Signal identification method and device, terminal equipment and storage medium

Abstract

The invention relates to the technical field of radio monitoring, in particular to a signal identification method and device, terminal equipment and a storage medium. The method comprises the following steps: acquiring a signal spectrum library, a standard signal spectrum set and a standard noise spectrum set corresponding to a target frequency band; determining a signal area and a noise area according to the relationship between the frequency spectrum in the signal frequency spectrum library and the frequency spectrum in the standard signal frequency spectrum set and the standard noise frequency spectrum set; acquiring a signal spectrum corresponding to the target frequency band to obtain a target signal spectrum; and determining whether the target signal spectrum belongs to the signal area or the noise area according to the relationship between the target signal spectrum and the standard signal spectrum set so as to identify the use state of the target frequency band. Therefore, the problems of low signal detection accuracy, low universality and the like in the prior art can be effectively solved.

Description

Technical Field

[0001] This application relates to the field of radio monitoring technology, and in particular, to a signal recognition method, device, terminal device, and storage medium. Background Art

[0002] In the field of radio monitoring, signal detection usually adopts the energy detection method. The basic principle of the energy detection method is to calculate the energy of the received signal within the observation time and compare it with the threshold level. If it is greater than the threshold level, it is determined that there is a signal, and if it is less than the threshold level, it is determined that there is no signal. That is, when using the energy detection method for signal detection, the detection threshold needs to be set in advance. Due to reasons such as complex electromagnetic environment, antenna bandwidth limitation, and uneven frequency response of radio monitoring receivers, the monitored receiver display spectrum varies with frequency, and the setting of the monitoring threshold level depends on human experience; at the same time, it is difficult to identify signal distortions caused by interference to authorized signals through energy detection. Therefore, the traditional energy detection method has great limitations in practical applications. Summary of the Invention

[0003] In view of this, the embodiments of this application provide a signal recognition method, device, terminal device, and storage medium, which can effectively solve the problems of low accuracy and low generality of existing signal detection.

[0004] In a first aspect, the embodiments of this application provide a signal recognition method, and the method includes:

[0005] Obtain a signal spectrum library, a standard signal spectrum set, and a standard noise spectrum set corresponding to a target frequency band;

[0006] Determine a signal region and a noise region according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set;

[0007] Obtain the signal spectrum corresponding to the target frequency band to obtain a target signal spectrum;

[0008] Determine whether the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set, so as to identify the usage status of the target frequency band.

[0009] In some embodiments, the determining the signal region and the noise region according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set includes:

[0010] Calculate the waveform similarity between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set respectively, and correspondingly obtain a signal waveform similarity distribution and a noise waveform similarity distribution;

[0011] Determine an optimal threshold based on the signal waveform similarity distribution and the noise waveform similarity distribution;

[0012] Determine the signal region and the noise region according to the optimal threshold.

[0013] In some embodiments, determining that the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set includes:

[0014] Calculate the waveform similarity between the target signal spectrum and the spectra in the standard signal spectrum set to obtain the waveform similarity of the signal to be measured;

[0015] Determine that the target signal spectrum belongs to the signal region or the noise region according to the positional relationship between the waveform similarity of the signal to be measured and the optimal threshold, so as to identify the usage status of the target frequency band.

[0016] In some embodiments, before determining that the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set, it includes: an a priori knowledge base of authorized frequency bands;

[0017] The a priori knowledge base of authorized frequency bands includes authorized frequency bands and corresponding usage time periods, as well as idle frequency bands; among them, on one side of the optimal threshold where the signal waveform similarities gather belongs to the signal distribution region, and on the other side where the noise waveform similarities gather belongs to the noise distribution region;

[0018] Determining that the target signal spectrum belongs to the signal region or the noise region to identify the usage status of the target frequency band includes:

[0019] For the authorized frequency band,

[0020] If it is during the usage time period of the authorized frequency band and the target signal spectrum belongs to the signal region, then the usage status of the authorized frequency band to be measured is a normal status;

[0021] If it is during the usage time period of the authorized channel and the target signal spectrum belongs to the noise region, then the usage status of the authorized frequency band to be measured is an abnormal status;

[0022] If it is outside the usage time period of the authorized frequency band and the target signal spectrum belongs to the signal region, then the usage status of the authorized frequency band to be measured is an abnormal status;

[0023] If it is outside the usage time period of the authorized channel and the target signal spectrum belongs to the noise region, then the usage status of the authorized frequency band to be measured is a normal status.

[0024] In some embodiments, determining whether the target signal spectrum belongs to the signal area or the noise area to identify the usage status of the target frequency band further includes:

[0025] For idle frequency bands,

[0026] If the target signal spectrum belongs to the signal area, the usage status of the idle frequency band to be tested is an abnormal status;

[0027] If the target signal spectrum belongs to the noise area, the usage status of the idle frequency band to be tested is a normal status.

[0028] In some embodiments, when calculating the waveform similarity, the waveform similarity is calculated based on the Frechet distance or using a trained twin network model.

[0029] In some embodiments, when determining the optimal threshold, the optimal threshold is calculated using the maximum inter-class variance method based on the signal waveform similarity distribution and the noise waveform similarity distribution.

[0030] In a second aspect, an embodiment of the present application provides a signal recognition device, including:

[0031] A spectrum acquisition module, used to acquire a signal spectrum library, a standard signal spectrum set and a standard noise spectrum set corresponding to a target frequency band;

[0032] A threshold determination module, used to determine an optimal threshold value according to the relationship between the spectrum in the signal spectrum library and the spectrum in the standard signal spectrum set and the standard noise spectrum set, so as to distinguish between signal and noise;

[0033] The spectrum acquisition module to be measured is used to acquire the signal spectrum corresponding to the target frequency band to obtain the target signal spectrum;

[0034] The usage status identification module is used to determine whether the target signal spectrum belongs to the signal or the noise according to the optimal threshold and the relationship between the target signal spectrum and the standard signal spectrum set, so as to identify the usage status of the target frequency band.

[0035] In a third aspect, an embodiment of the present application provides a terminal device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement a signal recognition method provided in the first aspect of the present application.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed on a processor, it implements a signal recognition method provided according to the first aspect of the present application.

[0037] The embodiments of the present application have the following beneficial effects:

[0038] The present application determines the optimal threshold according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set respectively; and determines whether the target signal spectrum belongs to the signal or the noise according to the optimal threshold and the relationship between the target signal spectrum and the standard signal spectrum set, so as to identify the usage status of the target frequency band. The present application eliminates the influence of human factors on the monitoring and identification results, and is more fair and objective in the judgment of the threshold and the identification of the signal. Therefore, the present application can effectively solve the problems of low accuracy and low generality of the existing signal detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 Fig. shows a schematic flow chart of the signal recognition method according to the embodiment of the present application;

[0041] Figure 2 Fig. shows a schematic flow chart of determining the optimal threshold in the signal recognition method according to the embodiment of the present application;

[0042] Figure 3 Fig. shows a schematic flow chart of identifying the usage status of the target frequency band in the signal recognition method according to the embodiment of the present application;

[0043] Figure 4 Fig. shows another schematic flow chart of identifying the usage status of the target frequency band in the signal recognition method according to the embodiment of the present application;

[0044] Figure 5 Fig. shows a schematic diagram of the frequency spectrum waveform of the FM radio frequency band (87 - 108 MHz) used in the signal recognition method according to the embodiment of the present application;

[0045] Figure 6 Fig. shows a schematic diagram of the comparison of multiple groups of signal spectrum and noise spectrum waveform samples used in the signal recognition method according to the embodiment of the present application;

[0046] Figure 7 Fig. shows a schematic diagram of the signal waveform similarity distribution and the noise waveform similarity distribution obtained based on the Frechet distance calculation in the signal recognition method according to the embodiment of the present application;

[0047] Figure 8It shows a schematic diagram of the test results obtained by testing with 1000 groups of test data in the signal recognition method of the embodiment of the present application;

[0048] Figure 9 It shows a schematic diagram of the Siamese network model used in the signal recognition method of the embodiment of the present application;

[0049] Figure 10 It shows a schematic diagram of the signal waveform similarity distribution, noise waveform similarity distribution and optimal threshold calculated based on the OTSU algorithm in the signal recognition method of the embodiment of the present application;

[0050] Figure 11 It shows another schematic diagram of the comparison of multiple groups of signal spectrum and noise spectrum waveform samples used in the signal recognition method of the embodiment of the present application;

[0051] Figure 12 It shows a schematic diagram of the relationship between the waveform similarity and time obtained by comparing the test data obtained based on the Siamese network model with the signal spectrum library in the signal recognition method of the embodiment of the present application;

[0052] Figure 13 It shows a schematic diagram of the abnormal samples of the spectrum waveform in the signal recognition method of the embodiment of the present application;

[0053] Figure 14 It shows a schematic diagram of a structure of the signal recognition device of the embodiment of the present application.

[0054] Main element symbol description:

[0055] 110 - Spectrum acquisition module; 120 - Threshold determination module; 130 - Spectrum to be measured acquisition module; 140 - Usage status recognition module. Detailed implementation manners

[0056] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0057] Generally, the components of the embodiments of the present application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0058] As used below, the terms "comprising", "having" and their cognates that may be used in various embodiments of the present application are only intended to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as precluding the existence or adding the possibility of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items. In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0059] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which various embodiments of the present application belong. The terms (such as those defined in a general-use dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in various embodiments of the present application.

[0060] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments may be combined with each other.

[0061] The energy detection method widely used in the current radio monitoring field needs to detect and identify signals by artificially setting the noise threshold level according to the frequency bands of different radio services. However, affected by the complex electromagnetic environment, antenna bandwidth limitation, and uneven frequency response of radio monitoring receivers, etc., the signal detection accuracy is low and the generality is limited. Therefore, the present application proposes a signal recognition method, device, terminal device and storage medium, which can effectively solve the problems of low signal detection accuracy and low generality in the prior art.

[0062] The following will describe the signal recognition method with reference to some specific embodiments.

[0063] Figure 1 A flowchart of a signal recognition method according to an embodiment of the present application is shown. Exemplarily, the signal recognition method includes the following steps:

[0064] S10, obtaining a signal spectrum library, a standard signal spectrum set and a standard noise spectrum set corresponding to a target frequency band.

[0065] Before step S10, it is also necessary to construct corresponding signal spectrum libraries, standard signal spectrum sets, and standard noise spectrum sets according to the monitored channels. Among them, different target frequency bands have their own corresponding signal spectrum libraries, and the signal spectrum libraries include normal signal spectra. The standard signal spectrum set includes the standard signal spectra of each target frequency band, and the standard noise spectrum set includes the standard noise spectra corresponding to each target frequency band.

[0066] Monitor a certain frequency band (channel) to establish the standard signal spectrum set of this channel. There is an interval between one frequency band and another frequency band, and this interval is the idle channel. The area between two frequency bands is noise. For the monitoring of the idle channel, a standard noise spectrum set is also established.

[0067] S20. Determine the signal area and the noise area according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set.

[0068] S30. Obtain the signal spectrum corresponding to the target frequency band to get the target signal spectrum.

[0069] S40. Determine whether the target signal spectrum belongs to the signal area or the noise area according to the relationship between the target signal spectrum and the standard signal spectrum set, so as to identify the usage status of the target frequency band.

[0070] In one implementation, as Figure 2 shown, the step of determining the signal area and the noise area according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set in step S20 includes:

[0071] S21. Calculate the waveform similarity between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set respectively, and correspondingly obtain the signal waveform similarity distribution and the noise waveform similarity distribution. For example, when calculating the waveform similarity, the waveform similarity can be calculated based on the Frechet distance, or the waveform similarity can be calculated by using a trained siamese network model.

[0072] S22. Determine the optimal threshold according to the signal waveform similarity distribution and the noise waveform similarity distribution. For example, when determining the optimal threshold, the optimal threshold is calculated by using the maximum inter-class variance method (OTSU algorithm) according to the signal waveform similarity distribution and the noise waveform similarity distribution.

[0073] S23. Determine the signal area and the noise area according to the optimal threshold.

[0074] In step S40, determining that the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set includes:

[0075] S41, calculating the waveform similarity between the target signal spectrum and the spectra in the standard signal spectrum set to obtain the waveform similarity of the signal to be measured;

[0076] S42, determining that the target signal spectrum belongs to the signal region or the noise region according to the positional relationship between the waveform similarity of the signal to be measured and the optimal threshold, so as to identify the usage status of the target frequency band.

[0077] In one implementation, before determining that the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set, it includes: obtaining a priori knowledge base of authorized frequency bands; before obtaining the a priori knowledge base of authorized frequency bands, it is also necessary to construct the a priori knowledge base of authorized frequency bands. The a priori knowledge base of authorized frequency bands includes authorized frequency bands and corresponding usage time periods, as well as idle frequency bands.

[0078] Among them, on both sides of the optimal threshold, the side where the waveform similarity of the signal aggregates belongs to the signal distribution region, and the other side where the waveform similarity of the noise aggregates belongs to the noise distribution region.

[0079] As Figure 3 shown, in step S42, determining that the target signal spectrum belongs to the signal region or the noise region to identify the usage status of the target frequency band includes:

[0080] For the authorized frequency band, after calculating the waveform similarity between the target signal spectrum and the spectra in the standard signal spectrum set to obtain the waveform similarity of the signal to be measured (spectrum waveform similarity):

[0081] If it is within the usage time period of the authorized frequency band and the target signal spectrum belongs to the signal region, the usage status of the authorized frequency band to be measured is the normal status;

[0082] If it is within the usage time period of the authorized channel and the target signal spectrum belongs to the noise region, the usage status of the authorized frequency band to be measured is the abnormal status;

[0083] If it is outside the usage time period of the authorized frequency band and the target signal spectrum belongs to the signal region, the usage status of the authorized frequency band to be measured is the abnormal status;

[0084] If it is outside the usage time period of the authorized channel and the target signal spectrum belongs to the noise region, the usage status of the authorized frequency band to be measured is the normal status.

[0085] As Figure 4 shown, for the idle frequency band, the waveform similarity between the target signal spectrum and the spectrum in the standard noise spectrum concentration is calculated to obtain the waveform similarity (spectrum waveform similarity) with the signal to be measured.

[0086] If the target signal spectrum belongs to the signal region, the usage status of the idle frequency band to be measured is an abnormal status;

[0087] If the target signal spectrum belongs to the noise region, the usage status of the idle frequency band to be measured is a normal status.

[0088] The signal recognition method of the present application will be described below in conjunction with a specific example. In this example, when calculating the waveform similarity, the waveform similarity is obtained based on the Frechet distance. When determining the optimal threshold, according to the signal waveform similarity distribution and the noise waveform similarity distribution, the maximum inter-class variance method (OTSU algorithm) is used to calculate the optimal threshold.

[0089] For the monitoring of the FM broadcast frequency band, a radio monitoring receiver (sensitivity -160 dBm, AD conversion accuracy 16 bits, maximum analysis bandwidth 40 MHz, frequency range 20 MHz - 6 GHz) was used to continuously measure the monitoring signal spectrum for seven days, and a standard signal spectrum set, a standard noise spectrum set, a signal spectrum library, a noise spectrum library, and a priori knowledge library of the usage period of the authorized frequency band were constructed. As Figure 5 shown is the spectrum of the FM broadcast service frequency band 87 MHz - 108 MHz. It can be seen from the figure that there are 14 authorized radio stations, among which Channel 4 is a digital radio station and the rest are analog FM radio stations.

[0090] Taking FM93 MHz (92.3 - 92.5 MHz) as an example, 1500 groups of signal spectrum data and noise spectrum data were taken and correspondingly stored in the standard signal spectrum set and the standard noise spectrum set. Among them, 500 groups were used for spectrum waveform similarity calculation, and 1000 groups were used as test data for testing. There are 300 groups of data in the signal spectrum library for comparison. The usage period of this authorized radio station (authorized frequency band) is from 6:00 in the morning to 12:00 at midnight. Figure 6 It is a schematic diagram of the comparison of multiple groups of signal spectrum and noise spectrum waveform samples (the upper part of the figure is the signal spectrum and the lower part is the noise spectrum). Based on the Frechet distance, the waveform similarity between the signal spectrum in the signal spectrum library and the signal spectrum in the standard signal spectrum set, and the waveform similarity between the signal spectrum in the signal spectrum library and the noise spectrum in the standard noise spectrum set are calculated, and the signal waveform similarity distribution and the noise waveform similarity distribution are correspondingly obtained. Among them, the smaller the Frechet distance, the more similar the spectrum waveforms, as Figure 7 shown.Figure 7 The medium gray area (left part) is the signal waveform similarity distribution area, and the blue area (right part) is the noise spectrum waveform similarity distribution area; the red dashed line (middle dashed line) is the optimal threshold th = 15.27 calculated based on the OTSU algorithm for the two distributions. The area smaller than the optimal threshold th is the signal distribution area (signal area), and the area larger than the optimal threshold th is the noise distribution area (noise area). Figure 8 For the detection rate, false alarm rate, and error probability statistics. After testing with 1000 groups of test data, the results show that after 1000 statistics, the detection rate pd = 98.61%, the false alarm rate pf = 0, and the error probability nacc = 1.39%.

[0091] The signal recognition method of the present application will be described below in combination with another specific example. In this example, when calculating the waveform similarity, the trained siamese network model is used to calculate the waveform similarity. When determining the optimal threshold, according to the signal waveform similarity distribution and the noise waveform similarity distribution, the maximum inter-class variance method (OTSU algorithm) is used to calculate the optimal threshold.

[0092] Train the siamese network to predict the waveform similarity between the signal spectra in the signal spectrum library and the signal spectra in the standard signal spectrum set, as well as calculate the waveform similarity between the signal spectra in the signal spectrum library and the noise spectra in the standard noise spectrum set. Threshold division is performed through the OTSU algorithm, and the prior knowledge of the authorized channel usage period is combined to judge the normal and abnormal states of the signal. The siamese network model is as Figure 9 shown. Table 1 shows the structural parameters of the backbone feature extraction network in the siamese network model.

[0093] Table 1 Structural parameters of the backbone feature extraction network

[0094]

[0095]

[0096] Taking a certain FM radio frequency band (FM95.4, 95.3 - 95.5 MHz) as an example, 10,000 groups of data from the standard signal spectrum set and the standard noise spectrum set are each converted into a spectral waveform binary image as training samples to train the model. The signal spectrum library is composed of 300 spectral waveform binary images of this channel. Figure 10 For the waveform similarity distribution between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set, as well as the waveform similarity distribution between the spectra in the signal spectrum library and the spectra in the standard noise spectrum set, calculated based on the siamese network. Among them, the waveform similarity between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set is distributed around 1, and the waveform similarity between the spectra in the signal spectrum library and the spectra in the standard noise spectrum set is close to 0, Figure 10The dashed line in the figure is the threshold obtained based on the OTSU algorithm (th = 0.96). Specifically, Figure 10 It is the waveform similarity distribution of the FM radio station signal in the 95.3 - 95.5 MHz channel and the standard signal spectrum (right side of the dashed line), and the signal and standard noise spectrum (left side of the dashed line) calculated based on the siamese network model. The dashed line is the threshold th obtained based on the OTSU algorithm, (th = 0.96). 10,000 groups of data from September 22, 2023 to September 23, 2023 are used to construct a dataset to test the model. As Figure 11 shown in the figure is a comparison schematic diagram of multiple groups of normal signal and noise spectrum waveform samples (the upper part is the normal signal in the authorized frequency band, and the lower part is the noise signal). The usage period of this authorized channel is 24 hours a day. Figure 12 Based on the trained siamese network model, it is the relationship between the similarity and time obtained by calculating the spectrum waveform similarity between the test data and the signal spectrum library data. It can be seen that during the usage period of this authorized channel, between 19:00 on September 22, 2023 and 17:00 on September 23, 2023, a situation where the spectrum waveform similarity distribution is less than the threshold, that is, in the noise area, is detected. And this time period is within the usage period of the authorized channel. From this, it can be judged that the authorized radio channel has an abnormality during this time period. The spectrum waveform of this time period is drawn as Figure 13 shown in the figure. It can be seen that the signal in this time period is distorted due to the interference of adjacent - frequency unauthorized radio stations.

[0097] It can be seen from this that the signal recognition method based on radio spectrum waveform similarity calculation proposed in this application has a very high recognition rate, and can accurately judge its normal and abnormal states by combining the usage period of the authorized channel.

[0098] This application calculates the distribution of the waveform similarity between the signals in the radio service frequency bands to be monitored and the standard signal spectrum, and the signal and standard noise spectrum, and automatically determines the threshold through the OTSU algorithm, removing the influence of human factors on the monitoring and recognition results, and making the judgment of the threshold and the recognition of the signal more fair and objective. That is to say, since this invention determines the threshold by calculating the signal spectrum similarity and combining the OTSU method, without the need to determine the threshold according to the background noise and human experience, it has objectivity and universality, and is convenient for actual promotion and application.

[0099] Figure 14 Shows a schematic structural diagram of a signal recognition device according to an embodiment of this application. Exemplarily, the signal recognition device includes: a spectrum acquisition module 110, a threshold determination module 120, a spectrum to be measured acquisition module 130, and a usage status recognition module 140.

[0100] A spectrum acquisition module 110, configured to acquire a signal spectrum library, a standard signal spectrum set, and a standard noise spectrum set corresponding to a target frequency band;

[0101] A threshold determination module 120, configured to determine an optimal threshold according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set, so as to distinguish signals and noise;

[0102] A to-be-tested spectrum acquisition module 130, configured to acquire a signal spectrum corresponding to a target frequency band to obtain a target signal spectrum;

[0103] A usage status recognition module 140, configured to determine whether the target signal spectrum belongs to the signal or the noise according to the optimal threshold and the relationship between the target signal spectrum and the standard signal spectrum set, so as to recognize the usage status of the target frequency band.

[0104] It can be understood that the device in this embodiment corresponds to the xx method in the above embodiment, and the optional items in the above embodiment are also applicable to this embodiment, so they will not be repeated here.

[0105] This application further provides a terminal device. Exemplarily, the terminal device includes a processor and a memory. The memory stores a computer program, and the processor runs the computer program to enable the terminal device to execute the above signal recognition method or the functions of each module in the above signal recognition device.

[0106] The processor may be an integrated circuit chip with signal processing capabilities. The processor may be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., which can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0107] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc. Among them, the memory is used to store a computer program, and after receiving an execution instruction, the processor can execute the computer program accordingly.

[0108] This application also provides a readable storage medium for storing the computer program used in the above terminal device.

[0109] In several embodiments provided by this application, it should be understood that the disclosed device and method can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architectures, functions, and operations of the device, method, and computer program product according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks can occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structure diagram and / or flowchart, as well as the combination of blocks in the structure diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0110] In addition, each functional module or unit in various embodiments of this application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0111] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0112] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. A signal recognition method, characterized in that, The method includes: Obtaining a signal spectrum library, a standard signal spectrum set, and a standard noise spectrum set corresponding to a target frequency band; Determining a signal region and a noise region according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set respectively; Obtaining the signal spectrum corresponding to the target frequency band to obtain a target signal spectrum; Determining whether the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set, so as to identify the usage state of the target frequency band.

2. The signal recognition method according to claim 1, wherein The determining of the signal region and the noise region according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set respectively includes: Calculating the waveform similarity between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set respectively, and correspondingly obtaining a signal waveform similarity distribution and a noise waveform similarity distribution; Determining an optimal threshold according to the signal waveform similarity distribution and the noise waveform similarity distribution; Determining the signal region and the noise region according to the optimal threshold.

3. The signal recognition method according to claim 2, characterized in that, The determining of whether the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set includes: Calculating the waveform similarity between the target signal spectrum and the spectra in the standard signal spectrum set to obtain a waveform similarity of the signal to be measured; Determining whether the target signal spectrum belongs to the signal region or the noise region according to the positional relationship between the waveform similarity of the signal to be measured and the optimal threshold, so as to identify the usage state of the target frequency band.

4. The signal recognition method according to claim 3, wherein, Before determining whether the target signal spectrum belongs to the signal region or the noise region according to the relationship between the target signal spectrum and the standard signal spectrum set, it includes: obtaining a prior knowledge base of authorized frequency bands; The prior knowledge base of authorized frequency bands includes authorized frequency bands and corresponding usage time periods, as well as idle frequency bands; wherein, on both sides of the optimal threshold, the side where the signal waveform similarity gathers belongs to the signal distribution region, and the other side where the noise waveform similarity gathers belongs to the noise distribution region; The determining of whether the target signal spectrum belongs to the signal region or the noise region, so as to identify the usage state of the target frequency band, includes: For the authorized frequency band, If it is in the usage time period of the authorized frequency band and the target signal spectrum belongs to the signal region, the usage state of the authorized frequency band to be measured is a normal state; If it is in the usage time period of the authorized channel and the target signal spectrum belongs to the noise region, the usage state of the authorized frequency band to be measured is an abnormal state; If it is outside the usage time period of the authorized frequency band and the target signal spectrum belongs to the signal region, the usage state of the authorized frequency band to be measured is an abnormal state; If it is outside the usage time period of the authorized channel and the target signal spectrum belongs to the noise region, the usage state of the authorized frequency band to be measured is a normal state.

5. The signal recognition method according to claim 4, characterized in that The determining of whether the target signal spectrum belongs to the signal region or the noise region, so as to identify the usage state of the target frequency band, further includes: For the idle frequency band, If the target signal spectrum belongs to the signal region, the usage status of the idle frequency band to be measured is an abnormal status; If the target signal spectrum belongs to the noise region, the usage status of the idle frequency band to be measured is a normal status.

6. The signal recognition method according to any one of claims 2 to 5, characterized in that When calculating the waveform similarity, the waveform similarity is calculated based on the Frechet distance or by using a trained siamese network model.

7. The signal recognition method according to any one of claims 2 to 5, characterized in that, When determining the optimal threshold, according to the signal waveform similarity distribution and the noise waveform similarity distribution, the optimal threshold is calculated by using the maximum inter-class variance method.

8. A signal recognition device, characterized in that, It includes: A spectrum acquisition module, configured to acquire a signal spectrum library, a standard signal spectrum set, and a standard noise spectrum set corresponding to a target frequency band; A threshold determination module, configured to determine an optimal threshold according to the relationship between the spectra in the signal spectrum library and the spectra in the standard signal spectrum set and the standard noise spectrum set, so as to distinguish signals and noise; A spectrum to be measured acquisition module, configured to acquire a signal spectrum corresponding to a target frequency band to obtain a target signal spectrum; A usage status identification module, configured to determine whether the target signal spectrum belongs to the signal or the noise according to the optimal threshold and the relationship between the target signal spectrum and the standard signal spectrum set, so as to identify the usage status of the target frequency band.

9. A terminal device, characterized in that, The terminal device includes a processor and a memory, the memory stores a computer program, and the processor is configured to execute the computer program to implement the signal recognition method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program, and when the computer program is executed on a processor, it implements the signal recognition method according to any one of claims 1-7.

Images