 3.1.3) GCN Model Training To precisely control model parameter updates and accelerate convergence, based on the dataset size and model complexity, each batch was set to process 30 samples (batch-size = 30), with 500 iterations (epoch = 500). The dropout probability p was set to 0.5, and training was performed using 10-fold cross-validation (N-fold = 10). After training, the optimal learning rate for the model was determined to be 0.001.

[0032] During training, the accuracy and loss function curves of the model are plotted, such as... Figure 5 , Figure 6 As shown.

[0033] The results show that the model begins to exhibit its best performance after 350 iterations, with the accuracy stabilizing above 90%. At the same time, the loss curve also shows a stable trend with a small fluctuation range, indicating that the model has achieved good stability and excellent performance.

[0034] 3.2) Layered identification of similar scenes A graph-based hierarchical scene recognition algorithm is used to identify the internal state of the scene: The graph sequence model is decomposed into a three-layer structure: graph unit, topological graph, and graph sequence. The similarity between dynamic graph models is measured layer by layer by calculating the similarity of these three layers, thus completing the layered identification of similar scenes. The layered identification process is detailed below. Figure 7 ; 2.2.1) Similar Graph Unit Identification 1) Graph unit similarity The internal structure of a topological graph can be represented by factors such as the attributes of nodes and edges and the connection methods. Therefore, the internal structure of a time sequence graph is represented by a combination of multiple graph units.

[0035] ①Graphic Unit A graph cell is a partial representation of the internal structure of a time series diagram; a graph cell... From the source node and multiple adjacent nodes Composition, using Representation; where node attributes Indicate the ship type, where: 6: passenger ship, 7: general cargo ship, 8: oil tanker; for the time sequence diagram The process for extracting its graph units is as follows: Figure 8 As shown.

[0036] Depend on Figure 8 It can be seen that, Each node contained herein is used sequentially as a source node to extract graph cells. , , , There are a total of 4 graph units. Since the order of adjacent nodes in a graph unit does not affect the result, it will not be considered for the time being.

[0037] ② Graph unit similarity Based on the definition of graph units above, it can be seen that the higher the similarity between graph units within a topological graph, the more similar the two graphs are. Node attributes and inter-node connections are selected as elements for calculating graph unit similarity. For two graph units... and The similarity of its graph units is defined as follows:

[0038] in, , They represent and The number of adjacent nodes; It is the number of adjacent nodes shared by the two graph units; This is the number of edges shared by the two graph units, calculated as follows:

[0039] It is the source node of the two graph units. , The similarity is calculated using the following formula:

[0040] For example, for Figure 8 In the diagram unit and : , ; ; ; its unit similarity .

[0041] 2) Graph Unit Identification Algorithm By query graph cells Similarity is calculated and filtered among all graph units in the database to obtain a queue of graph units with the minimum distance, and then an adaptive evaluation score is applied. Remove queue members whose distance is less than The graph units are used to filter graph units in the database that may be similar to the query graph unit. Evaluation score. The calculation formula is as follows:

[0042] 2.2.2) Identification of Similar Time Series Diagrams 1) Time series graph similarity Each time series graph is essentially an unordered set of graph units; therefore, calculating graph similarity can be viewed as solving for the optimal allocation of two sets of graph units. (Time series graph) , The similarity between them is calculated as follows:

[0043] in, It is a weight matrix. It is a Boolean matrix. The graph similarity calculation process is as follows: Figure 9 As shown.

[0044] The core of solving the optimal matching problem is to obtain the weight matrix. ,according to Figure 9 The obtained weight matrix is ​​shown below.

[0045] according to Figure 10 The weight matrix in the equation can be obtained by solving the Hungarian algorithm. , Graph similarity .

[0046] 2) Sequence diagram identification algorithm ①Graphical Association List For timing diagrams Each graph unit All can find their similar graph cell queues through the graph cell identification algorithm, denoted as . Therefore A queue of M similar graph units can be obtained; based on the elements in the queues, a time series graph containing the similar graph unit can be found in the database, thus filtering out the graphs that match the query graph. L time series diagrams that may have similar relationships are used to form a graph association list. This serves as the basis for similar time series graph identification.

[0047] ② Similar Time Series Graph Identification Algorithm Will Similarity is calculated and filtered for each time series graph in the associated list, and then based on the evaluation score. Obtain a queue of similar graphs that meet the criteria. Evaluate the scores. The calculation formula is as follows:

[0048] in, It is a query graph The qth graph unit; It is the current graph in the similarity graph queue. The graph unit, if yes For similar units, calculate their unit similarity and sum them. From equation (15), it can be seen that the evaluation score... This indicates the number of similar graph units contained in the two graphs.

[0049] 2.2.3) Similar Graph Sequence Identification 1) Graph sequence similarity A graph sequence containing n graphs A graph can be viewed as a time series composed of multiple time slices. Therefore, measuring the similarity of graph sequences is considered a problem of calculating time series similarity. Hence, Dynamic Time Warping (DTW) is introduced to define the similarity between graph sequences. For two graph sequences... , The similarity of their graph sequences is calculated as follows:

[0050] 2) Graph sequence identification algorithm A similar graph sequence identification algorithm is proposed: for graph sequences First, a sequence graph identification algorithm is used to find n similar sequence graph queues. Then, a graph sequence association list is constructed based on the sequence graphs within each queue. Finally, [the algorithm is then used to...] Iterate through the associated list and based on the evaluation score Obtain a queue of similar graph sequences. Evaluate scores. It is calculated using the following formula.

[0051]

[0052] in, It is a query graph sequence The nth time series diagram. Therefore This indicates the number of similar time series graphs contained in the two graph sequences.

[0053] By identifying similar graph units in the meeting scene, corresponding graph association lists can be obtained. By traversing the graph association lists to identify similar time sequence graphs, similar time sequence graphs of each graph in the two scenes can be obtained. Based on this, a graph sequence association list can be established. By traversing the two graph sequence association lists to identify similar graph sequences, the identification results can be obtained.

[0054] 3) The queue of identification results obtained from scene layer identification contains multiple graph sequences. The graph sequences are sorted in ascending order of similarity to obtain the final result, thus completing the acquisition of similar scenes in multi-ship encounters.

[0055] The method proposed in this invention can identify encounter scenarios with similar encounter evolution trends and can identify the encounter situation of corresponding ships within the scenario.

[0056] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for identifying similar multi-ship encounter scenes based on topological graph sequences, characterized in that, Includes the following steps: 1) Information collection for multi-ship encounter scenarios; A multi-ship encounter situation is defined as follows: when three or more ships approach each other, and at any given moment any ship encounters at least one other ship, a multi-ship encounter situation is constituted. The multi-ship encounter scenario is defined as: a combination of consecutive multi-ship encounter situations in chronological order; Acquire information on multi-ship encounter scenarios, including ship type, number of ships, ship MMSI, and ship navigation information; 2) Extraction of multi-ship encounter scenarios; Multi-ship encounter scenarios are extracted by constructing a sequence of multi-ship encounter topology maps. Ship information and encounter relationships are used as node features and edge attributes of the topology graph, and this type of topology graph with spatiotemporal information is defined as a time sequence graph. Multiple time sequence graphs are combined in chronological order to characterize the dynamic changes of ship encounters in the scene and construct a multi-ship encounter topology graph sequence. Construct the multi-ship encounter topology sequence as follows: 2.1) Construction of edge relationships in the topological graph The encounter relationship between ships is determined using three encounter characteristic parameters: relative distance, DCPA, and TCPA. t At that moment, when i boat and j If all the encounter characteristic parameters between ships meet the threshold, then they are determined to have an encounter relationship at the current moment. 2.2) Node attribute definition MMSI and ship type are selected as node features of the topology graph, and the topology graph is represented by an undirected graph. Let X be the set of nodes in graph G, containing ship information and the number of ships currently in the graph; E is the set of edges, containing the encounter relationships between ships. 2.3) Scene graph sequence construction; The encounter scenario is determined by calculating the Jaccard coefficient: When the Jaccard coefficients of two graphs are greater than a threshold, it indicates that they exist in the same encounter scenario. Clustering topological graphs belonging to the same scene to construct a graph sequence model representing the complete scene. , where Y represents the graph sequence features of C, including the duration of the scene and the start time; S represents the number of time sequence graphs contained in C; 3) Identification of similar scenarios when multiple ships encounter each other; 3.1) Use graph convolutional neural networks for overall identification of similar scenes; By compressing the topological relationships of the scene graph sequence, a representative topological graph representing the entire scene is generated as input; The GCN model is used to classify the input representative topology graph. The category of the representative graph is determined based on the probability distribution of the output graph category, thereby measuring the similarity of the overall topological relationships in the scene. 3.2) Layered identification of similar scenes A graph-based hierarchical encounter scene identification method is used to identify the internal states of the scene: The graph sequence model is split into three layers according to the graph structure: graph unit, topological graph, and graph sequence. The similarity between dynamic graph models is measured layer by layer by calculating the similarity of the three layers of graph structure, so as to complete the hierarchical identification of similar scenes. 4) The queue of identification results obtained from scene layer identification contains multiple graph sequences. The graph sequences are sorted in ascending order of similarity to obtain the final result, thus completing the acquisition of similar scenes in multi-ship encounter scenarios.

2. The method for identifying similar multi-ship encounter scenes based on topological graph sequences according to claim 1, characterized in that, In step 1), in the multi-ship encounter scenario, for the ships included in the earliest multi-ship encounter situation in the scenario, the time when the encounter occurs is recorded as the start time of the multi-ship encounter scenario; for the ships included in the encounter situation at the start time... ship s If at any given moment at least one ship is not in contact with ship s If other ships in the scene encounter each other, this moment will be recorded as the end of the scene.

3. The method for identifying similar multi-ship encounter scenes based on topological graph sequences according to claim 1, characterized in that, In step 3.1), the process of generating the topology graph is as follows: By aggregating the union of points and edges of all time-series graphs in the scene, a representative topological graph containing all graph structures within the scene is obtained. Feature information extraction: The encounter relationships between ships in the scene are extracted by extracting the adjacency matrix that represents the topological graph. For each node representing the topology graph Each has N features, denoted as MMSI and ship type are used as node feature inputs.

4. The method for identifying similar multi-ship encounter scenes based on topological graph sequences according to claim 1, characterized in that, In step 3.2), the similarity graph unit is identified as follows: 3.2.1) Similarity graph unit identification; 3.2.1.1) Extract graph elements; A graph cell is a partial representation of the internal structure of a time series diagram; a graph cell... From the source node and multiple adjacent nodes Composition, using express; Node attributes Indicates the type of vessel; For timing diagrams , time sequence diagram Each node contained herein is used sequentially as a source node to extract graph units; 3.2.1.2) Calculate the similarity of graph elements; Node attributes and inter-node connections are selected as elements of graph units to calculate graph unit similarity. 3.2.1.3) Similarity graph unit identification; By query graph cells Similarity is calculated and filtered among all graph units in the database to obtain a queue of graph units with the minimum distance, and then an adaptive evaluation score is applied. Remove queue members whose distance is less than The graph cells are used to filter graph cells in the database that may be similar to the query graph cell.

5. The method for identifying similar multi-ship encounter scenes based on topological graph sequences according to claim 4, characterized in that, In step 3.2.1.2), for two graph units... and The similarity of the graph units is calculated as follows: in, , They represent and The number of adjacent nodes; It is the number of adjacent nodes shared by the two graph units; This is the number of edges shared by the two graph units, calculated as follows: in, It is the source node of the two graph units. , The similarity is calculated using the following formula: 。 6. The method for identifying similar multi-ship encounter scenes based on topological graph sequences according to claim 1, characterized in that, In step 3.2), the similar time series diagrams are identified as follows: 3.2.2) Identification of similar time series diagrams; 3.2.2.1) Time series diagram similarity; Each time series graph is an unordered set of graph units, and the similarity of time series graphs is calculated as the optimal allocation of two sets of graph units; 3.2.2.2) Identification of similar time series diagrams; For timing diagrams Each graph unit All of them are identified by graph unit identification to find their similar graph unit queues, denoted as Therefore Obtain a queue of M similar graph units; based on the elements in the queues, find the time series graphs containing the similar graph units from the database, thereby filtering out those that match the query graph. L time series diagrams that have similar relationships are used to form a graph association list. ; Will Similarity is calculated and filtered for each time series graph in the associated list, and then based on the evaluation score. Obtain a queue of similar graphs that meet the criteria.

7. The method for identifying similar multi-ship encounter scenes based on topological graph sequences according to claim 1, characterized in that, In step 3.2), the similarity graph unit is identified as follows: 3.2.3) Similar graph sequence identification; 3.2.3.1) Graph sequence similarity; A graph sequence containing n graphs Since graph sequences are considered as time series composed of multiple time slices, measuring the similarity of graph sequences is viewed as a problem of calculating time series similarity. Therefore, dynamic time warping is introduced to define the similarity between graph sequences. For two graph sequences... , The similarity of their graph sequences is calculated as follows: 3.2.3.2) Similar graph sequence identification; For graph sequences First, a sequence graph identification algorithm is used to find n similar sequence graph queues. Then, a graph sequence association list is constructed based on the sequence graphs within each queue. Finally, [the algorithm is then used to...] Iterate through the associated list and based on the evaluation score Obtain a queue of similar graph sequences.

8. An electronic device, characterized in that, include: One or more processors; as well as Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 7.

Images