A method and system for real-time communication on ships

Abstract

This invention discloses a real-time communication method and system for ships, belonging to the field of data processing technology. By detecting the signal strength of each communication channel involved in the ship, the signal strength detection result corresponding to each communication channel is determined, and the target channel is determined based on the signal detection results corresponding to all communication channels. This allows for the identification of a superior channel for communication, thereby ensuring the quality of real-time communication. Then, a communication signal recognition model improved by information fusion search algorithm is used to blindly identify the real-time communication signal, which can quickly identify the modulation mode of the real-time communication signal, thereby quickly demodulating and further improving the quality of communication.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, specifically relating to a real-time communication method and system for ships. Background Technology

[0002] The booming global maritime economy has driven the rapid development of the shipping economy. Cutting-edge technologies in shipbuilding, navigation safety, and ship monitoring are advancing rapidly in the maritime field. During real-time communication, ships often need to identify modulation patterns. Modulation identification refers to determining the modulation pattern of a signal by analyzing its characteristics when the information and parameters carried by the communication signal are unknown. In non-cooperative communication systems, Automatic Modulation Identification (AMR) helps the receiver identify the modulation pattern of the received signal even when the transmitter's modulation pattern is unknown. If the receiver wants to extract information such as amplitude, phase, and frequency from the signal sample, it must receive and sample the signal at a matching frequency. Without AMR, it is impossible to correctly demodulate and encode the received signal.

[0003] In existing technologies, deep learning techniques are often used to identify communication information. However, these techniques typically only consider model improvement without optimizing parameters, resulting in poor modulation pattern recognition and ultimately hindering efficient real-time communication. Summary of the Invention

[0004] This invention provides a real-time communication method and system for ships, which solves the problem that existing technologies only consider model improvement without considering parameter optimization, resulting in poor modulation pattern recognition and ultimately inefficient real-time communication.

[0005] On one hand, the present invention provides a real-time communication method for ships, comprising:

[0006] Signal strength is detected for each communication channel involved in the ship, the signal strength detection result for each communication channel is determined, and the target channel is determined based on the signal strength detection results for all communication channels.

[0007] Based on the target channel, the instant communication signal transmitted by the external device is received, and the communication signal recognition model improved by the information fusion search algorithm is used to blindly identify the instant communication signal to obtain the modulation mode corresponding to the instant communication signal.

[0008] Based on the modulation mode corresponding to the real-time communication signal, the real-time communication signal is demodulated so that the ship can respond to the real-time communication signal and complete the ship's real-time communication.

[0009] Furthermore, signal strength is detected for each communication channel involved in the ship, and the signal strength detection results for each communication channel are determined, including:

[0010] The signal strength of the 5G channel, AIS channel, and BeiDou satellite channel corresponding to the ship is detected to obtain the signal strength detection results for each communication channel.

[0011] Furthermore, the target channel is determined based on the signal detection results corresponding to all communication channels, including:

[0012] If the signal strength detection result corresponding to the 5G channel meets the first preset requirement, then the 5G channel is determined as the target channel; otherwise, the AIS channel is judged.

[0013] If the signal strength detection result corresponding to the AIS channel meets the second preset requirement, then the AIS channel is determined as the target channel; otherwise, the BeiDou satellite channel is judged.

[0014] If the signal strength detection result corresponding to the BeiDou satellite channel meets the third preset requirement, then the BeiDou satellite channel is determined to be the target channel; otherwise, it is determined to be a response timeout, and the ship's real-time communication process ends.

[0015] Furthermore, based on the target channel, real-time communication signals transmitted by external devices are received, and a communication signal recognition model improved by an information fusion search algorithm is used to blindly identify the real-time communication signals to obtain the modulation mode corresponding to the real-time communication signals, including:

[0016] Receive instant communication signals transmitted by external devices and obtain the constellation diagram features corresponding to the instant communication signals;

[0017] An improved communication signal recognition model using an information fusion search algorithm is used to identify the constellation features corresponding to the instant communication signal, thereby obtaining the modulation mode corresponding to the instant communication signal.

[0018] Furthermore, before blindly identifying the instantaneous communication signal using the communication signal identification model improved by the information fusion search algorithm, the method further includes:

[0019] A signal blind recognition model is constructed using a convolutional neural network, and the signal blind recognition model is pre-trained using an information fusion search algorithm to obtain a communication signal recognition model improved by the information fusion search algorithm.

[0020] Furthermore, the signal blind identification model is pre-trained using an information fusion search algorithm to obtain an improved communication signal identification model, including:

[0021] Initialize the model parameters of the signal blind recognition model to obtain multiple individuals for training; where each individual includes the model parameters to be trained in the signal blind recognition model.

[0022] Obtain the error function value corresponding to each individual, and determine the individual with the smallest error function value as the global optimal individual;

[0023] In the initial information fusion stage, a strategy of exploring unknown regions of superiority is adopted to perform information fusion on each individual in the population to obtain individuals after initial information fusion;

[0024] In the extended information fusion stage, based on the global optimal individual, and using an optimal direction exploration strategy with jumps, information fusion is performed on the individuals after the initial information fusion to obtain individuals after enhanced information fusion;

[0025] In the fine information fusion stage, based on the global optimal individual, and using the optimal region exploration strategy, information fusion is performed on the individuals after enhanced information fusion to obtain the individuals after fine information fusion;

[0026] In the global information fusion stage, a global exploration strategy with random hit regions is used to fuse the information of individuals after fine information fusion, resulting in individuals after global information fusion.

[0027] The initial information fusion stage, extended information fusion stage, refined information fusion stage, and global information fusion stage are repeated until the current number of training iterations is greater than or equal to the maximum number of training iterations. The globally optimal individual is then re-obtained and used as the optimal parameters for the communication signal recognition model, thus obtaining the communication signal recognition model improved by the information fusion search algorithm.

[0028] Furthermore, it also includes:

[0029] When the ship responds to the instant communication signal, it uses an improved hybrid encryption algorithm to encrypt the response message, modulates the encrypted response message according to the modulation mode corresponding to the instant communication signal, and then sends it.

[0030] Furthermore, an improved hybrid encryption algorithm is used to encrypt the response message, including:

[0031] Obtain the public key corresponding to the external device; wherein, the private key corresponding to the public key is held by the external device;

[0032] The response message is encrypted using a symmetric encryption algorithm based on intelligent optimization algorithm to obtain an encrypted message;

[0033] The symmetric encryption key of the symmetric encryption algorithm is encrypted using the public key corresponding to the external device to obtain the encryption key;

[0034] The encrypted message and the encryption key are combined to form the encrypted response message.

[0035] Furthermore, a symmetric encryption algorithm based on intelligent optimization is used to encrypt the response message, resulting in an encrypted message, including:

[0036] The AES algorithm is used as the symmetric encryption algorithm.

[0037] An initial round key for a symmetric encryption algorithm is randomly generated; wherein the initial round key is a binary key;

[0038] Based on the initial round key of the symmetric encryption algorithm, an intelligent optimization algorithm is used to generate other round keys for the symmetric encryption algorithm;

[0039] The initial round key and the other round keys together form the complete key for the symmetric encryption algorithm;

[0040] Based on all the keys of the symmetric encryption algorithm, the response message is encrypted using the symmetric encryption algorithm to obtain an encrypted message.

[0041] On the other hand, the present invention provides a ship real-time communication system, including a channel selection module, a modulation mode recognition module, and a real-time communication module;

[0042] The channel selection module is used to detect the signal strength of each communication channel involved in the ship, determine the signal strength detection result corresponding to each communication channel, and determine the target channel based on the signal detection results corresponding to all communication channels.

[0043] The modulation pattern recognition module is used to receive real-time communication signals transmitted by external devices based on the target channel, and to perform blind recognition of the real-time communication signals using a communication signal recognition model improved by information fusion search algorithm, so as to obtain the modulation pattern corresponding to the real-time communication signals.

[0044] The instant communication module is used to demodulate the instant communication signal based on the modulation mode corresponding to the instant communication signal, so that the ship can respond to the instant communication signal and complete the ship's instant communication.

[0045] This invention provides a real-time communication method and system for ships. By detecting the signal strength of each communication channel involved in the ship, the signal strength detection result corresponding to each communication channel is determined, and the target channel is determined based on the signal detection results of all communication channels. This allows for the identification of a superior channel for communication, thereby ensuring the quality of real-time communication. Then, an improved communication signal recognition model using an information fusion search algorithm is employed to blindly identify the real-time communication signal, which can quickly identify the modulation mode of the real-time communication signal, thereby enabling rapid demodulation and further improving the quality of communication. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0047] Figure 1 This is a flowchart illustrating a real-time communication method for ships provided in an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram of a ship real-time communication system provided in an embodiment of the present invention.

[0049] Among them, 201-channel selection module, 202-modulation mode recognition module, and 203-instant communication module.

[0050] The accompanying drawings have illustrated specific embodiments of the invention, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0051] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0052] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0053] like Figure 1 As shown, an embodiment of the present invention provides a real-time communication method for ships, including:

[0054] S101. Perform signal strength detection on each communication channel involved in the ship, determine the signal strength detection result corresponding to each communication channel, and determine the target channel based on the signal strength detection results corresponding to all communication channels;

[0055] S102. Based on the target channel, receive the instant communication signal transmitted by the external device, and use the communication signal recognition model improved by the information fusion search algorithm to blindly identify the instant communication signal to obtain the modulation mode corresponding to the instant communication signal.

[0056] S103. Based on the modulation mode corresponding to the instant communication signal, demodulate the instant communication signal so that the ship can respond to the instant communication signal and complete the ship's instant communication.

[0057] This invention provides a real-time communication method and system for ships. By detecting the signal strength of each communication channel involved in the ship, the signal strength detection result corresponding to each communication channel is determined, and the target channel is determined based on the signal detection results of all communication channels. This allows for the identification of a superior channel for communication, thereby ensuring the quality of real-time communication. Then, an improved communication signal recognition model using an information fusion search algorithm is employed to blindly identify the real-time communication signal, which can quickly identify the modulation mode of the real-time communication signal, thereby enabling rapid demodulation and further improving the quality of communication.

[0058] In this embodiment of the invention, signal strength detection is performed on each communication channel involved in the ship, and the signal strength detection result corresponding to each communication channel is determined, including:

[0059] The signal strength of the 5G channel, AIS channel, and BeiDou satellite channel corresponding to the ship is detected to obtain the signal strength detection results for each communication channel.

[0060] In this embodiment of the invention, determining the target channel based on the signal detection results corresponding to all communication channels includes:

[0061] If the signal strength detection result corresponding to the 5G channel meets the first preset requirement (i.e., the signal strength detection result corresponding to the 5G channel exceeds the preset 5G signal strength threshold), then the 5G channel is determined as the target channel; otherwise, the AIS channel is judged.

[0062] If the signal strength detection result corresponding to the AIS channel meets the second preset requirement, then the AIS channel is determined as the target channel; otherwise, the BeiDou satellite channel is judged.

[0063] The signal strength detection result corresponding to the AIS channel can be its coverage area. When the coverage area corresponding to the AIS channel at the ship end coincides with the coverage area corresponding to the AIS channel of the external device, the second preset requirement is met.

[0064] If the signal strength detection result corresponding to the BeiDou satellite channel meets the third preset requirement, then the BeiDou satellite channel is determined to be the target channel; otherwise, it is determined to be a response timeout, and the ship's real-time communication process ends.

[0065] The signal strength detection result corresponding to the BeiDou satellite channel can be the number of its signal sources. When the number of signal sources is greater than a preset threshold, the third preset requirement is met.

[0066] Optionally, to ensure smooth instant communication, the above steps can be repeated to select a suitable target channel.

[0067] The present invention provides a method for determining the target channel based on the signal detection results corresponding to all communication channels, which can make real-time communication on ships smoother and prevent communication interruptions.

[0068] In this embodiment of the invention, based on the target channel, real-time communication signals transmitted by external devices are received, and a communication signal identification model improved by an information fusion search algorithm is used to blindly identify the real-time communication signals to obtain the modulation mode corresponding to the real-time communication signals, including:

[0069] Receive instant communication signals transmitted by external devices and obtain the constellation diagram features corresponding to the instant communication signals;

[0070] An improved communication signal recognition model using an information fusion search algorithm is used to identify the constellation features corresponding to the instant communication signal, thereby obtaining the modulation mode corresponding to the instant communication signal.

[0071] In this embodiment of the invention, before blindly identifying the instant communication signal using a communication signal identification model improved by an information fusion search algorithm, the method further includes:

[0072] A signal blind recognition model is constructed using a convolutional neural network, and the signal blind recognition model is pre-trained using an information fusion search algorithm to obtain a communication signal recognition model improved by the information fusion search algorithm.

[0073] It is worth noting that, in addition to using convolutional neural networks to build signal blind recognition models, other neural networks can also be used to build signal blind recognition models.

[0074] In this embodiment of the invention, an information fusion search algorithm is used to pre-train the signal blind identification model to obtain an improved communication signal identification model, including:

[0075] A1. Initialize the model parameters of the signal blind recognition model to obtain multiple individuals for training; where each individual includes the model parameters to be trained for the signal blind recognition model.

[0076] The model parameters of a blind signal recognition model are generally the connection weights and thresholds between each layer. These connection weights and thresholds usually have fixed upper and lower limits. Therefore, the model parameters of the blind signal recognition model can be initialized by randomly initializing them between the upper and lower limits to obtain individuals for training. After repeating this process multiple times, multiple individuals can be obtained.

[0077] A2. Obtain the error function value corresponding to each individual, and determine the individual with the smallest error function value as the global optimal individual;

[0078] For example, the root mean square error function value or cross-entropy loss function value corresponding to each individual can be obtained, thereby determining the globally optimal individual.

[0079] When obtaining the error function value, the sample constellation diagram features can be used as input, and the modulation mode corresponding to the sample constellation diagram features can be used as the expected label. Thus, the error function value between the actual output and the expected label can be obtained.

[0080] A3. In the initial information fusion stage, a strategy of exploring unknown regions of superiority is adopted to perform information fusion on each individual in the population to obtain individuals after initial information fusion;

[0081] Based on the error function value corresponding to each individual, all individuals are sorted in ascending order of their error function values ​​to obtain the sorted individuals;

[0082] For each individual, match it with the individual that is ranked first, and obtain the crossover individual corresponding to each individual; among the first half of the individuals, randomly match an individual for the first individual;

[0083] Based on the cross-individuals corresponding to each individual, the exploration of the unknown region of superiority for each individual is as follows:

[0084]

[0085]

[0086] in, Indicates the first t During the training process, the first j There are 1, 2, ..., J individuals, where J represents the total number of individuals. Represents the individual after initial information fusion , Indicates the first t +1 training session j The update volume of each individual, Indicates the first t During the training process, the first jThe update volume of each individual, The coefficient of fusion is represented by , and e represents the natural constant. Indicates the information fusion control coefficient. Represents an individual The corresponding crossover individuals.

[0087] The initial information fusion stage provided in this embodiment of the invention allows each individual to fuse information with other better individuals, explore more unknown local domains, and move towards a better direction. This not only helps to improve spatial traversal, but also effectively improves the convergence speed and accuracy of the algorithm.

[0088] A4. In the extended information fusion stage, based on the global optimal individual, and using an optimal direction exploration strategy with jumps, information fusion is performed on the individuals after the initial information fusion to obtain individuals after enhanced information fusion.

[0089] Regarding the first i Individuals after initial information fusion The jump terms are determined as follows: ;in, Indicates the update coefficients. express, Including individuals A random individual outside of, i =1,2,…,J;

[0090] Regarding the first i Individuals after initial information fusion The information item is determined to be: ;in, Represents the first random number between (0,1). This represents the second random number between (0,1). Represents the globally optimal individual;

[0091] Based on the aforementioned jump items and information items, the individual after enhanced information fusion is determined. = + ;

[0092] In the extended information fusion stage, the global optimal individual and the individual after initial information fusion are randomly weighted, and combined with another random location information, the exploration of unknown areas is extended, which ultimately improves the spatial convergence of the algorithm.

[0093] A5. In the fine information fusion stage, based on the global optimal individual, and using the optimal region exploration strategy, information fusion is performed on the individuals after enhanced information fusion to obtain the individuals after fine information fusion.

[0094] In the refined information fusion stage, based on the globally optimal individual, the refined fused information is determined by exploring the optimal region: ;in, Indicates the first exploration step size. Indicates except the first m An individual after enhanced information fusion A second random individual outside of the above. Indicates except the first m An individual after enhanced information fusion A random third individual outside of the above;

[0095] Based on the aforementioned finely fused information, the first... m An individual after enhanced information fusion Updated to:

[0096]

[0097] in, This represents the control factor for fine-grained information fusion. This represents a random number generated by a standard Gaussian distribution with a mean of 0 and a variance of 1. Represents an individual after fine information fusion .

[0098] In the fine information fusion stage, this embodiment of the invention uses the globally optimal individual and two other random individuals for information fusion. This allows the algorithm to learn the position information of other individuals while moving towards the globally optimal individual. It can effectively balance global search and local search, preventing the algorithm from getting stuck in local optima in the early stages. In the later stages of the algorithm, individuals tend to cluster together, which can effectively improve the convergence accuracy of the algorithm.

[0099] A6. In the global information fusion stage, a global exploration strategy with random hit regions is adopted to perform information fusion on the individuals after fine information fusion to obtain the individuals after global information fusion.

[0100] During the global information fusion phase, the randomly generated hit items are as follows: ;in, Represents a random number between (0, 1). This indicates the first random hit control factor, and Satisfies a normal distribution , Indicates intermediate parameters. , Represents the gamma function. Represents pi (π). v This indicates the second random hit control factor, and v Satisfies a normal distribution .

[0101] Based on the globally optimal individual, the information fusion term is determined as follows: ;in, This represents the preset constant coefficient. Indicates the first t During the training process, the first k The first individual after fine information fusion d Dimensional parameters, Indicates the first t The first globally optimal individual during the training process d Dimensional parameters, d =1,2,…,D, where D represents the total dimension of parameters in an individual;

[0102] Based on the random hit items and the information fusion items, the individuals after global information fusion are determined as follows: = + × ;in, Represents an individual after global information fusion. ;

[0103] In the global information fusion stage, this invention uses mutation to mutate the search information, so that the algorithm always maintains global search capability and will not get trapped in local optima.

[0104] Optionally, to ensure that the search results of the algorithm do not regress, a greedy strategy can be used to control the global information fusion stage.

[0105] A7. Repeat the initial information fusion stage, extended information fusion stage, refined information fusion stage, and global information fusion stage until the current training count is greater than or equal to the maximum training count. Re-obtain the global optimal individual and use the global optimal individual as the best parameter of the communication signal recognition model to obtain the communication signal recognition model improved by the information fusion search algorithm.

[0106] Deep learning technology is often used to identify communication information, but it usually only considers model improvement without considering parameter optimization, which ultimately leads to poor modulation pattern recognition and inefficient real-time communication. In the process of optimizing model parameters in existing technologies, there are often technical problems such as getting trapped in local optima and poor search accuracy, which also leads to poor modulation pattern recognition. Therefore, this embodiment of the invention uses an information fusion search algorithm to pre-train the signal blind recognition model in order to achieve the effect of searching for the global optimum.

[0107] It is worth noting that since each dimension of the communication signal recognition model has its upper and lower limits, after each update, out-of-bounds processing can be performed on individuals, pulling out-of-bounds parameters back to their nearest boundary or randomly generating them within the upper and lower limits.

[0108] In this embodiment of the invention, it further includes:

[0109] When the ship responds to the instant communication signal, it uses an improved hybrid encryption algorithm to encrypt the response message, modulates the encrypted response message according to the modulation mode corresponding to the instant communication signal, and then sends it.

[0110] In this embodiment of the invention, an improved hybrid encryption algorithm is used to encrypt the response message, including:

[0111] Obtain the public key corresponding to the external device; wherein, the private key corresponding to the public key is held by the external device;

[0112] The response message is encrypted using a symmetric encryption algorithm based on intelligent optimization algorithm to obtain an encrypted message;

[0113] The symmetric encryption key of the symmetric encryption algorithm is encrypted using the public key corresponding to the external device to obtain the encryption key;

[0114] The encrypted message and the encryption key are combined to form the encrypted response message.

[0115] In this embodiment of the invention, a symmetric encryption algorithm based on intelligent optimization algorithm is used to encrypt the response message to obtain an encrypted message, including:

[0116] B1. The AES (Advanced Encryption Standard) algorithm is used as the symmetric encryption algorithm.

[0117] B2. Randomly generate an initial round key for a symmetric encryption algorithm; wherein, the initial round key is a binary key;

[0118] For example, based on the single-round key length required by the symmetric encryption algorithm, multiple first candidate keys can be randomly generated, and the sum of the Euclidean distances between each first candidate key and all other first candidate keys can be obtained;

[0119] Based on the sum of the Euclidean distances corresponding to each first candidate key, the first candidate key with the largest sum of Euclidean distances is determined as the initial round key.

[0120] B3. Based on the initial round key of the symmetric encryption algorithm, generate other round keys for the symmetric encryption algorithm using an intelligent optimization algorithm;

[0121] To help those skilled in the art better understand the technical solutions described in the embodiments of the present invention, examples are provided for illustration.

[0122] Based on the first candidate key, multiple second candidate keys are generated using the crossover and mutation strategies of a genetic algorithm;

[0123] Determine the sum of the Euclidean distances between each second candidate key and the previously determined multi-round keys, and determine the second candidate key with the largest sum of Euclidean distances as the current round key;

[0124] All second-candidate keys are used as new first-candidate keys, and the previous step is repeated to obtain the next round's key, and so on, until the other round keys of the symmetric encryption algorithm are determined. This embodiment of the invention uses the AES algorithm as the symmetric encryption algorithm, which requires a total of 11 rounds of keys; therefore, 10 other round keys also need to be determined.

[0125] Determining the sum of Euclidean distances between each second candidate key and the previously determined multi-round keys can be understood as follows: assuming two round keys have been determined, then in the process of determining the current round key (i.e. the third round key), it is necessary to obtain the sum of Euclidean distances between the second candidate key and the previous two round keys.

[0126] B4. Combine the initial round key with the other round keys to form the complete key for the symmetric encryption algorithm;

[0127] B5. Based on all the keys of the symmetric encryption algorithm, the response message is encrypted using the symmetric encryption algorithm to obtain an encrypted message.

[0128] This invention employs a symmetric encryption algorithm based on intelligent optimization to encrypt response messages and uses the public key corresponding to an external device to encrypt the symmetric encryption key of the symmetric encryption algorithm. This not only effectively improves data encryption efficiency but also further ensures data security. Furthermore, to address the technical problem of existing symmetric encryption algorithms where multi-round keys are correlated and easily cracked, this invention combines an intelligent optimization algorithm to further enhance the randomness between multi-round keys, making the keys unpredictable and unbreakable, thereby further improving the encryption security of instant messaging data.

[0129] like Figure 2 As shown, this embodiment of the invention provides a ship real-time communication system, including a channel selection module 201, a modulation pattern recognition module 202, and a real-time communication module 203.

[0130] The channel selection module 201 is used to perform signal strength detection on each communication channel involved in the ship, determine the signal strength detection result corresponding to each communication channel, and determine the target channel based on the signal strength detection results corresponding to all communication channels.

[0131] The modulation pattern recognition module 202 is used to receive real-time communication signals transmitted by external devices based on the target channel, and to perform blind recognition of the real-time communication signals using a communication signal recognition model improved by information fusion search algorithm, so as to obtain the modulation pattern corresponding to the real-time communication signals.

[0132] The instant communication module 203 is used to demodulate the instant communication signal based on the modulation mode corresponding to the instant communication signal, so that the ship can respond to the instant communication signal and complete the ship's instant communication.

[0133] The ship real-time communication system provided in this embodiment of the invention can execute the above-described method embodiments, and its principle and beneficial effects are similar, so they will not be repeated here.

[0134] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0135] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0136] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0137] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0138] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0139] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A real-time communication method for ships, characterized in that, include: Signal strength is detected for each communication channel involved in the ship, the signal strength detection result for each communication channel is determined, and the target channel is determined based on the signal strength detection results for all communication channels. Based on the target channel, the instant communication signal transmitted by the external device is received, and the communication signal recognition model improved by the information fusion search algorithm is used to blindly identify the instant communication signal to obtain the modulation mode corresponding to the instant communication signal. Based on the modulation mode corresponding to the real-time communication signal, the real-time communication signal is demodulated so that the ship can respond to the real-time communication signal and complete the ship's real-time communication. Before blindly identifying the instantaneous communication signal using the communication signal identification model improved by the information fusion search algorithm, the following steps are also included: A blind signal recognition model is constructed using a convolutional neural network; Initialize the model parameters of the signal blind recognition model to obtain multiple individuals for training; where each individual includes the model parameters to be trained in the signal blind recognition model. Obtain the error function value corresponding to each individual, and determine the individual with the smallest error function value as the global optimal individual; In the initial information fusion stage, a strategy of exploring unknown regions of superiority is adopted to perform information fusion on each individual in the population to obtain individuals after initial information fusion; In the extended information fusion stage, based on the global optimal individual, and using an optimal direction exploration strategy with jumps, information fusion is performed on the individuals after the initial information fusion to obtain individuals after enhanced information fusion; In the fine information fusion stage, based on the global optimal individual, and using the optimal region exploration strategy, information fusion is performed on the individuals after enhanced information fusion to obtain the individuals after fine information fusion; In the global information fusion stage, a global exploration strategy with random hit regions is used to fuse the information of individuals after fine information fusion, resulting in individuals after global information fusion. The initial information fusion stage, extended information fusion stage, refined information fusion stage, and global information fusion stage are repeated until the current number of training iterations is greater than or equal to the maximum number of training iterations. The globally optimal individual is then re-obtained and used as the optimal parameters for the communication signal recognition model, thus obtaining the communication signal recognition model improved by the information fusion search algorithm.

2. The ship real-time communication method according to claim 1, characterized in that, Signal strength is measured for each communication channel involved in the ship, and the signal strength measurement results for each communication channel are determined, including: The signal strength of the 5G channel, AIS channel and BeiDou satellite channel corresponding to the ship is detected to obtain the signal strength detection results for each communication channel.

3. The ship real-time communication method according to claim 2, characterized in that, The target channel is determined based on the signal detection results corresponding to all communication channels, including: If the signal strength detection result corresponding to the 5G channel meets the first preset requirement, then the 5G channel is determined as the target channel; otherwise, the AIS channel is judged. If the signal strength detection result corresponding to the AIS channel meets the second preset requirement, then the AIS channel is determined as the target channel; otherwise, the BeiDou satellite channel is judged. If the signal strength detection result corresponding to the BeiDou satellite channel meets the third preset requirement, then the BeiDou satellite channel is determined to be the target channel; otherwise, it is determined to be a response timeout, and the ship's real-time communication process ends.

4. The ship real-time communication method according to claim 1, characterized in that, Based on the target channel, real-time communication signals transmitted by external devices are received, and a communication signal recognition model improved by information fusion search algorithm is used to blindly identify the real-time communication signals to obtain the modulation mode corresponding to the real-time communication signals, including: Receive instant communication signals transmitted by external devices and obtain the constellation diagram features corresponding to the instant communication signals; An improved communication signal recognition model using an information fusion search algorithm is used to identify the constellation features corresponding to the instant communication signal, thereby obtaining the modulation mode corresponding to the instant communication signal.

5. The ship real-time communication method according to claim 1, characterized in that, Also includes: When the ship responds to the instant communication signal, it uses an improved hybrid encryption algorithm to encrypt the response message, modulates the encrypted response message according to the modulation mode corresponding to the instant communication signal, and then sends it.

6. The ship real-time communication method according to claim 5, characterized in that, The response message is encrypted using an improved hybrid encryption algorithm, including: Obtain the public key corresponding to the external device; wherein, the private key corresponding to the public key is held by the external device; The response message is encrypted using a symmetric encryption algorithm based on intelligent optimization algorithm to obtain an encrypted message; The symmetric encryption key of the symmetric encryption algorithm is encrypted using the public key corresponding to the external device to obtain the encryption key; The encrypted message and the encryption key are combined to form the encrypted response message.

7. The ship real-time communication method according to claim 6, characterized in that, The response message is encrypted using a symmetric encryption algorithm based on intelligent optimization, resulting in an encrypted message including: The AES algorithm is used as the symmetric encryption algorithm. An initial round key for a symmetric encryption algorithm is randomly generated; wherein the initial round key is a binary key; Based on the initial round key of the symmetric encryption algorithm, an intelligent optimization algorithm is used to generate other round keys for the symmetric encryption algorithm; The initial round key and the other round keys together form the complete key for the symmetric encryption algorithm; Based on all the keys of the symmetric encryption algorithm, the response message is encrypted using the symmetric encryption algorithm to obtain an encrypted message.

8. A ship real-time communication system, the ship real-time communication system being capable of executing the ship real-time communication method according to any one of claims 1 to 7, characterized in that, It includes a channel selection module, a modulation pattern recognition module, and an instant messaging module; The channel selection module is used to detect the signal strength of each communication channel involved in the ship, determine the signal strength detection result corresponding to each communication channel, and determine the target channel based on the signal detection results corresponding to all communication channels. The modulation pattern recognition module is used to receive real-time communication signals transmitted by external devices based on the target channel, and to perform blind recognition of the real-time communication signals using a communication signal recognition model improved by information fusion search algorithm, so as to obtain the modulation pattern corresponding to the real-time communication signals. The instant communication module is used to demodulate the instant communication signal based on the modulation mode corresponding to the instant communication signal, so that the ship can respond to the instant communication signal and complete the ship's instant communication.

Images