Broadband signal type identification method, device and equipment, medium and computer product

Abstract

The invention discloses a broadband signal type identification method and device, equipment, a storage medium and a computer product, and relates to the technical field of signal identification, and the method comprises the steps: obtaining a to-be-identified broadband signal, determining to-be-identified frequency point signals distributed in the to-be-identified broadband signal, obtaining the pilot frequency feature information of all to-be-identified frequency point signals, and obtaining the pilot frequency feature information of the to-be-identified frequency point signals; and for each to-be-identified frequency point signal, comparing the pilot frequency characteristic information of the to-be-identified frequency point signal with at least one piece of preset pilot frequency template information to obtain a comparison result, and based on the comparison result, obtaining a signal type identification result of the to-be-identified frequency point signal, the technical effect of improving the broadband signal type identification efficiency by using the signal pilot frequency characteristics is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of signal recognition, and in particular to a method, device, equipment, storage medium and computer product for identifying broadband signal types. Background Art

[0002] The recognition and analysis of communication signals can provide more assistance for further information processing and applications, and has important practical significance in the fields of military reconnaissance, electronic countermeasure, information network security, etc.

[0003] In the related art, the methods for identifying and analyzing broadband signal types usually involve: one is a modulation recognition method that discriminates through specific parameters or corresponding spectral characteristics of different modulation types of the target signal, and the other is to identify the signal type through a deep learning model trained iteratively. However, the former requires the modulation type recognition of the target signal and the corresponding demodulation operation processing, while the latter requires a large number of labeled samples for model training, which both increase the computational complexity of signal type recognition and the deployment cost, thus affecting the efficiency of signal type recognition. Summary of the Invention

[0004] The main purpose of the present application is to provide a method, device, equipment, storage medium and computer product for identifying broadband signal types, aiming to solve the technical problem of low signal type recognition efficiency in the related art for broadband signal type recognition.

[0005] To achieve the above object, the present application proposes a method for identifying broadband signal types, and the method includes:

[0006] Obtain the broadband signal to be recognized;

[0007] Determine the frequency point signals to be recognized distributed in the bandwidth signal to be recognized, and obtain the pilot feature information of all the frequency point signals to be recognized;

[0008] For each frequency point signal to be recognized, compare the pilot feature information of the frequency point signal to be recognized with at least one preset pilot template information to obtain a comparison result;

[0009] Based on the comparison result, obtain the signal type recognition result of the frequency point signal to be recognized.

[0010] In one embodiment, the pilot feature information includes first basic parameter information and a first time-frequency matrix, and the preset pilot template information includes second basic parameter information and a second time-frequency matrix;

[0011] The step of comparing the pilot feature information of the frequency point signal to be recognized with at least one preset pilot template information to obtain a comparison result includes:

[0012] Compare the first basic parameter information and the second basic parameter information;

[0013] If the first basic parameter information and the second basic parameter information match, then compare the first time-frequency matrix and the second time-frequency matrix to obtain the similarity information of the first time-frequency matrix and the second time-frequency matrix.

[0014] In one embodiment, the step of comparing the first time-frequency matrix and the second time-frequency matrix to obtain the similarity information of the first time-frequency matrix and the second time-frequency matrix includes:

[0015] Reduce the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix to obtain the adjusted first time-frequency matrix and the second time-frequency matrix; wherein, the dynamic range difference includes the signal peak difference and the noise level difference;

[0016] Calibrate the pilot positions of the adjusted first time-frequency matrix and the second time-frequency matrix;

[0017] Compare the calibrated first time-frequency matrix and the second time-frequency matrix to obtain the similarity information of the first time-frequency matrix and the second time-frequency matrix.

[0018] In one embodiment, the step of reducing the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix to obtain the adjusted first time-frequency matrix and the second time-frequency matrix includes:

[0019] Determine the to-be-processed time-frequency matrix with relatively larger matrix strength from the first time-frequency matrix and the second time-frequency matrix;

[0020] Perform compression processing on the to-be-processed time-frequency matrix to reduce the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix, and obtain the adjusted first time-frequency matrix and the second time-frequency matrix.

[0021] In one embodiment, the step of calibrating the pilot positions of the adjusted first time-frequency matrix and the second time-frequency matrix includes:

[0022] Taking the adjusted second time-frequency matrix as a reference, perform matrix translation processing on the adjusted first time-frequency matrix to obtain the first time-frequency matrix with calibrated pilot positions.

[0023] In one embodiment, the step of comparing the calibrated first time-frequency matrix and the second time-frequency matrix to obtain the similarity information of the first time-frequency matrix and the second time-frequency matrix includes:

[0024] Based on a preset similarity calculation function, determine the similarity difference between the first time-frequency matrix and the second time-frequency matrix;

[0025] Based on the relationship between the similarity difference and a preset threshold, determine the similarity information of the first time-frequency matrix and the second time-frequency matrix.

[0026] Second aspect, to achieve the above object, the present application further provides a broadband signal type identification device, which includes:

[0027] An acquisition module, configured to acquire the broadband signal to be identified;

[0028] A determination module, configured to determine the frequency point signals to be identified distributed in the broadband signal to be identified, and obtain the pilot feature information of all the frequency point signals to be identified;

[0029] A comparison module, configured to, for each frequency point signal to be identified, compare the pilot feature information of the frequency point signal to be identified with at least one preset pilot template information to obtain a comparison result;

[0030] An identification module, based on the comparison result, obtains the signal type identification result of the frequency point signal to be identified.

[0031] Third aspect, to achieve the above object, the present application further provides a broadband signal type identification device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the above broadband signal type identification method.

[0032] Fourth aspect, to achieve the above object, the present application further provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the above broadband signal type identification method are implemented.

[0033] Fifth aspect, to achieve the above object, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the above broadband signal type identification method are implemented.

[0034] One or more technical solutions proposed by the present application have at least the following technical effects:

[0035] In the same communication system, the pilot characteristics of signals of the same signal type are usually set to be the same, and the power of the pilot signal is usually designed to be higher than that of the data signal. Based on this, in this application, a broadband signal to be identified is obtained, and the frequency point signals to be identified distributed in the broadband signal to be identified are determined. Subsequently, according to the pilot characteristic information of all the frequency point signals to be identified, for each frequency point signal to be identified, the pilot characteristic information of the frequency point signal to be identified is compared with at least one preset pilot template information, so as to realize the signal type recognition result by using the pilot characteristics between signals. This application does not rely on the recognition of the modulation type of the target signal and subsequent demodulation operations, and does not require a large number of sample annotation operations. Only the preset pilot template information needs to be accumulated to identify signals with specific pilot characteristics. Therefore, the overall calculation efficiency is high, and this application has an efficient and accurate recognition effect on complex frame structures or composite modulation type signals with obvious pilot characteristics accumulated in the early stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a schematic flowchart of a method for identifying the type of a broadband signal in an embodiment of the present application.

[0039] Figure 2 It is a schematic flowchart of a method for identifying the type of a broadband signal in a specific embodiment of the present application.

[0040] Figure 3 It is a schematic structural diagram of a device for identifying the type of a broadband signal in the present application.

[0041] Figure 4 It is a schematic structural diagram of a device for identifying the type of a broadband signal in the present application.

[0042] The realization of the purpose, functional features and advantages of the present application will be further described with reference to the embodiments and the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0044] To better understand the technical solution of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0045] In the related art, the methods for identifying and analyzing broadband signal types usually involve: one is a modulation recognition method that discriminates through specific parameters or corresponding spectral characteristics of different modulation types of the target signal, and the other is to identify the signal type through a deep learning model trained iteratively. However, the former requires modulation type recognition and corresponding demodulation operation processing of the target signal, while the latter requires a large number of labeled samples for model training, which both increase the computational complexity of signal type recognition and the deployment cost, thereby affecting the efficiency of signal type recognition.

[0046] In view of the problem of low efficiency in signal type recognition in the related art, the present application provides a solution: by performing similarity analysis on the pilot time-frequency characteristics of the signal at the frequency point to be recognized on the broadband signal to be recognized, the algorithm purpose of accurately recognizing a specific type of signal is achieved.

[0047] Signal pilots are a special type of signal used in wireless and wired communications. They are usually used to help the receiving device perform key tasks such as synchronization, channel estimation, and frequency correction at the receiving end. Due to the design of pilot signals being affected by various factors such as occupied bandwidth, power allocation, and system capacity, they are usually distributed in the time domain and frequency domain in a fixed pattern. Making full use of this can be used to detect and identify certain signal types of our interest in certain situations. The present application precisely realizes the accurate recognition of specific category signals by performing similarity analysis on the pilot time-frequency characteristics of the target signal to support work in related fields.

[0048] Based on this, the embodiments of the present application provide a method for identifying broadband signal types, referring to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the method for identifying broadband signal types of the present application.

[0049] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a broadband signal type recognition device, etc. that can implement the above functions. Hereinafter, the broadband signal type recognition device will be taken as an example to illustrate this embodiment and the following embodiments.

[0050] In this embodiment, the method for identifying broadband signal types includes steps S10 to S40:

[0051] Step S10, obtain the broadband signal to be recognized.

[0052] Step S20: Determine the frequency point signals to be recognized distributed in the broadband signal to be recognized, and obtain the pilot feature information of all the frequency point signals to be recognized.

[0053] It should be noted that the broadband signal to be recognized is the overall signal that needs to be analyzed. It has a large bandwidth and a large frequency spectrum range, can contain multiple frequency components, and can support the transmission of various types of signals (such as voice, video, data, etc.).

[0054] The frequency point signal to be recognized is the signal at a specific frequency point extracted from the broadband signal to be recognized. Exemplarily, by performing spectrum analysis or filtering on the broadband signal, the broadband signal can be decomposed into multiple independent frequency point signals. Each frequency point signal corresponds to the component of the broadband signal at a specific frequency, and it can be used as an independent signal type recognition unit.

[0055] The pilot feature information is data related to the frequency point signal to be recognized and contains the pilot characteristics describing the frequency point signal to be recognized, which provides a basis for the subsequent signal type recognition step.

[0056] In a specific example, a real-time broadband signal to be recognized can be obtained, the signals at each frequency point existing in the broadband signal to be recognized are detected to obtain their positions, and they are separated from the broadband signal to be recognized to obtain the frequency point signals to be recognized, and each frequency point signal to be recognized is analyzed to obtain the pilot feature information corresponding to the frequency point signal to be recognized.

[0057] Step S30: For each frequency point signal to be recognized, compare the pilot feature information of the frequency point signal to be recognized with at least one preset pilot template information to obtain a comparison result.

[0058] It should be noted that the preset pilot template information is pre-defined and stored pilot reference data. Each type of pilot reference data is used to describe the typical pilot characteristics of a signal type, and it can be obtained by analyzing the accumulated typical sample signals in the early stage.

[0059] It can be understood that the broadband signal to be recognized may contain multiple frequency point signals to be recognized, and there is more than one type of stored preset pilot template information. Each frequency point signal to be recognized needs to be compared with all the pilot template information to ensure the integrity of the comparison result.

[0060] It is worth mentioning that the comparison operations of multiple frequency point signals to be recognized with the preset pilot template information can be processed in parallel on a GPU with a general architecture, with high overall computing efficiency and strong device compatibility.

[0061] In a feasible implementation manner, the pilot feature information includes first basic parameter information and a first time-frequency matrix, and the preset pilot template information includes second basic parameter information and a second time-frequency matrix. Step S30 further includes steps A10 to A20:

[0062] Step A10, compare the first basic parameter information and the second basic parameter information.

[0063] Step A20, if the first basic parameter information and the second basic parameter information match, then compare the first time-frequency matrix and the second time-frequency matrix to obtain similarity information of the first time-frequency matrix and the second time-frequency matrix.

[0064] It should be noted that the first basic parameter information is the basic parameter of the signal at the frequency point to be recognized, such as symbol rate information, signal bandwidth information, etc., and the second basic parameter information is the basic parameter of the typical sample signal, such as symbol rate information, signal bandwidth information, etc.

[0065] The first time-frequency matrix is a time-frequency matrix obtained by performing time-frequency analysis on the signal at the frequency point to be recognized, which reflects the time-frequency domain of the signal at the frequency point to be recognized. The second time-frequency matrix is a time-frequency matrix obtained by performing time-frequency analysis on the typical sample signal, which reflects the time-frequency domain of the typical sample signal. It can be understood that the pilot feature of the signal is reflected through time-frequency analysis. By performing time-frequency analysis on the signal at the frequency point to be recognized and the typical sample signal, the pilot feature of the signal at the frequency point to be recognized and the pilot feature of the typical sample signal can be obtained.

[0066] Specifically, in this implementation manner, first, according to the preset matching rule, the first basic parameter information corresponding to the signal at the frequency point to be recognized and the second basic parameter information are matched. If the first basic parameter and the second basic parameter match, then the signal at the frequency point to be recognized is subjected to time-frequency transformation processing to obtain the first time-frequency matrix corresponding to the signal at the frequency point to be recognized, and the first time-frequency matrix of the signal at the frequency point to be recognized and the second time-frequency matrix of the typical sample signal are further compared and analyzed to obtain similarity information of the first time-frequency matrix and the second time-frequency matrix.

[0067] It can be understood that through the comparison of the first basic parameter information and the second basic parameter information, the initial screening of the signal at the frequency point to be recognized can be realized, filtering out the signal at the frequency point to be recognized that does not match the second basic parameter information, reducing the calculation amount of the subsequent time-frequency matrix comparison, and further improving the recognition efficiency.

[0068] Furthermore, the second time-frequency matrix and the second basic parameter information can be pre-stored, which omits the step of performing time-frequency analysis on the typical sample signal during the recognition process, and further improves the recognition efficiency.

[0069] In another feasible embodiment, step A20 may further include steps B10 to B30:

[0070] Step B10, reducing the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix to obtain the adjusted first time-frequency matrix and the second time-frequency matrix; wherein, the dynamic range difference includes the signal peak difference and the noise level difference.

[0071] Step B20, calibrating the pilot positions of the adjusted first time-frequency matrix and the second time-frequency matrix.

[0072] Step B30, comparing the calibrated first time-frequency matrix and the second time-frequency matrix to obtain the similarity information of the first time-frequency matrix and the second time-frequency matrix.

[0073] It should be noted that the adjustment part of the dynamic range difference is mainly for the difference between the signal peak and the average noise level. It can be understood that the energy values of the pilot signals in the first time-frequency matrix and the second time-frequency matrix may vary due to factors such as channel attenuation and transmit power. The background noise intensities of the two matrices may change due to different receiving environments or devices. By adjusting the dynamic range difference, the influence of signal strength or noise differences on the similarity of pilot features can be avoided, and the accuracy of the comparison result can be improved.

[0074] The pilot position refers to the distribution position of the pilot signal in the time-frequency matrix. Calibrating the pilot position can ensure the alignment of the pilot signals in the two matrices, facilitating the accurate comparison of their distribution patterns and similarities.

[0075] Specifically, in this embodiment, by reducing the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix, that is, by adjusting the signal strength ranges of the two, the signal peak difference and the noise level difference are reduced, so as to obtain the adjusted first time-frequency matrix and the second time-frequency matrix, ensuring that the subsequent pilot feature comparison is not affected by intensity fluctuations. Then, the pilot positions of the adjusted first time-frequency matrix and the second time-frequency matrix are calibrated to align the distribution positions of the pilot signals in the two matrices in time and frequency, avoiding misjudgment caused by position offset. Finally, the calibrated first time-frequency matrix and the second time-frequency matrix are compared, and the similarity information between the two is calculated, obtaining a relatively accurate similarity calculation result.

[0076] In yet another feasible embodiment, step B10 may further include steps B11 to B12. Step B20 may further include step B21.

[0077] Step B11, determining the to-be-processed time-frequency matrix with relatively larger matrix strength from the first time-frequency matrix and the second time-frequency matrix.

[0078] Step B12: Perform compression processing on the time-frequency matrix to be processed, so as to narrow the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix, and obtain the adjusted first time-frequency matrix and second time-frequency matrix.

[0079] Step B21: Using the adjusted second time-frequency matrix as a reference, perform matrix translation processing on the adjusted first time-frequency matrix to obtain the first time-frequency matrix with pilot position calibrated.

[0080] It should be noted that the matrix strength refers to the overall level of signal energy in the first time-frequency matrix and the second time-frequency matrix, usually measured by the numerical size of matrix elements. Compression processing reduces the signal dynamic range of the time-frequency matrix with higher matrix strength through non-linear transformation or amplitude adjustment, etc., so that its dynamic range matches that of another matrix.

[0081] Exemplarily, the difference in dynamic range is adjusted considering two factors: signal peak value and noise mean value. See the following pseudo-code for details:

[0082]

[0083] Let

[0084]

[0085] Let

[0086]

[0087] if R T > R S then

[0088]

[0089] else

[0090]

[0091] end

[0092] Wherein, R S represents the matrix strength of the first time-frequency matrix, R T represents the matrix strength of the second time-frequency matrix, N S represents the noise mean value of the first time-frequency matrix, N T represents the noise mean value of the second time-frequency matrix. M S represents the first time-frequency matrix, M T represents the second time-frequency matrix, represents the logarithmic transformation value of the first time-frequency matrix, represents the logarithmic transformation value of the second time-frequency matrix.

[0093] Specifically, the matrix strength is measured by using the noise mean and the peak (maximum) intensity of the video matrix. The time-frequency matrix with relatively large matrix strength is selected for compression processing to narrow the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix. During this process, the first time-frequency matrix M S and the second time-frequency matrix M T are subjected to logarithmic transformation processing to initially obtain the logarithmic change value of the time-frequency matrix and to reflect the signal-to-noise ratio characteristic of the matrix.

[0094] It can be understood that the above dynamic range adaptive adjustment part is mainly for the matching adjustment of the logarithmic transformation values of the signal peak and the average noise level of the first time-frequency matrix or the second time-frequency matrix. Since there are usually cases where the signal-to-noise ratio of the signal is not good in the actual application field, the logarithmic transformation uses log2 instead of the commonly used log 10 . And when performing adaptive adjustment, the signal with stronger matrix strength is selected for compression processing instead of amplifying the weaker signal to ensure that the noise is not amplified and the signal quality is not affected during adaptive adjustment.

[0095] Furthermore, during the matrix calibration process, based on the adjusted second time-frequency matrix, the adjusted first time-frequency matrix is subjected to matrix translation processing to obtain the first time-frequency matrix with the pilot position calibrated. See the following pseudocode for details:

[0096] Initialize Δl = 0, i = 0

[0097]

[0098] Δl = Δl + 1

[0099] i = i + 1

[0100] end

[0101]

[0102] where rownean represents mean processing, represents the first time-frequency matrix after logarithmic transformation processing of the i-th column, represents the second time-frequency matrix after logarithmic transformation processing of the i-th column, δ represents the calibration tolerance, represents the first time-frequency matrix after logarithmic transformation processing after the Δl-th column.

[0103] Specifically, based on the second time-frequency matrix after logarithmic transformation processing, if the absolute value of the column mean between the two matrices is less than the calibration tolerance δ, then for the first time-frequency matrix Perform matrix translation processing until the absolute value of the column mean is greater than or equal to the calibration tolerance δ.

[0104] It can be understood that there may also be different frequencies between the frequency point signals to be recognized and the typical sample signals of the same signal type (such as sound signals of different frequencies), which may cause the pilot features between the frequency point signals to be recognized of the same signal type to be reflected in different time dimensions. Therefore, it is necessary to perform calibration processing on the signals so that the distribution positions of the pilot features in the two matrices are aligned in time and frequency, avoiding misjudgment caused by position offset. And calibrating the first time-frequency matrix based on the second time-frequency matrix as a reference can improve the calibration efficiency to a certain extent.

[0105] In this embodiment, step B30 further includes steps B31 to B32:

[0106] Step B31, determine the similarity difference between the first time-frequency matrix and the second time-frequency matrix based on a preset similarity calculation function.

[0107] Step B32, determine the similarity information between the first time-frequency matrix and the second time-frequency matrix based on the relationship between the similarity difference and a preset threshold.

[0108] It should be noted that the similarity calculation function is used to calculate the similarity difference between the first time-frequency matrix and the second time-frequency matrix after compression and calibration. The similarity difference between the first time-frequency matrix and the second time-frequency matrix after compression and calibration can be determined according to the relationship between the similarity difference and the preset threshold. The preset threshold can be used as a standard for judging whether the frequency point signal to be recognized and the typical sample signal are of the same signal type.

[0109] Exemplarily, the similarity calculation function can be seen in Formula 1:

[0110]

[0111] where r represents the similarity difference between the first time-frequency matrix and the second time-frequency matrix after compression and calibration.

[0112] It can be understood that by calculating the difference degree between the two matrices and according to the relationship between the difference degree and the preset threshold, the similarity degree between the first time-frequency matrix and the second time-frequency matrix can be determined to obtain the similarity information between the first time-frequency matrix and the second time-frequency matrix.

[0113] Step S40, obtain the signal type recognition result of the frequency point signal to be recognized based on the comparison result.

[0114] It should be noted that the comparison result is the result obtained by comparing the pilot feature information of the signal of the frequency point to be recognized with at least one preset pilot template information. It can be understood that in this embodiment, the comparison result between each pilot feature information and each preset pilot template information can be represented by the similarity information between the first time-frequency matrix and the second time-frequency matrix.

[0115] Specifically, if the similarity difference r between the first time-frequency matrix and the second time-frequency matrix is less than the preset threshold, it can be considered that the pilot feature of the signal of the frequency point to be recognized corresponding to the first time-frequency matrix is the same as the pilot feature of the typical sample signal being currently compared, further indicating that the signal type of the signal of the frequency point to be recognized is the same as the signal type of the typical sample signal being currently compared, and then the recognition result of the signal of the frequency point to be recognized is obtained.

[0116] If the similarity difference r is not less than the preset threshold, it indicates that the signal type of the signal of the frequency point to be recognized is different from the signal type of the typical sample signal being currently compared. In one example, the second time-frequency matrix of other typical sample signals can be continuously compared and traversed. If none of them meet the conditions, the recognition result of the signal type of the currently to-be-recognized frequency point signal is an unknown type. Additionally, it can be understood that the comparison between time-frequency matrices can also be processed in parallel, and all comparison results are output to realize the display of the signal type recognition result, which will not be elaborated here.

[0117] It can be understood that in the same communication system, the pilot features of signals of the same signal type are usually set to be the same, and the power of the pilot signal is usually designed to be higher than that of the data signal. Based on this, by initially comparing the basic parameters of the signal of the frequency point to be recognized, signals that do not match the typical sample signal can be effectively filtered, thereby greatly reducing the subsequent calculation amount. By using logarithmic transformation, compression processing, and matrix translation calibration, the dynamic range difference between time-frequency matrices can be eliminated, and the distribution positions of the pilot signals in the time-frequency matrix can be ensured to be aligned, enhancing the signal-to-noise ratio characteristic and comparison accuracy of the signal, and then improving the accuracy of signal recognition using pilot features. In addition, by using GPU parallel processing, the comparison process can be made more efficient, further improving the recognition speed and robustness of the system.

[0118] Exemplarily, to facilitate understanding of the implementation process of the broadband signal type recognition method obtained in this embodiment, please refer to Figure 2 , Figure 2 which provides a schematic structural diagram of the broadband signal type recognition method in this embodiment. Specifically:

[0119] In this example, the identification method for broadband signals is to load existing templates from a pilot template library and obtain their basic signal parameters. Obtain the real-time broadband signal AD data; detect the signals at each frequency point existing in the broadband signal AD data to obtain their positions. Calculate the basic parameters of the signals at each frequency point and compare them with the basic signal parameters of the templates. When the basic parameters match, generate a time-frequency matrix for the signal to be identified, and at the same time obtain the time-frequency matrix of the pilot template. Perform adaptive adjustment on the time-frequency matrix of the pilot template and the time-frequency matrix of the signal to be identified to make their dynamic ranges approximately the same. Perform a calibration operation on the pilot positions of the adjusted time-frequency matrix of the pilot template and the time-frequency matrix of the signal to be identified. Measure the similarity between the time-frequency matrix of the calibrated pilot template and the time-frequency matrix of the signal to be identified. Determine whether the similarity difference between the time-frequency matrix of the pilot template and the time-frequency matrix of the signal to be identified exceeds the similarity threshold α. If not, determine that the signal to be identified belongs to the target template signal class; otherwise, it belongs to the unknown class, and standardize the determination result for output.

[0120] It can be understood that in this example, all possible signal positions within the entire frequency band are first detected and identified through broadband signal detection, and then the basic parameters of these signals are calculated in parallel and compared with the parameters of the template signals in the template library. When the basic parameters are successfully matched, the signal will be further expanded to the time-frequency domain for pilot matching analysis to ensure that the signal satisfying the basic parameters also has similar characteristics in terms of pilots. Compared with traditional technologies, this method does not rely on the identification of the modulation type of the target signal and subsequent demodulation operations. Only parameters such as bandwidth and symbol rate need to be calculated for the preliminary screening work, with relatively low computational complexity and fast signal scanning speed. The subsequent pilot matching algorithm mainly involves a large amount of matrix calculations and can be implemented on a GPU with a general architecture, with high overall computational efficiency and strong device compatibility. Compared with the method based on deep learning, the proposed calculation method of the present invention does not rely on a large number of labeled samples and can be quickly deployed only by providing typical samples accumulated in the early stage. At the same time, since the pilot similarity calculation is processed in parallel, adding new templates subsequently will not have an obvious impact on the overall architecture and calculation speed of this method, and it also avoids the problem of multiple training iterations required by deep learning methods, so the overall deployment iteration is faster. It should be particularly noted that this example can classify signals with obvious pilot discrimination points, which has significant differences in processing logic and implementation architecture from the traditional modulation recognition methods that distinguish through specific parameters or corresponding spectral characteristics of different modulation types. This example relies on accumulating typical samples to build a target template library to identify signals with specific pilot characteristics, and has high-efficiency and accurate recognition effects on complex frame structures or composite modulation type signals with obvious pilot characteristics accumulated in the early stage.

[0121] In summary, the broadband signal type recognition method provided by this application has at least the following beneficial effects: low computational complexity, fast signal scanning speed, does not rely on the recognition of the modulation type of the target signal and subsequent demodulation operations, and only needs to calculate parameters such as bandwidth and symbol rate for preliminary screening. The overall computational efficiency is high, and the device compatibility is strong. A large number of matrix calculations involved in the pilot matching algorithm can be implemented on a GPU with a general architecture, and the degree of parallelism is high. The cost is low and it is easy to deploy. The proposed calculation method does not rely on a large number of labeled samples, and only needs to provide typical samples accumulated in the early stage to quickly complete the deployment. The iterative upgrade is fast. The proposed pilot similarity matching algorithm can also be processed in parallel. Therefore, adding new templates later will not have an obvious impact on the overall architecture and computational speed of this method, avoiding the problem that deep learning methods need to be trained and iterated multiple times. It has strong scalability. For the recognition requirements of subsequent new pilots, the pilot similarity matching algorithm can add corresponding pilot templates at any time without changing other parts of this method.

[0122] This application also provides a broadband signal type recognition device. Please refer to Figure 3 , the broadband signal type recognition device includes:

[0123] An acquisition module for acquiring the broadband signal to be recognized;

[0124] A determination module for determining the frequency point signals to be recognized distributed in the broadband signal to be recognized and obtaining the pilot feature information of all the frequency point signals to be recognized;

[0125] A comparison module for comparing the pilot feature information of each frequency point signal to be recognized with at least one preset pilot template information to obtain a comparison result;

[0126] An identification module for obtaining the signal type recognition result of the frequency point signal to be recognized based on the comparison result.

[0127] The broadband signal type recognition device provided by this application adopts the broadband signal type recognition method in the above-mentioned embodiment, and can solve the technical problem of low signal type recognition efficiency. Compared with the related technology, the beneficial effects of the broadband signal type recognition device provided by this application are the same as those of the broadband signal type recognition method provided by the above-mentioned embodiment, and other technical features in the broadband signal type recognition device are the same as those disclosed in the method of the above-mentioned embodiment, and will not be elaborated here.

[0128] This application provides a broadband signal type recognition device. The broadband signal type recognition device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the broadband signal type recognition method in the above-mentioned embodiment.

[0129] Reference is made below to Figure 4 , which shows a schematic structural diagram of a broadband signal type identification device suitable for implementing the embodiments of the present application. The broadband signal type identification device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description: tablet computers), PMPs (Portable Media Player: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The broadband signal type identification device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0130] As Figure 4 shown, the broadband signal type identification device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the broadband signal type identification device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the broadband signal type identification device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a broadband signal type identification device having various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be alternatively implemented or had.

[0131] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0132] The broadband signal type identification device provided by the present application adopts the broadband signal type identification method in the above embodiments, and can solve the technical problem of low signal type identification efficiency. Compared with the related art, the beneficial effects of the broadband signal type identification device provided by the present application are the same as those of the broadband signal type identification method provided by the above embodiments, and other technical features in the broadband signal type identification device are the same as the features disclosed in the method of the previous embodiment, which will not be elaborated here.

[0133] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0134] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

[0135] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the broadband signal type identification method in the above embodiments.

[0136] The computer-readable storage medium provided by this application can, for example, be a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0137] The above computer-readable storage medium can be included in the broadband signal type identification device; or it can exist independently without being assembled into the broadband signal type identification device.

[0138] The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed by the broadband signal type identification device, the broadband signal type identification device implements the above broadband signal type identification method.

[0139] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0141] The modules described in the embodiments of the present application can be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0142] The readable storage medium provided by the present application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned broadband signal type recognition method, and can solve the technical problem of low signal type recognition efficiency. Compared with the related art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the broadband signal type recognition method provided by the above embodiments, and will not be elaborated here.

[0143] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the broadband signal type recognition method as described above.

[0144] The computer program product provided by the present application can solve the technical problem of low signal type recognition efficiency. Compared with the related art, the beneficial effects of the computer program product provided by the present application are the same as those of the broadband signal type recognition method provided by the above embodiments, and will not be elaborated here.

[0145] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A method for identifying the type of a broadband signal, characterized in that: The method includes: Acquire a broadband signal to be identified; Determine the frequency point signals to be identified distributed in the bandwidth signal to be identified, and obtain pilot characteristic information of all the frequency point signals to be identified; For each of the frequency point signals to be identified, comparing the pilot characteristic information of the frequency point signal to be identified with at least one preset pilot template information to obtain a comparison result; Based on the comparison result, a signal type recognition result of the frequency point signal to be identified is obtained.

2. The method according to claim 1, characterized in that The pilot feature information includes first basic parameter information and a first time-frequency matrix, and the preset pilot template information includes second basic parameter information and a second time-frequency matrix; The step of comparing the pilot characteristic information of the frequency point signal to be identified with at least one preset pilot template information to obtain a comparison result comprises: comparing the first basic parameter information and the second basic parameter information; If the first basic parameter information matches the second basic parameter information, the first time-frequency matrix and the second time-frequency matrix are compared to obtain similarity information between the first time-frequency matrix and the second time-frequency matrix.

3. The method according to claim 2, characterized in that The step of comparing the first time-frequency matrix and the second time-frequency matrix to obtain similarity information between the first time-frequency matrix and the second time-frequency matrix includes: Reduce the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix to obtain the adjusted first time-frequency matrix and the second time-frequency matrix; wherein the dynamic range difference includes a signal peak difference and a noise level difference; Calibrate pilot positions of the adjusted first time-frequency matrix and the second time-frequency matrix; The first time-frequency matrix and the second time-frequency matrix after calibration are compared to obtain similarity information between the first time-frequency matrix and the second time-frequency matrix.

4. The method according to claim 3, characterized in that The step of reducing the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix to obtain the adjusted first time-frequency matrix and the second time-frequency matrix comprises: Determine a time-frequency matrix to be processed with relatively greater matrix strength from the first time-frequency matrix and the second time-frequency matrix; The time-frequency matrix to be processed is compressed to reduce the dynamic range difference between the first time-frequency matrix and the second time-frequency matrix, so as to obtain the adjusted first time-frequency matrix and the second time-frequency matrix.

5. The method according to claim 3, characterized in that The step of calibrating the pilot positions of the adjusted first time-frequency matrix and the second time-frequency matrix comprises: The adjusted second time-frequency matrix is ​​used as a reference, and matrix translation processing is performed on the adjusted first time-frequency matrix to obtain the first time-frequency matrix after pilot position calibration.

6. The method according to claim 3, characterized in that The step of comparing the first time-frequency matrix and the second time-frequency matrix after calibration to obtain similarity information between the first time-frequency matrix and the second time-frequency matrix comprises: Determining a similarity difference between the first time-frequency matrix and the second time-frequency matrix based on a preset similarity calculation function; Based on the relationship between the similarity difference and a preset threshold, similarity information between the first time-frequency matrix and the second time-frequency matrix is ​​determined.

7. A broadband signal type identification device, characterized in that: The device comprises: An acquisition module, used for acquiring a broadband signal to be identified; A determination module, used to determine the frequency point signals to be identified distributed in the bandwidth signal to be identified, and obtain pilot characteristic information of all the frequency point signals to be identified; A comparison module, for comparing the pilot characteristic information of each of the frequency point signals to be identified with at least one preset pilot template information to obtain a comparison result; The identification module obtains a signal type identification result of the frequency point signal to be identified based on the comparison result.

8. A broadband signal type identification device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the broadband signal type identification method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the broadband signal type identification method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for identifying the type of a broadband signal according to any one of claims 1 to 6 are implemented.

Images