Ship monitoring method based on Beidou satellite and AIS data

Abstract

The invention relates to the technical field of ship monitoring, and particularly discloses a ship monitoring method based on a Beidou satellite and AI data, and the method comprises the steps: obtaining the AI data of a ship and surrounding ships through employing an AI receiving and transmitting module, carrying out the encryption of the obtained AI data through employing a data encryption algorithm based on deep learning, and carrying out the encryption of the obtained AI data, the method comprises the following steps: firstly, encrypting an AI data packet to identify and filter invalid or irrelevant ship information, and then sending the encrypted AI data packet to an AI data center for decoding analysis through a Beidou satellite communication array, thereby obtaining AI data such as position, speed, course and the like of a ship. Therefore, the ship monitoring capability of ocean and remote sea areas can be effectively improved, the problems of information overload and low data transmission efficiency are solved through data encryption processing, and meanwhile, the data transmission safety is enhanced.

Description

Technical Field

[0001] The present application relates to the field of ship monitoring technology, and more specifically, to a ship monitoring method based on Beidou satellite and AIS data. Background Art

[0002] With the continuous and rapid development of the global shipping industry, the demand for safe navigation and efficient management of ships is becoming increasingly urgent. The Automatic Identification System (AIS), as a shipborne equipment recommended by the International Maritime Organization, has the ability to automatically send and receive static, dynamic and voyage-related information of ships, which is of great significance for enhancing maritime traffic safety. However, the coverage of the AIS system is generally limited to coastal and offshore areas, and its monitoring capabilities for ships in the ocean and remote waters are obviously insufficient.

[0003] In recent years, with the continuous maturity and progress of the BeiDou satellite navigation system, its high-precision positioning capability and wide coverage have opened up new ways to solve the above problems. BeiDou Navigation Satellite System (BDS), as a global satellite navigation system independently developed by China, can provide all-weather, all-time, high-precision positioning, navigation and timing services. In particular, the short message communication function of the BeiDou system can achieve two-way communication in an environment without ground network support, which is particularly critical for ship monitoring in remote waters or under extreme conditions.

[0004] However, compared with the AIS shore-based system, the Beidou satellite navigation system still has certain limitations in data transmission rate and information capacity, which may lead to delays in information transmission and data loss. At the same time, the traditional AIS system lacks effective encryption measures during data transmission and is susceptible to eavesdropping, tampering and forgery attacks, which in turn leads to the risk of ship information being leaked or maliciously exploited.

[0005] Therefore, an optimized ship monitoring method based on Beidou satellite and AIS data is expected. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a ship monitoring method based on Beidou satellite and AIS data, which uses an AIS transceiver module to obtain the AIS data of the ship and surrounding ships, and uses a data encryption algorithm based on deep learning to encrypt the acquired AIS data to identify and filter out invalid or irrelevant ship information, and then send the encrypted AIS data packet to the AIS data center through the Beidou satellite communication array for decoding and analysis, so as to obtain the ship's position, speed, heading and other AIS data. In this way, the ship monitoring capability in the ocean and remote waters can be effectively improved, and through data encryption processing, the problems of information overload and low data transmission efficiency are solved, while the security of data transmission is enhanced.

[0007] Accordingly, according to one aspect of the present application, a ship monitoring method based on Beidou satellite and AIS data is provided, which includes:

[0008] The AIS data is obtained by using the AIS transceiver module, wherein the AIS data includes the information of the vessel and surrounding vessels;

[0009] The AIS data is processed by an encryption encoder to obtain an encrypted AIS data packet, wherein the encrypted AIS data packet conforms to a short message format of a Beidou satellite communication protocol;

[0010] Transmitting the encrypted AIS data packet to an AIS data center using a BeiDou satellite communication array;

[0011] In response to receiving a user's query for information about a ship, the monitoring terminal of the AIS data center selects a ship of interest and retrieves the encrypted AIS data packet of the ship;

[0012] The encrypted AIS data packet is decoded by a decryption decoder to obtain decoded data, wherein the decoded data is the AIS data of the ship.

[0013] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the AIS data is processed by an encryption encoder to obtain an encrypted AIS data packet, including: encrypting and embedding the ship information and surrounding ship information in the AIS data to obtain a set of the ship information embedding coding vector and the surrounding ship information embedding coding vector; taking the ship information embedding coding vector as a reference, performing feature dynamic propagation aggregation based on information correlation strength on the set of the ship information embedding coding vector and the surrounding ship information embedding coding vector to obtain the encrypted AIS data packet.

[0014] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the ship information and surrounding ship information in the AIS data are encrypted and embedded to obtain a set of the ship information embedded coding vector and the surrounding ship information embedded coding vector, including: using a Transformer model containing an embedding layer to encrypt and embed the ship information and surrounding ship information in the AIS data respectively to obtain the ship information embedded coding vector and the surrounding ship information embedded coding vector.

[0015] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, taking the embedded coding vector of the ship information as a benchmark, the set of the embedded coding vector of the ship information and the embedded coding vector of the surrounding ship information is subjected to characteristic dynamic propagation aggregation based on information correlation strength to obtain the encrypted AIS data packet, including: based on the information correlation strength of each surrounding ship information embedded coding vector in the set of the surrounding ship information embedded coding vector relative to the embedded coding vector of the ship information, the set of the surrounding ship information embedded coding vector is subjected to significance modulation to obtain a set of surrounding ship information embedded coding vectors after intensity modulation; and the set of the surrounding ship information embedded coding vectors after intensity modulation and the embedded coding vector of the ship information are subjected to global correlation aggregation coding to obtain a global significant propagation aggregation feature vector of ship information as the encrypted AIS data packet.

[0016] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, based on the information association strength of each surrounding ship information embedded coding vector in the set of surrounding ship information embedded coding vectors relative to the own ship information embedded coding vector, the set of surrounding ship information embedded coding vectors is saliency modulated to obtain a set of surrounding ship information embedded coding vectors after intensity modulation, including: using the own ship information embedded coding vector as a feature prompt gate, calculating the information association strength prompt value of each surrounding ship information embedded coding vector in the set of surrounding ship information embedded coding vectors relative to the own ship information embedded coding vector to obtain a set of surrounding ship information association strength prompt values; based on the set of surrounding ship information association strength prompt values, performing gated mask modulation on the set of surrounding ship information embedded coding vectors to obtain the set of surrounding ship information embedded coding vectors after intensity modulation.

[0017] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the information association strength prompt value of each surrounding ship information embedded coding vector in the set of surrounding ship information embedded coding vectors relative to the current ship information embedded coding vector is calculated to obtain a set of surrounding ship information association strength prompt values, including: calculating the positional dot division vector between the surrounding ship information embedded coding vector and the current ship information embedded coding vector, and calculating the base-two logarithmic value of the absolute value of each eigenvalue in the dot division vector to obtain a surrounding ship information association representation vector; calculating the dot product vector between the surrounding ship information association representation vector and the surrounding ship information embedded coding vector, and calculating the exponential function value with base e and the sum of the eigenvalues ​​of the dot product vector as the exponent to obtain the surrounding ship information association strength prompt value.

[0018] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, based on the set of surrounding ship information association strength prompt values, the set of surrounding ship information embedded coding vectors is gated mask modulated to obtain the set of surrounding ship information embedded coding vectors after intensity modulation, including: extracting the median of the set of surrounding ship information association strength prompt values ​​as the information association strength gate threshold; using the information association strength gate threshold as the switching threshold of the gating unit, and inputting the set of surrounding ship information embedded coding vectors and the set of surrounding ship information association strength prompt values ​​into the gating unit to obtain the set of surrounding ship information embedded coding vectors after intensity modulation.

[0019] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the information association strength gate threshold is used as the switching threshold of the gate control unit, and the set of surrounding ship information embedded coding vectors and the set of surrounding ship information association strength prompt values ​​are input into the gate control unit to obtain the set of surrounding ship information embedded coding vectors after intensity modulation, including: if the surrounding ship information association strength prompt value is less than the information association strength gate threshold, then the corresponding surrounding ship information embedded coding vector is set to 0 to obtain the surrounding ship information embedded coding vector after intensity modulation; if the surrounding ship information association strength prompt value is greater than or equal to the information association strength gate threshold, then it is divided by the information association strength gate threshold and used as a weight coefficient to perform weighted modulation with the corresponding surrounding ship information embedded coding vector to obtain the surrounding ship information embedded coding vector after intensity modulation.

[0020] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the set of surrounding ship information embedded coding vectors after intensity modulation and the embedded coding vector of the ship information are globally correlated and aggregated encoded to obtain the global significant propagation aggregate feature vector of the ship information as the encrypted AIS data packet, including: inputting the set of surrounding ship information embedded coding vectors after intensity modulation and the embedded coding vector of the ship information into a feature dynamic propagation module based on the forward LTSM model to obtain the global significant propagation aggregate feature vector of the ship information.

[0021] Compared with the prior art, the ship monitoring method based on Beidou satellite and AIS data provided by this application uses the AIS transceiver module to obtain the AIS data of the ship and surrounding ships, and uses a data encryption algorithm based on deep learning to encrypt the acquired AIS data to identify and filter out invalid or irrelevant ship information, and then, through the Beidou satellite communication array, the encrypted AIS data packet is sent to the AIS data center for decoding and analysis, so as to obtain the ship's position, speed, heading and other AIS data. In this way, the ship monitoring capability in the ocean and remote waters can be effectively improved, and through data encryption processing, the problems of information overload and low data transmission efficiency are solved, while the security of data transmission is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0023] Figure 1 The present invention is a flowchart of a ship monitoring method based on Beidou satellite and AIS data according to an embodiment of the present application.

[0024] Figure 2 Flow chart of step S120 in the ship monitoring method based on Beidou satellite and AIS data according to an embodiment of the present application.

[0025] Figure 3 This is a flowchart of sub-step S122 in the ship monitoring method based on Beidou satellite and AIS data according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] Below, the embodiments of the present application will be described in more detail in conjunction with the accompanying drawings, and the above and other purposes, features and advantages of the present application will become more apparent. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0027] Figure 1 FIG. 1 is a flow chart of a ship monitoring method based on Beidou satellite and AIS data according to an embodiment of the present application. Figure 1 As shown, according to the embodiment of the present application, the ship monitoring method based on Beidou satellite and AIS data includes the following steps: S110, using an AIS transceiver module to obtain AIS data, wherein the AIS data includes information about the ship and surrounding ships; S120, using an encryption encoder to process the AIS data to obtain an encrypted AIS data packet, wherein the encrypted AIS data packet conforms to the short message format of the Beidou satellite communication protocol; S130, using a Beidou satellite communication array to transmit the encrypted AIS data packet to an AIS data center; S140, in response to receiving a user query for information about a certain ship, selecting a ship of interest through a monitoring terminal of the AIS data center and retrieving the encrypted AIS data packet of the ship; S150, using a decryption decoder to decode the encrypted AIS data packet to obtain decoded data, wherein the decoded data is the AIS data of the ship.

[0028] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the step S110 uses the AIS transceiver module to obtain AIS data, and the AIS data includes the information of the ship and the surrounding ships. It should be understood that the AIS equipment can automatically collect and transmit the static information of the ship (such as ship identification number, length, ship width, etc.), dynamic information (such as position, speed, heading, etc.) and voyage information (such as destination, estimated arrival time, etc.) to facilitate other ships and shore-based facilities to receive and realize mutual identification and tracking between ships. In the technical solution of the present application, by obtaining the information of the ship and the surrounding ships, it is helpful to realize the comprehensive monitoring of the navigation environment around the ship, thereby optimizing the route planning, avoiding potential collision risks, and ensuring navigation safety.

[0029] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the step S120 uses an encryption encoder to process the AIS data to obtain an encrypted AIS data packet, and the encrypted AIS data packet conforms to the short message format of the Beidou satellite communication protocol. In the technical solution of the present application, in order to adapt to the data volume constraint of Beidou satellite short message transmission, a deep learning network model is used to construct an encryption encoder to encrypt the AIS data. By extracting and compressing the features of AIS data, data redundancy is effectively reduced, and a compact encrypted data packet is generated. In addition, the encrypted data packet complies with the short message format requirements of the Beidou satellite communication protocol, thereby ensuring that data can be smoothly transmitted in the Beidou satellite network and achieving high efficiency and reliability of communication.

[0030] Figure 2 FIG. 1 is a flow chart of step S120 in the ship monitoring method based on Beidou satellite and AIS data according to an embodiment of the present application. Figure 2 As shown, the step S120 includes: S121, encrypting and embedding the information of the ship and the surrounding ships in the AIS data to obtain a set of the embedded coding vector of the ship information and the embedded coding vector of the surrounding ships; S122, taking the embedded coding vector of the ship information as a reference, performing feature dynamic propagation aggregation based on information association strength on the set of the embedded coding vector of the ship information and the embedded coding vector of the surrounding ships information to obtain the encrypted AIS data packet.

[0031] Specifically, in step S121, the ship information and surrounding ship information in the AIS data are encrypted and embedded to obtain a set of embedded coding vectors of the ship information and surrounding ship information. It should be understood that, considering that the AIS data usually contains multiple categories of information content, such as the identification number, position, speed, heading, etc. of the ship, and each category of information usually has a different data format. Therefore, in order to achieve dimensionality reduction and structured representation of AIS data, the present application further encrypts and embeds the ship information and each surrounding ship information in the AIS data. In a specific example of the present application, a Transformer model containing an embedding layer is used to encrypt and embed the ship information and surrounding ship information in the AIS data to obtain a set of embedded coding vectors of the ship information and surrounding ship information. Specifically, the embedding layer of the Transformer model is first used to embed the various data items in each ship information, extract the semantic information of each data item, and convert it into a vector representation of a fixed length. Then, the self-attention mechanism of the Transformer model is used to capture the semantic relevance between different data items in each piece of ship information, and to integrate contextual information, thereby enhancing the comprehensive expression ability of ship information and generating a set of the embedded coding vector of the ship information and the embedded coding vector of the surrounding ship information.

[0032] Specifically, in step S122, the ship information embedding coding vector is used as a reference, and the set of the ship information embedding coding vector and the surrounding ship information embedding coding vector is subjected to feature dynamic propagation aggregation based on information association strength to obtain the encrypted AIS data packet. It should be understood that, considering that in the AIS data, the surrounding ship information has different degrees of influence on the navigation safety of the ship, for example, the ship information of the surrounding ships whose heading and position are closer to the ship usually has a more significant impact on the navigation safety of the ship. Therefore, in order to avoid invalid information from occupying too much data transmission resources, a feature dynamic propagation aggregation method based on information association strength is proposed in the technical solution of the present application, which takes the ship information as a reference, and dynamically selects and aggregates the surrounding ship information according to the strength of association between the surrounding ship information and the ship information, thereby forming the encrypted AIS data packet. In this way, unimportant information can be effectively identified and filtered out, ensuring that only the surrounding ship information closely related to the navigation safety of the ship is included in the encrypted AIS data packet, thereby further optimizing the data transmission efficiency and improving the accuracy of monitoring.

[0033] Figure 3 FIG. 1 is a flow chart of sub-step S122 in the ship monitoring method based on Beidou satellite and AIS data according to an embodiment of the present application. Figure 3 As shown, the step S122 includes: S1221, based on the information correlation strength of each surrounding ship information embedding coding vector in the set of surrounding ship information embedding coding vectors relative to the own ship information embedding coding vector, the set of surrounding ship information embedding coding vectors is significantly modulated to obtain a set of surrounding ship information embedding coding vectors after intensity modulation; S1222, the set of surrounding ship information embedding coding vectors after intensity modulation and the own ship information embedding coding vector are globally correlated and aggregated encoded to obtain a global significant propagation aggregate feature vector of ship information as the encrypted AIS data packet.

[0034] More specifically, the step S1221 includes: taking the own ship information embedded coding vector as a feature prompt gate, calculating the information association strength prompt value of each surrounding ship information embedded coding vector in the set of surrounding ship information embedded coding vectors relative to the own ship information embedded coding vector to obtain a set of surrounding ship information association strength prompt values; based on the set of surrounding ship information association strength prompt values, performing gated mask modulation on the set of surrounding ship information embedded coding vectors to obtain the set of surrounding ship information embedded coding vectors after intensity modulation.

[0035] In a specific example of the present application, the information association strength prompt value of each surrounding ship information embedded coding vector in the set of surrounding ship information embedded coding vectors relative to the current ship information embedded coding vector is calculated to obtain a set of surrounding ship information association strength prompt values, including: calculating the positional dot division vector between the surrounding ship information embedded coding vector and the current ship information embedded coding vector, and calculating the base-two logarithmic value of the absolute value of each eigenvalue in the dot division vector to obtain a surrounding ship information association representation vector; calculating the dot product vector between the surrounding ship information association representation vector and the surrounding ship information embedded coding vector, and calculating an exponential function value with base e and the sum of the eigenvalues ​​of the dot product vector as the exponent to obtain the surrounding ship information association strength prompt value.

[0036] In a specific example of the present application, based on the set of surrounding ship information association strength prompt values, the set of surrounding ship information embedded coding vectors is gated mask modulated to obtain the set of surrounding ship information embedded coding vectors after intensity modulation, including: extracting the median of the set of surrounding ship information association strength prompt values ​​as the information association strength gate threshold; using the information association strength gate threshold as the switching threshold of the gating unit, and inputting the set of surrounding ship information embedded coding vectors and the set of surrounding ship information association strength prompt values ​​into the gating unit to obtain the set of surrounding ship information embedded coding vectors after intensity modulation.

[0037] In a specific example of the present application, the information association strength gate threshold is used as the switching threshold of the gating unit, and the set of surrounding ship information embedded coding vectors and the set of surrounding ship information association strength prompt values ​​are input into the gating unit to obtain the set of surrounding ship information embedded coding vectors after intensity modulation, including: if the surrounding ship information association strength prompt value is less than the information association strength gate threshold, then the corresponding surrounding ship information embedded coding vector is set to 0 to obtain the surrounding ship information embedded coding vector after intensity modulation; if the surrounding ship information association strength prompt value is greater than or equal to the information association strength gate threshold, then it is divided by the information association strength gate threshold and used as a weight coefficient to perform weighted modulation with the corresponding surrounding ship information embedded coding vector to obtain the surrounding ship information embedded coding vector after intensity modulation.

[0038] That is, firstly, the ship information embedding coding vector is used as the feature prompt gate to construct the perspective of attention for the surrounding ship information propagation aggregation, and the information association strength prompt value between each surrounding ship information embedding coding vector in the set of surrounding ship information embedding coding vectors and the ship information embedding coding vector is calculated to evaluate the relative importance of each surrounding ship information, identify the surrounding ship information that has a greater impact on the ship, and give it a higher weight in the subsequent information propagation aggregation process. Subsequently, in order to avoid the degradation of model performance due to a few extreme cases, the median is further extracted from the above-obtained information association strength prompt value aggregation as the threshold switch, and the set of surrounding ship information embedding coding vectors is modulated for feature intensity. Based on the gating mechanism, the feature representations that are weakly associated with the ship information embedding coding vector are filtered out, and more attention is paid to the surrounding ship information that is closely related to the ship information.

[0039] More specifically, step S1222 includes: inputting the set of surrounding ship information embedded coding vectors after intensity modulation and the embedded coding vector of the ship information into the feature dynamic propagation module based on the forward LTSM model to obtain the global significant propagation aggregation feature vector of the ship information. That is, the global association aggregation is performed on the set of the embedded coding vector of the ship information and the embedded coding vector of the surrounding ship information after feature intensity modulation through the forward LSTM model, so as to capture the spatiotemporal correlation relationship between the ship information and the surrounding ship information by using the long-term memory ability of the LSTM model, and obtain the global significant propagation aggregation feature vector of the ship information. Finally, the global significant propagation aggregation feature vector of the ship information is encapsulated by adding header and tail information according to the short message format requirements of the Beidou satellite communication protocol to form the encrypted AIS data packet as the final output.

[0040] In summary, the step S122 includes: processing the set of the embedded coding vector of the ship information and the embedded coding vector of the surrounding ship information by the following information dynamic propagation aggregation formula to obtain the global significant propagation aggregation feature vector of the ship information, wherein the information dynamic propagation aggregation formula is:

[0041] X={x1,x2,...,x i ,...,x n}

[0042]

[0043] τ=median[{s1,s2,...,s i ...,s n}]

[0044]

[0045] X′={x1′,x2′,...,x i ′,...,x n ′}

[0046] x p+1 =LSTM(x p ; X′)

[0047] Where X represents the set of surrounding ship information embedded coding vectors, x1, x2, x i and x n represents the first, second, i-th and n-th surrounding ship information embedding coding vectors in the set of surrounding ship information embedding coding vectors respectively, n is the number of surrounding ship information embedding coding vectors, x p represents the ship information embedded coding vector, and denote the eigenvalue of the jth position of the i-th surrounding ship information embedded coding vector and the eigenvalue of the jth position of the current ship information embedded coding vector, log(·) denotes a logarithmic function with base 2, exp(·) denotes a natural exponential function, L denotes the characteristic scale of the surrounding ship information embedded coding vector, s1, s2, s i and n represents the first, second, i-th and n-th surrounding ship information association strength prompt values, respectively; median[·] represents the median; τ represents the information association strength gate threshold; mask(·) represents the gate control unit; X′ represents the set of surrounding ship information embedding coding vectors after intensity modulation; x1′, x2′, x i ′ and x n′ respectively represent the first, second, i-th and n-th intensity modulated surrounding ship information embedding coding vectors in the set of intensity modulated surrounding ship information embedding coding vectors, LSTM(·) represents the forward LTSM model, x p+1 Represents the global significant propagation aggregate feature vector of the ship information.

[0048] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the step S130 uses the Beidou satellite communication array to transmit the encrypted AIS data packet to the AIS data center. It should be understood that the Beidou satellite communication array has the characteristics of wide coverage and stable transmission, which can ensure the reliable transmission of the encrypted AIS data packet in a complex marine environment. The AIS data center is equipped with advanced data processing algorithms and storage resources, which are responsible for collecting and storing encrypted AIS data packets from different ships, and decrypting and analyzing the received encrypted AIS data packets to restore detailed information of the ship and surrounding ships, thereby realizing real-time monitoring and management of maritime traffic flows.

[0049] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, in step S140, in response to receiving a user query for a certain ship information, the monitoring terminal of the AIS data center selects the ship of interest and retrieves the encrypted AIS data packet of the ship. In other words, the AIS data center supports user query operations. On the monitoring terminal of the AIS data center, the user can enter specific query conditions to retrieve and retrieve the encrypted AIS data packet of the ship of interest, and display the real-time position, speed, heading and other key information of the ship through decryption processing and a graphical interface.

[0050] In the above-mentioned ship monitoring method based on Beidou satellite and AIS data, the step S150 uses a decryption decoder to decode the encrypted AIS data packet to obtain decoded data, and the decoded data is the AIS data of the ship. In an embodiment of the present application, the decryption decoder adopts an LSTM model architecture, and gradually deconstructs the feature coding representation in the encrypted data packet through its internal loop connection and gating mechanism, and then restores the original AIS data. Through this efficient data processing and transmission mechanism, the AIS data center can monitor the maritime traffic conditions in real time, provide timely navigation guidance and safety warnings for ships, thereby greatly improving the safety and efficiency of maritime navigation.

[0051] In summary, the ship monitoring method based on Beidou satellite and AIS data according to the embodiment of the present application is explained, which uses the AIS transceiver module to obtain the AIS data of the ship and surrounding ships, and uses the data encryption algorithm based on deep learning to encrypt the acquired AIS data to identify and filter out invalid or irrelevant ship information, and then, through the Beidou satellite communication array, the encrypted AIS data packet is sent to the AIS data center for decoding and analysis, so as to obtain the ship's position, speed, heading and other AIS data. In this way, the ship monitoring capability in the ocean and remote waters can be effectively improved, and through data encryption processing, the problems of information overload and low data transmission efficiency are solved, while the security of data transmission is enhanced.

[0052] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0053] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the module division is only a logical function division, and there may be other division methods in actual implementation. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0054] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0055] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0056] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A ship monitoring method based on Beidou satellite and AIS data, characterized in that: include: The AIS data is obtained by using the AIS transceiver module, wherein the AIS data includes the information of the vessel and surrounding vessels; The AIS data is processed by an encryption encoder to obtain an encrypted AIS data packet, wherein the encrypted AIS data packet conforms to a short message format of a Beidou satellite communication protocol; Transmitting the encrypted AIS data packet to an AIS data center using a BeiDou satellite communication array; In response to receiving a user's query for information about a ship, the monitoring terminal of the AIS data center selects a ship of interest and retrieves the encrypted AIS data packet of the ship; Decoding the encrypted AIS data packet using a decryption decoder to obtain decoded data, wherein the decoded data is the AIS data of the ship; The AIS data is processed by an encryption encoder to obtain an encrypted AIS data packet, including: encrypting and embedding the ship information and surrounding ship information in the AIS data to obtain a set of the ship information embedding coding vector and the surrounding ship information embedding coding vector; taking the ship information embedding coding vector as a reference, performing feature dynamic propagation aggregation based on information correlation strength on the set of the ship information embedding coding vector and the surrounding ship information embedding coding vector to obtain the encrypted AIS data packet.

2. The ship monitoring method based on Beidou satellite and AIS data according to claim 1, characterized in that: Encrypting and embedding the information of the ship and the surrounding ships in the AIS data to obtain a set of the embedding coding vector of the ship information and the embedding coding vector of the surrounding ships information, including: The information of the ship and the surrounding ships in the AIS data are encrypted and embedded respectively using a Transformer model including an embedding layer to obtain a set of the embedding coding vector of the ship information and the embedding coding vector of the surrounding ships information.

3. The ship monitoring method based on Beidou satellite and AIS data according to claim 2 is characterized in that: Taking the vessel information embedding coding vector as a benchmark, performing feature dynamic propagation aggregation based on information association strength on the set of the vessel information embedding coding vector and the surrounding vessel information embedding coding vector to obtain the encrypted AIS data packet, including: Based on the information correlation strength of each surrounding ship information embedding coding vector in the set of surrounding ship information embedding coding vectors relative to the ship information embedding coding vector, significance modulation is performed on the set of surrounding ship information embedding coding vectors to obtain a set of surrounding ship information embedding coding vectors after intensity modulation; The set of surrounding ship information embedded coding vectors after the intensity modulation and the ship information embedded coding vector are globally correlated and aggregated encoded to obtain a global significant propagation aggregate feature vector of the ship information as the encrypted AIS data packet.

4. The ship monitoring method based on Beidou satellite and AIS data according to claim 3 is characterized in that: Based on the information correlation strength of each surrounding ship information embedding coding vector in the set of surrounding ship information embedding coding vectors relative to the ship information embedding coding vector, the set of surrounding ship information embedding coding vectors is saliency modulated to obtain a set of surrounding ship information embedding coding vectors after intensity modulation, including: Taking the own ship information embedding coding vector as a feature prompt gate, calculating the information association strength prompt value of each surrounding ship information embedding coding vector in the set of surrounding ship information embedding coding vectors relative to the own ship information embedding coding vector to obtain a set of surrounding ship information association strength prompt values; Based on the set of surrounding ship information association strength prompt values, gated mask modulation is performed on the set of surrounding ship information embedded coding vectors to obtain the set of surrounding ship information embedded coding vectors after intensity modulation.

5. The ship monitoring method based on Beidou satellite and AIS data according to claim 4 is characterized in that: Calculating the information association strength prompt value of each surrounding ship information embedding coding vector in the set of surrounding ship information embedding coding vectors relative to the current ship information embedding coding vector to obtain a set of surrounding ship information association strength prompt values, including: Calculate the positional dotted division vector between the surrounding ship information embedded coding vector and the own ship information embedded coding vector, and calculate the base-two logarithm of the absolute value of each eigenvalue in the dotted division vector to obtain the surrounding ship information association representation vector; The dot product vector between the surrounding ship information association representation vector and the surrounding ship information embedded coding vector is calculated, and the exponential function value with e as the base and the sum of the eigenvalues ​​of the dot product vector as the exponent is calculated to obtain the surrounding ship information association strength prompt value.

6. The ship monitoring method based on Beidou satellite and AIS data according to claim 5, characterized in that: Based on the set of surrounding ship information association strength prompt values, gated mask modulation is performed on the set of surrounding ship information embedded coding vectors to obtain the set of surrounding ship information embedded coding vectors after intensity modulation, including: Extracting the median of the set of prompt values ​​of the surrounding ship information association strength as the information association strength gate threshold; The information association strength gate threshold is used as the switching threshold of the gating unit, and the set of surrounding ship information embedded coding vectors and the set of surrounding ship information association strength prompt values ​​are input into the gating unit to obtain the set of surrounding ship information embedded coding vectors after intensity modulation.

7. The ship monitoring method based on Beidou satellite and AIS data according to claim 6, characterized in that: The information association strength gate threshold is used as the switch threshold of the gate control unit, and the set of surrounding ship information embedded coding vectors and the set of surrounding ship information association strength prompt values ​​are input into the gate control unit to obtain the set of surrounding ship information embedded coding vectors after intensity modulation, including: If the surrounding ship information association strength prompt value is less than the information association strength gate threshold, the corresponding surrounding ship information embedding coding vector is set to 0 to obtain the surrounding ship information embedding coding vector after intensity modulation; If the surrounding ship information association strength prompt value is greater than or equal to the information association strength gate threshold, it is divided by the information association strength gate threshold and used as a weight coefficient to perform weighted modulation with the corresponding surrounding ship information embedding coding vector to obtain the surrounding ship information embedding coding vector after intensity modulation.

8. The ship monitoring method based on Beidou satellite and AIS data according to claim 7, characterized in that: The set of the surrounding ship information embedded coding vectors after the intensity modulation and the embedded coding vector of the ship information are subjected to global correlation aggregation coding to obtain the global significant propagation aggregation feature vector of the ship information as the encrypted AIS data packet, including: The set of surrounding ship information embedded coding vectors after intensity modulation and the ship information embedded coding vector are input into the feature dynamic propagation module based on the forward LTSM model to obtain the global significant propagation aggregate feature vector of the ship information.

Images