Radio signal identification method, device, equipment, storage medium and program product

Abstract

The invention provides a radio signal identification method, device and equipment, a storage medium and a program product, which are applied to the technical field of signal processing. The method comprises the following steps: acquiring a hybrid radio signal to be detected; inputting the mixed radio signal into a high and low signal-to-noise ratio discrimination network for high and low signal-to-noise ratio determination so as to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; inputting the high-signal-to-noise-ratio signal into a high-signal-to-noise-ratio signal identification network to determine the signal type of the high-signal-to-noise-ratio signal; and inputting the low-signal-to-noise-ratio signal into a low-signal-to-noise-ratio signal identification network to determine the signal type of the low-signal-to-noise-ratio signal.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a radio signal recognition method, device, equipment, storage medium and program product. Background Art

[0002] With the development of deep learning technology, many researchers have begun to focus on the application of hybrid radio classification and recognition technology in deep learning technology.

[0003] In the prior art, since multi-dimensional information is not fully utilized, the mixed radio classification recognition method can only recognize signals of known mixed types, that is, it can only perform effective recognition in low signal-to-noise ratio signals or only in high signal-to-noise ratio signals. Summary of the invention

[0004] The present invention provides a radio signal recognition method, device, equipment, storage medium and program product, which are used to solve the problem that the mixed radio classification recognition method in the prior art can only recognize signals of known mixed types.

[0005] The present invention provides a radio signal identification method, comprising: obtaining a mixed radio signal to be detected; inputting the mixed radio signal into a high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; inputting the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; and inputting the low signal-to-noise ratio signal into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

[0006] According to a radio signal recognition method provided by the present invention, the signal recognition model includes the high and low signal-to-noise ratio discrimination network, the high signal-to-noise ratio signal recognition network and the low signal-to-noise ratio signal recognition network; before obtaining the mixed radio signal to be detected, the method further includes: according to the formula: Adaptively adjust the signal recognition model; wherein, is the parameter of the output result of the high signal-to-noise ratio signal recognition network, is the parameter of the output of the low signal-to-noise ratio signal recognition network, , in each training cycle, by dynamically adjusting and The loss value of the signal recognition model is reduced until a result that satisfies a preset condition is reached or a preset condition for early termination is met; It is the classification result of high signal-to-noise ratio signal through high signal-to-noise ratio signal recognition network. It is the classification result of low signal-to-noise ratio signal through low signal-to-noise ratio signal recognition network.

[0007] According to a radio signal recognition method provided by the present invention, the high and low signal-to-noise ratio discrimination network includes: an Input layer, a Reshape layer, a Flatten layer, three Dense layers, and an Activation layer.

[0008] According to a radio signal recognition method provided by the present invention, the high signal-to-noise ratio signal recognition network includes: a Reshape layer, a Residual_Stack layer, a MaxPooling2D layer, a Residual_Stack layer, a Flatten layer, a Dense layer, a Dropout layer, a Dense layer, a Dropout layer, a Dense layer, and an Activation layer.

[0009] According to a radio signal recognition method provided by the present invention, the low signal-to-noise ratio signal recognition network includes: a Reshape layer, a Transformer Block layer, a GlobalAveragePooling1D layer, a BatchNormalization layer, an Alpha Dropout layer, a Dense layer, an Alpha Dropout layer, a Dense layer, and an Alpha Dropout layer.

[0010] The present invention also provides a radio signal identification device, comprising the following modules: an acquisition module and a processing module; the acquisition module is used to acquire a mixed radio signal to be detected; the processing module is used to input the mixed radio signal into a high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; the high signal-to-noise ratio signal is input into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; the low signal-to-noise ratio signal is input into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

[0011] According to a radio signal recognition device provided by the present invention, the signal recognition model includes the high and low signal-to-noise ratio discrimination network, the high signal-to-noise ratio signal recognition network and the low signal-to-noise ratio signal recognition network; the processing module is used to calculate the signal according to the formula: Adaptively adjust the signal recognition model; wherein, is the parameter of the output result of the high signal-to-noise ratio signal recognition network, is the parameter of the output of the low signal-to-noise ratio signal recognition network, , in each training cycle, by dynamically adjusting and The loss value of the signal recognition model is reduced until a result that satisfies a preset condition is reached or a preset condition for early termination is met; It is the classification result of high signal-to-noise ratio signal through high signal-to-noise ratio signal recognition network. It is the classification result of low signal-to-noise ratio signal through low signal-to-noise ratio signal recognition network.

[0012] According to a radio signal recognition device provided by the present invention, the high and low signal-to-noise ratio discrimination network includes: an Input layer, a Reshape layer, a Flatten layer, three Dense layers, and an Activation layer.

[0013] According to a radio signal recognition device provided by the present invention, the high signal-to-noise ratio signal recognition network includes: a Reshape layer, a Residual_Stack layer, a MaxPooling2D layer, a Residual_Stack layer, a Flatten layer, a Dense layer, a Dropout layer, a Dense layer, a Dropout layer, a Dense layer, and an Activation layer.

[0014] According to a radio signal recognition device provided by the present invention, the low signal-to-noise ratio signal recognition network includes: a Reshape layer, a Transformer Block layer, a GlobalAveragePooling1D layer, a BatchNormalization layer, an Alpha Dropout layer, a Dense layer, an Alpha Dropout layer, a Dense layer, and an Alpha Dropout layer.

[0015] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the radio signal recognition methods described above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the radio signal identification method described in any one of the above methods is implemented.

[0017] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned radio signal identification methods.

[0018] The radio signal identification method, device, equipment, storage medium and program product provided by the present invention can obtain a mixed radio signal to be detected; input the mixed radio signal into a high-low signal-to-noise ratio discrimination network to perform high-low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; input the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; input the low signal-to-noise ratio signal into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal. Through this scheme, since the mixed radio signal can be input into the high-low signal-to-noise ratio discrimination network to perform high-low signal-to-noise ratio judgment, and the signal type is respectively identified after determining the high signal-to-noise ratio signal and the low signal-to-noise ratio signal, the multi-dimensional information of the mixed radio signal can be fully utilized, thereby realizing the identification of any mixed type signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is one of the flow charts of the radio signal identification method provided by the present invention; Figure 2 This is the second flow chart of the radio signal identification method provided by the present invention; Figure 3 It is a structural schematic diagram of the radio signal identification device provided by the present invention; Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0022] It should be noted that, in this article, the terms "comprises", "includes" 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 includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved.

[0023] The embodiments of the present application describe some exemplary embodiments for the purpose of explanation. It should be understood that the present application can be implemented in other ways that are not specifically shown in the drawings.

[0024] like Figure 1 As shown, an embodiment of the present application provides a signal recognition model, including a high and low signal-to-noise ratio discrimination network 110 , a high signal-to-noise ratio signal recognition network 120 , and a low signal-to-noise ratio signal recognition network 130 .

[0025] The high and low signal-to-noise ratio discrimination network 110 may be a fuzzy neural network (FNN) for receiving a mixed radio signal, distinguishing a low signal-to-noise ratio signal from a high signal-to-noise ratio signal in the received mixed radio signal, and sending the high signal-to-noise ratio signal to the high signal-to-noise ratio signal recognition network 120 and sending the low signal-to-noise ratio signal to the low signal-to-noise ratio signal recognition network 130.

[0026] The high signal-to-noise ratio signal recognition network 120 may be a Ti-CNN network, which is used to receive the high signal-to-noise ratio signal sent by the FNN and identify the signal type of the high signal-to-noise ratio signal.

[0027] The low signal-to-noise ratio signal identification network 130 may be an L-Transformer network, which is used to receive the low signal-to-noise ratio signal sent by the FNN and identify the signal type of the low signal-to-noise ratio signal.

[0028] Optionally, the radio signal recognition device can first train the high and low signal-to-noise ratio discrimination network 110, and then train the high signal-to-noise ratio signal recognition network 120 and the low signal-to-noise ratio signal recognition network 130 respectively, and then combine the high and low signal-to-noise ratio discrimination network FNN, the high signal-to-noise ratio signal recognition network Ti-CNN and the low signal-to-noise ratio signal recognition network L-Transformer to form the FCT-Former network, that is, the signal recognition model.

[0029] Optionally, the radio signal identification device may be based on the formula: Adaptively adjust the signal recognition model; wherein, is the parameter of the output result of the high signal-to-noise ratio signal recognition network, is the parameter of the output of the low signal-to-noise ratio signal recognition network, ; It is the classification result of high signal-to-noise ratio signal through high signal-to-noise ratio signal recognition network. It is the classification result of low signal-to-noise ratio signal through low signal-to-noise ratio signal recognition network.

[0030] Specifically, in each training cycle, the radio signal recognition device can dynamically adjust and The loss value of the signal recognition model is reduced until a result that satisfies a preset condition is reached or a preset condition for early termination is met.

[0031] It should be noted that in the training stage of the signal recognition model, the radio signal recognition device can be trained using the RadioML2018.01A data set, which includes 24 signal types: 32PSK, 16APSK, 32QAM, FM, GMSK, 32APSK, OQPSK, 8ASK, BPSK, 8PSK, AM-SSB-SC, 4ASK, 16PSK, 64APSK, 128QAM, 128APSK, AM-DSB-SC, AM-SSB-WC, 64QAM, QPSK, 256QAM, AM-DSB-WC, OOK, and 6QAM.

[0032] like Figure 2 As shown, the embodiment of the present application provides a radio signal recognition method, which can be applied to a radio signal recognition device. The radio signal recognition method may include S201-S203: S201. A radio signal identification device obtains a mixed radio signal to be detected.

[0033] Optionally, the signal types in the above-mentioned mixed radio signal may include one or more of 32PSK, 16APSK, 32QAM, FM, GMSK, 32APSK, OQPSK, 8ASK, BPSK, 8PSK, AM-SSB-SC, 4ASK, 16PSK, 64APSK, 128QAM, 128APSK, AM-DSB-SC, AM-SSB-WC, 64QAM, QPSK, 256QAM, AM-DSB-WC, OOK, and 6QAM.

[0034] S202: The radio signal identification device inputs the mixed radio signal into a high and low signal-to-noise ratio judgment network to perform high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal.

[0035] Optionally, the high and low signal-to-noise ratio discrimination network FNN includes 279042 parameters, an Input layer, a Reshape layer, a Flatten layer, three Dense layers, and an Activation layer. Its specific network structure is shown in Table 1: Table 1

[0036] Optionally, the radio signal recognition device can input the above-mentioned mixed radio signal into the input interface of the signal recognition model, and the high and low signal-to-noise ratio discrimination network FNN can determine whether the mixed radio signal is a low signal-to-noise ratio signal or a high signal-to-noise ratio signal, and then send the high signal-to-noise ratio signal to the high signal-to-noise ratio signal recognition network Ti-CNN, and send the low signal-to-noise ratio signal to the low signal-to-noise ratio signal recognition network L-Transformer.

[0037] S203: The radio signal identification device inputs the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal.

[0038] Specifically, the high signal-to-noise ratio signal recognition network Ti-CNN is used to receive the high signal-to-noise ratio signal sent by the FNN and identify the high signal-to-noise ratio signal type through parameter training.

[0039] Optionally, the high signal-to-noise ratio signal recognition network Ti-CNN includes a Reshape layer, a Residual_Stack layer, a MaxPooling2D layer, a Residual_Stack layer, a Flatten layer, a Dense layer, a Dropout layer, a Dense layer, a Dropout layer, a Dense layer, and an Activation layer.

[0040] S204: The radio signal identification device inputs the low signal-to-noise ratio signal into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

[0041] Specifically, the low signal-to-noise ratio signal recognition network L-Transformer is used to receive the low signal-to-noise ratio signal sent by the FNN and identify the type of the low signal-to-noise ratio signal through parameter training.

[0042] Optionally, the low signal-to-noise ratio signal recognition network L-Transformer includes a Reshape layer, a Transformer Block layer, a GlobalAveragePooling1D layer, a Batch Normalization layer, an Alpha Dropout layer, a Dense layer, an Alpha Dropout layer, a Dense layer, and an AlphaDropout layer.

[0043] By training and experimentally comparing the signal recognition model the FCT-Former on the RadioML2018.01A dataset, it was found that the FCT-Former had the highest overall accuracy compared to Ti-CNN and L-Transformer.

[0044] When the signal-to-noise ratio (SNR) is less than -6, the overall accuracy of The FCT-Former is close to the overall accuracy of L-Transformer but better than the overall accuracy of Ti-CNN algorithm; When -6≤SNR≤12, the overall accuracy of the FCT-Former algorithm is better than that of the Ti-CNN network and the L-Transformer network; When SNR>12, the overall accuracy of the FCT-Former algorithm is similar to that of the Ti-CNN network but better than that of the L-Transformer network.

[0045] In particular, when the signal-to-noise ratio is 0dB, the overall accuracy of The FCT-Former algorithm is improved by nearly 17%, and when the signal-to-noise ratio is 10dB, the overall accuracy of The FCT-Former algorithm reaches 95.97%. Therefore, The FCT-Former algorithm outperforms the independent Ti-CNN network and L-Transformer network.

[0046] In the embodiment of the present application, since the mixed radio signal can be input into the high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment, and the signal type is identified after the high signal-to-noise ratio signal and the low signal-to-noise ratio signal are determined, the multi-dimensional information of the mixed radio signal can be fully utilized, thereby realizing the identification of any mixed type of signal.

[0047] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0048] The radio signal recognition method provided in the embodiment of the present application can be executed by a radio signal recognition device or a control module for radio signal recognition in the radio signal recognition device. The radio signal recognition device provided in the embodiment of the present application is described by taking the radio signal recognition device executing the radio signal recognition method as an example.

[0049] It should be noted that the embodiment of the present application can divide the functional modules of the radio signal identification device according to the above method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0050] like Figure 3 As shown, an embodiment of the present application provides a radio signal identification device 300. The radio signal identification device 300 includes: an acquisition module 301 and a processing module 302. The acquisition module 301 is used to acquire a mixed radio signal to be detected; the processing module 302 is used to input the mixed radio signal into a high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; input the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; input the low signal-to-noise ratio signal into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

[0051] Optionally, the signal recognition model includes the high and low signal-to-noise ratio discrimination network, the high signal-to-noise ratio signal recognition network and the low signal-to-noise ratio signal recognition network; the processing module 302 is used to calculate the signal according to the formula: Adaptively adjust the signal recognition model; wherein, is the parameter of the output result of the high signal-to-noise ratio signal recognition network, is the parameter of the output of the low signal-to-noise ratio signal recognition network, ; In each training cycle, by dynamically adjusting and The loss value of the signal recognition model is reduced until a result that satisfies a preset condition is reached or a preset condition for early termination is met; It is the classification result of high signal-to-noise ratio signal through high signal-to-noise ratio signal recognition network. It is the classification result of low signal-to-noise ratio signal through low signal-to-noise ratio signal recognition network.

[0052] Optionally, the high and low signal-to-noise ratio discrimination network includes: an Input layer, a Reshape layer, a Flatten layer, three Dense layers, and an Activation layer.

[0053] Optionally, the high signal-to-noise ratio signal recognition network includes: a Reshape layer, a Residual_Stack layer, a MaxPooling2D layer, a Residual_Stack layer, a Flatten layer, a Dense layer, a Dropout layer, a Dense layer, a Dropout layer, a Dense layer, and an Activation layer.

[0054] Optionally, the low signal-to-noise ratio signal recognition network includes: a Reshape layer, a TransformerBlock layer, a GlobalAveragePooling1D layer, a Batch Normalization layer, an AlphaDropout layer, a Dense layer, an Alpha Dropout layer, a Dense layer, and an Alpha Dropout layer.

[0055] In the embodiment of the present application, since the mixed radio signal can be input into the high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment, and the signal type is identified after the high signal-to-noise ratio signal and the low signal-to-noise ratio signal are determined, the multi-dimensional information of the mixed radio signal can be fully utilized, thereby realizing the identification of any mixed type of signal.

[0056] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the radio signal identification method, which includes: obtaining a mixed radio signal to be detected; inputting the mixed radio signal into a high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; inputting the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; inputting the low signal-to-noise ratio signal into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

[0057] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0058] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the radio signal identification method provided by the above methods, which includes: obtaining a mixed radio signal to be detected; inputting the mixed radio signal into a high and low signal-to-noise ratio discrimination network for high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; inputting the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; inputting the low signal-to-noise ratio signal into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

[0059] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the radio signal identification method provided by the above-mentioned methods, the method comprising: obtaining a mixed radio signal to be detected; inputting the mixed radio signal into a high and low signal-to-noise ratio discrimination network for high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; inputting the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; inputting the low signal-to-noise ratio signal into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

[0060] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0061] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A radio signal recognition method, characterized in that: include: Acquire a mixed radio signal to be detected; Inputting the mixed radio signal into a high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; Inputting the high signal-to-noise ratio signal into a high signal-to-noise ratio signal identification network to determine the signal type of the high signal-to-noise ratio signal; The low signal-to-noise ratio signal is input into a low signal-to-noise ratio signal identification network to determine the signal type of the low signal-to-noise ratio signal.

2. The radio signal recognition method according to claim 1, characterized in that: The signal recognition model includes the high and low signal-to-noise ratio discrimination network, the high signal-to-noise ratio signal recognition network and the low signal-to-noise ratio signal recognition network; before acquiring the mixed radio signal to be detected, the method further includes: According to the formula: Adaptively adjusting the signal recognition model; in, is the parameter of the output result of the high signal-to-noise ratio signal recognition network, is the parameter of the output of the low signal-to-noise ratio signal recognition network, ; In each training cycle, by dynamically adjusting and The loss value of the signal recognition model is reduced until a result that satisfies a preset condition is reached or a preset condition for early termination is met; It is the classification result of high signal-to-noise ratio signal through high signal-to-noise ratio signal recognition network. It is the classification result of low signal-to-noise ratio signal through low signal-to-noise ratio signal recognition network.

3. The radio signal recognition method according to claim 1 or 2, characterized in that: The high and low signal-to-noise ratio discrimination network includes: an Input layer, a Reshape layer, a Flatten layer, three Dense layers, and an Activation layer.

4. The radio signal recognition method according to claim 1 or 2, characterized in that: The high signal-to-noise ratio signal recognition network includes: a Reshape layer, a Residual_Stack layer, a MaxPooling2D layer, a Residual_Stack layer, a Flatten layer, a Dense layer, a Dropout layer, a Dense layer, a Dropout layer, a Dense layer, and an Activation layer.

5. The radio signal recognition method according to claim 1 or 2, characterized in that: The low signal-to-noise ratio signal recognition network includes: a Reshape layer, a Transformer Block layer, a GlobalAveragePooling1D layer, a Batch Normalization layer, an Alpha Dropout layer, a Dense layer, an AlphaDropout layer, a Dense layer, and an Alpha Dropout layer.

6. A radio signal recognition device, characterized in that: include: Acquisition module and processing module; The acquisition module is used to acquire the mixed radio signal to be detected; The processing module is used to input the mixed radio signal into a high and low signal-to-noise ratio discrimination network to perform high and low signal-to-noise ratio judgment to determine a high signal-to-noise ratio signal and a low signal-to-noise ratio signal; input the high signal-to-noise ratio signal into a high signal-to-noise ratio signal recognition network to determine the signal type of the high signal-to-noise ratio signal; and input the low signal-to-noise ratio signal into a low signal-to-noise ratio signal recognition network to determine the signal type of the low signal-to-noise ratio signal.

7. The radio signal recognition device according to claim 6, characterized in that: The signal recognition model includes the high and low signal-to-noise ratio discrimination network, the high signal-to-noise ratio signal recognition network and the low signal-to-noise ratio signal recognition network; the processing module is used to, according to the formula: Adaptively adjust the signal recognition model; wherein, is the parameter of the output result of the high signal-to-noise ratio signal recognition network, is the parameter of the output of the low signal-to-noise ratio signal recognition network, , in each training cycle, by dynamically adjusting and The loss value of the signal recognition model is reduced until a result that satisfies a preset condition is reached or a preset condition for early termination is met; It is the classification result of high signal-to-noise ratio signal through high signal-to-noise ratio signal recognition network. It is the classification result of low signal-to-noise ratio signal through low signal-to-noise ratio signal recognition network.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the radio signal recognition method according to any one of claims 1 to 5 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the radio signal recognition method according to any one of claims 1 to 5 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the radio signal recognition method according to any one of claims 1 to 5 is implemented.

Images