A ship identification method and system based on big data

Abstract

The present invention relates to a ship identification method and system based on big data, the method comprising: obtaining the AIS data of each ship in the waterway at the current moment in real time, identifying the identity information of each ship according to the AIS data of the ship at the current moment, obtaining a first identity information set, and preliminarily determining whether there is an abnormality; when the preliminarily determined abnormality, synchronously obtaining the ship image of each ship in the waterway, obtaining the ship information and the second identity information set based on the ship image, and determining whether the ship identity in the first identity information set is accurate and complete according to the ship information; when the ship identity is inaccurate and complete, correcting and modifying the first identity information set based on the second identity information set to obtain a corrected first identity information set. The present invention effectively ensures the accuracy of AIS data, can timely and effectively identify whether the AIS data is stable and continuous, and ensures the integrity of ship identity identification in the waterway.

Description

Technical Field

[0001] The present invention relates to the technical field of ship identification, and in particular to a ship identification method and system based on big data. Background Art

[0002] At present, in the field of ship identification, the AIS system has been widely used. The AIS system is a digital navigation aid system and equipment that integrates network technology, modern communication technology, computer technology, and electronic information display technology. It uses the global satellite positioning system (GPS) and communication technology to automatically and continuously send static information (such as ship name, call sign, MMSI code, etc.), dynamic information (such as location, heading, speed, etc.) and navigation-related information (such as dangerous goods information, destination port, etc.) of the ship. This information is transmitted through very high frequency (VHF) radio waves, so that ships and shore stations in nearby waters can timely grasp the dynamic and static information of all ships on the nearby water surface. The AIS system plays an important role in improving ship navigation safety and reducing maritime collision accidents. Through the AIS system, fishing boats can send their own location, heading, speed and other information in real time, and share information with other ships and shore, thereby effectively avoiding the risk of collision on the water. However, in actual applications, due to factors such as signal interference and equipment failure, there is a phenomenon that AIS data cannot be stably and continuously received and sent, resulting in the failure to identify ships in a timely and effective manner, resulting in the occurrence of water safety accidents. Summary of the invention

[0003] The present invention provides a ship identification method and system based on big data to solve the technical problems mentioned in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A ship identification method based on big data, the method comprising the following steps:

[0006] Acquire the AIS data of each ship in the waterway at the current moment in real time, identify the identity information of each ship according to the AIS data of the ship at the current moment, obtain the first identity information set, and preliminarily determine whether there is an abnormality;

[0007] When an abnormality is initially determined, the ship images of each ship in the waterway are synchronously acquired, the ship information and the second identity information set are acquired based on the ship images, and whether the ship identity in the first identity information set is accurate and complete is determined based on the ship information;

[0008] When the ship identity is inaccurate and incomplete, the first identity information set is corrected and modified based on the second identity information set to obtain a corrected first identity information set.

[0009] As a further technical solution of the present invention, the steps of acquiring the AIS data of each ship in the waterway at the current moment in real time, identifying the identity information of each ship according to the AIS data of the ship at the current moment, obtaining the first identity information set, and preliminarily determining whether there is an abnormality include:

[0010] Receive AIS data sent by ships through the AIS base station, obtain the AIS data of each ship in the waterway at the current moment in real time, determine the identity information of each ship according to the ship name, ship type and captain in the AIS data of the ship at the current moment, and obtain a first identity information set;

[0011] Obtain AIS data of each ship in the waterway in the verification interval in real time;

[0012] The AIS data of each ship at the current moment is compared with the AIS data within the verification interval to determine whether the difference meets the preset threshold. If it does not meet the threshold, it is initially determined to be abnormal; if it meets the threshold, it is initially determined to be normal.

[0013] As a further technical solution of the present invention, when an abnormality is initially determined, the steps of synchronously acquiring ship images of each ship in the waterway, acquiring ship information and a second identity information set based on the ship images, and determining whether the ship identity in the first identity information set is accurate and complete according to the ship information include:

[0014] When an abnormality is initially determined, images of each ship in the channel are acquired simultaneously;

[0015] Analyzing the ship image based on the ship identity recognition model, identifying and extracting the ship information of each ship at the current moment, identifying the identity information of each ship according to the ship information, and obtaining a second identity information set;

[0016] Compare the ship information of each ship at the current moment with the AIS data of each ship at the current moment. If they are the same, the ship identity is determined to be accurate and complete, but the ship navigation is determined to be abnormal, and abnormal navigation prompt information is generated. At this time, the ship image is continuously acquired until the preliminary judgment result is normal;

[0017] If they are not the same, a ship identity complete verification instruction is generated, and based on the ship identity complete verification instruction, it is determined whether the ship identity in the first identity information set is accurate and complete. At this time, the ship image is continuously acquired until the preliminary determination result is normal.

[0018] As a further technical solution of the present invention, the step of determining whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction includes:

[0019] Copy the second identity information set to obtain a set to be checked;

[0020] Read data from the first identity information set in sequence, traverse the set to be checked according to the read data, and when a match is successful, delete the corresponding data in the set to be checked;

[0021] When the data in the set to be checked is empty, a traversal cutoff signal is generated and the ship identity in the first identity information set is determined to be accurate and complete; when each data in the first identity information set is read and the set to be checked is not empty, the ship identity in the first identity information set is determined to be inaccurate and incomplete.

[0022] As a further technical solution of the present invention, when the ship identity is inaccurate and incomplete, the step of correcting and modifying the first identity information set based on the second identity information set to obtain the corrected first identity information set includes:

[0023] When the ship identity is inaccurate and incomplete, obtain the identity information of the remaining ships in the inspection set;

[0024] When there is no unmatched identity information in the first identity information set, inserting the identity information of the remaining ships in the to-be-inspected set into the first identity information set to obtain a revised first identity information set;

[0025] When there is unmatched identity information in the first identity information set, the similarity between the unmatched identity information in the first identity information set and the identity information of the remaining ships in the to-be-inspected set is calculated. When the similarity between the two reaches a preset similarity condition, the match is determined to be successful, and the identity information of the corresponding remaining ships in the to-be-inspected set is used to replace the corresponding unmatched identity information in the first identity information set. On this basis, the final remaining unmatched identity information in the to-be-inspected set is also inserted into the first identity information set to obtain a revised first identity information set.

[0026] Another object of the present invention is to provide a ship identification system based on big data, the system comprising:

[0027] The abnormal preliminary judgment module is used to obtain the AIS data of each ship in the channel at the current moment in real time, identify the identity information of each ship according to the AIS data of the ship at the current moment, obtain the first identity information set, and preliminarily judge whether there is an abnormality;

[0028] An identity integrity determination module is used to synchronously obtain ship images of each ship in the waterway when an abnormality is initially determined, obtain ship information and a second identity information set based on the ship images, and determine whether the ship identity in the first identity information set is accurate and complete based on the ship information;

[0029] The identity correction module is used to correct and modify the first identity information set based on the second identity information set when the ship identity is inaccurate and incomplete, so as to obtain a corrected first identity information set.

[0030] As a further technical solution of the present invention, the abnormal preliminary determination module includes:

[0031] A current data acquisition unit is used to acquire the AIS data of each ship in the waterway at the current moment in real time, determine the identity information of each ship according to the ship name, ship type and captain in the AIS data of the ship at the current moment, and obtain a first identity information set;

[0032] A verification data acquisition unit is used to obtain the AIS data of each ship in the waterway in the verification interval in real time;

[0033] The data comparison unit is used to compare the AIS data of each ship at the current moment with the AIS data within the verification interval to determine whether the difference meets the preset threshold. If it does not meet the threshold, it is initially determined to be abnormal; if it meets the threshold, it is initially determined to be normal.

[0034] As a further technical solution of the present invention, the identity integrity determination module includes:

[0035] A ship image acquisition unit, used to synchronously acquire ship images of each ship in the waterway when an abnormality is preliminarily determined;

[0036] A ship information extraction unit, configured to analyze the ship image based on a ship identity recognition model, identify and extract the ship information of each ship at the current moment, identify the identity information of each ship according to the ship information, and obtain a second identity information set;

[0037] The static information comparison unit is used to compare the ship information of each ship at the current moment with the AIS data of each ship at the current moment. If they are the same, the ship identity is determined to be accurate and complete, but the ship navigation is determined to be abnormal, and abnormal navigation prompt information is generated;

[0038] The verification instruction generating unit is used to generate a ship identity complete verification instruction if they are not the same, and determine whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction.

[0039] As a further technical solution of the present invention, the content of determining whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction includes:

[0040] Copy the second identity information set to obtain a set to be checked;

[0041] Read data from the first identity information set in sequence, traverse the set to be checked according to the read data, and when a match is successful, delete the corresponding data in the set to be checked;

[0042] When the data in the set to be checked is empty, a traversal cutoff signal is generated and the ship identity in the first identity information set is determined to be accurate and complete; when each data in the first identity information set is read and the set to be checked is not empty, the ship identity in the first identity information set is determined to be inaccurate and incomplete.

[0043] As a further technical solution of the present invention, the identity correction module includes:

[0044] When the ship identity is inaccurate and incomplete, obtain the identity information of the remaining ships in the inspection set;

[0045] When there is no unmatched identity information in the first identity information set, inserting the identity information of the remaining ships in the to-be-inspected set into the first identity information set to obtain a revised first identity information set;

[0046] When there is unmatched identity information in the first identity information set, the similarity between the unmatched identity information in the first identity information set and the identity information of the remaining ships in the to-be-inspected set is calculated. When the similarity between the two reaches a preset similarity condition, the match is determined to be successful, and the identity information of the corresponding remaining ships in the to-be-inspected set is used to replace the corresponding unmatched identity information in the first identity information set. On this basis, the final remaining unmatched identity information in the to-be-inspected set is also inserted into the first identity information set to obtain a revised first identity information set.

[0047] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides a ship identity recognition method and system based on big data, the present invention obtains a first identity information set through the AIS data at the current moment, compares the AIS data at the current moment with the AIS data in the verification interval, and judges in real time whether the AIS data is abnormal. When it is initially judged to be abnormal, it will trigger the acquisition of the ship image, obtain the ship information and the second identity information set based on the ship image, and judge whether the ship identity in the first identity information set is accurate and complete based on the ship information. When the ship identity is inaccurate and complete, the first identity information set is corrected and modified based on the second identity information set. The present invention effectively ensures the accuracy of the AIS data, can timely and effectively identify whether the AIS data is stable and continuous, and ensures the integrity of the ship identity recognition in the waterway. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The figure is a flowchart of a ship identification method based on big data.

[0049] Figure 2 The figure is a flowchart of the steps for determining whether the AIS data at the current moment is normal in a ship identification method based on big data.

[0050] Figure 3The figure is a flowchart of the steps for judging whether the identity information is accurate and complete in a ship identification method based on big data.

[0051] Figure 4 The present invention is a flowchart of the step of correcting the first identity information set in a ship identification method based on big data.

[0052] Figure 5 This is a structural block diagram of a ship identification system based on big data. DETAILED DESCRIPTION

[0053] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] like Figure 1 As shown, an embodiment of the present invention provides a ship identification method based on big data, and the method comprises the following steps:

[0055] Step S100, real-time acquisition of the AIS data of each ship in the waterway at the current moment, identification of the identity information of each ship based on the AIS data of the ship at the current moment, obtaining a first identity information set, and preliminarily determining whether there is an abnormality. For details, please refer to Figure 2 ;

[0056] Step S101, obtaining the AIS data of each ship in the waterway at the current moment in real time, identifying and determining the identity information of each ship according to the ship name, ship type and captain in the AIS data of the ship at the current moment, and obtaining a first identity information set, wherein the identity information includes the ship name, ship type, captain, etc.; the AIS data includes the ship name, ship type, captain, ship width, position, heading, speed, etc.; in this embodiment, the AIS data is received by an AIS base station;

[0057] Step S102, obtaining in real time the AIS data of each ship in the waterway in the verification interval, wherein the AIS data in the verification interval may be AIS data obtained within a period with the current time as the end point and a preset time step as the interval length, or may be preset historical AIS data;

[0058] Step S103, compare the AIS data of each ship at the current moment with the AIS data within the verification interval to determine whether the difference meets the preset threshold. If it does not meet the threshold, it is initially determined to be abnormal. If it meets the threshold, it is initially determined to be normal. The abnormality may be external interference, AIS equipment abnormality, or navigation abnormality.

[0059] Step S200: When an abnormality is initially determined, images of each ship in the waterway are synchronously acquired, ship information and a second identity information set are acquired based on the ship images, and the ship identity in the first identity information set is determined to be accurate and complete based on the ship information. For details, please refer to Figure 3 ;

[0060] Step S201, when an abnormality is initially determined, synchronously acquiring ship images of each ship in the channel;

[0061] Step S202, analyze the ship image based on the ship identity recognition model, identify and extract the ship information of each ship at the current moment, the ship information includes ship name, ship type, length, ship width, position, heading, speed, etc.; identify the identity information of each ship according to the ship information to obtain a second identity information set; wherein, the ship identity recognition model is a pre-trained model, and the ship identity recognition model is a technical model that extracts and recognizes ship identity information by analyzing ship images. The training process of the ship identity recognition model is as follows: Data collection: Collect a large amount of ship images and data from various sources (such as port surveillance cameras, AIS systems, satellite images, etc.). Ensure that the data set contains a variety of ship types, postures, lighting conditions and background environments. Data annotation: Annotate the ships in the image, including key information such as the ship's bounding box, ship name, and ship type. Manual annotation can be performed using professional annotation tools, or semi-automatic and automatic annotation technologies can be used to improve efficiency. Data preprocessing: The image is cropped, scaled, normalized, etc. to improve the efficiency and accuracy of model training. Data enhancement operations such as rotation, flipping, color transformation, etc. can be performed as needed to increase the diversity and robustness of the data. Model selection: Select a suitable deep learning framework: such as TensorFlow, PyTorch, etc. These frameworks provide a wealth of deep learning algorithms and tools. Select or design a suitable network structure: You can choose an existing target detection network, such as the YOLO series (YOLOv4, YOLOv5, YOLOv7, etc.), ResNet series, etc. Adjust and optimize the network structure according to specific needs and data characteristics. Model training: Divide the training set and validation set: Divide the dataset into a training set and a validation set for model training and performance evaluation. Set training parameters: including key parameters such as learning rate, batch size, and number of iterations. These parameters need to be adjusted and optimized according to specific tasks and datasets. Train the model: Input the training set into the model, perform forward propagation and back propagation, and continuously update the weights and biases of the model. During the training process, the validation set can be used for performance evaluation to monitor the training progress of the model and avoid overfitting. Performance evaluation and optimization: Use the validation set to evaluate the performance of the model, including indicators such as accuracy, until the preset standards are met.

[0062] Step S203, comparing the ship information of each ship at the current moment with the AIS data of each ship at the current moment, if they are the same, it is determined that the ship identity is accurate and complete, but the ship navigation is determined to be abnormal, and abnormal navigation prompt information is generated. At this time, the ship image is continuously acquired until the preliminary judgment result is normal;

[0063] Step S204: If they are not the same, a ship identity complete verification instruction is generated, and based on the ship identity complete verification instruction, it is determined whether the ship identity in the first identity information set is accurate and complete. At this time, the ship image is continuously acquired until the preliminary determination result is normal.

[0064] The step of determining whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction includes:

[0065] Copy the second identity information set to obtain a set to be checked;

[0066] Read data from the first identity information set in sequence, traverse the set to be checked according to the read data, and when a match is successful (that is, when the identity information of a certain ship in the set to be checked is the same as the identity information read from the first identity information set, it is determined that the match is successful), delete the corresponding data in the set to be checked;

[0067] When the data in the set to be checked is empty, a traversal cutoff signal is generated and the ship identity in the first identity information set is determined to be accurate and complete; when each data in the first identity information set is read and the set to be checked is not empty, the ship identity in the first identity information set is determined to be inaccurate and incomplete.

[0068] Step S300: When the ship identity is inaccurate and incomplete, the first identity information set is corrected and modified based on the second identity information set to obtain a corrected first identity information set. Figure 4 .

[0069] Step S301, when the ship identity is inaccurate and incomplete, obtain the identity information of the remaining ships in the set to be inspected;

[0070] Step S302, when there is no unmatched identity information in the first identity information set, insert the identity information of the remaining ships in the to-be-checked set into the first identity information set to obtain a revised first identity information set, and insert the ship information corresponding to the remaining ships in the to-be-checked set into the AIS data at the current moment, thereby ensuring the integrity of the AIS data;

[0071] Step S303, when there is unmatched identity information in the first identity information set, calculate the similarity between the unmatched identity information in the first identity information set and the identity information of the remaining ships in the to-be-checked set, and when the similarity between the two reaches a preset similarity condition, the preset similarity condition can be: the similarity between the two reaches a preset similarity threshold, and the match is determined to be successful, and the identity information corresponding to the remaining ships in the to-be-checked set is used to replace the corresponding unmatched identity information in the first identity information set. On this basis, the final remaining unmatched identity information in the to-be-checked set is inserted into the first identity information set to obtain a revised first identity information set. Wherein, the identity information includes ship name, ship type, captain, etc., and the specific calculation method can be: similarity = A*ship name similarity + B*ship type similarity + C*captain similarity, etc., A, B and C are the weights of ship name similarity, ship type similarity and captain similarity respectively, A+B+C=1, and the ship name similarity can be determined by judging whether the two ship names are the same, the ship type similarity can be determined by judging whether the two ship type similarities are the same, and the captain similarity can be determined by judging the ratio of the two captains.

[0072] In this embodiment, when the AIS data at the current moment is abnormal compared with the AIS data in the verification interval, the ship image recognition function will be awakened, and the accuracy of the AIS data at the current moment will be further verified by acquiring and identifying the ship image. When the ship information recognized by the ship image is the same as the AIS data at the current moment, the AIS data at the current moment is determined to be accurate, that is, the ship identity in the second identity information set is determined to be accurate and complete, but the ship navigation is determined to be abnormal, and abnormal navigation prompt information is generated. At this time, the ship image is continuously acquired until the preliminary judgment result is normal; when the ship information recognized by the ship image is different from the AIS data at the current moment, a ship identity complete verification instruction is generated, and whether the ship identity in the first identity information set is accurate and complete is determined based on the ship identity complete verification instruction; when the ship identity is inaccurate and complete, the first identity information set is corrected and modified based on the second identity information set to obtain a corrected first identity information set; at the same time, the AIS data at the current moment is supplemented based on the ship information, thereby ensuring the integrity of the data and improving the safety of ship navigation.

[0073] See also Figure 5 Another object of the present invention is to provide a ship identification system based on big data, the system comprising:

[0074] The abnormal preliminary determination module 100 is used to obtain the AIS data of each ship in the waterway at the current moment in real time, identify the identity information of each ship according to the AIS data of the ship at the current moment, obtain the first identity information set, and preliminarily determine whether there is an abnormality;

[0075] The identity integrity determination module 200 is used to synchronously obtain ship images of each ship in the waterway when an abnormality is initially determined, obtain ship information and a second identity information set based on the ship images, and determine whether the ship identity in the first identity information set is accurate and complete based on the ship information;

[0076] The identity correction module 300 is used to correct and modify the first identity information set based on the second identity information set to obtain a corrected first identity information set when the ship identity is inaccurate and incomplete.

[0077] As another preferred embodiment of the present invention, the abnormal preliminary determination module 100 includes:

[0078] A current data acquisition unit is used to receive AIS data sent by ships through an AIS base station, acquire the AIS data of each ship in the waterway at the current moment in real time, determine the identity information of each ship according to the ship name, ship type and captain identification in the AIS data of the ship at the current moment, and obtain a first identity information set;

[0079] A verification data acquisition unit is used to obtain the AIS data of each ship in the waterway in the verification interval in real time;

[0080] The data comparison unit is used to compare the AIS data of each ship at the current moment with the AIS data within the verification interval to determine whether the difference meets the preset threshold. If it does not meet the threshold, it is initially determined to be abnormal; if it meets the threshold, it is initially determined to be normal.

[0081] As another preferred embodiment of the present invention, the identity integrity determination module 200 includes:

[0082] A ship image acquisition unit, used to synchronously acquire ship images of each ship in the waterway when an abnormality is preliminarily determined;

[0083] A ship information extraction unit is used to analyze the ship image based on a ship identity recognition model, identify and extract the ship information of each ship at the current moment, the ship information includes the name of the ship, the type of ship, the length, the width of the ship, the heading, the speed, etc.; identify the identity information of each ship according to the ship information, and obtain a second identity information set;

[0084] The static information comparison unit is used to compare the ship information of each ship at the current moment with the AIS data of each ship at the current moment. If they are the same, the ship identity is determined to be accurate and complete, but the ship navigation is determined to be abnormal, and abnormal navigation prompt information is generated;

[0085] The verification instruction generating unit is used to generate a ship identity complete verification instruction if they are not the same, and determine whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction.

[0086] As another preferred embodiment of the present invention, the content of determining whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction includes:

[0087] Copy the second identity information set to obtain a set to be checked;

[0088] Read data from the first identity information set in sequence, traverse the set to be checked according to the read data, and when a match is successful (that is, when the identity information of a certain ship in the set to be checked is the same as the identity information read from the first identity information set, it is determined that the match is successful), delete the corresponding data in the set to be checked;

[0089] When the data in the set to be checked is empty, a traversal cutoff signal is generated and the ship identity in the first identity information set is determined to be accurate and complete; when each data in the first identity information set is read and the set to be checked is not empty, the ship identity in the first identity information set is determined to be inaccurate and incomplete.

[0090] As another preferred embodiment of the present invention, the identity correction module 300 includes:

[0091] When the ship identity is inaccurate and incomplete, obtain the identity information of the remaining ships in the inspection set;

[0092] When there is no unmatched identity information in the first identity information set, inserting the identity information of the remaining ships in the to-be-inspected set into the first identity information set to obtain a revised first identity information set;

[0093] When there is unmatched identity information in the first identity information set, the similarity between the unmatched identity information in the first identity information set and the identity information of the remaining ships in the to-be-inspected set is calculated. When the similarity between the two reaches a preset similarity condition, the match is determined to be successful, and the identity information of the corresponding remaining ships in the to-be-inspected set is used to replace the corresponding unmatched identity information in the first identity information set. On this basis, the final remaining unmatched identity information in the to-be-inspected set is also inserted into the first identity information set to obtain a revised first identity information set.

[0094] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0095] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A ship identification method based on big data, characterized in that: The method comprises the following steps: Acquire the AIS data of each ship in the waterway at the current moment in real time, identify the identity information of each ship according to the AIS data of the ship at the current moment, obtain the first identity information set, and preliminarily determine whether there is an abnormality; When an abnormality is initially determined, the ship images of each ship in the waterway are synchronously acquired, the ship information and the second identity information set are acquired based on the ship images, and whether the ship identity in the first identity information set is accurate and complete is determined based on the ship information; When the ship identity is inaccurate and incomplete, the first identity information set is corrected and modified based on the second identity information set to obtain a corrected first identity information set; The steps of synchronously acquiring ship images of each ship in the waterway when an abnormality is preliminarily determined, acquiring ship information and a second identity information set based on the ship images, and determining whether the ship identity in the first identity information set is accurate and complete based on the ship information include: When an abnormality is initially determined, images of each ship in the channel are acquired simultaneously; Analyzing the ship image based on the ship identity recognition model, identifying and extracting the ship information of each ship at the current moment, identifying the identity information of each ship according to the ship information, and obtaining a second identity information set; Compare the ship information of each ship at the current moment with the AIS data of each ship at the current moment. If they are the same, the ship identity is determined to be accurate and complete, but the ship navigation is determined to be abnormal, and abnormal navigation prompt information is generated; If they are not the same, a ship identity complete verification instruction is generated, and whether the ship identity in the first identity information set is accurate and complete is determined based on the ship identity complete verification instruction; The step of determining whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction comprises: Copy the second identity information set to obtain a set to be checked; Read data from the first identity information set in sequence, traverse the set to be checked according to the read data, and when a match is successful, delete the corresponding data in the set to be checked; When the data in the set to be checked is empty, a traversal cutoff signal is generated and the ship identity in the first identity information set is determined to be accurate and complete; when each data in the first identity information set is read and the set to be checked is not empty, the ship identity in the first identity information set is determined to be inaccurate and incomplete; When the ship identity is inaccurate and incomplete, the step of correcting and modifying the first identity information set based on the second identity information set to obtain a corrected first identity information set includes: When the ship identity is inaccurate and incomplete, obtain the identity information of the remaining ships in the inspection set; When there is no unmatched identity information in the first identity information set, inserting the identity information of the remaining ships in the to-be-inspected set into the first identity information set to obtain a revised first identity information set; When there is unmatched identity information in the first identity information set, the similarity between the unmatched identity information in the first identity information set and the identity information of the remaining ships in the to-be-inspected set is calculated. When the similarity between the two reaches a preset similarity condition, the match is determined to be successful, and the identity information of the corresponding remaining ships in the to-be-inspected set is used to replace the corresponding unmatched identity information in the first identity information set. On this basis, the final remaining unmatched identity information in the to-be-inspected set is also inserted into the first identity information set to obtain a revised first identity information set.

2. A ship identification method based on big data according to claim 1, characterized in that: The steps of acquiring the AIS data of each ship in the waterway at the current moment in real time, identifying the identity information of each ship according to the AIS data of the ship at the current moment, obtaining the first identity information set, and preliminarily determining whether there is an abnormality include: Acquire the AIS data of each ship in the waterway at the current moment in real time, determine the identity information of each ship according to the ship name, ship type and captain in the AIS data of the ship at the current moment, and obtain a first identity information set; Obtain AIS data of each ship in the waterway in the verification interval in real time; The AIS data of each ship at the current moment is compared with the AIS data within the verification interval to determine whether the difference meets the preset threshold. If it does not meet the threshold, it is initially determined to be abnormal; if it meets the threshold, it is initially determined to be normal.

3. A ship identification system based on big data, characterized in that: The system comprises: The abnormal preliminary judgment module is used to obtain the AIS data of each ship in the waterway at the current moment in real time, identify the identity information of each ship according to the AIS data of the ship at the current moment, and obtain the first identity information set; An identity integrity determination module is used to synchronously obtain ship images of each ship in the waterway when an abnormality is initially determined, obtain ship information and a second identity information set based on the ship images, and determine whether the ship identity in the first identity information set is accurate and complete based on the ship information; An identity correction module, used for correcting and modifying the first identity information set based on the second identity information set to obtain a corrected first identity information set when the ship identity is inaccurate and incomplete; The identity integrity determination module comprises: A ship image acquisition unit, used to synchronously acquire ship images of each ship in the waterway when an abnormality is preliminarily determined; A ship information extraction unit, configured to analyze the ship image based on a ship identity recognition model, identify and extract the ship information of each ship at the current moment, identify the identity information of each ship according to the ship information, and obtain a second identity information set; The static information comparison unit is used to compare the ship information of each ship at the current moment with the AIS data of each ship at the current moment. If they are the same, the ship identity is determined to be accurate and complete, but the ship navigation is determined to be abnormal, and abnormal navigation prompt information is generated; a verification instruction generating unit, configured to generate a ship identity complete verification instruction if they are not the same, and determine whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction; The content of determining whether the ship identity in the first identity information set is accurate and complete based on the ship identity complete verification instruction includes: Copy the second identity information set to obtain a set to be checked; Read data from the first identity information set in sequence, traverse the set to be checked according to the read data, and when a match is successful, delete the corresponding data in the set to be checked; When the data in the set to be checked is empty, a traversal cutoff signal is generated and the ship identity in the first identity information set is determined to be accurate and complete; when each data in the first identity information set is read and the set to be checked is not empty, the ship identity in the first identity information set is determined to be inaccurate and incomplete; The identity redress module includes: When the ship identity is inaccurate and incomplete, obtain the identity information of the remaining ships in the inspection set; When there is no unmatched identity information in the first identity information set, inserting the identity information of the remaining ships in the to-be-inspected set into the first identity information set to obtain a revised first identity information set; When there is unmatched identity information in the first identity information set, the similarity between the unmatched identity information in the first identity information set and the identity information of the remaining ships in the to-be-inspected set is calculated. When the similarity between the two reaches a preset similarity condition, the match is determined to be successful, and the identity information of the corresponding remaining ships in the to-be-inspected set is used to replace the corresponding unmatched identity information in the first identity information set. On this basis, the final remaining unmatched identity information in the to-be-inspected set is also inserted into the first identity information set to obtain a revised first identity information set.

4. A ship identification system based on big data according to claim 3, characterized in that: The abnormal preliminary determination module comprises: A current data acquisition unit is used to acquire the AIS data of each ship in the waterway at the current moment in real time, determine the identity information of each ship according to the ship name, ship type and captain in the AIS data of the ship at the current moment, and obtain a first identity information set; A verification data acquisition unit is used to obtain the AIS data of each ship in the waterway in the verification interval in real time; The data comparison unit is used to compare the AIS data of each ship at the current moment with the AIS data within the verification interval to determine whether the difference meets the preset threshold. If it does not meet the threshold, it is initially determined to be abnormal; if it meets the threshold, it is initially determined to be normal.

Images