Signal recognition method, device, recognition equipment and storage medium

Abstract

The present application relates to the technical field of signal recognition, and in particular to a signal recognition method, device, recognition equipment and storage medium. The method includes preprocessing the collected signal to be recognized, obtaining the waveform diagram, power diagram and effective bandwidth of the signal to be recognized, determining the actual length of each special sequence through the waveform diagram and power diagram, and estimating the length of each OFDM symbol through the actual length of each special sequence; taking the length and effective bandwidth of each OFDM symbol as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, mapping the signal to be recognized into a constellation diagram based on each estimated parameter and determining the modulation type corresponding to each constellation diagram, determining the target parameter from each estimated parameter based on the modulation type corresponding to each constellation diagram, and determining the complete parameters of the signal to be recognized based on the target parameter to obtain the recognition result. Through the method of the present application, the recognition efficiency of unknown OFDM signals can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of signal recognition, and in particular to a signal recognition method, apparatus, recognition device and storage medium. Background Art

[0002] OFDM (Orthogonal Frequency Division Multiplexing) is a multi-carrier modulation technology widely used in modern wireless communication systems; for example, the telemetry signal of a drone is an OFDM signal. In some scenarios, OFDM signals need to be identified / decoded. For example, in the field of drone control, the telemetry signal of an illegal drone needs to be identified. After identifying the various parameters of the telemetry signal of the illegal drone, relevant countermeasures can be taken against the illegal drone.

[0003] In related technologies, there are usually two technologies for OFDM signal recognition. The first is to identify the various parameters of OFDM signals based on standard protocol specifications. The second method is blind recognition, that is, brute force cracking through a large number of combinations and operations. However, in practice, unknown OFDM signals that are not generated based on standard protocols often appear, and it is difficult to identify the location of OFDM signals through the first method. The second method requires a large amount of calculations and often takes a long time to identify an OFDM signal.

[0004] Therefore, how to improve the recognition efficiency of unknown OFDM signals is an urgent problem to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide a signal recognition method, apparatus, recognition device and storage medium that can improve the recognition efficiency of unknown OFDM signals in order to address the above technical problems.

[0006] In a first aspect, the present application provides a signal recognition method, comprising:

[0007] Preprocessing the collected signal to be identified to obtain a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified, and determining each special sequence and an actual length of each special sequence through the waveform diagram and the power diagram, wherein the special sequence is a preamble sequence or a pilot sequence;

[0008] estimating the length of each OFDM symbol according to the actual length of each of the special sequences;

[0009] Taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, the estimated parameters at least including the basic parameters, symbol rate and FFT length, and the estimated parameters are parameters required for designing the signal to be identified;

[0010] Mapping the signal to be identified into a constellation diagram based on each of the estimated parameters, and determining a modulation type corresponding to each of the constellations, and determining a target parameter from each of the estimated parameters based on the modulation type corresponding to each of the constellations, wherein the modulation type of the constellation diagram corresponding to the target parameter is a known type;

[0011] The complete parameters of the signal to be identified are determined based on the target parameters, and the signal to be identified is identified based on the complete parameters to obtain an identification result.

[0012] By adopting the signal recognition method of the present application, it is possible to determine the actual length of each special sequence in the signal to be identified based on the waveform diagram, power diagram and effective bandwidth obtained by preprocessing the signal to be identified, and further estimate the length of the OFDM symbol according to the actual length of each special sequence, so as to use the length and effective bandwidth of each OFDM symbol as basic parameters, and from the perspective of forward design of the OFDM signal, estimate multiple groups of estimated parameters including basic parameters, FFT length and symbol rate; further, the multiple groups of estimated parameters are used to map the signal to be identified into constellation diagrams respectively, and according to the modulation type represented by the constellation diagram, the modulation type represented by a known type is determined as the target parameter from the constellation diagram corresponding to each group of estimated parameters, that is, the target parameter is used to generate the signal to be identified. The actual parameters used when identifying the signal; compared with the related art, the signal identification method of the present application can not only identify the OFDM signal of the standard protocol, but also does not require a large number of operations used in blind identification. Instead, the basic parameters of the signal to be identified are first determined, and multiple groups of possible estimated parameters are further estimated based on the basic parameters, and then the parameters required to generate the signal to be identified are determined from the multiple groups of estimated parameters; that is, the signal identification method of the present application can also estimate the parameters of unknown signals, thereby realizing the identification of unknown OFDM signals, and because the parameters are estimated based on the determined basic parameters, rather than trying all the parameters one by one, the scheme of the present application can narrow the range of parameters that need to be calculated, thereby improving the efficiency of signal recognition.

[0013] In one embodiment, determining each special sequence and an actual length of each special sequence by using the waveform diagram and the power diagram includes:

[0014] Calling a special sequence recognition component to analyze the waveform diagram and the power diagram, determine each initial sequence in the signal to be recognized, and determine a characteristic sequence of each initial sequence, wherein the characteristic sequence is a fragment intercepted from the initial sequence;

[0015] Performing sliding correlation operations on each of the characteristic sequences and the signal to be identified, and determining the characteristic sequences with repeated sequence contents as repeated sequence pairs according to the correlation peak information obtained by the sliding correlation operations;

[0016] For each of the repeated sequence pairs, in the power graph, the power distribution of each of the characteristic sequences in the repeated sequence pair is determined, and the power distribution of each of the characteristic sequences is matched to determine a special sequence and the length of the special sequence.

[0017] In one of the embodiments, taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, comprises:

[0018] Inputting the basic parameters, the waveform diagram and the power diagram into an estimation model to obtain at least one set of estimation parameters output by the estimation model;

[0019] The estimation model is obtained by training an initial model based on a plurality of training samples, wherein the training samples include a waveform diagram of a sample signal, a power diagram, a design protocol, and some design parameters required for designing the sample signal, and the sample labels of the training samples are complete parameters for designing the sample signal, and the some design parameters include at least an effective bandwidth and a length of each OFDM symbol;

[0020] The designed protocols in the training samples include standard protocols and unknown protocols.

[0021] In one of the embodiments, taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, comprises:

[0022] The design table is queried to obtain at least one set of complete parameters including the basic parameters as estimated parameters, wherein the design table includes complete parameters required for designing a signal based on any standard protocol.

[0023] In one embodiment, mapping the to-be-identified signal into a constellation diagram based on each of the estimated parameters, and determining a modulation type corresponding to each of the constellation diagrams, includes:

[0024] Determine the frequency deviation of the signal to be identified based on at least two of the special sequences, and compensate the signal to be identified based on the frequency deviation to obtain a compensated signal;

[0025] The compensation signal is mapped into a constellation diagram based on each of the estimated parameters, and a modulation type corresponding to each of the constellation diagrams is determined.

[0026] In one embodiment, mapping the compensation signal into a constellation diagram based on each of the estimated parameters, and determining a modulation type corresponding to each of the constellation diagrams, includes:

[0027] Demodulating the compensation signal based on each of the estimated parameters to obtain demodulated data;

[0028] The demodulated data is converted into a constellation diagram, and the modulation type corresponding to each constellation diagram is determined.

[0029] In a second aspect, the present application further provides a signal recognition device, the device comprising a preprocessing module, a first estimation module, a second estimation module, a target parameter determination module and a recognition module, wherein:

[0030] A preprocessing module, used for preprocessing the collected signal to be identified, obtaining a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified, and determining each special sequence and an actual length of each special sequence through the waveform diagram and the power diagram, wherein the special sequence is a leading sequence or a pilot sequence;

[0031] A first estimation module, used for estimating the length of each OFDM symbol according to the actual length of each special sequence;

[0032] A second estimation module, configured to use the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimate at least one set of estimated parameters based on the basic parameters, wherein the estimated parameters at least include the basic parameters, a symbol rate, and an FFT length, and the estimated parameters are parameters required for designing the signal to be identified;

[0033] a target parameter determination module, configured to map the signal to be identified into a constellation diagram based on each of the estimated parameters, determine a modulation type corresponding to each of the constellations, and determine a target parameter from each of the estimated parameters based on the modulation type corresponding to each of the constellations, wherein the modulation type of the constellation diagram corresponding to the target parameter is a known type;

[0034] The identification module is used to determine the complete parameters of the signal to be identified based on the target parameters, and identify the signal to be identified based on the complete parameters to obtain an identification result.

[0035] In a third aspect, the present application further provides an identification device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Preprocessing the collected signal to be identified to obtain a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified, and determining each special sequence and an actual length of each special sequence through the waveform diagram and the power diagram, wherein the special sequence is a preamble sequence or a pilot sequence;

[0037] estimating the length of each OFDM symbol according to the actual length of each of the special sequences;

[0038] Taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, the estimated parameters at least including the basic parameters, symbol rate and FFT length, and the estimated parameters are parameters required for designing the signal to be identified;

[0039] Mapping the signal to be identified into a constellation diagram based on each of the estimated parameters, and determining a modulation type corresponding to each of the constellations, and determining a target parameter from each of the estimated parameters based on the modulation type corresponding to each of the constellations, wherein the modulation type of the constellation diagram corresponding to the target parameter is a known type;

[0040] The complete parameters of the signal to be identified are determined based on the target parameters, and the signal to be identified is identified based on the complete parameters to obtain an identification result.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0042] Preprocessing the collected signal to be identified to obtain a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified, and determining each special sequence and an actual length of each special sequence through the waveform diagram and the power diagram, wherein the special sequence is a preamble sequence or a pilot sequence;

[0043] estimating the length of each OFDM symbol according to the actual length of each of the special sequences;

[0044] Taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, the estimated parameters at least including the basic parameters, symbol rate and FFT length, and the estimated parameters are parameters required for designing the signal to be identified;

[0045] Mapping the signal to be identified into a constellation diagram based on each of the estimated parameters, and determining a modulation type corresponding to each of the constellations, and determining a target parameter from each of the estimated parameters based on the modulation type corresponding to each of the constellations, wherein the modulation type of the constellation diagram corresponding to the target parameter is a known type;

[0046] The complete parameters of the signal to be identified are determined based on the target parameters, and the signal to be identified is identified based on the complete parameters to obtain an identification result.

[0047] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0048] Preprocessing the collected signal to be identified to obtain a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified, and determining each special sequence and an actual length of each special sequence through the waveform diagram and the power diagram, wherein the special sequence is a preamble sequence or a pilot sequence;

[0049] estimating the length of each OFDM symbol according to the actual length of each of the special sequences;

[0050] Taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, the estimated parameters at least including the basic parameters, symbol rate and FFT length, and the estimated parameters are parameters required for designing the signal to be identified;

[0051] Mapping the signal to be identified into a constellation diagram based on each of the estimated parameters, and determining a modulation type corresponding to each of the constellations, and determining a target parameter from each of the estimated parameters based on the modulation type corresponding to each of the constellations, wherein the modulation type of the constellation diagram corresponding to the target parameter is a known type;

[0052] The complete parameters of the signal to be identified are determined based on the target parameters, and the signal to be identified is identified based on the complete parameters to obtain an identification result.

[0053] The above-mentioned signal recognition method, device, recognition equipment and storage medium determine the actual length of each special sequence in the signal to be recognized based on the waveform diagram, power diagram and effective bandwidth obtained by preprocessing the signal to be recognized, and further estimate the length of the OFDM symbol according to the actual length of each special sequence, so as to use the length and effective bandwidth of each OFDM symbol as basic parameters, and estimate multiple groups of estimated parameters including basic parameters, FFT length and symbol rate from the perspective of forward design of OFDM signal; further, the multiple groups of estimated parameters are used to map the signal to be recognized into constellation diagrams respectively, and according to the modulation type represented by the constellation diagram, the modulation type represented by the known type is determined as the target parameter from the constellation diagram corresponding to each group of estimated parameters, that is, the target parameter is used for The actual parameters used when generating the signal to be identified; compared with the related art, the signal identification method of the present application can not only identify the OFDM signal of the standard protocol, but also does not require a large number of operations used in blind identification. Instead, the basic parameters of the signal to be identified are first determined, and multiple groups of possible estimated parameters are further estimated based on the basic parameters, and then the parameters required to generate the signal to be identified are determined from the multiple groups of estimated parameters; that is, the signal identification method of the present application can also estimate the parameters of unknown signals, thereby realizing the identification of unknown OFDM signals, and because the parameters are estimated based on the determined basic parameters, rather than trying all the parameters one by one, the scheme of the present application can narrow the range of parameters that need to be calculated, thereby improving the efficiency of signal recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] FIG1 is a schematic flow chart of a signal recognition method in one embodiment;

[0056] FIG2 is a schematic diagram of a process for determining the length of a special sequence in one embodiment;

[0057] FIG3 is an example diagram of a signal to be identified in one embodiment;

[0058] FIG4 is an example diagram of a power diagram of a signal to be identified in one embodiment;

[0059] FIG5 is an example diagram of a waveform diagram of a signal to be identified in one embodiment;

[0060] FIG6 is a schematic diagram of a process for determining estimated parameters in one embodiment;

[0061] FIG7 is a schematic diagram of a process for determining a modulation type in one embodiment;

[0062] FIG8 is a schematic flow chart of a signal recognition method in another embodiment;

[0063] FIG9 is a schematic diagram of a process for determining a special sequence length in another embodiment;

[0064] FIG10 is an exemplary diagram of correlation peaks of a special sequence in another embodiment;

[0065] FIG11 is a logic diagram of a signal recognition method in another embodiment;

[0066] FIG12 is an example diagram of a general LTE standard protocol in another embodiment;

[0067] Fig.13 is an example diagram of a Wi-Fi standard protocol in another embodiment;

[0068] Fig.14 is an example diagram of a set of estimated parameters in another embodiment;

[0069] Fig.15 is an example diagram of a constellation diagram in another embodiment;

[0070] Fig.16 is a structural block diagram of a signal recognition device in an embodiment;

[0071] FIG. 17 is a diagram showing the internal structure of an identification device in one embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] In an exemplary embodiment, as shown in FIG. 1 , a signal recognition method is provided, which is described by taking the method applied to a recognition device as an example, and includes the following steps 10 to 50, wherein:

[0074] Step 10: preprocess the collected signal to be identified to obtain a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified, and determine each special sequence and the actual length of each special sequence through the waveform diagram and the power diagram. The special sequence is a leading sequence or a pilot sequence.

[0075] For the embodiments of the present application, the signal to be identified may be input by a user, or may be collected by a signal acquisition unit of an identification device, or may be collected by an external signal acquisition device and sent to the identification device. This is not specifically limited in the embodiments of the present application; however, no matter in which way the signal to be identified is obtained, the signal sampling rate of the signal to be identified is known.

[0076] Specifically, the preprocessing includes frequency domain spectrum analysis and time domain characteristic analysis; wherein, after the frequency domain spectrum analysis of the signal to be identified, the effective bandwidth BW (Bandwidth) of the signal to be identified can be obtained; the time domain characteristic analysis of the signal to be identified can be performed to obtain the waveform diagram and power diagram of the signal to be identified; wherein the waveform diagram includes the real part waveform diagram and the imaginary part waveform diagram. By analyzing the waveform diagram and the signal sampling rate, the total length T1 of the signal to be identified can be obtained. Specifically, T1 can be determined by formula (1).

[0077] Formula (1); where T1 is the total length of the signal, is the total number of data points determined based on the waveform graph, is the sampling rate.

[0078] Furthermore, based on the characteristics of OFDM signals, there are some repeated special sequences in OFDM signals, such as preamble sequences and pilot sequences, which are all special sequences. In the embodiment of the present application, a special sequence identification component can be called to identify the waveform diagram and power diagram of the signal to be identified, determine each special sequence in the signal to be identified, and determine the actual length of each special sequence.

[0079] Step 20: Estimate the length of each OFDM symbol based on the actual length of each special sequence.

[0080] For the embodiments of the present application, the effective symbol length is generally determined by the number of subcarriers and the sampling rate. After the actual length of the special sequence is determined, the number of subcarriers can be determined based on the actual length of the special sequence, and then the length of each OFDM symbol can be determined based on the number of subcarriers and the sampling rate of the signal to be identified.

[0081] Step 30: Take the length and effective bandwidth of each OFDM symbol as basic parameters, and estimate at least one set of estimated parameters based on the basic parameters. The estimated parameters include at least basic parameters, symbol rate and FFT length. The estimated parameters are parameters required for designing the signal to be identified.

[0082] For the embodiment of the present application, in the stage of forward designing an OFDM signal, multiple parameters are required, wherein the required parameters include cyclic prefix length, subcarrier spacing, OFDM symbol length, time slot structure, FFT (Fast Fourier Transform) length, symbol rate and other parameters. In the embodiment of the present application, it is not necessary to estimate all parameters, only the two key parameters of FFT length and symbol rate need to be estimated.

[0083] In the embodiment of the present application, the design specification of the OFDM signal based on the standard protocol can be queried based on the basic parameters to obtain several possible combinations of FFT length and symbol rate; the basic parameters can also be input into a pre-trained neural network model to obtain several possible combinations of FFT length and symbol rate output by the neural network model. Among them, each combination of FFT length and symbol rate is combined with the basic parameters to form a set of estimated parameters, and each set of estimated parameters may be the parameters used in the stage of designing the signal to be identified.

[0084] Step 40: Map the signal to be identified into a constellation diagram based on each estimated parameter, and determine the modulation type corresponding to each constellation diagram, and determine the target parameter from each estimated parameter based on the modulation type corresponding to each constellation diagram, and the modulation type of the constellation diagram corresponding to the target parameter is a known type.

[0085] Step 50: determine the complete parameters of the signal to be identified based on the target parameters, and identify the signal to be identified based on the complete parameters to obtain an identification result.

[0086] For the embodiment of the present application, for the signal to be identified, after obtaining multiple groups of estimated parameters, the signal to be identified is demodulated based on each group of estimated parameters, and then the demodulated data is obtained, and then the demodulated data is converted into a constellation diagram. The constellation diagram of the OFDM signal is used to visualize the mapping relationship of the modulation symbols on each subcarrier. The constellation diagram is usually displayed on a complex plane, where the horizontal axis represents the real part (I component) and the vertical axis represents the imaginary part (Q component). Different modulation types have different distribution methods on the constellation diagram; common modulation types include BPSK (Binary Phase Shift Keying), QPSK (Quadrature Phase Shift Keying), 16QAM (QuadratureAmplitude Modulation), 64QAM (QuadratureAmplitude Modulation), etc. Therefore, the demodulation type can be characterized by the constellation diagram after the signal to be identified is demodulated by each group of estimated parameters. During the generation (modulation) of the OFDM signal, various parameters of the designed OFDM signal may vary, but the modulation type is selected from known modulation types.

[0087] The known modulation types are organized into a modulation type table, and the constellation diagram recognition component is called to recognize the obtained constellation diagram. If the modulation type represented by the constellation diagram generated after the signal to be identified is demodulated by a set of estimated parameters matches any modulation type in the modulation type table, then it is determined that the modulation type represented by the constellation diagram is a known type, which means that the set of estimated parameters is the parameter used to generate (modulate) the signal to be identified, that is, the target parameter. If the constellation diagram generated after the signal to be identified is demodulated by a set of estimated parameters does not represent a known type, it means that the signal to be identified is not generated (modulated) based on the set of estimated signals.

[0088] Then, according to the determined target parameters (FFT length and symbol rate), combined with the length of each special sequence of the signal to be identified, as well as the waveform diagram and power diagram, other parameters of the signal to be identified are determined, thereby obtaining the complete parameters required for designing the signal to be identified. Then, based on the complete parameters of the signal to be identified, the signal to be identified can be identified to obtain an identification result. Among them, the complete parameters of the signal to be identified can be identified in the design specifications of the OFDM signal based on the standard protocol, or the complete parameters of the signal to be identified can be retrieved in the historical identification library to determine the identification result of the signal to be identified, wherein the historical identification library stores various known OFDM signals and the complete parameters of each OFDM signal.

[0089] In the above signal recognition method, based on the waveform diagram, power diagram and effective bandwidth obtained by preprocessing the signal to be recognized, the actual length of each special sequence in the signal to be recognized is determined, and the length of the OFDM symbol is further estimated according to the actual length of each special sequence, so that the length of each OFDM symbol and the effective bandwidth are used as basic parameters, and from the perspective of forward design of OFDM signal, multiple groups of estimated parameters including basic parameters, FFT length and symbol rate are estimated; further, the multiple groups of estimated parameters are used to map the signal to be recognized into constellation diagrams respectively, and according to the modulation type represented by the constellation diagram, the modulation type represented by the known type is determined as the target parameter from the constellation diagram corresponding to each group of estimated parameters, that is, the target parameter is used to generate the signal to be recognized. The actual parameters used when generating a signal; compared with the related art, the signal recognition method of the present application can not only recognize the OFDM signal of the standard protocol, but also does not require a large number of operations used in blind recognition. Instead, the basic parameters of the signal to be recognized are first determined, and multiple groups of possible estimated parameters are further estimated based on the basic parameters, and then the parameters required to generate the signal to be recognized are determined from the multiple groups of estimated parameters; that is, the signal recognition method of the present application can also estimate the parameters of unknown signals, thereby realizing the recognition of unknown OFDM signals, and because the parameters are estimated based on the determined basic parameters, rather than trying all the parameters one by one, the scheme of the present application can narrow the range of parameters that need to be calculated, thereby improving the efficiency of signal recognition.

[0090] In an exemplary embodiment, as shown in FIG2 , in step 10, steps 11 to 13 may be specifically included, wherein:

[0091] Step 11: Call the special sequence recognition component to analyze the waveform diagram and the power diagram, determine each initial sequence in the signal to be recognized, and determine the characteristic sequence of each initial sequence, where the characteristic sequence is a fragment intercepted from the initial sequence.

[0092] Specifically, the collected signal to be identified is shown in FIG3 , the power diagram obtained by analyzing the signal to be identified is shown in FIG4 , and the waveform diagram is shown in FIG5 .

[0093] In one possible implementation, the special sequence identification component can be constructed based on an algorithm for cyclic prefix identification, or based on a pilot tracking algorithm based on a minimum mean square error, or based on other existing algorithms capable of identifying special sequences. In another possible implementation, the special sequence can also be determined from the signal to be identified based on a marking instruction or an interception instruction input by a user, and then according to the marking instruction and / or the interception instruction of the user.

[0094] After analyzing the waveform diagram and the power diagram through the special sequence recognition component, the initial sequence obtained is the initial special sequence. However, in practice, there may be repeated or non-special sequence parts in each initial special sequence. Therefore, in order to more accurately determine the actual length of each special sequence, further, a fragment is intercepted from each initial sequence as the characteristic sequence of the initial sequence, wherein the length of the characteristic sequence is T2, and T2 is less than the length of the initial sequence; then a more detailed identification is performed based on each characteristic sequence to determine a more accurate special sequence. However, the specific correspondence between the length of the characteristic sequence and the initial sequence is not specifically limited in the embodiments of the present application; in practice, the characteristic sequence is usually taken as 1 / 2 of the initial sequence, or the characteristic sequence is taken as 1 / 3 of the initial sequence; but it should be noted that one endpoint of the characteristic sequence must coincide with one endpoint of the corresponding characteristic sequence.

[0095] Step 12: Perform sliding correlation operations on each feature sequence and the signal to be identified, and determine the feature sequence with repeated sequence content as a repeated sequence pair based on the correlation peak information obtained by the sliding correlation operation.

[0096] Specifically, for a feature sequence of length T2, each feature sequence is subjected to a sliding correlation operation with the signal to be identified; the sliding step length can be a preset value, or can be determined based on the length T2 of the feature sequence, for example, the sliding step length is set to be positively correlated with the length T2 of the feature sequence. The sliding correlation operation is to slide the feature sequence point by point from the starting point to the end point of the signal to be identified, and calculate the correlation value at each position. The correlation value can be calculated by dot product, normalized dot product (i.e., correlation coefficient) or other similarity metrics. The calculation method of the correlation value is not specifically limited in the embodiment of the present application.

[0097] In the sliding correlation results between each feature sequence and the signal to be identified, find the point with the highest correlation value or the point exceeding the preset threshold, that is, the correlation peak. The position of the correlation peak represents the most similar part of the feature sequence and the signal to be identified. If two or more feature sequences produce significant correlation peaks at similar positions in the signal to be identified, then these feature sequences are repeated sequence pairs. Among them, the preset threshold can be set by the user.

[0098] Step 13: For each repeating sequence pair, determine the power distribution of each characteristic sequence in the repeating sequence pair in the power diagram, match the power distribution of each characteristic sequence, and determine the special sequence and the length of the special sequence.

[0099] Specifically, in one possible implementation, for each characteristic sequence in each repeated sequence pair, a power distribution is extracted from the power map; the power map is assumed to be a two-dimensional matrix ,in Indicates time, Represents frequency; for each feature sequence, extract its power distribution in the power diagram, according to the start and end time of the feature sequence and , extract the corresponding row in the power diagram, i.e. ; If the feature sequence has a specific range in the frequency domain, the corresponding column in the power map can also be extracted, that is, . Among them, fs is the frequency corresponding to time ts, and fe is the frequency corresponding to time te.

[0100] Determine a suitable matching criterion for comparing the power distributions of different feature sequences. For example, you can use the correlation coefficient, mean square error (MSE), or other similarity measure; for each pair of repeated sequences, calculate the matching degree of their power distributions. The specific steps include: calculating the correlation coefficient or other similarity measure of the power distributions; if the correlation coefficient is used, assuming that there are two power distributions and , correlation coefficient Calculated by formula (2).

[0101] in: Formula (2); where is the covariance, and is the standard deviation.

[0102] A matching threshold is set based on the matching degree to determine which repeated sequences have power distributions similar enough to determine that they are special sequences; for repeated sequence pairs whose matching degree exceeds the matching threshold, they can be regarded as special sequences. Special sequences can be one or more pairs of repeated sequences; if the special sequence is matched by the time dimension, the length of the special sequence can be taken as the shorter of the time lengths of the two matching sequences; if the special sequence is matched by the frequency dimension, the length of the special sequence can be taken as the shorter of the frequency spans of the two matching sequences.

[0103] Through step 12 and step 13, an actual special sequence that is more accurate than the initial sequence in step 11 can be determined, and then the actual length T3 of each special sequence can be determined.

[0104] In another possible implementation, it is also possible to directly intercept from the power graph of the signal to be identified, intercept the corresponding segment graph based on the length T2 of each characteristic sequence in each repeated sequence pair, and then perform similarity matching and recognition of the graphs through a graph matching model or component to determine the special sequence. Specifically, select the power graphs of several repeated special sequences, draw them on the same graph, and continuously adjust the starting position through the graph matching model so that the several segment graphs overlap or have the same waveform, and then determine the actual length T3 of each repeated special sequence based on the overlapping range or waveform.

[0105] In one embodiment, referring to FIG. 6 , step 30 may specifically include steps 31 to 33, wherein:

[0106] Step 31: input the basic parameters, waveform diagram and power diagram into the estimation model to obtain at least one set of estimation parameters output by the estimation model.

[0107] Specifically, the estimation model is obtained by training the initial model based on multiple training samples. The training samples include the waveform diagram, power diagram, design protocol and some design parameters required for the design sample signal of the sample signal. The sample label of the training sample is the complete parameter of the design sample signal. Some design parameters include at least the effective bandwidth and the length of each OFDM symbol (the length is T4); and the design protocol in the training sample includes standard protocols and unknown protocols.

[0108] Among them, the initial model can be any one of RNN (Recurrent Neural Network), CNN (Convolutional Neural Networks) and GNN (Graph Neural Network), and no specific limitation is made in the embodiments of the present application.

[0109] Step 32: query in the design table to obtain at least one set of complete parameters including basic parameters as estimated parameters, wherein the design table includes complete parameters required for designing a signal based on any standard protocol.

[0110] Among them, in steps 31 and 32, the standard protocol may include Wi-Fi (IEEE 802.11a / g / n / ac / ax), 4GLTE, 5GNR and other protocols. The type of specific standard protocol is not specifically limited in the embodiment of the present application. Among them, the complete parameters of the OFDM signal are designed, including at least parameters such as cyclic prefix length, subcarrier spacing, OFDM symbol length, time slot structure, FFT length and symbol rate. Of course, other types of parameters may also be included, which are not specifically limited in the embodiment of the present application.

[0111] Step 33: Receive at least one set of supplementary parameters input by the user, and construct a set of estimated parameters by combining each set of supplementary parameters with the basic parameters; wherein each set of supplementary parameters includes at least an FFT length and a symbol rate.

[0112] Further, at least one group of possible estimated parameters is determined respectively through step 31, step 32 and step 33, wherein each estimated parameter includes an effective bandwidth and a length of each OFDM symbol, as well as an FFT length and a symbol rate. The obtained groups of estimated parameters are deduplicated, and only one group of two or more groups of estimated parameters with the same FFT length and symbol rate is retained, thereby reducing the occurrence of duplicate estimated parameters.

[0113] In one embodiment, referring to FIG. 7 , step 40 may specifically include step 41 and step 42, wherein:

[0114] Step 41: Determine the frequency offset of the signal to be identified based on at least two special sequences, and compensate the signal to be identified based on the frequency offset to obtain a compensated signal.

[0115] Step 42: Map the compensation signal into constellation diagrams based on the estimated parameters, and determine the modulation type corresponding to each constellation diagram.

[0116] Specifically, the collected signal to be identified may have frequency deviation. The frequency deviation value of the signal is estimated using the determined special sequence, and then the frequency deviation correction processing is performed on the entire signal to be identified to reduce the impact of the frequency deviation on subsequent signal processing. Specifically, the frequency deviation value is calculated through two consecutive special sequences (length T3), and the frequency deviation value is used as the frequency deviation value of the signal to be identified; then, channel compensation is performed on the entire signal to be identified based on the frequency deviation value, thereby obtaining a signal to be identified with better signal quality, that is, a compensated signal; by compensating the signal to be identified to obtain a compensated signal, and using the compensated signal for subsequent signal processing steps, the reliability of the parameters obtained by subsequent analysis can be improved.

[0117] Furthermore, the compensation signal is demodulated based on each estimated parameter to obtain demodulated data, the demodulated data is converted into a constellation diagram, and the modulation type corresponding to each constellation diagram is determined. It is observed whether the modulation type represented by the constellation diagram is a known modulation type; if it is determined that the modulation type represented by a certain constellation diagram is a known modulation type, the symbol rate and FFT length in the estimated parameters corresponding to the constellation diagram can be determined to be the correct target parameters, and then other parameters of the signal to be identified can be determined based on the determined target parameters, thereby realizing the identification of the signal to be identified.

[0118] Further, in an exemplary embodiment, as shown in FIG8 , a signal recognition method is provided, which is described by taking the method applied to a recognition device as an example, and includes the following steps S1 to S8, wherein:

[0119] S1. Analyze the basic characteristics of the signal to be identified: time domain diagram, spectrum diagram, peak-to-average ratio, and total length of the signal.

[0120] S2. Analyze the signal to be identified and find out the length of the special sequence (preamble sequence and pilot sequence).

[0121] S3. The effective bandwidth of the signal to be identified and the length of each OFDM symbol are consulted with the general waveform parameters, and combined with the forward waveform parameter design, possible parameter combinations (effective bandwidth, length of each OFDM symbol, FFT length and symbol rate) are derived.

[0122] S4. Analyze the frequency deviation of the signal to be identified using a continuous special sequence.

[0123] S5. Perform OFDM demodulation on the signal to be identified using possible parameter combinations, and map the demodulated data into a constellation diagram.

[0124] S6. Identify whether the modulation type represented by the constellation diagram is a known modulation type.

[0125] S7. Determine the symbol rate and FFT length, and then identify the CP length.

[0126] S8. Decode the OFDM parameters (complete parameters) and frame structure of the signal to be identified.

[0127] Specifically, in step S1 and step S2, the special sequence is generally a preamble sequence or a pilot sequence. The preamble sequence is used for timing synchronization, and the pilot sequence is used for channel estimation, frequency offset estimation, etc. When analyzing the signal to be identified, the frame structure of the signal to be identified can be analyzed to determine the special sequence. Among them, since the signal to be identified is an OFDM signal, the existing OFDM signal analysis tool can be directly called to analyze the frame structure of the signal to be identified, such as through the Signal Processing Toolbox (Signal Processing Toolbox) or the Communications Toolbox (Communications Toolbox) in MATLAB (Matrix Laboratory) to analyze the frame structure of the signal to be identified.

[0128] Furthermore, the process of determining the actual length (T3) of the special sequence is shown in FIG9 : by observing the waveform diagram and power diagram of the signal to be identified, it can be found that there are some repeated initial sequences; then, from each initial sequence, a characteristic sequence of a part length of T2 is selected; each characteristic sequence of length T2 is respectively subjected to sliding correlation operation with the entire signal to be identified T1; as shown in FIG10 , it is an example of the correlation peak of the special sequence in the sliding correlation operation. Through the situation of the correlation peak, it can be determined that there are several repeated special sequences (repeating sequence pairs), and then the power diagram of each sequence in several repeated special sequences (repeating sequence pairs) is selected and drawn on the same diagram. By continuously adjusting the starting position, overlapping or consistent waveforms, the actual length T3 of each repeated special sequence can be known.

[0129] In one example, for example, the lengths of several selected repetitive sequences are all 2000 (it can be determined through the above-mentioned correlation peak calculation that the spacing distance of each repetitive sequence is the same); the power graphs of these repetitive sequences are displayed on the same graph for waveform overlap comparison; if it is determined that the power graphs of these repetitive sequences completely overlap, the lengths of several more repetitive sequences are further increased, for example, a length of 3000 is selected, and they are again drawn on the same graph for waveform overlap comparison. If it is found that there is no complete overlap, the length of the overlapping part can be used as the actual length T3 of the special sequence; for example, the power graphs of two repetitive sequences overlap in the middle part and do not overlap at both ends, then the length of the overlapping part is the actual length T3 of the special sequence.

[0130] Specifically, referring to FIG. 11 , the specific implementation process of steps S3-S8 includes: determining the effective bandwidth BW of the signal to be identified based on the power diagram of the entire signal to be identified, and predicting the length (T4) of each OFDM symbol through the actual length T3 of the special sequence determined in steps S1 and S2. Further, according to the effective bandwidth of the signal to be identified and each Symbol length T4, forward design of OFDM waveform signal, that is, to estimate the possible signal symbol rate and FFT length parameter combination , and . Further, according to the signal bandwidth (effective bandwidth) and each The length of the symbol is used to retrieve the general LTE standard protocol, the NR standard protocol, and the Wi-Fi standard protocol; wherein the general LTE standard protocol is shown in FIG12, and the Wi-Fi standard protocol is shown in FIG13. Fig.13 In determining the effective bandwidth After calculating the length of each OFDM symbol, find the possible signal symbol rate and FFT length parameter combination based on the standard protocol. .

[0131] Each parameter combination determined is compared with the basic parameter (effective bandwidth and each The length of the symbol) constitutes a set of estimation parameters. An exemplary estimation parameter composition is as follows Fig.14 As shown, the basic parameters also include the transmission redundancy of the OFDM signal, and the transmission redundancy may be one of the cyclic prefix, the guard interval, the preamble sequence, the pilot sequence and the redundant coding, which is not specifically limited in the embodiments of the present application. Each set of estimated parameters is further used to demodulate the OFDM signal to be identified in turn, and then a constellation diagram is drawn for the demodulated data; wherein, an example of a constellation diagram is shown in FIG5. Observe whether the modulation type represented by the constellation diagram is a known modulation type; if it is determined that the modulation type represented by a certain constellation diagram is a known modulation type, the symbol rate and FFT length in the estimated parameters corresponding to the constellation diagram can be determined as the correct target parameters, and then other parameters of the signal to be identified can be determined based on the determined target parameters, thereby realizing the identification of the signal to be identified.

[0132] In practice, the collected signal to be identified may have frequency deviation. Through two consecutive special sequences T3, the frequency deviation value of the signal to be identified is calculated, and then channel compensation is performed on the entire signal to be identified based on the frequency deviation to obtain a compensated signal to reduce the impact of the frequency deviation on subsequent signal processing, thereby improving the signal quality and the reliability of subsequent analysis parameters.

[0133] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0134] Based on the same inventive concept, the embodiment of the present application also provides a signal recognition device for implementing the signal recognition method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more signal recognition device embodiments provided below can refer to the limitations on the signal recognition method above, and will not be repeated here.

[0135] In an exemplary embodiment, Fig.16 As shown, a signal recognition device is provided, including a preprocessing module 1601, a first estimation module 1602, a second estimation module 1603, a target parameter determination module 1604 and an identification module 1605, wherein:

[0136] The preprocessing module 1601 is used to preprocess the collected signal to be identified to obtain a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified, and determine each special sequence and the actual length of each special sequence through the waveform diagram and the power diagram, wherein the special sequence is a leading sequence or a pilot sequence;

[0137] The first estimation module 1602 is used to estimate the length of each OFDM symbol according to the actual length of each special sequence.

[0138] The second estimation module 1603 is used to use the length and effective bandwidth of each OFDM symbol as basic parameters, and estimate at least one set of estimated parameters based on the basic parameters. The estimated parameters include at least basic parameters, symbol rate and FFT length. The estimated parameters are parameters required for designing the signal to be identified.

[0139] The target parameter determination module 1604 is used to map the signal to be identified into a constellation diagram based on each estimated parameter, and determine the modulation type corresponding to each constellation diagram, and determine the target parameter from each estimated parameter based on the modulation type corresponding to each constellation diagram, and the modulation type of the constellation diagram corresponding to the target parameter is a known type.

[0140] The identification module 1605 is used to determine the complete parameters of the signal to be identified based on the target parameters, and identify the signal to be identified based on the complete parameters to obtain an identification result.

[0141] In the above-mentioned signal recognition device, based on the waveform diagram, power diagram and effective bandwidth obtained by preprocessing the signal to be recognized, the actual length of each special sequence in the signal to be recognized is determined, and the length of the OFDM symbol is further estimated according to the actual length of each special sequence, so that the length of each OFDM symbol and the effective bandwidth are used as basic parameters, and from the perspective of forward design of OFDM signal, multiple groups of estimated parameters including basic parameters, FFT length and symbol rate are estimated; further, the multiple groups of estimated parameters are used to map the signal to be recognized into constellation diagrams respectively, and according to the modulation type represented by the constellation diagram, the modulation type represented by the known type is determined as the target parameter from the constellation diagram corresponding to each group of estimated parameters, that is, the target parameter is used to generate the signal to be recognized. The actual parameters used when generating a signal; compared with the related art, the signal recognition method of the present application can not only recognize the OFDM signal of the standard protocol, but also does not require a large number of operations used in blind recognition. Instead, the basic parameters of the signal to be recognized are first determined, and multiple groups of possible estimated parameters are further estimated based on the basic parameters, and then the parameters required to generate the signal to be recognized are determined from the multiple groups of estimated parameters; that is, the signal recognition method of the present application can also estimate the parameters of unknown signals, thereby realizing the recognition of unknown OFDM signals, and because the parameters are estimated based on the determined basic parameters, rather than trying all the parameters one by one, the scheme of the present application can narrow the range of parameters that need to be calculated, thereby improving the efficiency of signal recognition.

[0142] In one embodiment, the preprocessing module 1601 is specifically used to:

[0143] Call the special sequence recognition component to analyze the waveform diagram and the power diagram, determine each initial sequence in the signal to be recognized, and determine the characteristic sequence of each initial sequence, where the characteristic sequence is a fragment intercepted from the initial sequence;

[0144] Perform sliding correlation operations on each characteristic sequence and the signal to be identified, and determine the characteristic sequence with repeated sequence content as a repeated sequence pair according to the correlation peak information obtained by the sliding correlation operation;

[0145] For each repeating sequence pair, in the power diagram, the power distribution of each characteristic sequence in the repeating sequence pair is determined, and the power distribution of each characteristic sequence is matched to determine the special sequence and the length of the special sequence.

[0146] In one embodiment, the second estimation module 1603 is specifically configured to:

[0147] Inputting the basic parameters, the waveform diagram and the power diagram into the estimation model to obtain at least one set of estimation parameters output by the estimation model;

[0148] The estimation model is obtained by training the initial model based on multiple training samples. The training samples include a waveform diagram, a power diagram, a design protocol, and some design parameters required for the design sample signal. The sample labels of the training samples are complete parameters of the design sample signal. Some design parameters include at least an effective bandwidth and the length of each OFDM symbol.

[0149] Among them, the designed protocols in the training samples include standard protocols and unknown protocols.

[0150] In one embodiment, the second estimation module 1603 is further configured to:

[0151] The design table is queried to obtain at least one set of complete parameters including basic parameters as estimated parameters, wherein the design table includes complete parameters required for designing a signal based on any standard protocol.

[0152] In one embodiment, the target parameter determination module 1604 is specifically configured to:

[0153] Determine a frequency deviation of a signal to be identified based on at least two special sequences, and compensate the signal to be identified based on the frequency deviation to obtain a compensated signal;

[0154] The compensation signal is mapped into a constellation diagram based on each estimated parameter, and the modulation type corresponding to each constellation diagram is determined.

[0155] In one embodiment, the target parameter determination module 1604 is specifically configured to:

[0156] Demodulating the compensation signals based on the estimated parameters to obtain demodulated data;

[0157] The demodulated data is converted into a constellation diagram, and the modulation type corresponding to each constellation diagram is determined.

[0158] Each module in the above signal recognition device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the recognition device in the form of hardware, or can be stored in the memory in the recognition device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0159] In an exemplary embodiment, an identification device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG17. The identification device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the identification device is used to provide computing and control capabilities. The memory of the identification device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the identification device is used to exchange information between the processor and an external device. The communication interface of the identification device is used to communicate with an external terminal in a wired or wireless manner, and the wireless type can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a signal recognition method is realized. The display unit of the identification device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the recognition device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the recognition device shell, or an external keyboard, touchpad or mouse.

[0160] Those skilled in the art will understand that the structure shown in FIG. 17 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the identification device to which the scheme of the present application is applied. The specific identification device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0161] In an exemplary embodiment, an identification device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the signal identification method as described in any one of the above method embodiments are implemented.

[0162] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the signal recognition method as described in any one of the above method embodiments are implemented.

[0163] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the signal recognition method as described in any one of the above method embodiments.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0165] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0166] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] The above-described embodiments only express several implementation types of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A signal recognition method, characterized in that: The method comprises: Preprocessing the collected signal to be identified to obtain a waveform diagram, a power diagram and an effective bandwidth of the signal to be identified; Calling a special sequence recognition component to analyze the waveform diagram and the power diagram, determine each initial sequence in the signal to be recognized, and determine a characteristic sequence of each initial sequence, wherein the characteristic sequence is a fragment intercepted from the initial sequence; Performing sliding correlation operations on each of the characteristic sequences and the signal to be identified, and determining the characteristic sequences with repeated sequence contents as repeated sequence pairs according to the correlation peak information obtained by the sliding correlation operations; For each of the repeated sequence pairs, in the power graph, determining the power distribution of each of the characteristic sequences in the repeated sequence pair, matching the power distribution of each of the characteristic sequences, determining a special sequence and an actual length of the special sequence, wherein the special sequence is a leading sequence or a pilot sequence; estimating the length of each OFDM symbol according to the actual length of each of the special sequences; Taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, the estimated parameters at least including the basic parameters, symbol rate and FFT length, and the estimated parameters are parameters required for designing the signal to be identified; Determine the frequency deviation of the signal to be identified based on at least two of the special sequences, and compensate the signal to be identified based on the frequency deviation to obtain a compensated signal; Mapping the compensation signal into a constellation diagram based on each of the estimated parameters, and determining a modulation type corresponding to each of the constellation diagrams; Based on the modulation type corresponding to each of the constellation diagrams, determining a target parameter from each of the estimated parameters, the modulation type of the constellation diagram corresponding to the target parameter being a known type; The complete parameters of the signal to be identified are determined based on the target parameters, and the signal to be identified is identified based on the complete parameters to obtain an identification result.

2. The method according to claim 1, characterized in that The taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, comprises: Inputting the basic parameters, the waveform diagram and the power diagram into an estimation model to obtain at least one set of estimation parameters output by the estimation model; The estimation model is obtained by training an initial model based on a plurality of training samples, wherein the training samples include a waveform diagram of a sample signal, a power diagram, a design protocol, and some design parameters required for designing the sample signal, and the sample labels of the training samples are complete parameters for designing the sample signal, and the some design parameters include at least an effective bandwidth and a length of each OFDM symbol; The designed protocols in the training samples include standard protocols and unknown protocols.

3. The method according to claim 1, characterized in that The taking the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimating at least one set of estimated parameters based on the basic parameters, comprises: The design table is queried to obtain at least one set of complete parameters including the basic parameters as estimated parameters, wherein the design table includes complete parameters required for designing a signal based on any standard protocol.

4. The method according to claim 1, characterized in that: The step of mapping the compensation signal into a constellation diagram based on each of the estimated parameters and determining a modulation type corresponding to each of the constellation diagrams includes: Demodulating the compensation signal based on each of the estimated parameters to obtain demodulated data; The demodulated data is converted into a constellation diagram, and the modulation type corresponding to each constellation diagram is determined.

5. A signal recognition device, characterized in that: The device comprises a preprocessing module, a first estimation module, a second estimation module, a target parameter determination module and an identification module, wherein: A preprocessing module, used for preprocessing the collected signal to be identified, obtaining the waveform diagram, power diagram and effective bandwidth of the signal to be identified, and calling the special sequence identification component to analyze the waveform diagram and the power diagram, determine each initial sequence in the signal to be identified, and determine the characteristic sequence of each initial sequence, wherein the characteristic sequence is a fragment intercepted from the initial sequence; perform sliding correlation operation on each characteristic sequence and the signal to be identified, and determine the characteristic sequence with repeated sequence content as a repeated sequence pair according to the correlation peak information obtained by the sliding correlation operation; for each repeated sequence pair, determine the power distribution of each characteristic sequence in the repeated sequence pair in the power diagram, match the power distribution of each characteristic sequence, determine the special sequence and the actual length of the special sequence, wherein the special sequence is a leading sequence or a pilot sequence; A first estimation module, used for estimating the length of each OFDM symbol according to the actual length of each special sequence; A second estimation module, configured to use the length of each OFDM symbol and the effective bandwidth as basic parameters, and estimate at least one set of estimated parameters based on the basic parameters, wherein the estimated parameters at least include the basic parameters, a symbol rate, and an FFT length, and the estimated parameters are parameters required for designing the signal to be identified; A target parameter determination module, used to determine the frequency deviation of the signal to be identified based on at least two of the special sequences, and compensate the signal to be identified based on the frequency deviation to obtain a compensated signal; map the compensated signal into a constellation diagram based on each of the estimated parameters, and determine the modulation type corresponding to each of the constellation diagrams; determine the target parameter from each of the estimated parameters based on the modulation type corresponding to each of the constellation diagrams, the modulation type of the constellation diagram corresponding to the target parameter being a known type; The identification module is used to determine the complete parameters of the signal to be identified based on the target parameters, and identify the signal to be identified based on the complete parameters to obtain an identification result.

6. The device according to claim 5, characterized in that The second estimation module is specifically used for: Inputting the basic parameters, the waveform diagram and the power diagram into an estimation model to obtain at least one set of estimation parameters output by the estimation model; The estimation model is obtained by training an initial model based on a plurality of training samples, wherein the training samples include a waveform diagram of a sample signal, a power diagram, a design protocol, and some design parameters required for designing the sample signal, and the sample labels of the training samples are complete parameters for designing the sample signal, and the some design parameters include at least an effective bandwidth and a length of each OFDM symbol; The designed protocols in the training samples include standard protocols and unknown protocols.

7. The device according to claim 5, characterized in that The second estimation module is further used for: The design table is queried to obtain at least one set of complete parameters including the basic parameters as estimated parameters, wherein the design table includes complete parameters required for designing a signal based on any standard protocol.

8. The device according to claim 5, characterized in that The target parameter determination module is specifically used for: Demodulating the compensation signal based on each of the estimated parameters to obtain demodulated data; The demodulated data is converted into a constellation diagram, and the modulation type corresponding to each constellation diagram is determined.

9. An identification device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images