A method and system for analyzing abnormal behaviors of ships

Abstract

The present invention relates to the technical field of ship behavior analysis, and discloses a method and system for analyzing abnormal ship behavior. According to the ship behavior prediction and analysis model, the behavior information of the target ship at the next moment is predicted; the prediction result is compared with the ship behavior threshold to obtain the initial analysis result of the ship abnormal behavior; then the behavior stability of the target ship and the prediction accuracy of the ship behavior prediction and analysis model are obtained; by combining the behavior stability of the target ship and the accuracy of the ship behavior prediction and analysis model, the initial analysis result is adjusted to obtain the final analysis result of the ship abnormal behavior. It overcomes the problem of relying only on the prediction result for analysis during abnormal behavior analysis, and takes multiple aspects into consideration to improve the accuracy of the abnormal behavior determination result.

Description

Technical Field

[0001] The present invention relates to the technical field of ship behavior analysis, and particularly to a method and system for analyzing abnormal ship behavior. Background Art

[0002] Abnormal ship behavior generally refers to behavior that deviates from the normal behavior pattern of a ship. Such deviation may stem from various factors, such as environmental uncertainty, uncertainty in crew operation, and problems in information acquisition or identification. Conducting abnormal ship behavior analysis can not only capture and identify non-standard or potentially dangerous behaviors that occur during a ship's navigation on water in real time, thereby effectively preventing water traffic accidents and ensuring the safety of personnel, cargo, and the water environment; but also optimize the use of waterways, improve shipping efficiency, reduce unnecessary delays and costs by analyzing the reasons behind abnormal behaviors. In addition, this analysis process helps to ensure that all ships comply with relevant laws and regulations and maintain the legal order of water traffic. Therefore, conducting abnormal ship behavior analysis is an important means to improve the level of water traffic management, ensure safety and efficiency, and is of great significance for promoting the sustainable development of the shipping industry.

[0003] Currently, when analyzing abnormal ship behavior, it is usually based on the prediction results of ship behavior and compares them with pre-set thresholds. When the predicted ship behavior parameters exceed these thresholds, the system will trigger an alarm to indicate that there may be abnormal behavior. However, the accuracy of the prediction results directly determines the effectiveness of abnormal behavior analysis. If there are biases or errors in the prediction results themselves, then the threshold comparison based on these prediction results will be meaningless, greatly reducing the accuracy of the abnormal ship behavior analysis results.

[0004] Therefore, a more accurate and comprehensive method for analyzing abnormal ship behavior is urgently needed to improve the accuracy and efficiency of abnormal ship behavior recognition and provide stronger protection for water traffic safety. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a method for analyzing abnormal ship behavior, and the method includes the following steps:

[0006] S1: Obtain the ship data and marine hydro-meteorological environment data of the target ship at the current moment, input them into the trained ship behavior prediction and analysis model, and predict the behavior information of the target ship at the next moment;

[0007] S2: Compare the prediction result in S1 with the ship behavior threshold to obtain the initial analysis result of the abnormal ship behavior;

[0008] S3: Calculate the behavior stability of the target ship by calculating the historical behavior information of the target ship;

[0009] S4: Statistically analyze the prediction accuracy rate of the ship behavior prediction analysis model at the current moment;

[0010] S5: Combine the behavior stability of the target ship and the prediction accuracy rate of the ship behavior prediction analysis model to determine the initial analysis result, so as to determine the final analysis result of the abnormal ship behavior.

[0011] Furthermore, the ship behavior prediction analysis model includes GRU units, Spatial-ReductionAttention units, and fully connected layers.

[0012] Furthermore, the behavior information includes course, speed, and longitude and latitude.

[0013] Furthermore, in S3, by calculating the historical behavior information of the target ship, the behavior stability of the target ship is obtained, specifically:

[0014] S31: Collect the historical behavior information of the target ship within a certain time range, and preprocess the collected historical behavior information;

[0015] S32: Calculate respectively according to the course, speed, and longitude and latitude in the preprocessed historical behavior information to obtain the course stability, speed stability, and longitude and latitude stability;

[0016] S33: Based on the weighted method, obtain the behavior stability of the target ship according to the course stability, speed stability, and longitude and latitude stability.

[0017] Furthermore, in S5, combine the behavior stability of the target ship and the prediction accuracy rate of the ship behavior prediction analysis model to determine the initial analysis result, so as to determine the final analysis result of the abnormal ship behavior, specifically:

[0018] Construct a feature vector according to the behavior stability of the target ship and the prediction accuracy rate of the ship behavior prediction analysis model;

[0019] According to the feature vector, adjust the model through the analysis result to obtain the confidence level of the initial analysis result;

[0020] Based on the confidence level, combine the initial analysis result to determine the final analysis result of the abnormal ship behavior.

[0021] Furthermore, according to the feature vector, adjusting the model through the analysis result to obtain the confidence level of the initial analysis result includes:

[0022] Perform normalization processing on the feature vector to obtain the normalized feature vector;

[0023] Based on the normalized eigenvector, adjust the model through the trained analysis result to obtain the decision value corresponding to the initial analysis result;

[0024] Perform a conversion process on the decision value as the confidence level of the initial analysis result.

[0025] Further, use an activation function to perform a conversion process on the decision value.

[0026] On the other hand, this application also provides a ship abnormal behavior analysis system that executes the ship abnormal behavior analysis method described in any one of the above. The system includes: an initial analysis result acquisition module, a ship behavior stability acquisition module, a model accuracy acquisition module, and an output module;

[0027] The initial analysis result acquisition module is used to obtain the ship data and marine hydrometeorological environment data of the target ship at the current moment, input them into the trained ship behavior prediction analysis model, and predict the behavior information of the target ship at the next moment; compare the prediction result with the ship behavior threshold to obtain the initial analysis result of the ship abnormal behavior;

[0028] The ship behavior stability acquisition module calculates the behavior stability of the target ship by calculating the historical behavior information of the target ship;

[0029] The model accuracy acquisition module is used to statistically analyze the prediction accuracy of the ship behavior prediction analysis model at the current moment;

[0030] The output module is used to determine the initial analysis result by combining the behavior stability of the target ship and the prediction accuracy of the ship behavior prediction analysis model, so as to determine the final analysis result of the ship abnormal behavior.

[0031] The embodiments of the present invention have the following technical effects:

[0032] In the ship abnormal behavior analysis method provided by this application, the behavior information of the target ship at the next moment is predicted according to the ship behavior prediction analysis model; the prediction result is compared with the ship behavior threshold to obtain the initial analysis result of the ship abnormal behavior; then, by combining the behavior stability of the target ship and the accuracy of the ship behavior prediction analysis model, the initial analysis result is judged to determine the final analysis result of the ship abnormal behavior. It overcomes the problem of relying solely on the prediction result for analysis during abnormal behavior analysis and avoids the influence of the deviation of the prediction result itself on the analysis result.

[0033] When judging the initial analysis result, not only the prediction accuracy of the ship behavior prediction analysis model for obtaining the prediction result is considered, but also the behavior stability of the target ship is taken into account. By combining the prediction result and the behavior characteristics of the target ship itself, the accuracy of ship abnormal behavior analysis is further improved. Brief Description of the Drawings

[0034] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0035] Figure 1 is a flowchart of a method for analyzing ship abnormal behavior provided by an embodiment of the present invention;

[0036] Figure 2 is a structural diagram of a system for analyzing ship abnormal behavior provided by an embodiment of the present invention. Detailed Embodiments

[0037] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0038] A method for analyzing ship abnormal behavior, as Figure 1 shown, the method includes the following steps:

[0039] S1: Obtain the ship data and marine hydrometeorological environment data of the target ship at the current moment, input them into the trained ship behavior prediction analysis model, and predict the behavior information of the target ship at the next moment;

[0040] In some embodiments, the behavior information includes course, speed, and longitude and latitude.

[0041] In some embodiments, the ship behavior prediction analysis model includes GRU units, Spatial-ReductionAttention units, and fully connected layers.

[0042] For single-ship prediction in complex environments, a bidirectional gated recurrent neural network with a spatial-reduction attention mechanism (A Spatial-Reduction Attention Based on Bidirectional Gate Recurrent Unit, SRA-BiGRU) is proposed. Compared with a single model structure, this model utilizes the ability of GRU units to learn temporal features in data. By introducing Spatial-Reduction Attention units, it captures the key factors affecting ship behavior, reduces the influence of interference information while retaining important features, enables the network to process longer temporal information, makes the model robust and accurate, and has characteristics such as high computational efficiency and strong engineering applicability.

[0043] Specifically, ship data and marine hydro-meteorological environment data are used as input parameters for the ship behavior prediction analysis model. Through GRU units, feature vectors with temporal features are obtained. The Spatial-Reduction Attention mechanism unit obtains the weight coefficients corresponding to each feature vector with temporal features through the attention mechanism. Thus, it realizes the rapid identification of key variables related to ship trajectory prediction such as marine information, and accurately extracts the key information affecting the current ship's navigation. At the same time, it can capture time dependence, identify hidden key factors from the historical data of ship trajectories, extract the key time information affecting the current ship trajectory, and dynamically extract the corresponding key influencing factors by adjusting the weight coefficients, accurately predicting the behavior information of the target ship at the next moment.

[0044] S2: Compare the prediction result in S1 with the ship behavior threshold to obtain the initial analysis result of the ship's abnormal behavior;

[0045] According to the historical behavior data of the ship, set the course and speed of the ship at each position (represented by longitude and latitude) under normal conditions, which is the ship behavior threshold. Through the ship behavior prediction analysis model, predict the course, speed, longitude, and latitude of the target ship at the next moment. Compare the predicted course, speed, longitude, and latitude with the ship behavior threshold respectively: if the predicted longitude and latitude are not within the threshold, it is determined that the ship behavior is abnormal; if there is a deviation between the predicted course and the threshold, it is determined that the ship behavior is abnormal; if the predicted speed is not within the threshold, whether the speed is too high or too low, it will be determined that the ship behavior is abnormal.

[0046] S3: Calculate the behavior stability of the target ship by calculating the historical behavior information of the target ship;

[0047] S31: Collect the historical behavior information of the target ship within a certain time range and preprocess the collected historical behavior information;

[0048] Collect historical behavior information, that is, collect the historical behavior information of the target ship collected in real time over a period of time in the past, including data such as heading, speed, longitude and latitude. These data can be obtained from channels such as the ship's Automatic Identification System (AIS), voyage log, monitoring system, etc. Ensure the integrity, accuracy and consistency of the data.

[0049] The collected data also needs to be preprocessed, including data cleaning: removing duplicate, incorrect or abnormal data points, such as sudden changes in heading, abnormal speed, etc.; interpolation: for missing data points, use appropriate interpolation methods (such as linear interpolation, nearest neighbor interpolation, etc.) to fill in.

[0050] S32: Calculate according to the heading, speed, longitude and latitude in the preprocessed historical behavior information respectively to obtain heading stability, speed stability and longitude and latitude stability;

[0051] Heading stability: Use the standard deviation to measure the stability of the heading. The smaller the standard deviation, the more stable the heading.

[0052] ;

[0053] Among them, A represents the heading stability, represents the data point of the i-th heading, represents the average value of the heading data, and n represents the number of data points.

[0054] Speed stability: Also use the standard deviation to measure the speed stability B.

[0055] Longitude and latitude stability C: Use the position change rate to measure the stability of longitude and latitude. The smaller the change rate, the more stable the position, that is, driving smoothly along the established route. The position change rate can be represented by the ratio of the direct distance between two consecutive data points to the time interval between the two data points, where the direct distance between two consecutive data points can be calculated from the longitude and latitude.

[0056] S33: Based on the weighted method, obtain the behavior stability of the target ship according to the heading stability, speed stability and longitude and latitude stability. The respective weight coefficients of the heading stability, speed stability and longitude and latitude stability can be set according to the respective fluctuations in the historical data of the target ship, or can be predicted through a neural network model, or obtained by other methods, which are not limited here.

[0057] S4: Statistically analyze the prediction accuracy rate of the ship behavior prediction analysis model at the current moment;

[0058] The prediction accuracy rate can be represented by the ratio of the number of accurate predictions made by the ship behavior prediction analysis model to the total number of predictions. Compare the behavior information of the ship predicted by the ship behavior prediction analysis model with the behavior information of the ship obtained in real time. If the deviation is within a predetermined range, it is determined that the prediction is accurate for this time. Then, count the number of accurate predictions and the total number of predictions made by the ship behavior prediction analysis model.

[0059] S5: Combine the behavior stability of the target ship and the prediction accuracy rate of the ship behavior prediction analysis model to determine the initial analysis result, so as to determine the final analysis result of the abnormal ship behavior. Specifically:

[0060] S51: Construct a feature vector based on the behavior stability of the target ship and the prediction accuracy rate of the ship behavior prediction analysis model;

[0061] Exemplarily, construct a feature vector in the form of a two-dimensional array, where each feature vector contains two elements: the behavior stability value (y 1 ) and the prediction accuracy rate value (y 2 ).

[0062] Prepare label data, that is, the true label (1 indicates abnormal, 0 indicates normal) of whether the ship behavior corresponding to each feature vector is abnormal.

[0063] S52: Adjust the model according to the feature vector to obtain the confidence level of the initial analysis result. Specifically, it includes:

[0064] S521: Normalize the feature vector to obtain a normalized feature vector to ensure that different features are comparable numerically.

[0065] S522: According to the normalized feature vector, adjust the model through the trained analysis result to obtain the decision value corresponding to the initial analysis result;

[0066] Exemplarily, the support vector machine (SVM) can be selected as the algorithm for the analysis result adjustment model. Based on its powerful classification and regression functions, in the analysis of abnormal ship behavior, SVM can learn a decision boundary based on the two features of behavior stability and prediction accuracy rate, so as to distinguish normal behavior and abnormal behavior and give the confidence level of the analysis result.

[0067] SVM does not directly output the confidence level, but can indirectly evaluate the confidence level by observing the decision function (that is, the distance from the model output to the decision boundary). Specifically, the output value of the decision function (also called the decision value or score) can be used as a measure of the confidence level. The larger the decision value (for abnormal behavior) or the smaller the decision value (for normal behavior), the higher the confidence level of the model for this prediction result.

[0068] The prepared dataset is divided into a training set and a test set for training and validating the trained SVM model. The trained analysis results are used to adjust the model.

[0069] S523: Perform a conversion process on the decision value as the confidence level of the initial analysis result.

[0070] In some embodiments, an activation function is used to perform a conversion process on the decision value.

[0071] To convert the decision value into a confidence level, a sigmoid activation function or other mapping functions can be used for conversion. However, it should be noted that this conversion is usually based on experience or specific application scenarios and there is no fixed formula. In practical applications, the conversion rules can be customized according to needs.

[0072] The confidence level can be presented in the form of probability, that is, the probability that the ship behavior is abnormal (or normal). However, it should be noted that this interpretation is based on the confidence level output by the SVM model and specific conversion rules, and is not an absolute probability value.

[0073] Combination of classification label and confidence level: When outputting the classification label (abnormal or normal), attach the corresponding confidence level value to more comprehensively understand the reliability of the analysis result for adjusting the model analysis result.

[0074] S53: Based on the confidence level, combined with the initial analysis result, determine the final analysis result of the abnormal ship behavior.

[0075] According to the converted confidence level value, the reliability of the initial analysis result can be judged. For example, a confidence level threshold can be set. When the confidence level exceeds this threshold, the analysis result is considered reliable; otherwise, it is considered that there may be errors or further verification is required.

[0076] In the ship abnormal behavior analysis method provided by this application, according to the ship behavior prediction analysis model, the behavior information of the target ship at the next moment is predicted; the prediction result is compared with the ship behavior threshold to obtain the initial analysis result of the ship abnormal behavior; then, by combining the behavior stability of the target ship and the accuracy rate of the ship behavior prediction analysis model, the initial analysis result is judged to determine the final analysis result of the ship abnormal behavior. It overcomes the problem of completely relying on the prediction result for analysis during abnormal behavior analysis and avoids the influence of the deviation of the prediction result itself on the analysis result.

[0077] Among them, when judging the initial analysis result, not only the prediction accuracy rate of the ship behavior prediction analysis model for obtaining the prediction result is considered, but also the behavior stability of the target ship is taken into account. By combining the prediction result and the behavior characteristics of the target ship itself, the accuracy of ship abnormal behavior analysis is further improved.

[0078] The present application also provides a ship abnormal behavior analysis system, which executes the above-mentioned ship abnormal behavior analysis method, such as Figure 2 As shown, the system includes: an initial analysis result acquisition module, a ship behavior stability acquisition module, a model accuracy acquisition module, and an output module;

[0079] The initial analysis result acquisition module is used to obtain the ship data and marine hydrometeorological environment data of the target ship at the current moment, input the trained ship behavior prediction and analysis model, and predict the behavior information of the target ship at the next moment; compare the prediction result with the ship behavior threshold to obtain the initial analysis result of the ship abnormal behavior;

[0080] The ship behavior stability acquisition module calculates the behavior stability of the target ship by analyzing the historical behavior information of the target ship;

[0081] The model accuracy acquisition module is used to statistically analyze the prediction accuracy of the ship behavior prediction and analysis model at the current moment;

[0082] The output module is used to combine the behavior stability of the target ship and the prediction accuracy of the ship behavior prediction and analysis model to determine the initial analysis result, so as to determine the final analysis result of the ship abnormal behavior.

[0083] The present invention also provides an electronic device, including one or more processors and a memory.

[0084] The processor can be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and can control other components in the electronic device to execute the desired functions.

[0085] The memory can include one or more computer program products, and the computer program products can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory can include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory can include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions can be stored on the computer-readable storage media, and the processor can run the program instructions to implement the ship abnormal behavior analysis method of any embodiment of the present application described above and / or other desired functions. Various contents such as initial external parameters and thresholds can also be stored in the computer-readable storage media.

[0086] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown). The input device may include, for example, a keyboard, a mouse, and so on. The output device may output various information to the outside, including warning prompt information, braking force, and so on. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, and so on.

[0087] Of course, for simplicity, components such as buses, input / output interfaces, and so on are omitted. In addition, according to specific application scenarios, the electronic device may further include any other appropriate components.

[0088] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, and when the computer program instructions are run by a processor, the processor implements the functions of a method for analyzing abnormal behaviors of a ship provided by any embodiment of the present application.

[0089] The computer program product may be written in any combination of one or more programming languages for programming code to execute the operations of the embodiments of the present application. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The programming code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0090] In addition, an embodiment of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are run by a processor, the processor implements a method for analyzing abnormal behaviors of a ship provided by any embodiment of the present application.

[0091] The computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing abnormal behavior of a ship, characterized in that: The method comprises the following steps: S1: Obtain the current ship data and ocean hydrological and meteorological environmental data of the target ship, input the trained ship behavior prediction analysis model, and predict the behavior information of the target ship at the next moment; S2: Compare the prediction results in S1 with the ship behavior threshold to obtain the initial analysis results of the abnormal ship behavior; S3: The behavior stability of the target ship is obtained by calculating the historical behavior information of the target ship; S4: Counting the prediction accuracy of the ship behavior prediction analysis model at the current moment; the prediction accuracy is represented by the ratio of the number of accurate predictions of the ship behavior prediction analysis model to the total number of predictions; S5: Combine the behavior stability of the target ship and the prediction accuracy of the ship behavior prediction analysis model to judge the initial analysis results, so as to determine the final analysis results of the abnormal behavior of the ship.

2. A method for analyzing abnormal ship behavior according to claim 1, characterized in that: The ship behavior prediction and analysis model includes a GRU unit, a Spatial-Reduction Attention unit and a fully connected layer.

3. A method for analyzing abnormal ship behavior according to claim 1, characterized in that: The behavior information includes heading, speed, and longitude and latitude.

4. A method for analyzing abnormal ship behavior according to claim 3, characterized in that: In S3, the historical behavior information of the target ship is calculated to obtain the behavior stability of the target ship, which is specifically: S31: collecting historical behavior information of the target ship within a certain time range, and preprocessing the collected historical behavior information; S32: Calculate the heading, speed, and longitude and latitude in the pre-processed historical behavior information to obtain heading stability, speed stability, and longitude and latitude stability; S33: Based on the weighted method, the behavior stability of the target ship is obtained according to the heading stability, speed stability and longitude and latitude stability.

5. A method for analyzing abnormal ship behavior according to claim 1, characterized in that: In S5, the initial analysis results are judged in combination with the behavior stability of the target ship and the prediction accuracy of the ship behavior prediction analysis model, so as to determine the final analysis results of the abnormal behavior of the ship, specifically: Constructing a feature vector according to the behavior stability of the target ship and the prediction accuracy of the ship behavior prediction analysis model; According to the characteristic vector, the model is adjusted by analyzing the result to obtain the confidence of the initial analysis result; According to the confidence level and in combination with the initial analysis result, a final analysis result of the abnormal behavior of the ship is determined.

6. A method for analyzing abnormal ship behavior according to claim 5, characterized in that: According to the characteristic vector, the model is adjusted by analyzing the results to obtain the confidence of the initial analysis results, including: Normalizing the feature vector to obtain a normalized feature vector; According to the normalized feature vector, the model is adjusted by the trained analysis result to obtain a decision value corresponding to the initial analysis result; The decision value is converted to serve as the confidence level of the initial analysis result.

7. A method for analyzing abnormal ship behavior according to claim 6, characterized in that: The decision value is converted using an activation function.

8. A ship abnormal behavior analysis system, executing a ship abnormal behavior analysis method according to any one of claims 1 to 7, characterized in that: The system comprises: an initial analysis result acquisition module, a ship behavior stability acquisition module, a model accuracy acquisition module and an output module; The initial analysis result acquisition module is used to obtain the ship data and ocean hydrological and meteorological environmental data of the target ship at the current moment, input the trained ship behavior prediction analysis model, and predict the behavior information of the target ship at the next moment; compare the prediction result with the ship behavior threshold to obtain the initial analysis result of the abnormal behavior of the ship; The ship behavior stability acquisition module obtains the behavior stability of the target ship by calculating the historical behavior information of the target ship; The model accuracy acquisition modulus is used to count the prediction accuracy of the ship behavior prediction analysis model at the current moment; the prediction accuracy is represented by the ratio of the number of accurate predictions of the ship behavior prediction analysis model to the total number of predictions; The output module is used to judge the initial analysis results by combining the behavior stability of the target ship and the prediction accuracy of the ship behavior prediction analysis model, so as to determine the final analysis results of the abnormal behavior of the ship.

Images