Communication target identification method, device, equipment and program product

Abstract

The invention provides a communication target identification method, device, equipment and program product, and the method comprises the steps: extracting a key signal component from a communication signal transmitted by a to-be-identified communication target, and the key signal component comprises a signal component reflecting the characteristics of the communication target; performing feature extraction processing on the key signal components to obtain key signal features; and classifying the key signal features, and determining whether the communication target to be identified is a preset communication target. The method can improve the communication target identification accuracy.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a communication target identification method, device, equipment and program product. Background Art

[0002] Communication target identification refers to the technical means of determining the identity of a communication target by analyzing the signal emitted by the communication target. For example, in scenarios such as signal source identification and false lock target discrimination, the identity of the communication individual that transmits the signal is identified by analyzing the captured signal.

[0003] At the same time, the communication individual also transmits interference signals, or transmits signals containing more interference signal components to resist communication target identification, so as to confuse the other party and become invisible. In this case, communication target identification is more difficult and the identification accuracy is poor. Summary of the invention

[0004] Based on the above technical problems, the present application proposes a communication target identification method, device, equipment and program product, which can improve the accuracy of communication target identification.

[0005] The first aspect of the present application provides a communication target identification method, comprising:

[0006] Extracting key signal components from the communication signal transmitted by the communication target to be identified, wherein the key signal components include signal components reflecting the characteristics of the communication target;

[0007] Performing feature extraction processing on the key signal components to obtain key signal features;

[0008] The key signal features are classified to determine whether the communication target to be identified is a preset communication target.

[0009] In some implementations, extracting a key signal component from a communication signal transmitted by a communication target to be identified includes:

[0010] Perform feature extraction processing on the communication signal emitted by the communication target to be identified to obtain signal features;

[0011] Determining key features from the signal features by evaluating the importance of different feature components of the signal features;

[0012] Based on the key features, key signal components are extracted from the communication signal.

[0013] In some implementations, the method further includes:

[0014] The key signal components are subjected to signal enhancement processing.

[0015] In some implementations, performing feature extraction processing on the key signal components to obtain key signal features; and classifying the key signal features to determine whether the communication target to be identified is a preset communication target, including:

[0016] Inputting the key signal component into a pre-trained communication individual identification model so that the communication individual identification model performs feature extraction processing on the key signal component to obtain key signal features, and classifying the key signal features to determine whether the communication target to be identified is a preset communication target;

[0017] The communication individual identification model is obtained by performing communication individual identification training on the communication signals in the enhanced signal set, and the enhanced signal set includes enhanced signals generated based on the original communication signals.

[0018] In some implementations, the enhanced signal set is constructed by the following processing:

[0019] Adjust at least one of the time, frequency and phase of the original communication signal to obtain an enhanced signal;

[0020] Performing time-frequency transform processing and / or wavelet transform processing on the enhanced signal;

[0021] An enhanced signal set is constructed by using the enhanced signal and a signal obtained by performing time-frequency transformation processing and / or wavelet transformation processing on the enhanced signal.

[0022] In some implementations, the communication individual identification model is constructed based on a convolutional neural network and a support vector machine.

[0023] In some implementations, the communication individual identification model is constructed by connecting a convolutional layer, a pooling layer, and a support vector machine of a convolutional neural network in series.

[0024] The second aspect of the present application provides a communication target identification device, comprising:

[0025] A signal analysis unit, configured to extract key signal components from a communication signal transmitted by a communication target to be identified, wherein the key signal components include signal components that reflect the characteristics of the communication target;

[0026] The identification processing unit is used to perform feature extraction processing on the key signal components to obtain key signal features; classify the key signal features to determine whether the communication target is a preset communication target.

[0027] A third aspect of the present application provides a communication target identification device, including a memory and a processor;

[0028] The memory is connected to the processor and is used to store programs;

[0029] The processor is used to implement the above-mentioned communication target identification method by running the program in the memory.

[0030] A fourth aspect of the present application provides a computer program product, comprising computer program instructions, which, when executed by a processor, enable the processor to implement the above-mentioned communication target identification method.

[0031] The communication target identification method proposed in the present application first extracts the key signal components reflecting the characteristics of the communication target from the communication signal emitted by the communication target to be identified, and then performs feature extraction and classification based on the key signal components to determine whether the communication target is a preset communication target. The above scheme can avoid the influence of interference signal components in the communication signal on the communication target identification, and only uses the key signal components reflecting the characteristics of the communication target to identify the communication target, which can improve the accuracy of communication target identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0033] Figure 1 A flow chart of a communication target identification method provided in an embodiment of the present application.

[0034] Figure 2 A schematic diagram of the structure of a communication individual identification model provided in an embodiment of the present application.

[0035] Figure 3 A schematic diagram of the structure of a communication target identification device provided in an embodiment of the present application.

[0036] Figure 4 A schematic diagram of the structure of a communication target identification device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The embodiments of the present application are suitable for application scenarios in which identity identification of communication targets is performed. The technical solution of the embodiments of the present application can more accurately identify the identity of the communication target.

[0038] Communication target identification refers to the technical means of determining the identity of a communication target by analyzing the signal emitted by the communication target. In scenarios such as signal source identification and false lock target identification, the identity of the communication individual that transmits the signal is identified by analyzing the captured signal.

[0039] At the same time, the communicating individuals also counter the communication target identification by emitting interference signals, or emitting signals containing more interference signal components, so as to confuse the other party and achieve the purpose of invisibility.

[0040] For example, false target interference refers to simulating the signal characteristics of a real radar target and sending a false signal to the opponent's radar, causing it to mistakenly believe that it has locked onto the real radar target after identifying the false signal.

[0041] In the above scenario, it is very necessary and essential to analyze the received radar signal to distinguish the real target from the false target. The common processing method is to extract the features of the received radar signal to obtain the signal features used to distinguish the real target from the false target. The commonly used features include pulse width, pulse repetition frequency, pulse interval time, etc. Then the extracted signal features are classified to distinguish the real target from the false target.

[0042] In practical applications, in order to avoid being quickly identified by the other party, the communicating individual usually transmits a large amount of interference signals, which makes it difficult to extract signal features useful for identifying its identity from the signals it transmits, resulting in low accuracy in identifying the communication target.

[0043] In response to the above technical problems, an embodiment of the present application proposes a communication target identification method, which, on the one hand, extracts key signal components from the communication signal for communication target identity identification, thereby avoiding the influence of interference signals or redundant signals on communication target identification. On the other hand, the present application also optimizes the training of the communication target identification model so that the model can more accurately distinguish different communication individuals. In addition, the embodiment of the present application also improves the model structure of the communication target identification model to make it more suitable for performing communication target classification tasks, thereby improving the communication target identification performance.

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] The present application embodiment first proposes a communication target identification method, see Figure 1 As shown, the method includes:

[0046] S101, extracting key signal components from a communication signal emitted by a communication target to be identified, wherein the key signal components include signal components reflecting the characteristics of the communication target.

[0047] Specifically, the communication target to be identified refers to a communication individual that transmits communication signals and whose identity needs to be identified, such as radar, navigation equipment, broadcasting equipment, and other equipment with signal transmission function.

[0048] After acquiring the communication signal transmitted by the communication target to be identified, the embodiment of the present application first analyzes the signal characteristics of the communication signal to identify characteristic components useful for determining the identity of the communication target, and then based on the analysis results of the signal characteristics, extracts the signal components useful for identifying the identity of the communication target from the communication signal, that is, extracts the signal components that embody the characteristics of the communication target, and obtains the key signal components.

[0049] Exemplarily, the embodiments of the present application use a signal focus mechanism to focus on a feature area useful for determining the identity of the communication target from the signal features of the communication signal emitted by the communication target to be identified, and then determine the corresponding key signal components based on the feature area.

[0050] S102: Perform feature extraction processing on the key signal components to obtain key signal features.

[0051] Specifically, after extracting the key signal components from the communication signal emitted by the communication target to be identified, the embodiment of the present application further performs feature extraction processing on the key signal components, such as performing feature extraction and feature fusion processing at different levels on the key signal components to obtain the key signal features corresponding to the key signal components.

[0052] Exemplarily, the key signal components mentioned above can be processed for feature extraction through a neural network model, such as through a convolutional neural network, so as to extract features at different levels and fuse features at different levels to obtain key signal features.

[0053] S103: Classify the key signal features to determine whether the communication target to be identified is a preset communication target.

[0054] Specifically, classification is performed based on the key signal feature to identify the identity of the communication target. In this embodiment, the above classification specifically classifies whether the key signal feature is a signal feature of a communication signal emitted by a preset communication target, thereby determining whether the communication target to be identified is a preset communication target.

[0055] Exemplarily, after the key signal components are feature extracted by a convolutional neural network, the extracted key signal features can be classified using a softmax layer to determine whether the key signal features are consistent with the signal features of the communication signal transmitted by the preset communication target, thereby determining whether the communication target to be identified is the preset communication target. If it is determined through the above classification that the key signal features are consistent with the signal features of the communication signal transmitted by the preset communication target, then the communication target to be identified can be determined to be the preset communication target, otherwise, it can be determined that the communication target to be identified is not the preset communication target.

[0056] From the above introduction, it can be seen that the communication target identification method proposed in the embodiment of the present application first extracts the key signal components that reflect the characteristics of the communication target from the communication signal emitted by the communication target to be identified, and then performs feature extraction and classification based on the key signal components to determine whether the communication target is a preset communication target. The above scheme can avoid the influence of interference signal components in the communication signal on the communication target identification, and only uses the key signal components that reflect the characteristics of the communication target to identify the communication target, which can improve the accuracy of communication target identification.

[0057] In another embodiment, extracting key signal components from a communication signal transmitted by a communication target to be identified can be achieved by executing the following steps A1-A3:

[0058] A1. Perform feature extraction processing on the communication signal emitted by the communication target to be identified to obtain signal features.

[0059] Specifically, before extracting features from the communication signal emitted by the communication target to be identified, the communication signal is preprocessed, such as denoising, filtering and normalizing the communication signal. This step aims to reduce noise and interference and ensure the clarity of the communication signal.

[0060] Then, feature extraction is performed on the preprocessed communication signal: feature extraction is performed on the preprocessed communication signal through Fourier transform, short-time Fourier transform (STFT) or other time-frequency analysis methods to generate time-frequency diagrams, spectrum diagrams and other images of the communication signal that can represent the characteristics of the signal in the time and frequency dimensions, providing basic data for the subsequent focus mechanism (a processing mechanism that focuses on important and useful signal feature components from signal features).

[0061] A2. Determine key features from the signal features by evaluating the importance of different feature components of the signal features.

[0062] Specifically, based on the signal features of the communication signal, the time-frequency diagram or feature diagram of the signal is analyzed, and the importance scores of the signal features in each time period or time window in the signal are calculated to determine the key feature area, that is, to obtain the key features in the signal features.

[0063] Exemplarily, the importance score of the signal features of each time period or time window can be determined by analyzing the proportion of the communication individual features contained in the signal features of each time period or time window. The greater the proportion of the communication individual features contained in the signal features of a certain time period or time window, the higher the importance score of the signal features of the time period or time window, and vice versa, the lower the importance score of the signal features of the time period or time window.

[0064] Alternatively, you can also train a feature scoring neural network model in advance, input the signal features of each time period or time window into the feature scoring neural network model, and you can obtain the importance score of the signal features of each time period or time window.

[0065] A3. Extracting key signal components from the communication signal based on the key features.

[0066] Specifically, after the key features are extracted from the signal features, based on the corresponding relationship between the signal features and the signal components, the key signal components corresponding to the key features can be extracted from the communication signal.

[0067] In other embodiments, after obtaining the above-mentioned key signal components, the key signal components may be further enhanced, such as amplifying the absorbed strength or feature significance of the key signal components, while suppressing or filtering out interference information.

[0068] In other embodiments, after obtaining the above key features, further analysis and feature extraction may be performed on the key features, such as performing time-frequency analysis, wavelet transform and other processing on the key features to extract more accurate signal features.

[0069] In other embodiments, a communication individual recognition model is pre-trained to recognize communication targets.

[0070] The key signal components extracted from the communication signal emitted by the communication target to be identified are input into a pre-trained communication individual identification model, so that the communication individual identification model performs feature extraction processing on the input key signal components to obtain key signal features, and classifies the key signal features to determine whether the communication target to be identified is a preset communication target.

[0071] The embodiments of the present application improve the structure and training process of the above-mentioned communication individual identification model, so that the communication individual identification model can achieve more accurate communication target identification.

[0072] First, for the training of the above-mentioned communication individual recognition model, the embodiment of the present application generates an enhanced signal based on the original communication signal, and then uses the communication signal in the enhanced signal set composed of the enhanced signal to perform communication individual recognition training on the communication individual recognition model.

[0073] The above-mentioned enhanced signal is obtained by adjusting at least one aspect of the time, frequency and phase of the original communication signal.

[0074] Specifically, after the original communication signal is collected, such as the communication signal transmitted by the target radar, the original communication signal is first preprocessed, such as filtering, denoising, normalization, etc., to ensure signal quality and signal consistency.

[0075] Then, at least one of the time, frequency and phase of the original communication signal is adjusted to obtain an enhanced signal.

[0076] Among them, adjusting the time of the original communication signal means shifting the original communication signal on the time axis to generate signals with different time delays. For example, each sampling point of the original communication signal is moved forward or backward by a certain time step to generate multiple delayed signal versions. Let the original communication signal be s(t), and the signal after the time delay processing of the signal is expressed as s(t+\Delta t), where \Delta t represents the time offset. The signal generated by time shift can help the model improve its ability to identify real targets when dealing with Doppler effects or dynamic targets.

[0077] Adjusting the frequency of the original communication signal refers to adjusting the frequency of the original communication signal to generate multiple frequency-shifted signals. For example, the signal can be frequency-shifted to simulate the frequency change caused by the target speed or other factors. A common method is to multiply the signal by a frequency shift factor, such as \exp(j2\pi f_{shift}t), to generate a frequency-shifted signal. Let the original communication signal be s(t), and the signal after frequency shift processing be s(t)\cdot\exp(j2\pi f_{shift}t), where f_{shift} represents the frequency shift amount. These frequency-shifted signals help enhance the model's recognition of frequency-variable targets and improve the ability to exclude false targets.

[0078] Adjusting the phase of the original communication signal means adjusting the phase of the original communication signal to generate multiple signals with different phases. The phase of the signal can be changed by multiplying the original communication signal by a phase factor \exp(j\theta_{shift}). Let the original signal be s(t), and the signal after phase adjustment be s(t)\cdot\exp(j\theta_{shift}), where \theta_{shift} represents the phase offset. These phase-adjusted signals can help the model better cope with phase interference caused by environmental reflection or scattering, thereby improving the positioning accuracy of the real target.

[0079] When actually generating the enhanced signal, any one or more of the time, frequency, and phase of the original communication signal may be adjusted to obtain the enhanced signal. For example, only the time of the original communication signal may be adjusted to obtain an enhanced signal, or only the frequency of the original communication signal may be adjusted to obtain an enhanced signal, or both the time and frequency of the original communication signal may be adjusted to obtain an enhanced signal.

[0080] After the enhanced signal is obtained through the above adjustment, the enhanced signal is further subjected to time-frequency transformation processing and / or wavelet transformation processing to generate more diverse enhanced signals.

[0081] Finally, an enhanced signal set is constructed using the enhanced signal obtained by the above adjustment and a signal obtained by performing time-frequency transformation processing and / or wavelet transformation processing on the enhanced signal.

[0082] Based on the above-mentioned enhanced signal set, the communication individual recognition model is trained for communication individual recognition. Specifically, the original communication signal is used as the communication signal emitted by the preset communication target, and then the signal in the above-mentioned enhanced signal set is input into the above-mentioned communication individual recognition model as the communication signal emitted by the communication target to be identified. The communication individual recognition model extracts features from the signals in the enhanced signal set, and finally performs feature classification to determine whether the enhanced signal is consistent with the original communication signal, and then determines whether the communication target to be identified is the preset communication target.

[0083] During the training process, the cross entropy loss function can be used to measure the difference between the model prediction results and the true labels, and the model parameters can be updated using an adaptive optimization algorithm.

[0084] In the above training process, the enhanced signal set is used to train the communication individual recognition model. The signal samples in the enhanced signal set increase the diversity of the training data and retain the core features of the communication target, so that the model can learn more change patterns and details during the training process, thereby enhancing the recognition performance and robustness of the model, effectively improving the recognition ability of real targets, reducing the misjudgment of false targets, and improving the overall recognition accuracy of the model.

[0085] The above-mentioned communication individual identification model can be constructed using a convolutional neural network.

[0086] Convolutional Neural Networks (CNN) is a deep learning model that can efficiently extract features and classify input data.

[0087] CNN consists of multiple convolutional layers, pooling layers, fully connected layers, etc. Each layer has some trainable parameters for extracting and processing the features of the input data. The convolutional layer is the core layer of CNN, which is used to extract features from the input data. The convolutional layer includes multiple convolution kernels, each of which can extract the features of a certain area in the input data. The convolution kernel performs a convolution operation on the input data to obtain a feature map. Each pixel in the feature map represents the features of a certain area in the input data.

[0088] The pooling layer is used to downsample the feature map and reduce its size. Commonly used pooling operations include maximum pooling and average pooling.

[0089] The fully connected layer is used to map the summarized features into the target output. Commonly used fully connected layers include the softmax layer and the sigmoid layer.

[0090] Training the convolutional neural network according to the training method introduced in the above embodiment of the present application can enable the convolutional neural network to more accurately extract features useful for identifying the identity of the communication target from the input communication signal, and then accurately identify whether the communication target is a preset communication target based on these features.

[0091] In another embodiment, the above-mentioned communication individual identification model is jointly constructed by a convolutional neural network and a support vector machine.

[0092] Among them, Support Vector Machine (SVM) is a common supervised learning algorithm that can be used to solve classification and regression problems. SVM maps input data into a high-dimensional space and then continuously updates the system. Due to changes in targets and scenarios, the system needs to use real-time feedback and adaptive learning algorithms to continuously update to improve recognition accuracy and speed. In a high-dimensional space, SVM constructs an optimal hyperplane to separate data of different categories. The goal of SVM is to maximize the interval between the hyperplane and data of different categories, so that the model has better generalization ability.

[0093] Since SVM has better classification processing performance than the fully connected layer of a convolutional neural network, the embodiment of the present application combines SVM with a convolutional neural network to construct a communication individual recognition model.

[0094] like Figure 2 As shown, in this embodiment, the communication individual identification model is composed of a convolutional layer, a pooling layer and a support vector machine SVM of a convolutional neural network in series, that is, after the data is input into the communication individual identification model, the convolutional layer and the pooling layer perform feature extraction and processing, and then the support vector machine SVM classifies the features to obtain a classification result.

[0095] Compared with conventional convolutional neural networks, the communication individual identification model proposed in the embodiment of the present application optimizes the model structure, so that the model has better feature classification performance. The communication individual identification model is used to identify communication targets, and more accurate identification results can be obtained.

[0096] In addition, through the above-mentioned model training scheme, the enhanced signal set is used to perform communication individual recognition training on the communication individual recognition model proposed in the embodiment of the present application, which can further improve the recognition accuracy of the communication individual recognition model.

[0097] Corresponding to the above communication target identification method, the present application embodiment also provides a communication target identification device, see Figure 3 As shown, the device comprises:

[0098] The signal analysis unit 100 is used to extract key signal components from the communication signal transmitted by the communication target to be identified, wherein the key signal components include signal components that reflect the characteristics of the communication target;

[0099] The identification processing unit 110 is used to perform feature extraction processing on the key signal components to obtain key signal features; classify the key signal features to determine whether the communication target is a preset communication target.

[0100] In some implementations, the signal analysis unit 100 extracts key signal components from the communication signal transmitted by the communication target to be identified, including:

[0101] Perform feature extraction processing on the communication signal emitted by the communication target to be identified to obtain signal features;

[0102] Determining key features from the signal features by evaluating the importance of different feature components of the signal features;

[0103] Based on the key features, key signal components are extracted from the communication signal.

[0104] In some implementations, the signal analysis unit 100 is further configured to:

[0105] The key signal components are subjected to signal enhancement processing.

[0106] In some implementations, the identification processing unit 110 performs feature extraction processing on the key signal components to obtain key signal features; and classifies the key signal features to determine whether the communication target to be identified is a preset communication target, including:

[0107] Inputting the key signal component into a pre-trained communication individual identification model so that the communication individual identification model performs feature extraction processing on the key signal component to obtain key signal features, and classifying the key signal features to determine whether the communication target to be identified is a preset communication target;

[0108] The communication individual identification model is obtained by performing communication individual identification training on the communication signals in the enhanced signal set, and the enhanced signal set includes enhanced signals generated based on the original communication signals.

[0109] In some implementations, the enhanced signal set is constructed by the following processing:

[0110] Adjust at least one of the time, frequency and phase of the original communication signal to obtain an enhanced signal;

[0111] Performing time-frequency transform processing and / or wavelet transform processing on the enhanced signal;

[0112] An enhanced signal set is constructed by using the enhanced signal and a signal obtained by performing time-frequency transformation processing and / or wavelet transformation processing on the enhanced signal.

[0113] In some implementations, the communication individual identification model is constructed based on a convolutional neural network and a support vector machine.

[0114] In some implementations, the communication individual identification model is constructed by connecting a convolutional layer, a pooling layer, and a support vector machine of a convolutional neural network in series.

[0115] The communication target identification device provided in this embodiment belongs to the same application concept as the communication target identification method provided in the above embodiments of this application, and can execute the communication target identification method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of the execution method. For the technical details not described in detail in this embodiment, please refer to the specific processing content of the communication target identification method provided in the above embodiments of this application, which will not be repeated here.

[0116] The functions implemented by the above signal analysis unit 100 and the identification processing unit 110 may be implemented by the same or different processors, respectively, and the embodiments of the present application are not limited thereto.

[0117] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by the configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the remaining part is implemented in the form of hardware circuits.

[0118] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0119] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0120] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0121] Another embodiment of the present application also provides a communication target identification device, see Figure 4 As shown, the device includes:

[0122] Memory 200 and processor 210;

[0123] The memory 200 is connected to the processor 210 and is used to store programs;

[0124] The processor 210 is used to implement the communication target identification method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0125] Specifically, the communication target identification device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0126] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0127] A bus may include a pathway that transfers information between components of a computer system.

[0128] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0129] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0130] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0131] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0132] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0133] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0134] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement each step of any communication target identification method provided in the above embodiments of the present application.

[0135] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the communication target identification method described in any of the above-mentioned embodiments of this specification.

[0136] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0137] In addition, an embodiment of the present application may also be a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the communication target identification method described in any of the above embodiments of this specification.

[0138] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0139] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0140] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0141] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0143] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0145] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0146] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0147] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0148] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A communication target identification method, characterized in that: include: Extracting key signal components from the communication signal transmitted by the communication target to be identified, wherein the key signal components include signal components reflecting the characteristics of the communication target; Performing feature extraction processing on the key signal components to obtain key signal features; The key signal features are classified to determine whether the communication target to be identified is a preset communication target.

2. The method according to claim 1, characterized in that Extract key signal components from the communication signal emitted by the communication target to be identified, including: Perform feature extraction processing on the communication signal emitted by the communication target to be identified to obtain signal features; Determining key features from the signal features by evaluating the importance of different feature components of the signal features; Based on the key features, key signal components are extracted from the communication signal.

3. The method according to claim 2, characterized in that The method further comprises: The key signal components are subjected to signal enhancement processing.

4. The method according to any one of claims 1 to 3, characterized in that Performing feature extraction processing on the key signal components to obtain key signal features; and classifying the key signal features to determine whether the communication target to be identified is a preset communication target, including: Inputting the key signal component into a pre-trained communication individual identification model so that the communication individual identification model performs feature extraction processing on the key signal component to obtain key signal features, and classifying the key signal features to determine whether the communication target to be identified is a preset communication target; The communication individual identification model is obtained by performing communication individual identification training on the communication signals in the enhanced signal set, and the enhanced signal set includes enhanced signals generated based on the original communication signals.

5. The method according to claim 4, characterized in that The enhanced signal set is constructed by the following processing: Adjust at least one of the time, frequency and phase of the original communication signal to obtain an enhanced signal; Performing time-frequency transform processing and / or wavelet transform processing on the enhanced signal; An enhanced signal set is constructed by using the enhanced signal and a signal obtained by performing time-frequency transformation processing and / or wavelet transformation processing on the enhanced signal.

6. The method according to claim 4, characterized in that The communication individual identification model is jointly constructed based on a convolutional neural network and a support vector machine.

7. The method according to claim 6, characterized in that The communication individual identification model is constructed by connecting the convolution layer, the pooling layer and the support vector machine of the convolutional neural network in series.

8. A communication target identification device, characterized in that: include: A signal analysis unit, configured to extract key signal components from a communication signal transmitted by a communication target to be identified, wherein the key signal components include signal components that reflect the characteristics of the communication target; The identification processing unit is used to perform feature extraction processing on the key signal components to obtain key signal features; classify the key signal features to determine whether the communication target is a preset communication target.

9. A communication target identification device, characterized in that: including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the communication target identification method according to any one of claims 1 to 7 by running the program in the memory.

10. A computer program product, characterized in that The method comprises computer program instructions, which, when executed by a processor, enable the processor to implement the communication target identification method according to any one of claims 1 to 7.

Images