A method for identifying specific radiation source signals

Abstract

The present invention discloses a method for identifying a specific radiation source signal source, comprising the following steps: obtaining at least one signal to be identified within a target area, and determining a to-be-used digital afterglow spectrum graph corresponding to each to-be-identified signal; for each to-be-identified digital afterglow spectrum graph, processing the current to-be-identified digital afterglow spectrum graph based on a target detection neural network to obtain to-be-identified feature information corresponding to the current to-be-identified digital afterglow spectrum graph, wherein the to-be-identified feature information includes at least one of color, frequency, and amplitude; and determining the target signal source corresponding to the to-be-identified signal based on the to-be-identified feature information. The present invention is applied to the field of radiation source identification, solving the problem of inaccurate identification of the signal source corresponding to the signal, and achieving the effect of accurately identifying the signal source corresponding to the signal.

Description

Technical Field

[0001] The present invention relates to the technical field of radiation source identification, and in particular to a method for identifying a specific radiation source signal. Background Art

[0002] Modern warfare is an information war. In the processing of electronic reconnaissance signals, it is necessary to identify the signals received by the electronic reconnaissance receiver and determine the radiation source corresponding to the collected signals.

[0003] Traditional methods for identifying specific radiation source signals construct feature vectors using conventional characteristic parameters and then match them against a database using attribute measurements, gray correlation, or by using expert systems to quickly infer attribute information based on prior expert knowledge. However, given the increasing complexity of electromagnetic environments, these methods rely heavily on prior expert knowledge, lack effective theoretical support, and have certain limitations. This means that traditional identification methods can lead to inaccurate identification of radiation sources.

[0004] In order to accurately identify the received signal and determine the radiation source corresponding to the signal, it is necessary to improve the radiation source identification method. Summary of the Invention

[0005] In response to the problem in the prior art that the signal source corresponding to a signal is not accurately identified, the present invention provides a method for identifying a specific radiation source signal source, which can accurately determine the signal source corresponding to the signal.

[0006] To achieve the above object, the present invention provides a method for identifying a specific radiation source signal source, characterized in that it includes the following steps:

[0007] Acquire at least one signal to be identified in the target area, and determine a digital persistence spectrum to be used corresponding to each signal to be identified;

[0008] For each digital persistence spectrum graph to be used, processing the current digital persistence spectrum graph to be used based on the target detection neural network to obtain feature information to be determined corresponding to the current digital persistence spectrum graph to be used, wherein the feature information to be determined includes at least one of color, frequency, and amplitude;

[0009] A target signal source corresponding to the signal to be identified is determined according to the characteristic information to be determined.

[0010] In one embodiment, acquiring at least one signal to be identified in the target area and determining a digital persistence spectrum to be used corresponding to each signal to be identified specifically includes:

[0011] Based on the signal acquisition device, wireless signals in the target area are collected to obtain at least one signal to be identified;

[0012] For each signal to be identified, signal processing is performed on the current signal to be identified to obtain a current digital persistence spectrum to be used corresponding to the current signal to be identified.

[0013] In one embodiment, performing signal processing on the current signal to be identified to obtain a current digital persistence spectrum corresponding to the current signal to be identified specifically includes:

[0014] Determining information to be used corresponding to the current signal to be identified, wherein the information to be used includes at least one of color information, frequency information, and amplitude information;

[0015] The information to be used is processed based on a spectrum analyzer to obtain characteristic information to be determined corresponding to the current digital persistence spectrum diagram to be used.

[0016] In one embodiment, the target detection neural network is used to process the current digital persistence spectrum to obtain the feature information to be determined corresponding to the current digital persistence spectrum, specifically including:

[0017] Extracting shallow feature information and deep feature information corresponding to the current digital afterglow spectrum graph based on the target detection neural network;

[0018] The shallow feature information to be used and the deep feature information to be used are subjected to feature fusion to obtain feature information to be determined corresponding to the digital persistence spectrum graph to be currently used.

[0019] In one embodiment, determining the target signal source corresponding to the signal to be identified based on the feature information to be determined specifically includes:

[0020] According to the feature identifier to be identified carried by the feature information to be determined, the target signal source corresponding to the feature identifier to be identified is determined from the target mapping table; wherein the target mapping table includes at least one feature information to be matched and the feature identifier to be matched corresponding to each feature information to be matched.

[0021] The present invention provides a method for identifying a specific radiation source signal source, which uses a digital afterglow spectrum diagram as the basis for identifying a specific radiation source signal source. The target signal source corresponding to the signal to be identified is determined by processing the digital afterglow spectrum diagram. Compared with traditional spectrum analysis technology, the digital spectrum afterglow diagram can intuitively display multiple signals within the same frequency range at different times, and use digital enhancement technologies such as intensity level, color scheme and statistical trajectory to highlight the various different information of each signal, greatly improving the detection and capture capabilities of the signal. At the same time, the digital spectrum afterglow diagram also retains multiple characteristics of the signal. There are multiple amplitude values ​​at each frequency point, which is different from the traditional spectrum. Figure 1 Each frequency point corresponds to an amplitude value. These signal characteristics are intuitively displayed, making them easy to observe and distinguish. Using this method to monitor signals, signals of interest can be easily found even in complex electromagnetic environments, making it ideal for signal reconnaissance and individual emitter identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0023] Figure 1 This is a flow chart of the method for identifying a specific radiation source signal in Example 1 of the present invention;

[0024] Figure 2 This is a flow chart of a method for identifying a specific radiation source signal in Example 2 of the present invention;

[0025] Figure 3 Schematic diagram of the structure of the signal acquisition system in Example 2 of the present invention;

[0026] Figure 4 Schematic diagram of signal acquisition for detection in embodiment 2 of the present invention;

[0027] Figure 5 A flowchart for constructing a data set for a target detection neural network in Example 2 of the present invention;

[0028] Figure 6 Schematic diagram of six Wi-Fi radiation source signals in Example 2 of the present invention;

[0029] Figure 7 This is a schematic diagram of the signal source identification results in Example 2 of the present invention.

[0030] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0032] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0033] In the description of the present invention, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0034] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in this field can implement it. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0035] Example 1

[0036] like Figure 1 The figure shows a flowchart of a specific radiation source identification method provided by this embodiment. This embodiment can be applied to the situation of determining the signal source corresponding to the collected signal. The method can be executed by a signal source identification device. The signal source identification device can be implemented in the form of hardware / or software. The signal source identification device can be configured in a computing device.

[0037] refer to Figure 1 The specific radiation source identification method in this embodiment includes the following steps:

[0038] S110 , obtaining at least one signal to be identified in a target area, and determining a digital persistence spectrum to be used corresponding to each signal to be identified.

[0039] Among them, the target area can be understood as the area where the signal emitted by the radiation source is collected, and can also be understood as the area corresponding to the emission range of the radiation source. The signal to be identified can be understood as the signal sent by the radiation source. For example, the radiation source can be a chip in an electronic device. For example, the electronic device can be a mobile device or a terminal device, and the signal to be identified is the signal emitted by the chip based on the electronic device. The digital afterglow spectrum diagram to be used can be understood as the digital afterglow spectrum diagram corresponding to the signal to be identified. Each signal to be identified corresponds to a specific digital afterglow spectrum diagram to be used. That is to say, different digital afterglow spectrum diagrams to be used can be obtained according to different signals to be identified.

[0040] In this embodiment, signal source identification mainly involves signal source identification of the signal emitted by the radiation source. Identification of radiation source signals, also known as radiation source fingerprint identification, individual identification, etc., refers to "a technology that uses only the external characteristics of the received signal to identify the radiation source individual to which it belongs. This external characteristic is usually referred to as the radio frequency fingerprint characteristic of the radiation source individual, which is caused by the non-ideal characteristics of the internal hardware of the radiation source and has the characteristics of being difficult to copy and impossible to eliminate. In addition, the radio frequency fingerprint characteristic of the radiation source also has the characteristic of uniqueness. It is independent of the content of the signal transmission. It shows consistency in different signal parts of the same radiation source, but shows obvious differences between different radiation source individuals. Even radiation source individuals of the same manufacturer and the same model still have differences in their radio frequency fingerprint characteristics. In other words, the radiation source fingerprint characteristic has unique identification.

[0041] Specifically, the signal to be identified in the target area is collected and processed to obtain a digital persistence spectrum to be used corresponding to the signal to be identified, so as to determine the corresponding signal source corresponding to the signal to be identified based on the characteristic information in the digital persistence spectrum to be used.

[0042] Optionally, the acquiring of at least one signal to be identified within the target area and the determination of a digital afterglow spectrum diagram to be used corresponding to each signal to be identified include: based on a signal acquisition device, collecting wireless signals within the target area to obtain at least one signal to be identified; for each signal to be identified, performing signal processing on the current signal to be identified to obtain a current digital afterglow spectrum diagram to be used corresponding to the current signal to be identified.

[0043] The signal acquisition device can be understood as a device that collects signals within the target area, such as a signal acquisition system, which may include modules such as a receiver, a signal receiving antenna, a display, and a computer. It is understood that the signal acquisition device can simultaneously collect one or more signals to be identified during signal acquisition. The currently used digital persistence spectrum can be understood as the digital persistence spectrum corresponding to the currently identified signal.

[0044] Specifically, based on the signal acquisition device collecting the signals to be identified in the target area, taking the signals to be identified as wireless signals as an example, the signal acquisition device can capture the wireless signals on the preset frequency band of the receiver through the signal receiving antenna, such as the Wi-Fi radiation source signal, and display the captured signal on a display connected to the receiver, and then use the computer equipment to collect the signal and save the acquired data. For at least one signal to be identified, the signal to be identified that needs to be identified at the current moment is determined as the current signal to be identified. Furthermore, the current signal to be identified is processed to obtain the digital persistence spectrum diagram to be used.

[0045] Optionally, signal processing is performed on the current signal to be identified to obtain a current digital persistence spectrum to be used corresponding to the current signal to be identified, specifically including: determining information to be used corresponding to the current signal to be identified; and processing the information to be used based on a spectrum analyzer to obtain current feature information to be determined corresponding to the current digital persistence spectrum to be used. The information to be used can be understood as feature information of the current signal to be identified, and can include at least one of bandwidth information, frequency information, and amplitude information. A spectrum analyzer can be understood as an instrument for analyzing the signal to be identified, such as a real-time spectrum analyzer.

[0046] Different signals to be identified correspond to different information to be used. Therefore, by analyzing and processing different signals to be identified based on a spectrum analyzer, different digital persistence spectrum graphs to be used can be obtained. Taking the signal processing of the current signal to be identified as an example, the current signal to be identified is input into a real-time spectrum analyzer, and the real-time spectrum analyzer is used to process and analyze the color information, frequency information, and amplitude information in the current signal to be identified, so as to obtain the current digital persistence spectrum graph to be used corresponding to the current signal to be identified. It should be noted that the current signal to be used is a digital persistence spectrum graph. The real-time spectrum analyzer uses digital fluorescence technology to analyze and process the signal to be identified, and thus a digital persistence spectrum graph corresponding to the current signal to be identified can be obtained. The advantage of this is that, compared with traditional spectrum analysis technology, the digital spectrum persistence graph can intuitively display multiple signals in the same frequency range at different times, and use digital enhancement technologies such as intensity levels, color schemes, and statistical trajectories to highlight the various different information of each signal, greatly improving the detection and capture capabilities of the signal. The digital spectrum persistence graph retains multiple characteristics of the signal, and has multiple amplitude values ​​at each frequency point, which is different from the traditional spectrum. Figure 1 Each frequency point corresponds to an amplitude value. These signal characteristics are intuitively displayed, making them easy to observe and distinguish. Using this method to monitor signals, signals of interest can be easily found even in complex electromagnetic environments, making it ideal for signal reconnaissance and individual emitter identification.

[0047] S120 : For each digital afterglow spectrum graph to be used, process the current digital afterglow spectrum graph to be used based on the target detection neural network to obtain feature information to be determined corresponding to the current digital afterglow spectrum graph to be used.

[0048] The target detection neural network can be understood as a pre-built classification model neural network, such as a YOLOv5 deep learning network model. The target detection neural network extracts the feature information to be determined in the digital persistence spectrum to be used, so as to determine the signal source corresponding to the digital persistence spectrum to be used, and the obtained target signal source is used as the target signal source corresponding to the signal to be identified. The feature information to be determined can be understood as feature information extracted based on the current digital persistence spectrum to be used, and can include at least one of color, frequency, and amplitude.

[0049] Specifically, the digital afterglow spectrum diagram to be used is input into the target detection neural network, and the feature information to be determined in the spectrum to be used is extracted based on the target detection neural network to determine the signal source corresponding to the spectrum to be used according to the feature information to be determined.

[0050] The target detection neural network is used to process the current digital afterglow spectrum diagram to be used to obtain the to-be-determined feature information corresponding to the current digital afterglow spectrum diagram to be used, specifically including: extracting the to-be-used shallow feature information and the to-be-used deep feature information corresponding to the current digital afterglow spectrum diagram to be used based on the target detection neural network; in order to be able to identify the signal source based on the feature information, the shallow feature information to be used and the deep feature information to be used are feature-fused to obtain the to-be-determined feature information corresponding to the current digital afterglow spectrum diagram to be used.

[0051] S130: Determine a target signal source corresponding to the signal to be identified based on the characteristic information to be determined. The target signal source can be understood as a signal source corresponding to the signal to be identified. For example, if the signal to be identified is a signal emitted by signal source A, then the target signal source corresponding to the signal to be identified is signal source A.

[0052] Specifically, the method of determining the target signal source corresponding to the signal to be identified based on the characteristic information to be determined specifically includes: determining the target signal source corresponding to the characteristic identifier to be identified from the target mapping table based on the characteristic identifier to be identified carried by the characteristic information to be determined. The characteristic identifier to be identified can be understood as unique identification information corresponding to the characteristic information to be determined, which is used to determine the signal source corresponding to the characteristic information to be determined. The target mapping table includes at least one characteristic information to be matched, and a characteristic identifier to be matched corresponding to each characteristic information to be matched. The characteristic information to be matched can be understood as characteristic information corresponding to each signal to be identified, and each characteristic information to be matched corresponds to a unique characteristic identifier to be matched.

[0053] Specifically, after obtaining the feature information to be determined corresponding to the digital afterglow spectrum diagram to be used based on the target detection neural network, the signal source corresponding to the feature identifier to be identified is queried from the target mapping table according to the feature identifier to be identified corresponding to the feature information to be determined, and the queried signal source is used as the target signal source corresponding to the signal to be identified.

[0054] Example 2

[0055] like Figure 2 The figure shows a flow chart of a signal source identification method provided in this embodiment. A signal acquisition system (i.e., a signal acquisition device) is pre-built, such as Figure 3As shown, the signal acquisition system primarily consists of a receiver, a signal receiving antenna, a display, and a computer. Its working process is to capture Wi-Fi radiation source signals (i.e., signals to be identified) in the receiver's preset frequency band through the antenna. For example, the operating frequency bands of Wi-Fi signals are divided into 2.4 GHz and 5 GHz. In this embodiment, the more commonly used 2.4 GHz band can be used. The captured signals are displayed on a display screen connected to the receiver, and the computer equipment is then used to collect the signals and save the acquired data.

[0056] Exemplarily, in this embodiment, the signal acquisition system collects signals to be identified emitted by 6 radiation sources (i.e., signal sources to be identified), which belong to 4 brands and 5 models respectively. The corresponding signals are recorded as signal 1 to signal 6, among which signal 1 and signal 2 come from radiation source individuals of the same brand but different models, and signal 5 and signal 6 come from different radiation source individuals of the same brand and model.

[0057] The corresponding relationship between brands and models of signals 1 to 6 is shown in Table 1 below:

[0058] Table 1

[0059]

[0060] Specifically, when collecting signals to be identified, field measurements can be used to determine the collection points in the east, west, south, and north directions and vertical directions (a total of five directions) on the same horizontal plane, with the signal collection system as the center. To obtain signals of different powers and different signal-to-noise ratios, collection is performed at positions 5, 20, 50, and 100 cm away from the collection system in the horizontal direction; and at positions 10, 20, and 55 cm away from the collection system in the vertical direction. For a schematic diagram of the collection of signals to be identified, see Figure 4 .

[0061] After obtaining the signal to be identified, the signal analysis of each signal to be identified is performed based on the real-time spectrum analyzer, and the digital persistence spectrum diagram corresponding to each signal to be identified can be obtained. It can be understood that the digital persistence spectrum diagram is an innovative spectrum in the real-time spectrum analyzer, which intuitively displays the spectrum situation within a certain time period through an image. This digital persistence spectrum diagram contains three-dimensional information of color, frequency, and amplitude during this period, fully showing the signal characteristics. Digital phosphor technology (DPX) is a key technology for generating digital spectrum persistence diagrams, which helps to observe short events or rare events. Compared with traditional spectrum analysis technology, the digital spectrum persistence diagram can intuitively display multiple signals in the same frequency range at different times, and use digital enhancement technologies such as intensity levels, color schemes, and statistical trajectories to highlight the various different information of each signal, greatly improving the detection and capture capabilities of the signal. The digital spectrum persistence diagram retains multiple characteristics of the signal, and there are multiple amplitude values ​​at each frequency point, which is different from the traditional spectrum. Figure 1 Each frequency point corresponds to an amplitude value. These signal characteristics are intuitively displayed, making them easy to observe and distinguish. Using this method to monitor signals, signals of interest can be easily found even in complex electromagnetic environments, making it ideal for signal reconnaissance and individual emitter identification.

[0062] Furthermore, in order to determine the radiation source corresponding to each signal to be identified based on the target detection neural network, it is necessary to pre-build a target detection neural network model. The target detection neural network model can be a YOLOv5 deep learning network model. Specifically, the digital spectrum persistence map dataset of the Wi-Fi radiation source signal is constructed as follows: Figure 5As shown, the obtained digital afterglow spectrum graph can be processed by data screening and data labeling to obtain a data set. Among them, data screening is to make appropriate selections for the obtained digital spectrum afterglow graph data to ensure that the data does not contain pure background images without targets, so that the image data distribution of the dataset is more balanced, which is conducive to model learning and parameter fitting; data labeling is to use image labeling tools to label the image data to clarify the category, size and location information of the target. For each image, an eXtensible Markup Language (XML) file containing the above information is generated, and the target information in the XML file is written into the corresponding text file by writing a Python program. Finally, the Wi-Fi Emitter Identification Datasets (WFEID) is created using the labeled data in a standard format, which contains six categories of signals 1 to 6, with 190 images in each category, totaling 1140 images. The number of images collected for a specific radiation source signal is not specifically limited in the embodiments of the present invention.

[0063] It should be noted that, in order to avoid the situation where the random selection of training samples results in a small number of training samples for a certain radiation source signal and poor recognition results, the embodiment of the present invention constructs a training set and a test set from the target radar radiation source signal dataset according to a preset ratio. The preset ratio may refer to selecting 80% of the image samples of each specific radiation source signal as the training set and 20% of the image samples of each specific radiation source signal as the test set, i.e. Figure 6 shown.

[0064] Further, a YOLOv5 deep learning network model (i.e., target detection neural network) is constructed. Common model building methods include TensorFlow framework, Keras framework, MXNet framework, and PyTorch framework. The PyTorch framework has powerful GPU tensor computing capabilities, and the calculation graph is a dynamic calculation graph. The convolutional neural network built by the PyTorch framework has the ability of automatic derivation and is easy to use. Therefore, this technical solution comprehensively considers factors such as ease of use, performance, and community activity, and preferably uses the PyTorch deep learning framework to build an improved YOLOv5 neural network model. The model training environment of the present invention is as follows: the computer hardware configuration is i9-10900K CPU @ 3.70GHz, NVIDIAGeForce RTX 3080, and the operating system is Windows 10. The network model is built using the PyTorch framework, and CUDA11.1 and cuDNN8.0 are configured to better utilize GPU acceleration. All network models are built based on the Pytorch framework, and the training rounds are 200. For the YOLOv5 model, the same parameter settings were used: a batch size of 8, an image size of 640×640, an initial learning rate of 0.01, a momentum of 0.937, and a decay coefficient of 0.0005. The training sample of the signal's digital persistence spectrogram was input into the YOLOv5 network and sliced. The original image, 640×640×3, was converted to a 320×320×12 feature map. After a convolution operation with 64 convolution kernels, the feature map was finally reduced to 320×320×64. The YOLOv5 network was iteratively trained, and training ended when the number of iterations reached 1000, resulting in the YOLOv5 network model.

[0065] After the YOLOv5 network model is built, the digital afterglow spectrum to be used corresponding to each signal to be detected is input into the target network model. The shallow feature information to be used and the deep feature information to be used in the digital afterglow spectrum to be used are extracted based on the target network model. The shallow feature information to be used and the deep feature information to be used are fused to obtain the feature information to be determined. Based on the signal source corresponding to the information to be determined, the target signal source corresponding to the current signal to be identified can be determined, that is, Figure 7 As shown, Figure 7 Signal 1 in the example is Signal 1. The YOLOv5 network model was tested using the test set. The digital persistence spectrogram was analyzed to obtain the precision (P), recall (R), and mean average precision (mAP). The results are shown in the table below.

[0066]

[0067] Among them, precision can refer to the proportion of samples predicted as positive examples to all positive examples, recall rate can refer to the proportion of samples predicted as positive examples to all predicted samples, and average precision represents a detection indicator of a class.

[0068] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. All equivalent structural transformations made by using the contents of the present invention description and drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A method for identifying a specific radiation source signal, characterized in that: The steps include: Acquiring at least one signal to be identified in a target area and determining a digital persistence spectrum to be used corresponding to each signal to be identified specifically includes: Based on the signal acquisition device, wireless signals in the target area are collected to obtain at least one signal to be identified; For each signal to be identified, signal processing is performed on the current signal to be identified to obtain a current digital persistence spectrum to be used corresponding to the current signal to be identified, specifically including: determining information to be used corresponding to the current signal to be identified, wherein the information to be used includes at least one of color information, frequency information, and amplitude information; processing the information to be used based on a spectrum analyzer to obtain feature information to be determined corresponding to the current digital persistence spectrum to be used; The digital spectrum persistence diagram can intuitively display multiple signals in the same frequency range at different times, and use intensity levels, color schemes and statistical trace digital enhancement technology to highlight the various different information of each signal; For each digital persistence spectrum to be used, the current digital persistence spectrum to be used is processed based on the target detection neural network to obtain the to-be-determined feature information corresponding to the current digital persistence spectrum to be used, specifically including: Extracting shallow feature information and deep feature information corresponding to the current digital afterglow spectrum graph based on the target detection neural network; Performing feature fusion on the shallow feature information to be used and the deep feature information to be used to obtain feature information to be determined corresponding to the digital persistence spectrum to be used, wherein the feature information to be determined includes at least one of color, frequency, and amplitude; A target signal source corresponding to the signal to be identified is determined according to the characteristic information to be determined.

2. The method for identifying a specific radiation source signal according to claim 1, wherein: The determining, based on the characteristic information to be determined, a target signal source corresponding to the signal to be identified, specifically includes: According to the feature identifier to be identified carried by the feature information to be determined, the target signal source corresponding to the feature identifier to be identified is determined from the target mapping table; wherein the target mapping table includes at least one feature information to be matched and the feature identifier to be matched corresponding to each feature information to be matched.

Images