Blind recognition method, apparatus, and system for signal modulation mode

Abstract

The present application relates to a blind recognition method, apparatus, and system for a signal modulation mode. The method comprises: establishing a target recognition model, the target recognition model being used for recognizing a signal modulation mode corresponding to a received signal; when a signal is received, extracting each instantaneous feature of the signal to obtain an instantaneous feature set corresponding to the signal; for each instantaneous feature in the instantaneous feature set, on the basis of the instantaneous feature, determining an instantaneous feature statistic corresponding to the signal to obtain an instantaneous feature statistic set corresponding to the signal; and inputting the instantaneous feature statistic set into the target recognition model, to enable the target recognition model to output a target signal modulation mode corresponding to the signal. The present application improves the accuracy and reliability of performing blind recognition on a signal modulation mode corresponding to a signal.

Description

Blind identification method, device and system for signal modulation mode Technical Field

[0001] This application relates to the field of signal processing technology, and in particular to a blind identification method, apparatus and system for signal modulation modes. Background Technology

[0002] In traditional communication systems, when a signal is received, the receiver knows the signal modulation scheme and can demodulate it to recover the original information. However, with the rapid development of wireless communication technology and the widespread application of various wireless communication systems, in many practical scenarios, the receiver is unaware of the modulation scheme of the received signal. Therefore, the receiver needs to analyze the received signal to achieve blind identification of the modulation scheme, and then use the identified modulation scheme to demodulate the received signal.

[0003] However, when the receiving end performs blind identification of the modulation scheme of the received signal, it mostly does so by analyzing the time-domain or frequency-domain characteristics of the received signal. But the above-mentioned blind identification methods, which rely on a single signal feature, result in inaccurate blind identification and make it difficult to meet the requirements of high reliability. Summary of the Invention

[0004] This application provides a blind identification method, apparatus, and system for signal modulation modes to solve the problems of inaccurate identification and low reliability in the prior art for blind identification of received signals.

[0005] In a first aspect, this application provides a blind identification method for signal modulation schemes, including:

[0006] A target recognition model is established, which is used to identify the signal modulation mode corresponding to the received signal;

[0007] Upon receiving a signal, each instantaneous feature of the signal is extracted to obtain the instantaneous feature set corresponding to the signal;

[0008] For each instantaneous feature in the instantaneous feature set, the instantaneous feature statistics corresponding to the signal are determined based on the instantaneous feature to obtain the instantaneous feature statistics set corresponding to the signal;

[0009] The instantaneous feature statistics set is input into the target recognition model so that the target recognition model outputs the target signal modulation mode corresponding to the signal.

[0010] In an optional implementation, when the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal include a first feature statistic, the first feature statistic representing the maximum value of the instantaneous amplitude spectral density;

[0011] The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes:

[0012] When the instantaneous feature set includes the instantaneous amplitude, the number of samples corresponding to the signal is obtained;

[0013] The instantaneous amplitude is subjected to zero-center normalization to obtain the processed instantaneous amplitude;

[0014] The processed instantaneous amplitude and the number of samples are input into the first feature determination formula to obtain the first feature statistic. The first feature determination formula includes:

[0015] γ max =max|DFT(A) cn (n))| 2 / N

[0016] In the above formula, γ max The first characteristic statistic is represented by 'max', the maximum value is represented by 'DFT()', and A represents the Discrete Fourier Transform. cn (n) represents the processed instantaneous amplitude, and N represents the number of samples.

[0017] In an optional implementation, when the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal further include a second feature statistic, a third feature statistic, and a fourth feature statistic. The second feature statistic represents the standard deviation of the instantaneous amplitude of the zero-center normalized non-weak signal segment, the third feature statistic represents the standard deviation of the absolute value of the zero-center normalized instantaneous amplitude, and the fourth feature statistic represents the compactness of the zero-center normalized instantaneous amplitude.

[0018] The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes:

[0019] Determine the first number belonging to the non-weak signal from the signals of the specified number of samples;

[0020] The first number and the processed instantaneous amplitude are input into the second feature determination formula to obtain the second feature statistic;

[0021] The number of samples and the processed instantaneous amplitude are input into the third feature determination formula to obtain the third feature statistic;

[0022] The processed instantaneous amplitude is input into the fourth feature determination formula to obtain the fourth feature statistic; wherein,

[0023] The formula for determining the second feature includes:

[0024] The formula for determining the third feature includes:

[0025] The formula for determining the fourth feature includes:

[0026] In the above formula, σ da A represents the second characteristic statistic. cn (n) represents the processed instantaneous amplitude, C represents the first number, and σ aa This represents the third characteristic statistic, where N represents the number of samples. A represents the fourth characteristic statistic. cn (n)>at indicates a non-weak signal, at represents the threshold level, and E() represents the Gaussian density function.

[0027] In an optional implementation, when the instantaneous feature set includes an instantaneous phase, the instantaneous feature statistics corresponding to the signal include a fifth feature statistic and a sixth feature statistic. The fifth feature statistic characterizes the standard deviation of the instantaneous phase nonlinear component of the zero-center non-weak signal segment, and the sixth feature statistic characterizes the standard deviation of the absolute value of the instantaneous phase nonlinear component of the zero-center non-weak signal segment.

[0028] The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes:

[0029] When the instantaneous feature set includes the instantaneous phase, the instantaneous phase is subjected to zero-center processing to obtain the nonlinear component of the instantaneous phase;

[0030] The first number and the nonlinear component are respectively input into the fifth feature determination formula and the sixth feature determination formula to obtain the fifth feature statistic and the sixth feature statistic; wherein,

[0031] The formula for determining the fifth feature includes:

[0032] The formula for determining the sixth feature includes:

[0033] In the above formula, σ dp φ represents the fifth characteristic statistic. NL (n) represents the nonlinear component, C represents the first number, and σ ap A represents the sixth characteristic statistic.cn (n)>at indicates a non-weak signal, and at indicates the threshold level.

[0034] In an optional implementation, when the instantaneous feature set includes instantaneous frequencies, the instantaneous feature statistics corresponding to the signal include a seventh feature statistic and an eighth feature statistic. The seventh feature statistic characterizes the standard deviation of the absolute value of the instantaneous frequency of the zero-center normalized non-weak signal segment, and the eighth feature statistic characterizes the compactness of the zero-center normalized instantaneous frequency.

[0035] The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes:

[0036] When the instantaneous feature set includes the instantaneous frequency, the instantaneous frequency is processed to obtain a first instantaneous frequency and a second instantaneous frequency. The first instantaneous frequency represents the instantaneous frequency of the zero-center normalized non-weak signal segment, and the second instantaneous frequency represents the zero-center normalized instantaneous frequency.

[0037] The first number and the first instantaneous frequency are input into the formula for determining the seventh feature to obtain the seventh feature statistic;

[0038] The second instantaneous frequency is input into the formula for determining the eighth feature to obtain the eighth feature statistic; wherein,

[0039] The formula for determining the seventh feature includes:

[0040] The formula for determining the eighth feature includes:

[0041] In the above formula, σ af This represents the seventh characteristic statistic, where C represents the first number. A represents the eighth characteristic statistic. cn (n)>at indicates a non-weak signal, at represents the threshold level, E() represents the Gaussian density function, and f N (n) represents the frequency at the first instant, f cn (n) represents the second instantaneous frequency.

[0042] In an optional implementation, establishing the target recognition model includes:

[0043] Obtain a first preset signal set and a preset signal modulation scheme corresponding to each first preset signal in the first preset signal set;

[0044] Preset instantaneous features are extracted from each of the first preset signals in the first preset signal set to obtain a preset instantaneous feature set corresponding to each preset signal;

[0045] For each preset instantaneous feature in the preset instantaneous feature set corresponding to each first preset signal in the first preset signal set, a preset instantaneous feature statistic corresponding to the preset signal is determined based on the preset instantaneous feature, so as to obtain a preset instantaneous feature statistic set corresponding to each first preset signal in the first preset signal set;

[0046] The preset instantaneous feature statistics set corresponding to each of the first preset signals in the first preset signal set is associated with the preset signal modulation mode corresponding to each of the first preset signals in the first preset signal set to obtain a first association relationship.

[0047] Using the first association relationship, a preset machine learning model is trained to establish the target recognition model.

[0048] In an optional implementation, the step of extracting various instantaneous features of the signal upon receiving the signal to obtain an instantaneous feature set corresponding to the signal includes:

[0049] Determine whether the received signal is in the second preset signal set, wherein the second preset signal in the second preset signal set represents a preset signal with a known signal modulation method;

[0050] When the received signal is not in the second preset signal set, each instantaneous feature of the signal is extracted to obtain the instantaneous feature set corresponding to the signal.

[0051] In an optional implementation, the method further includes:

[0052] A decision tree model is established, which is used to identify the signal modulation mode corresponding to the received signal;

[0053] Before performing the step of extracting each instantaneous feature of the signal to obtain the instantaneous feature set corresponding to the signal, the method further includes:

[0054] Upon receiving the signal, it is determined whether the received signal is in the third preset signal set. The third preset signal in the third preset signal set can be used to identify the preset signal of the signal modulation mode using the decision tree model.

[0055] When the received signal is in the third preset signal set, the decision tree model is used to identify the target signal modulation mode corresponding to the signal;

[0056] When the received signal is not in the third preset signal set, the step of extracting each instantaneous feature of the signal to obtain the instantaneous feature set corresponding to the signal is performed.

[0057] Secondly, this application provides a blind identification device for a signal modulation method, comprising:

[0058] A module is established to build a target recognition model, which is used to identify the signal modulation mode corresponding to the received signal;

[0059] An extraction module is used to extract various instantaneous features of a signal upon receipt, so as to obtain an instantaneous feature set corresponding to the signal;

[0060] The determining module is used to determine the instantaneous feature statistics corresponding to the signal for each instantaneous feature in the instantaneous feature set, so as to obtain the instantaneous feature statistics set corresponding to the signal;

[0061] The identification module is used to input the instantaneous feature statistics set into the target identification model so that the target identification model outputs the target signal modulation mode corresponding to the signal.

[0062] Thirdly, this application provides a blind identification system for signal modulation, including a signal transmitting device and a signal receiving device;

[0063] The signal transmitting device is used to send signals to the signal receiving device;

[0064] The signal receiving device is used to establish a target recognition model and, when a signal is received, to execute a blind recognition method with the signal modulation mode as described above. The target recognition model is used to identify the signal modulation mode corresponding to the received signal.

[0065] Compared with the prior art, the above-mentioned technical solutions provided in this application have the following advantages. The blind identification method for signal modulation mode provided in this application includes establishing a target identification model, which is used to identify the signal modulation mode corresponding to the received signal; when the signal is received, extracting each instantaneous feature of the signal to obtain the instantaneous feature set corresponding to the signal; for each instantaneous feature in the instantaneous feature set, determining the instantaneous feature statistic corresponding to the signal based on the instantaneous feature to obtain the instantaneous feature statistic set corresponding to the signal; and inputting the instantaneous feature statistic set into the target identification model so that the target identification model outputs the target signal modulation mode corresponding to the signal. By employing the above methods, this application pre-establishes a target recognition model for identifying the signal modulation scheme corresponding to the received signal. Upon receiving the signal, it extracts features from each instantaneous feature of the signal and uses these extracted instantaneous features to determine the instantaneous feature statistics corresponding to each instantaneous feature. All the obtained instantaneous feature statistics are then input into the pre-trained target recognition model, enabling the target recognition model to output the target signal modulation scheme corresponding to the signal. This avoids the drawbacks of blindly identifying the signal modulation scheme using a single signal feature, thus improving the accuracy and reliability of blindly identifying the signal modulation scheme corresponding to the signal. Attached Figure Description

[0066] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0067] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0068] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0069] Figure 1 is a flowchart illustrating a blind identification method for a signal modulation scheme provided in an embodiment of this application;

[0070] Figure 2 is a schematic diagram of a feature extraction process provided in an embodiment of this application;

[0071] Figure 3 is a schematic diagram of the structure of a blind identification system for a signal modulation method provided in an embodiment of this application;

[0072] Figure 4 is a schematic diagram of the structure of a blind identification device for a signal modulation method provided in an embodiment of this application;

[0073] Figure 5 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0074] In the above figures: 301, signal transmitting device; 302, signal receiving device; 401, establishment module; 402, extraction module; 403, determination module; 404, identification module; 501, processor; 502, communication interface; 503, memory; 504, communication bus. Detailed Implementation

[0075] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0076] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0077] Referring to Figure 1, Figure 1 is a schematic flowchart of a blind identification method for a signal modulation scheme provided in an embodiment of this application. The blind identification method for a signal modulation scheme provided in this embodiment includes the following steps:

[0078] S101: Establish a target recognition model.

[0079] In this embodiment, the target recognition model is used to identify the signal modulation method corresponding to the received signal. The target recognition model is actually a pre-trained machine learning model. Based on the classification and recognition capabilities of machine learning models, it can achieve higher computational complexity and detection performance. It is suitable for high-precision signal recognition under adverse conditions such as strong interference, rapidly changing harsh electromagnetic environments, and lack of prior information. Therefore, this embodiment establishes a target recognition model so that when a signal is received, it can perform blind recognition of the received signal according to the established target recognition model, thereby improving the accuracy and reliability of blind signal recognition.

[0080] The above-mentioned target recognition model includes:

[0081] Obtain the first preset signal set and the preset signal modulation scheme corresponding to each first preset signal in the first preset signal set;

[0082] Preset instantaneous features are extracted from each of the first preset signals in the first preset signal set to obtain the preset instantaneous feature set corresponding to each preset signal;

[0083] For each preset instantaneous feature in the preset instantaneous feature set corresponding to each first preset signal in the first preset signal set, the preset instantaneous feature statistics corresponding to the preset signal are determined based on the preset instantaneous features, so as to obtain the preset instantaneous feature statistics set corresponding to each first preset signal in the first preset signal set;

[0084] The preset instantaneous feature set corresponding to each first preset signal in the first preset signal set is associated with the preset signal modulation mode corresponding to each first preset signal in the first preset signal set to obtain the first association relationship.

[0085] The first association relationship is used to train the preset machine learning model to establish a target recognition model.

[0086] The first preset signal set may include single-carrier signals with different modulations, such as BPSK, 8PSK, QAM, 16QAM, and 64QAM. The preset signal modulation method corresponding to each first preset signal can be set according to actual needs; this embodiment does not impose specific limitations on it. After obtaining each first preset signal in the first preset signal set, preset instantaneous features such as preset instantaneous amplitude, preset instantaneous phase, and preset instantaneous frequency of each first preset signal can be extracted, thereby obtaining the preset instantaneous feature set corresponding to each first preset signal. For each preset instantaneous feature in each preset instantaneous feature set, the preset instantaneous feature statistics set corresponding to the signal is determined based on the preset instantaneous features, so as to associate each preset instantaneous feature statistics set with the preset signal modulation method corresponding to each first preset signal. Using the above association relationship, a preset machine learning model is trained to establish a target recognition model.

[0087] Specifically, when training a pre-defined machine learning model, a loss function is pre-set, and the trainable parameters are updated based on the gradients calculated in each training process. The learning rate determines the step size of the parameter updates, further exploring the optimal combination of the two to avoid overfitting or underfitting. Training samples are divided into training and validation sets, and cross-validation is used to effectively train the network. The trained network is then used for blind recognition validation of signal modulation methods.

[0088] More specifically, cross-entropy is used as the loss function, which includes:

[0089] In the above formula, L represents the loss function, M represents the number of samples, N represents the number of classes, and p ic Let x represent the probability that the i-th sample belongs to class C. ic ∈{0,1} represents the sample label, which uses one-hot encoding.

[0090] It should be noted that the method for determining the preset instantaneous features mentioned above is consistent with the method for determining the instantaneous features described below, and the method for determining the preset instantaneous feature statistics mentioned above is consistent with the method for determining the instantaneous feature statistics described below. For details, please refer to the following description, which will not be repeated here in this embodiment.

[0091] S102: Upon receiving a signal, extract each instantaneous feature of the signal to obtain the instantaneous feature set corresponding to the signal.

[0092] In this embodiment, the instantaneous feature set includes instantaneous amplitude, instantaneous phase, and instantaneous frequency. Assuming the carrier frequency of the signal has been accurately estimated, the signal is frequency-converted, resulting in the following expression for the modulated signal:

[0093] In the above formula, x(t) represents the signal, and a k Let M represent the transmitted code, e represent the signal energy coefficient, p(t) represent the transmitted symbol waveform, and T represent the transmitted symbol waveform. s θ is the symbol width. c This refers to the carrier phase.

[0094] After obtaining the expression for the modulated signal, the signal can be converted from digital to digital (A / D) and then subjected to Hilbert transform to obtain the analytical expression of the signal, as follows: x(n) = x s (n)+jx c (n)

[0095] In the above formula, x(n) represents the signal, x s (n) represents the real part, which is the original signal sequence, the actual physical quantity part, containing the amplitude information of the signal itself, x c (n) represents the imaginary part, which contains behavioral information about the signal.

[0096] The signal analytical expression obtained above is transformed to obtain the instantaneous amplitude, instantaneous phase, and instantaneous frequency. The expressions for the instantaneous amplitude, instantaneous phase, and instantaneous frequency are as follows:

[0097] Instantaneous amplitude:

[0098] Instantaneous phase:

[0099] Instantaneous frequency:

[0100] In the above formula, A(n) represents the instantaneous amplitude, θ(n) represents the instantaneous phase, f(n) represents the instantaneous frequency, and f s Indicates the sampling frequency.

[0101] In step S102 above, upon receiving a signal, various instantaneous features of the signal are extracted to obtain the instantaneous feature set corresponding to the signal, including:

[0102] Determine whether the received signal is in the second preset signal set. The second preset signal in the second preset signal set represents a preset signal with a known signal modulation method.

[0103] When the received signal is not in the second preset signal set, the instantaneous features of the signal are extracted to obtain the instantaneous feature set corresponding to the signal.

[0104] In this embodiment, to reduce unnecessary waste of computing resources, upon receiving a signal, it is determined whether the signal is a preset signal with a known modulation scheme. If the signal is a preset signal with a known modulation scheme, there is no need to call the target recognition model to blindly identify the target signal modulation scheme corresponding to the signal; the signal can be directly demodulated using the preset modulation scheme corresponding to the signal. If the signal is not a preset signal with a known modulation scheme, then each instantaneous feature of the signal needs to be extracted to obtain the instantaneous feature set corresponding to the signal. The instantaneous feature set and the target recognition model are then used to achieve blind identification of the target signal modulation scheme corresponding to the signal.

[0105] It should be noted that each of the second preset signals in the second preset signal set can be set according to actual needs. In this embodiment, there is no limitation on each of the second preset signals in the second preset signal set.

[0106] In this embodiment, the blind identification method for signal modulation scheme provided further includes:

[0107] A decision tree model is established to identify the modulation scheme of the received signal.

[0108] Before the step of extracting various instantaneous features of the signal in step S102 to obtain the instantaneous feature set corresponding to the signal, the blind identification method for signal modulation mode provided in this embodiment further includes the following steps:

[0109] When a signal is received, it is determined whether the received signal is in the third preset signal set. The third preset signal in the third preset signal set can be used to identify the preset signal of the signal modulation mode using a decision tree model.

[0110] When the received signal is in the third preset signal set, the decision tree model is used to identify the target signal modulation mode corresponding to the signal.

[0111] When the received signal is not in the third preset signal set, the step of extracting each instantaneous feature of the signal to obtain the instantaneous feature set corresponding to the signal is performed.

[0112] The decision tree model is a blind identification model for existing signal modulation methods, and specific details can be found in existing technologies; this embodiment does not limit its application. Since it is not necessary to determine instantaneous feature statistics based on instantaneous features when building the decision tree model, it uses fewer resources than machine learning models. Therefore, when a decision tree model can be used for blind identification of signal modulation methods in a received signal, it can be used directly without calling a target identification model, thus reducing unnecessary waste of computational resources.

[0113] Specifically, each of the third preset signals can be pre-set to identify the target signal modulation mode corresponding to the signal using a decision tree model, in order to determine whether the received signal is in the third preset signal set. If the received signal is a third preset signal, the target signal modulation mode corresponding to the signal can be directly identified using the decision tree model. If the received signal is not a third preset signal, the target identification model needs to be called to identify the target signal modulation mode corresponding to the signal.

[0114] S103: For each instantaneous feature in the instantaneous feature set, determine the instantaneous feature statistics corresponding to the signal based on the instantaneous feature, so as to obtain the instantaneous feature statistics set corresponding to the signal.

[0115] In this embodiment, since the target recognition model is trained by the preset instantaneous feature statistics corresponding to the preset instantaneous features of each first preset signal, when each instantaneous feature corresponding to the signal is obtained, the instantaneous feature statistics corresponding to each instantaneous feature are determined, thereby using the determined instantaneous feature statistics to realize the blind recognition of the target signal modulation mode corresponding to the signal, so as to improve the accuracy and reliability of the blind recognition of the signal modulation mode.

[0116] In the above, when the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal include a first feature statistic, which characterizes the maximum value of the instantaneous amplitude spectral density. In step S103, determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes:

[0117] When the instantaneous feature set includes the instantaneous amplitude, the number of samples corresponding to the signal is obtained;

[0118] The instantaneous amplitude is normalized to zero center to obtain the processed instantaneous amplitude;

[0119] The processed instantaneous amplitude and the number of samples are input into the first feature determination formula to obtain the first feature statistic. The first feature determination formula includes:

[0120] γ max =max|DFT(A) cn (n))| 2 / N

[0121] In the above formula, γ max The first characteristic statistic is represented by 'max', the maximum value is represented by 'DFT()', and A represents the Discrete Fourier Transform. cn (n) represents the processed instantaneous amplitude, and N represents the number of samples.

[0122] The processed instantaneous amplitude is determined by the following formula:

[0123] In the above formula, A(n) represents the instantaneous amplitude, and N represents the number of samples.

[0124] Since the maximum value of the zero-center normalized instantaneous amplitude spectral density characterizes the instantaneous amplitude change of the signal, reflects the change characteristics of the signal envelope, and distinguishes between constant envelope and non-constant envelope signal modulation methods.

[0125] In this embodiment, when the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal also include a second feature statistic, a third feature statistic, and a fourth feature statistic. The second feature statistic characterizes the standard deviation of the instantaneous amplitude of the zero-center normalized non-weak signal segment, the third feature statistic characterizes the standard deviation of the absolute value of the zero-center normalized instantaneous amplitude, and the fourth feature statistic characterizes the compactness of the zero-center normalized instantaneous amplitude. The step S103 above, determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features, includes:

[0126] Determine the first number that belongs to the non-weak signal from the number of samples;

[0127] The first number and the processed instantaneous amplitude are input into the formula for determining the second feature to obtain the second feature statistic.

[0128] The number of samples and the processed instantaneous amplitude are input into the formula for determining the third feature to obtain the third feature statistic;

[0129] The processed instantaneous amplitude is input into the formula for determining the fourth feature to obtain the fourth feature statistic; where,

[0130] The formula for determining the second feature includes:

[0131] The formula for determining the third feature includes:

[0132] The formula for determining the fourth feature includes:

[0133] In the above formula, σ da A represents the second characteristic statistic. cn (n) represents the processed instantaneous amplitude, C represents the first number, and σ aa This represents the third characteristic statistic, where N represents the number of samples. A represents the fourth characteristic statistic. cn (n)>at indicates a non-weak signal, at represents the threshold level, and E() represents the Gaussian density function.

[0134] Specifically, the first number is actually A among N signals. cn The number of signals where (n) > at. The second characteristic statistic characterizes the amplitude variation information of a signal within a symbol interval. It can distinguish between signal modulation schemes where the normalized center instantaneous amplitude is zero within a symbol interval, such as MPSK signals, and signal modulation schemes where the normalized center instantaneous amplitude is not zero, such as DSB composite signals and AM-FM composite signals. The third characteristic statistic can distinguish between signal modulation schemes that lack normalized absolute amplitude information, such as 2ASK signals, and signal modulation schemes that do have normalized absolute amplitude information, such as higher-order MASK signals. The fourth characteristic statistic can distinguish between signals with a high density of instantaneous amplitude distribution, such as AM signals, and signals with a relatively sparse instantaneous amplitude distribution, such as MASK signals.

[0135] In the above, when the instantaneous feature set includes the instantaneous phase, the instantaneous feature statistics corresponding to the signal include a fifth feature statistic and a sixth feature statistic. The fifth feature statistic characterizes the standard deviation of the instantaneous phase nonlinear component of the zero-center non-weak signal segment, and the sixth feature statistic characterizes the standard deviation of the absolute value of the instantaneous phase nonlinear component of the zero-center non-weak signal segment. In step S103 above, determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes:

[0136] The instantaneous phase is processed to obtain the nonlinear components of the instantaneous phase;

[0137] The first number and the nonlinear component are input into the formulas for determining the fifth and sixth features, respectively, to obtain the fifth and sixth feature statistics; where,

[0138] The formula for determining the fifth feature includes:

[0139] The formula for determining the sixth feature includes:

[0140] In the above formula, σ dp φ represents the fifth characteristic statistic. NL (n) represents the nonlinear component, C represents the first number, and σ ap A represents the sixth characteristic statistic. cn (n)>at indicates a non-weak signal, and at indicates the threshold level.

[0141] The fifth characteristic statistic characterizes the instantaneous phase change of the signal, distinguishing signals with direct phase information, such as DSB, LSB, USB, and 2PSK signals, as well as signals without direct phase information, such as AM, 2ASK, and 4ASK signals. The sixth characteristic statistic can distinguish signals containing absolute phase information, such as 4PSK signals, as well as signals without phase information, such as 2ASK and 2PSK signals.

[0142] In the above, when the instantaneous feature set includes instantaneous frequency, the instantaneous feature statistics corresponding to the signal include a seventh feature statistic and an eighth feature statistic. The seventh feature statistic characterizes the standard deviation of the absolute value of the instantaneous frequency of the zero-center normalized non-weak signal segment, and the eighth feature statistic characterizes the compactness of the zero-center normalized instantaneous frequency. In step S103 above, determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes:

[0143] The instantaneous frequencies are processed to obtain the first instantaneous frequency and the second instantaneous frequency. The first instantaneous frequency represents the instantaneous frequency of the zero-center normalized non-weak signal segment, and the second instantaneous frequency represents the zero-center normalized instantaneous frequency.

[0144] Input the first number and the first instantaneous frequency into the formula for determining the seventh feature to obtain the seventh feature statistic;

[0145] The second instantaneous frequency is input into the formula for determining the eighth feature to obtain the eighth feature statistic; where,

[0146] The formula for determining the seventh feature includes:

[0147] The formula for determining the eighth feature includes:

[0148] In the above formula, σ af This represents the seventh characteristic statistic, where C represents the first number. A represents the eighth characteristic statistic. cn (n)>at indicates a non-weak signal, at represents the threshold level, E() represents the Gaussian density function, and f N(n) is the frequency at the first instant, f cn (n) represents the second instantaneous frequency.

[0149] Among them, the eighth characteristic statistic can distinguish signals with a high and dense distribution of instantaneous frequency, such as FM signals, and signals with a relatively sparse distribution of instantaneous frequency, such as MFSK signals.

[0150] In the above, the first instantaneous frequency can be determined in the following way:

[0151] Determine the mean instantaneous frequency;

[0152] Determine the instantaneous frequency after zero-center processing based on the mean instantaneous frequency and the instantaneous frequency.

[0153] The first instantaneous frequency is determined based on the instantaneous frequency after zero-center processing.

[0154] The instantaneous frequency mean can be expressed by the following formula:

[0155] The instantaneous frequency after zero-center processing can be expressed by the following formula: f c (n)=f(n)-m f

[0156] The first instantaneous frequency can be expressed by the following formula: f N (n)=f c (n) / r b

[0157] In the above formula, m f Let f(n) represent the instantaneous average frequency, N represent the number of samples, and f(n) represent the instantaneous frequency. c (n) represents the instantaneous frequency after zero-center processing, f N (n) represents the frequency at the first instant, r b This represents the normalization coefficient.

[0158] In the above, the second instantaneous frequency can be determined in the following way:

[0159] Determine the mean instantaneous frequency;

[0160] The second instantaneous frequency is determined based on the instantaneous frequency and the average instantaneous frequency.

[0161] The method for determining the average instantaneous frequency can be referred to the above description, and will not be repeated here in this embodiment. The second instantaneous frequency can be expressed by the following formula:

[0162] In the above formula, f cn (n) represents the second instantaneous frequency, m f Let f(n) represent the instantaneous average frequency, and f(n) represent the instantaneous frequency.

[0163] It should be noted that the process of feature extraction from the signal can be referred to Figure 2.

[0164] S104: Input the instantaneous feature statistics set into the target recognition model so that the target recognition model outputs a signal corresponding to the target signal modulation mode.

[0165] In this embodiment, after obtaining the set of instantaneous feature statistics corresponding to the signal, each instantaneous feature statistic in the set of instantaneous feature statistics is input into the target recognition model, so that the target recognition model can identify the target signal modulation mode corresponding to the signal based on each instantaneous feature statistic. Then, when the target recognition model identifies the target signal modulation mode corresponding to the signal, the target signal modulation mode is output.

[0166] After obtaining the target signal modulation method, the received signal can be demodulated using the target signal modulation method to obtain the target demodulation result corresponding to the signal. When the target demodulation result is a demodulation failure, the target prompt information corresponding to the signal is generated based on the target demodulation result and sent to the target terminal corresponding to the signal. When the target adjustment information corresponding to the target prompt information displayed in the target terminal is received, the target recognition model is updated using the target adjustment information to obtain the updated target recognition model. The instantaneous feature statistics are input into the target recognition model until the target demodulation result is a successful demodulation.

[0167] Specifically, to improve the accuracy of the target recognition model in identifying signal modulation methods, when demodulation fails using the identified target signal modulation method, a corresponding target prompt message is generated. This prompt message can be something like, "Target signal modulation method identification error; please readjust the parameters of the target recognition model." After generating the prompt message, it is pushed to the target terminal, which can be a mobile phone or computer. Upon receiving the prompt message, the target terminal displays it. Personnel at the target terminal adjust the parameters of the target recognition model based on the terminal's settings to obtain the corresponding target adjustment information. This information is then used to update the target recognition model, enabling accurate identification of the target signal modulation method and thus accurate signal demodulation.

[0168] This embodiment provides a blind identification method for signal modulation schemes. By pre-establishing a target identification model for recognizing the signal modulation scheme corresponding to a received signal, the method extracts features from each instantaneous feature of the received signal. Using these extracted instantaneous features, the method determines the instantaneous feature statistics corresponding to each instantaneous feature. All the obtained instantaneous feature statistics are then input into the pre-trained target identification model, which outputs the target signal modulation scheme corresponding to the signal. This avoids the drawbacks of blindly identifying signal modulation schemes using a single signal feature, and improves the accuracy and reliability of blindly identifying the signal modulation scheme corresponding to the signal.

[0169] Referring to Figure 3, which is a schematic diagram of a blind identification system for a signal modulation mode provided in an embodiment of this application, the blind identification system for a signal modulation mode provided in this embodiment includes a signal transmitting device 301 and a signal receiving device 302. The signal transmitting device 301 is used to transmit a signal to the signal receiving device 302; the signal receiving device 302 is used to establish a target identification model and, upon receiving a signal, execute the blind identification method for the signal modulation mode described above. The target identification model is used to identify the signal modulation mode corresponding to the received signal.

[0170] Referring to Figure 4, which is a schematic diagram of a blind signal modulation mode identification device provided in an embodiment of this application, the blind signal modulation mode identification device provided in this application includes: a setup module 401, an extraction module 402, a determination module 403, and an identification module 404. The setup module 401 is used to establish a target identification model, which is used to identify the signal modulation mode corresponding to a received signal; the extraction module 402 is used to extract various instantaneous features of the received signal to obtain an instantaneous feature set corresponding to the signal; the determination module 403 is used to determine the instantaneous feature statistics corresponding to the signal for each instantaneous feature in the instantaneous feature set, to obtain an instantaneous feature statistics set corresponding to the signal; and the identification module 404 is used to input the instantaneous feature statistics set into the target identification model, so that the target identification model outputs the target signal modulation mode corresponding to the signal.

[0171] In this embodiment, when the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal include a first feature statistic, which characterizes the maximum value of the instantaneous amplitude spectral density. The determining module 403 is further configured to:

[0172] When the instantaneous feature set includes the instantaneous amplitude, the number of samples corresponding to the signal is obtained;

[0173] The instantaneous amplitude is subjected to zero-center normalization to obtain the processed instantaneous amplitude;

[0174] The processed instantaneous amplitude and the number of samples are input into the first feature determination formula to obtain the first feature statistic. The first feature determination formula includes:

[0175] γ max =max|DFT(A) cn (n))| 2 / N

[0176] In the above formula, γ max The first characteristic statistic is represented by 'max', the maximum value is represented by 'DFT()', and A represents the Discrete Fourier Transform. cn (n) represents the processed instantaneous amplitude, and N represents the number of samples.

[0177] In this embodiment, when the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal further include a second feature statistic, a third feature statistic, and a fourth feature statistic. The second feature statistic characterizes the standard deviation of the zero-center normalized instantaneous amplitude of the non-weak signal segment, the third feature statistic characterizes the standard deviation of the absolute value of the zero-center normalized instantaneous amplitude, and the fourth feature statistic characterizes the compactness of the zero-center normalized instantaneous amplitude. The determining module 403 is further configured to:

[0178] Determine the first number belonging to the non-weak signal from the signals of the specified number of samples;

[0179] The first number and the processed instantaneous amplitude are input into the second feature determination formula to obtain the second feature statistic;

[0180] The number of samples and the processed instantaneous amplitude are input into the third feature determination formula to obtain the third feature statistic;

[0181] The processed instantaneous amplitude is input into the fourth feature determination formula to obtain the fourth feature statistic; wherein,

[0182] The formula for determining the second feature includes:

[0183] The formula for determining the third feature includes:

[0184] The formula for determining the fourth feature includes:

[0185] In the above formula, σ da A represents the second characteristic statistic. cn(n) represents the processed instantaneous amplitude, C represents the first number, and σ aa This represents the third characteristic statistic, where N represents the number of samples. A represents the fourth characteristic statistic. cn (n)>at indicates a non-weak signal, at represents the threshold level, and E() represents the Gaussian density function.

[0186] In this embodiment, when the instantaneous feature set includes instantaneous phase, the instantaneous feature statistics corresponding to the signal include a fifth feature statistic and a sixth feature statistic. The fifth feature statistic characterizes the standard deviation of the instantaneous phase nonlinear component of the zero-center non-weak signal segment, and the sixth feature statistic characterizes the standard deviation of the absolute value of the instantaneous phase nonlinear component of the zero-center non-weak signal segment. The determining module 403 is further configured to:

[0187] When the instantaneous feature set includes the instantaneous phase, the instantaneous phase is subjected to zero-center processing to obtain the nonlinear component of the instantaneous phase;

[0188] The first number and the nonlinear component are respectively input into the fifth feature determination formula and the sixth feature determination formula to obtain the fifth feature statistic and the sixth feature statistic; wherein,

[0189] The formula for determining the fifth feature includes:

[0190] The formula for determining the sixth feature includes:

[0191] In the above formula, σ dp φ represents the fifth characteristic statistic. NL (n) represents the nonlinear component, C represents the first number, and σ ap A represents the sixth characteristic statistic. cn (n)>at indicates a non-weak signal, and at indicates the threshold level.

[0192] In this embodiment, when the instantaneous feature set includes instantaneous frequencies, the instantaneous feature statistics corresponding to the signal include a seventh feature statistic and an eighth feature statistic. The seventh feature statistic characterizes the standard deviation of the absolute value of the instantaneous frequency of the zero-center normalized non-weak signal segment, and the eighth feature statistic characterizes the compactness of the zero-center normalized instantaneous frequency. The determining module 403 is further configured to:

[0193] When the instantaneous feature set includes the instantaneous frequency, the instantaneous frequency is processed to obtain a first instantaneous frequency and a second instantaneous frequency. The first instantaneous frequency represents the instantaneous frequency of the zero-center normalized non-weak signal segment, and the second instantaneous frequency represents the zero-center normalized instantaneous frequency.

[0194] The first number and the first instantaneous frequency are input into the formula for determining the seventh feature to obtain the seventh feature statistic;

[0195] The second instantaneous frequency is input into the formula for determining the eighth feature to obtain the eighth feature statistic; wherein,

[0196] The formula for determining the seventh feature includes:

[0197] The formula for determining the eighth feature includes:

[0198] In the above formula, σ af This represents the seventh characteristic statistic, where C represents the first number. A represents the eighth characteristic statistic. cn (n)>at indicates a non-weak signal, at represents the threshold level, E() represents the Gaussian density function, and f N (n) represents the frequency at the first instant, f cn (n) represents the second instantaneous frequency.

[0199] In this embodiment, the establishment module 401 is further configured to:

[0200] Obtain a first preset signal set and a preset signal modulation scheme corresponding to each first preset signal in the first preset signal set;

[0201] Preset instantaneous features are extracted from each of the first preset signals in the first preset signal set to obtain a preset instantaneous feature set corresponding to each preset signal;

[0202] For each preset instantaneous feature in the preset instantaneous feature set corresponding to each first preset signal in the first preset signal set, a preset instantaneous feature statistic corresponding to the preset signal is determined based on the preset instantaneous feature, so as to obtain a preset instantaneous feature statistic set corresponding to each first preset signal in the first preset signal set;

[0203] The preset instantaneous feature statistics set corresponding to each of the first preset signals in the first preset signal set is associated with the preset signal modulation mode corresponding to each of the first preset signals in the first preset signal set to obtain a first association relationship.

[0204] Using the first association relationship, a preset machine learning model is trained to establish the target recognition model.

[0205] In this embodiment, the extraction module 402 is further configured to:

[0206] Determine whether the received signal is in the second preset signal set, wherein the second preset signal in the second preset signal set represents a preset signal with a known signal modulation method;

[0207] When the received signal is not in the second preset signal set, each instantaneous feature of the signal is extracted to obtain the instantaneous feature set corresponding to the signal.

[0208] In this embodiment, the establishment module 401 is further configured to:

[0209] A decision tree model is established, which is used to identify the signal modulation mode corresponding to the received signal.

[0210] In this embodiment, the extraction module 402 is further configured to:

[0211] Upon receiving the signal, it is determined whether the received signal is in the third preset signal set. The third preset signal in the third preset signal set can be used to identify the preset signal of the signal modulation mode using the decision tree model.

[0212] When the received signal is in the third preset signal set, the decision tree model is used to identify the target signal modulation mode corresponding to the signal;

[0213] When the received signal is not in the third preset signal set, each instantaneous feature of the signal is extracted to obtain the instantaneous feature set corresponding to the signal.

[0214] This embodiment provides a blind identification device for signal modulation modes. By pre-establishing a target identification model for identifying the signal modulation mode corresponding to the received signal, the device extracts features from each instantaneous feature of the received signal. Using the extracted instantaneous features, the device determines the instantaneous feature statistics corresponding to each instantaneous feature. All the obtained instantaneous feature statistics are then input into the pre-trained target identification model, which outputs the target signal modulation mode corresponding to the signal. This avoids the drawbacks of blind identification of signal modulation modes using a single signal feature, and improves the accuracy and reliability of blind identification of the signal modulation mode corresponding to the signal.

[0215] As shown in Figure 5, this embodiment of the application provides an electronic device, including a processor 501, a communication interface 502, a memory 503, and a communication bus 504. The processor 501, communication interface 502, and memory 503 communicate with each other via the communication bus 504.

[0216] Memory 503 is used to store computer programs;

[0217] In one embodiment of this application, the processor 501, when executing the program stored in the memory 503, implements the blind identification method of signal modulation mode provided in any of the foregoing method embodiments.

[0218] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the blind identification method for signal modulation as provided in any of the foregoing method embodiments.

[0219] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0220] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0221] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0222] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily 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 invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A blind identification method for a signal modulation scheme, characterized in that, include: A target recognition model is established, which is used to identify the signal modulation mode corresponding to the received signal; Upon receiving a signal, each instantaneous feature of the signal is extracted to obtain the instantaneous feature set corresponding to the signal; For each instantaneous feature in the instantaneous feature set, the instantaneous feature statistics corresponding to the signal are determined based on the instantaneous feature to obtain the instantaneous feature statistics set corresponding to the signal; The instantaneous feature statistics set is input into the target recognition model so that the target recognition model outputs the target signal modulation mode corresponding to the signal.

2. The method according to claim 1, characterized in that, When the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal include a first feature statistic, which characterizes the maximum value of the instantaneous amplitude spectral density; The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes: When the instantaneous feature set includes the instantaneous amplitude, the number of samples corresponding to the signal is obtained; The instantaneous amplitude is subjected to zero-center normalization to obtain the processed instantaneous amplitude; The processed instantaneous amplitude and the number of samples are input into the first feature determination formula to obtain the first feature statistic. The first feature determination formula includes: c max =max|DFT(A cn (n))| 2 / N In the above formula, γ max The first characteristic statistic is represented by 'max', the maximum value is represented by 'DFT()', and A represents the Discrete Fourier Transform. cn (n) represents the processed instantaneous amplitude, and N represents the number of samples.

3. The method according to claim 2, characterized in that, When the instantaneous feature set includes instantaneous amplitude, the instantaneous feature statistics corresponding to the signal also include a second feature statistic, a third feature statistic, and a fourth feature statistic. The second feature statistic represents the standard deviation of the instantaneous amplitude of the zero-center normalized non-weak signal segment, the third feature statistic represents the standard deviation of the absolute value of the zero-center normalized instantaneous amplitude, and the fourth feature statistic represents the compactness of the zero-center normalized instantaneous amplitude. The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes: Determine the first number belonging to the non-weak signal from the signals of the specified number of samples; The first number and the processed instantaneous amplitude are input into the second feature determination formula to obtain the second feature statistic; The number of samples and the processed instantaneous amplitude are input into the third feature determination formula to obtain the third feature statistic; The processed instantaneous amplitude is input into the fourth feature determination formula to obtain the fourth feature statistic; wherein, The formula for determining the second feature includes: The formula for determining the third feature includes: The formula for determining the fourth feature includes: In the above formula, σ da A represents the second characteristic statistic. cn (n) represents the processed instantaneous amplitude, C represents the first number, and σ aa This represents the third characteristic statistic, where N represents the number of samples. A represents the fourth characteristic statistic. cn (n)>at indicates a non-weak signal, at represents the threshold level, and E() represents the Gaussian density function.

4. The method according to claim 3, characterized in that, When the instantaneous feature set includes instantaneous phase, the instantaneous feature statistics corresponding to the signal include a fifth feature statistic and a sixth feature statistic. The fifth feature statistic represents the standard deviation of the instantaneous phase nonlinear component of the zero-center non-weak signal segment, and the sixth feature statistic represents the standard deviation of the absolute value of the instantaneous phase nonlinear component of the zero-center non-weak signal segment. The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes: When the instantaneous feature set includes the instantaneous phase, the instantaneous phase is subjected to zero-center processing to obtain the nonlinear component of the instantaneous phase; The first number and the nonlinear component are respectively input into the fifth feature determination formula and the sixth feature determination formula to obtain the fifth feature statistic and the sixth feature statistic; wherein, The formula for determining the fifth feature includes: The formula for determining the sixth feature includes: In the above formula, σ dp φ represents the fifth characteristic statistic. NL (n) represents the nonlinear component, C represents the first number, and σ ap A represents the sixth characteristic statistic. cn (n) > at indicates a non-weak signal, and at indicates the threshold level.

5. The method according to claim 3, characterized in that, When the instantaneous feature set includes instantaneous frequency, the instantaneous feature statistics corresponding to the signal include a seventh feature statistic and an eighth feature statistic. The seventh feature statistic characterizes the standard deviation of the absolute value of the instantaneous frequency of the zero-center normalized non-weak signal segment, and the eighth feature statistic characterizes the compactness of the zero-center normalized instantaneous frequency. The step of determining the instantaneous feature statistics corresponding to the signal based on the instantaneous features includes: When the instantaneous feature set includes the instantaneous frequency, the instantaneous frequency is processed to obtain a first instantaneous frequency and a second instantaneous frequency. The first instantaneous frequency represents the instantaneous frequency of the zero-center normalized non-weak signal segment, and the second instantaneous frequency represents the zero-center normalized instantaneous frequency. The first number and the first instantaneous frequency are input into the formula for determining the seventh feature to obtain the seventh feature statistic; The second instantaneous frequency is input into the formula for determining the eighth feature to obtain the eighth feature statistic; wherein, The formula for determining the seventh feature includes: The formula for determining the eighth feature includes: In the above formula, σ af This represents the seventh characteristic statistic, where C represents the first number. A represents the eighth characteristic statistic. cn (n) > at indicates a non-weak signal, at represents the threshold level, E() represents the Gaussian density function, and f N (n) represents the frequency at the first instant, f cn (n) represents the second instantaneous frequency.

6. The method according to claim 1, characterized in that, The establishment of the target recognition model includes: Obtain a first preset signal set and a preset signal modulation scheme corresponding to each first preset signal in the first preset signal set; Preset instantaneous features are extracted from each of the first preset signals in the first preset signal set to obtain a preset instantaneous feature set corresponding to each preset signal; For each preset instantaneous feature in the preset instantaneous feature set corresponding to each first preset signal in the first preset signal set, a preset instantaneous feature statistic corresponding to the preset signal is determined based on the preset instantaneous feature, so as to obtain a preset instantaneous feature statistic set corresponding to each first preset signal in the first preset signal set; The preset instantaneous feature statistics set corresponding to each of the first preset signals in the first preset signal set is associated with the preset signal modulation mode corresponding to each of the first preset signals in the first preset signal set to obtain a first association relationship. Using the first association relationship, a preset machine learning model is trained to establish the target recognition model.

7. The method according to claim 1, characterized in that, Upon receiving a signal, the step of extracting various instantaneous features of the signal to obtain an instantaneous feature set corresponding to the signal includes: Determine whether the received signal is in the second preset signal set, wherein the second preset signal in the second preset signal set represents a preset signal with a known signal modulation method; When the received signal is not in the second preset signal set, each instantaneous feature of the signal is extracted to obtain the instantaneous feature set corresponding to the signal.

8. The method according to claim 1, characterized in that, The method further includes: A decision tree model is established, which is used to identify the signal modulation mode corresponding to the received signal; Before performing the step of extracting each instantaneous feature of the signal to obtain the instantaneous feature set corresponding to the signal, the method further includes: Upon receiving the signal, it is determined whether the received signal is in the third preset signal set. The third preset signal in the third preset signal set can be used to identify the preset signal of the signal modulation mode using the decision tree model. When the received signal is in the third preset signal set, the decision tree model is used to identify the target signal modulation mode corresponding to the signal; When the received signal is not in the third preset signal set, the step of extracting each instantaneous feature of the signal to obtain the instantaneous feature set corresponding to the signal is performed.

9. A blind identification device based on a signal modulation method, characterized in that, include: A module is established to build a target recognition model, which is used to identify the signal modulation mode corresponding to the received signal; An extraction module is used to extract various instantaneous features of a signal upon receipt, so as to obtain an instantaneous feature set corresponding to the signal; The determining module is used to determine the instantaneous feature statistics corresponding to the signal for each instantaneous feature in the instantaneous feature set, so as to obtain the instantaneous feature statistics set corresponding to the signal; The identification module is used to input the instantaneous feature statistics set into the target identification model so that the target identification model outputs the target signal modulation mode corresponding to the signal.

10. A blind identification system with a signal modulation method, characterized in that, Includes a signal transmitting device and a signal receiving device; The signal transmitting device is used to send signals to the signal receiving device; The signal receiving device is used to establish a target recognition model and, when a signal is received, to execute a blind recognition method for the signal modulation mode as described in any one of claims 1 to 8, wherein the target recognition model is used to identify the signal modulation mode corresponding to the received signal.

Images