Radiation source individual information identification method, device, electronic device and medium

Abstract

The embodiments of the present disclosure disclose a method, device, electronic device and medium for identifying individual information of a radiation source. A specific implementation of the method includes: obtaining a set of intermediate frequency signals of a radiation source; performing signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to obtain a first signal domain set and a second signal domain set; performing individual identification on the first signal domain according to a preset first radiation source individual identification model to obtain an individual identification result and a first confidence level corresponding to the first signal domain; performing individual identification on the second signal domain according to a preset second radiation source individual identification model to obtain an individual identification result and a second confidence level corresponding to the second signal domain; determining the individual identification result corresponding to the confidence level with the largest value between the first confidence level and the second confidence level as the radiation source individual information corresponding to the intermediate frequency signal of the radiation source. This implementation can accurately extract subtle unintentional modulation information within a pulse, thereby improving the accuracy of identifying individual information of the radiation source.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of radar signal processing technology, and in particular to a method, device, electronic device, and medium for identifying individual information of a radiation source. Background Art

[0002] Radiation source individual identification technology refers to the technology of extracting fingerprint characteristic parameters of radiation source signals. Intra-pulse fingerprint features play an extremely important role in radiation source individual identification. Intra-pulse fingerprint features mainly come from the undue modulation of the signal by the non-ideal devices of the transmitter during the generation of the pulse signal, which is called intra-pulse unintentional modulation. Intra-pulse fingerprint feature extraction is the key to radiation source individual identification. For extracting intra-pulse fingerprint features, the usual method is to use the radiation source information database to identify the individual information of the radiation source.

[0003] However, the inventors have found that when the above method is used to identify the individual identification information of the radiation source, the following technical problems often occur:

[0004] First, since the characteristics of unintentional modulation within the pulse are complex nonlinear changes in a short period of time, the accuracy of identifying the individual information of the radiation source is low.

[0005] Second, the model’s accuracy is low due to the low quality of the sample data.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0007] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0008] Some embodiments of the present disclosure propose a method, device, electronic device and medium for identifying individual information of a radiation source to solve one or more of the technical problems mentioned in the above background technology section.

[0009] In a first aspect, some embodiments of the present disclosure provide a method for identifying individual information of a radiation source, comprising: obtaining a set of intermediate frequency signals of a radiation source; performing signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate a first signal domain and a second signal domain, and obtaining a first signal domain set and a second signal domain set; for each first signal domain in the first signal domain set and a second signal domain corresponding to the first signal domain in the second signal domain set, executing processing steps: performing individual identification on the first signal domain according to a preset first radiation source individual identification model, and obtaining an individual identification result and a first confidence level corresponding to the first signal domain; performing individual identification on the second signal domain according to a preset second radiation source individual identification model, and obtaining an individual identification result and a second confidence level corresponding to the second signal domain; and determining the individual identification result corresponding to the confidence level with the largest value between the first confidence level and the second confidence level as the radiation source individual information corresponding to the intermediate frequency signal of the radiation source.

[0010] In a second aspect, some embodiments of the present disclosure provide a radiation source individual information identification device, comprising: an acquisition unit, configured to acquire a radiation source intermediate frequency signal set; a segmentation unit, configured to perform signal segmentation on each intermediate frequency signal in the above-mentioned radiation source intermediate frequency signal set to generate a first signal domain and a second signal domain, and obtain a first signal domain set and a second signal domain set; a processing unit, configured to execute processing steps for each first signal domain in the above-mentioned first signal domain set and the second signal domain corresponding to the above-mentioned first signal domain in the above-mentioned second signal domain set: according to a preset first radiation source individual identification model, perform individual identification on the above-mentioned first signal domain to obtain an individual identification result and a first confidence level corresponding to the first signal domain; according to a preset second radiation source individual identification model, perform individual identification on the above-mentioned second signal domain to obtain an individual identification result and a second confidence level corresponding to the second signal domain; determine the individual identification result corresponding to the confidence level with the largest value between the above-mentioned first confidence level and the above-mentioned second confidence level as the radiation source individual information corresponding to the above-mentioned radiation source intermediate frequency signal.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0013] In a fifth aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which implements the method described in any implementation manner of the above-mentioned first aspect when executed by a processor.

[0014] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: the radiation source individual information identification method of some embodiments of the present disclosure can accurately extract subtle unintentional modulation information within the pulse, thereby improving the accuracy of radiation source individual information identification. Specifically, the reason for the low accuracy of the relevant radiation source individual information identification is that the characteristic of the unintentional modulation within the pulse is a complex nonlinear change law in a short period of time, resulting in low accuracy of radiation source individual information identification. Based on this, the radiation source individual information identification method of some embodiments of the present disclosure, first, obtains the radiation source intermediate frequency signal set. Therefore, the obtained radiation source intermediate frequency signal set is used for subsequent analysis and processing of the radiation source intermediate frequency signal set. Then, each intermediate frequency signal in the above radiation source intermediate frequency signal set is segmented to generate a first signal domain and a second signal domain, and obtain a first signal domain set and a second signal domain set. Therefore, the obtained first signal domain set and the second signal domain set can be used as the input of the subsequent initial radiation source individual identification model. Finally, for each first signal domain in the first signal domain set and the second signal domain corresponding to the first signal domain in the second signal domain set, a processing step is performed: according to the preset first radiation source individual recognition model, the first signal domain is individually recognized to obtain the individual recognition result and the first confidence corresponding to the first signal domain. According to the preset second radiation source individual recognition model, the second signal domain is individually recognized to obtain the individual recognition result and the second confidence corresponding to the second signal domain. The individual recognition result corresponding to the confidence with the largest value between the first confidence and the second confidence is determined as the radiation source individual information corresponding to the intermediate frequency signal of the radiation source. Therefore, through the two pre-trained initial radiation source individual recognition models, the different pulses of the same radiation source are individually recognized. The two confidences obtained are compared, and the radiation source individual recognition model with a large confidence is selected to improve the accuracy of the radiation source individual recognition result. It can be obtained that the radiation source individual information recognition method can accurately extract subtle pulses of unintentional modulation information, thereby improving the accuracy of radiation source individual information recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0016] Figure 1is a flow chart of some embodiments of the radiation source individual information identification method according to the present disclosure;

[0017] Figure 2 is a schematic structural diagram of some embodiments of the radiation source individual information identification device according to the present disclosure;

[0018] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0025] refer to Figure 1 , shows a process 100 of some embodiments of the radiation source individual information identification method according to the present disclosure. The radiation source individual information identification method comprises the following steps:

[0026] Step 101: Acquire a set of intermediate frequency signals of a radiation source.

[0027] In some embodiments, the execution subject of the above-mentioned radiation source individual information identification method can obtain the radiation source intermediate frequency signal set through a wireless connection. Among them, the radiation source intermediate frequency signal can be an electromagnetic signal emitted by a radar radiation source. For example, through a radio monitoring receiver, A / D (Analog to Digital Converter) data acquisition is performed on multiple radiation sources to obtain the intermediate frequency signal of the radiation source.

[0028] Step 102: perform signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate a first signal domain and a second signal domain, thereby obtaining a first signal domain set and a second signal domain set.

[0029] In some embodiments, the execution entity may perform signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate a first signal domain and a second signal domain, thereby obtaining a first signal domain set and a second signal domain set.

[0030] As an example, first, perform a Hilbert transform on the intermediate frequency signal of the radiation source to extract the envelope amplitude. The envelope amplitude characterizes the energy characteristics of the signal. Secondly, perform a smoothing filter on the envelope amplitude. Then, using the existing K-means algorithm, perform K-means clustering on the filtered envelope amplitude to obtain the cluster center of the pulse signal part and the cluster center of the noise part of the envelope amplitude. Finally, take the mean of the two cluster centers as the optimal threshold, and divide the signal into the pulse signal and the noise part according to the optimal threshold, so as to obtain the starting point and the ending point of the envelope, and then obtain the first signal domain set and the second signal domain set.

[0031] In some optional implementations of some embodiments, the signal segmentation of each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate the first signal domain and the second signal domain may include the following steps:

[0032] The first step is to detect the intermediate frequency signal to obtain an intermediate frequency signal envelope sequence.

[0033] For example, the intermediate frequency signal of the radiation source is detected by using Hilbert transform to obtain an intermediate frequency signal envelope sequence.

[0034] In the second step, for each intermediate frequency signal envelope in the intermediate frequency signal envelope sequence, a segmentation step is performed:

[0035] Sub-step 1, performing a signal domain search on the intermediate frequency signal envelope to obtain the starting point and the ending point of the pulse signal. The intermediate frequency signal envelope can be a curve reflecting the change in the amplitude of the intermediate frequency signal obtained by connecting the peak points of the intermediate frequency signal over a period of time.

[0036] For example, by using the threshold method, by setting reasonable threshold parameters, the starting point and the ending point of the pulse signal can be determined according to the mutation coordinates at the rising edge and the falling edge of the pulse.

[0037] Sub-step 2: determining the pulse signal data near the starting point and the ending point of the pulse signal as the first signal domain.

[0038] Sub-step 3: determining the pulse signal data between the starting point and the ending point of the pulse signal as the second signal domain.

[0039] Step 103: for each first signal domain in the first signal domain set and the second signal domain in the second signal domain set corresponding to the first signal domain, perform the following processing steps:

[0040] Step 1031: Perform individual recognition on the first signal domain according to a preset first radiation source individual recognition model to obtain an individual recognition result and a first confidence level corresponding to the first signal domain.

[0041] In some embodiments, the execution subject may perform individual identification on the first signal domain according to a preset first radiation source individual identification model, and obtain an individual identification result and a first confidence level corresponding to the first signal domain. The first radiation source individual identification model may be a variety of neural networks that extract subtle features from the signal sent by the radiation source to identify individual information of different radiation sources. For example, various neural networks include but are not limited to at least one of the following: Dense Convolutional Network (DenseNet), Visual Geometry Group Network (VGG), Residual Network (ResNet). The individual identification result may be the result of identifying the individual information of the radiation source. For example, the individual identification result may be the number of the radiation source that generates the signal. The first confidence level may be the accuracy of the first radiation source individual identification model in identifying the individual information of the radiation source.

[0042] As an example, the execution entity may input the first signal domain in the sample selected in step 102 into a preset first radiation source individual recognition model. By extracting and classifying features of the first signal domain, an individual recognition result and a first confidence level corresponding to the first signal domain are obtained.

[0043] In some optional implementations of some embodiments, the first radiation source individual recognition model is trained in the following manner:

[0044] The first step is to obtain a sample set, wherein the samples in the sample set include: a first signal domain set, and a sample label set corresponding to the first signal domain set. The sample label set corresponding to the first signal domain set may be an individual identification information set of the corresponding radiation source. For example, the individual identification information of the radiation source may be, but is not limited to, at least one of the following: the number of the radiation source, the type of the radiation source, the signal parameter, and the location information.

[0045] In the second step, for each sample in the above sample set, perform the following training steps:

[0046] Sub-step 1: Input the first signal domain of the sample into the first initial radiation source individual identification model to obtain the radiation source individual identification result corresponding to the sample. The radiation source individual identification result set corresponding to the sample may be, but is not limited to, at least one of the following: radiation source number, radiation source type, signal parameter, and location information.

[0047] Sub-step 2: comparing the radiation source individual identification result with the sample label corresponding to the corresponding first signal domain.

[0048] Sub-step 3, determining whether the first initial radiation source individual recognition model reaches a preset optimization target based on the comparison result. The optimization target may be the accuracy of the first initial radiation source individual recognition model. For example, the preset optimization target of the first initial radiation source individual recognition model may be 99%. The comparison result may include: information indicating that the first initial radiation source individual recognition result is the same as the sample label corresponding to the corresponding first signal domain, and information indicating that the first initial radiation source individual recognition result is different from the sample label corresponding to the corresponding first signal domain.

[0049] As an example, when the difference between the radiation source individual identification result corresponding to a sample and the sample label corresponding to the corresponding first signal domain is less than or equal to a preset error threshold, the radiation source individual identification result corresponding to the sample is considered accurate. The preset error threshold may be 0.05.

[0050] Sub-step 4, in response to determining that the first initial radiation source individual recognition model achieves the above-mentioned optimization goal, the first initial radiation source individual recognition model is used as the trained first radiation source individual recognition model.

[0051] Optionally, the above method may further include the following steps:

[0052] In response to determining that the first initial radiation source individual identification model does not achieve the above-mentioned optimization goal, the relevant parameters of the first initial radiation source individual identification model are adjusted, and samples are reselected from the above-mentioned sample set, and the adjusted first initial radiation source individual identification model is used as the first initial radiation source individual identification model, and the above-mentioned training steps are performed again.

[0053] As an example, the network parameters of the initial neural network may be adjusted by using a back propagation algorithm (BP algorithm) and a gradient descent method (eg, a mini-batch gradient descent algorithm).

[0054] Optionally, the above method further comprises the following steps:

[0055] The first step is to verify whether the first radiation source individual identification result set is accurate. For example, the first radiation source individual identification result set is compared with the sample label set corresponding to the corresponding first signal domain. If the error value is greater than or equal to 0.2, it is determined that the first radiation source individual identification result set is inaccurate.

[0056] In the second step, in response to determining that it is inaccurate, determining a first radiation source individual identification model corresponding to the verification radiation source individual information, and performing the following processing steps on the sample:

[0057] Sub-step 1, input the first signal domain set of the above sample into the signal noise addition module of the deep residual shrinkage network model to obtain the first signal domain set after noise addition as the third signal domain set. The deep residual shrinkage network (DRSN) model includes a signal noise addition module, a residual shrinkage filtering module and a fully connected dimensionality reduction module.

[0058] Sub-step 2, input the above-mentioned third signal domain set into the residual shrinkage filter module of the deep residual shrinkage network model to obtain the third signal domain set that filters out noise and redundant information as the fourth signal domain set. Among them, the residual shrinkage filter module can be built according to the basic residual network structure, and the residual shrinkage filter module includes multiple residual shrinkage modules (Residual Shrinkage Building Unit, RSBU). Noise can be an irregular additional signal that does not exist in the original signal generated when collecting signals.

[0059] Sub-step 3: input the fourth signal domain set into the fully connected dimensionality reduction module of the deep residual shrinkage network model to obtain the fourth signal domain set after dimensionality reduction.

[0060] In the third step, the fourth signal domain set is input into the first radiation source individual recognition model, and the first radiation source individual recognition model is trained again.

[0061] The above-mentioned related content, as an inventive point of an embodiment of the present disclosure, solves the technical problem 2 mentioned in the technical background, "due to the low quality of the sample data, the accuracy of the model is low.". The factors that lead to the low accuracy of the model are often as follows: the quality of the sample data is low. If the above factors are solved, the accuracy of the model can be improved. In order to achieve this effect, the present disclosure first verifies whether the above-mentioned first radiation source individual identification result set is accurate. Therefore, by verifying whether the radiation source individual identification result set is accurate, the accuracy of the radiation source individual identification model is judged. Secondly, in response to the determination of inaccuracy, the first radiation source individual identification model corresponding to the verified radiation source individual information is determined, and the following processing steps are performed on the sample: the first signal domain set of the above-mentioned sample is input into the signal noise module of the deep residual shrinkage network model to obtain the first signal domain set after noise as the third signal domain set. Among them, the deep residual shrinkage network (DRSN) model includes a signal noise module, a residual shrinkage filtering module and a fully connected dimensionality reduction module. Therefore, the input first signal domain set is Gaussian noised by the Gaussian noise layer for the input of the subsequent model. Then, the third signal domain set is input into the residual shrinkage filter module of the deep residual shrinkage network model to obtain the third signal domain set that filters out noise and redundant information as the fourth signal domain set. Among them, the residual shrinkage filter module can be built according to the basic residual network structure, and the residual shrinkage filter module includes multiple residual shrinkage modules (ResidualShrinkage Building Unit, RSBU). Thus, the absolute value of the useful information in the input third signal domain set is amplified, the noise in the third signal domain set is converted to the near-zero domain, and the noise and redundant information in the third signal domain set are filtered out. Among them, the near-zero domain represents data close to zero value. Finally, the fourth signal domain set is input into the fully connected dimensionality reduction module of the deep residual shrinkage network model to obtain the fourth signal domain set after dimensionality reduction. Thus, a relatively pure sample set is obtained. The fourth signal domain set is input into the first radiation source individual recognition model, and the first radiation source individual recognition model is trained again. Thus, the optimization of the sample is completed, and the accuracy of the radiation source individual recognition model is improved.

[0062] Step 1032: Perform individual identification on the second signal domain according to the preset second radiation source individual identification model to obtain an individual identification result and a second confidence level corresponding to the second signal domain.

[0063] In some embodiments, the execution subject may perform individual identification on the second signal domain according to a preset second radiation source individual identification model, and obtain an individual identification result and a second confidence level corresponding to the second signal domain. The second radiation source individual identification model may be various neural networks that identify individual information of the radiation source according to the second signal domain. For example, various neural networks include but are not limited to at least one of the following: a dense convolutional neural network (DenseNet), a visual geometry group network (VGG), and a residual neural network (ResNet). The individual identification result may be the result of identifying the individual information of the radiation source. For example, the individual identification result may be the number of the radiation source that generates the signal. The second confidence level may be the accuracy of the second radiation source individual identification model in identifying the individual information of the radiation source.

[0064] As an example, the execution entity may input the second signal domain in the sample selected in step 102 into a preset second radiation source individual recognition model. By analyzing the second signal domain, an individual recognition result and a second confidence level corresponding to the second signal domain may be obtained.

[0065] In some optional implementations of some embodiments, the second radiation source individual recognition model is trained in the following manner:

[0066] The first step is to obtain a sample set, wherein the samples in the sample set include: a second signal domain set, and a sample label set corresponding to the second signal domain set. The sample label set corresponding to the second signal domain set may be an individual identification information set of the corresponding radiation source. For example, the individual identification information set of the radiation source may be, but is not limited to, at least one of the following: the number of the radiation source, the type of the radiation source, the signal parameter, and the location information.

[0067] In the second step, for each sample in the above sample set, perform the following training steps:

[0068] Sub-step 1: Input the second signal domain of the sample into the second initial radiation source individual identification model to obtain the radiation source individual identification result corresponding to the sample. The radiation source individual identification result set corresponding to the sample may be, but is not limited to, at least one of the following: radiation source number, radiation source type, signal parameter, and location information.

[0069] Sub-step 2: comparing the radiation source individual identification result with the sample label corresponding to the corresponding second signal domain.

[0070] Sub-step 3, determining whether the second initial radiation source individual recognition model reaches a preset optimization target based on the comparison result. The optimization target may be the accuracy of the second initial radiation source individual recognition model. For example, the preset optimization target of the second initial radiation source individual recognition model may be 99%. The comparison result may include: information indicating that the radiation source individual recognition result is the same as the sample label corresponding to the corresponding second signal domain, and information indicating that the radiation source individual recognition result is different from the sample label corresponding to the corresponding second signal domain.

[0071] As an example, when the difference between the radiation source individual identification result corresponding to a sample and the sample label corresponding to the corresponding first signal domain is less than or equal to a preset difference threshold, the radiation source individual identification result corresponding to the sample is considered to be accurate.

[0072] Sub-step 4, in response to determining that the second initial radiation source individual recognition model achieves the above optimization goal, the second initial radiation source individual recognition model is used as the trained second radiation source individual recognition model.

[0073] Optionally, the above method may further include the following steps:

[0074] In response to determining that the second initial radiation source individual identification model does not achieve the above-mentioned optimization goal, the relevant parameters of the second initial radiation source individual identification model are adjusted, and samples are reselected from the above-mentioned sample set, and the adjusted second initial radiation source individual identification model is used as the second initial radiation source individual identification model, and the above-mentioned training steps are performed again.

[0075] As an example, the network parameters of the initial neural network may be adjusted by using a back propagation algorithm (BP algorithm) and a gradient descent method (eg, a mini-batch gradient descent algorithm).

[0076] Step 1033: determine the individual identification result corresponding to the confidence degree with the largest value between the first confidence degree and the second confidence degree as the radiation source individual information corresponding to the radiation source intermediate frequency signal.

[0077] In some embodiments, the execution subject may determine the individual identification result corresponding to the maximum confidence value between the first confidence value and the second confidence value as the radiation source individual information corresponding to the radiation source intermediate frequency signal. For example, if the first confidence value is greater than or equal to the second confidence value, the individual identification result corresponding to the first confidence value is determined as the radiation source individual information corresponding to the radiation source intermediate frequency signal. If the first confidence value is less than the second confidence value, the individual identification result corresponding to the second confidence value is determined as the radiation source individual information corresponding to the radiation source intermediate frequency signal.

[0078] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: the radiation source individual information identification method of some embodiments of the present disclosure can accurately extract subtle unintentional modulation information within the pulse, thereby improving the accuracy of radiation source individual information identification. Specifically, the reason for the low accuracy of the relevant radiation source individual information identification is that the characteristic of the unintentional modulation within the pulse is a complex nonlinear change law in a short period of time, resulting in low accuracy of radiation source individual information identification. Based on this, the radiation source individual information identification method of some embodiments of the present disclosure, first, obtains the radiation source intermediate frequency signal set. Therefore, the obtained radiation source intermediate frequency signal set is used for subsequent analysis and processing of the radiation source intermediate frequency signal set. Then, each intermediate frequency signal in the above radiation source intermediate frequency signal set is segmented to generate a first signal domain and a second signal domain, and obtain a first signal domain set and a second signal domain set. Therefore, the obtained first signal domain set and the second signal domain set can be used as the input of the subsequent initial radiation source individual identification model. Finally, for each first signal domain in the first signal domain set and the second signal domain corresponding to the first signal domain in the second signal domain set, a processing step is performed: according to the preset first radiation source individual recognition model, the first signal domain is individually recognized to obtain the individual recognition result and the first confidence corresponding to the first signal domain. According to the preset second radiation source individual recognition model, the second signal domain is individually recognized to obtain the individual recognition result and the second confidence corresponding to the second signal domain. The individual recognition result corresponding to the confidence with the largest value between the first confidence and the second confidence is determined as the radiation source individual information corresponding to the intermediate frequency signal of the radiation source. Therefore, through the two pre-trained initial radiation source individual recognition models, the different pulses of the same radiation source are individually recognized. The two confidences obtained are compared, and the radiation source individual recognition model with a large confidence is selected to improve the accuracy of the radiation source individual recognition result. It can be obtained that the radiation source individual information recognition method can accurately extract subtle pulses of unintentional modulation information, thereby improving the accuracy of radiation source individual information recognition.

[0079] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a radiation source individual information identification device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0080] like Figure 2As shown, a radiation source individual information identification device 200 includes: an acquisition unit 201, a segmentation unit 202 and a processing unit 203. The acquisition unit 201 is configured to: acquire a radiation source intermediate frequency signal set. The segmentation unit 202 is configured to: perform signal segmentation on each intermediate frequency signal in the above-mentioned radiation source intermediate frequency signal set to generate a first signal domain and a second signal domain, and obtain a first signal domain set and a second signal domain set. The processing unit 203 is configured to: for each first signal domain in the above-mentioned first signal domain set and the second signal domain corresponding to the above-mentioned first signal domain in the above-mentioned second signal domain set, perform processing steps: according to a preset first radiation source individual identification model, perform individual identification on the above-mentioned first signal domain, and obtain an individual identification result and a first confidence corresponding to the first signal domain; according to a preset second radiation source individual identification model, perform individual identification on the above-mentioned second signal domain, and obtain an individual identification result and a second confidence corresponding to the second signal domain; determine the individual identification result corresponding to the confidence with the largest value between the above-mentioned first confidence and the above-mentioned second confidence as the radiation source individual information corresponding to the above-mentioned radiation source intermediate frequency signal.

[0081] It can be understood that the units recorded in the radiation source individual information identification device 200 are similar to the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be described in detail here.

[0082] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0083] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0084] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0085] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0086] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0087] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0088] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a set of intermediate frequency signals of a radiation source; performs signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate a first signal domain and a second signal domain, and obtains a first signal domain set and a second signal domain set; for each first signal domain in the first signal domain set and a second signal domain corresponding to the first signal domain in the second signal domain set, performs processing steps: according to a preset first radiation source individual recognition model, perform individual recognition on the first signal domain, and obtain an individual recognition result and a first confidence corresponding to the first signal domain; according to a preset second radiation source individual recognition model, perform individual recognition on the second signal domain, and obtain an individual recognition result and a second confidence corresponding to the second signal domain; determine the individual recognition result corresponding to the confidence with the largest value between the first confidence and the second confidence as the radiation source individual information corresponding to the intermediate frequency signal of the radiation source.

[0089] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] The units described in some embodiments of the present disclosure may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a segmentation unit, and a processing unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the acquisition unit may also be described as a "unit for acquiring a set of intermediate frequency signals of a radiation source".

[0092] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0093] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for identifying individual information of a radiation source, include: Obtaining a set of intermediate frequency signals of a radiation source; Performing signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate a first signal domain and a second signal domain, and obtaining a first signal domain set and a second signal domain set, wherein performing signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate a first signal domain and a second signal domain comprises: Detecting the intermediate frequency signal to obtain an intermediate frequency signal envelope sequence; For each intermediate frequency signal envelope in the intermediate frequency signal envelope sequence, a segmentation step is performed: Performing a signal domain search on the intermediate frequency signal envelope to obtain a starting point and an ending point of a pulse signal; Determine the pulse signal data near the starting point and the ending point of the pulse signal as the first signal domain; Determine the pulse signal data between the starting point and the ending point of the pulse signal as the second signal domain; For each first signal domain in the first signal domain set and a second signal domain in the second signal domain set corresponding to the first signal domain, performing a processing step: According to a preset first radiation source individual identification model, individual identification is performed on the first signal domain to obtain an individual identification result and a first confidence level corresponding to the first signal domain; According to a preset second radiation source individual recognition model, performing individual recognition on the second signal domain to obtain an individual recognition result and a second confidence level corresponding to the second signal domain; The individual identification result corresponding to the confidence degree with the largest value between the first confidence degree and the second confidence degree is determined as the radiation source individual information corresponding to the radiation source intermediate frequency signal.

2. The method according to claim 1, in, The first radiation source individual recognition model is trained in the following way: Acquire a sample set, wherein the samples in the sample set include: a first signal domain set, and a sample label set corresponding to the first signal domain set; For each sample in the sample set, the following training steps are performed: Inputting the first signal domain of the sample into a first initial radiation source individual identification model to obtain a radiation source individual identification result corresponding to the sample; Comparing the radiation source individual identification result with the sample label corresponding to the corresponding first signal domain; Determining whether the first initial radiation source individual identification model reaches a preset optimization goal according to the comparison result; In response to determining that the first initial radiation source individual recognition model achieves the optimization target, the first initial radiation source individual recognition model is used as the trained first radiation source individual recognition model.

3. The method according to claim 2, in, The method further comprises: In response to determining that the first initial radiation source individual identification model does not achieve the optimization goal, the relevant parameters of the first initial radiation source individual identification model are adjusted, and samples are reselected from the sample set, and the adjusted first initial radiation source individual identification model is used as the first initial radiation source individual identification model, and the training step is performed again.

4. The method according to claim 1, in, The second radiation source individual identification model is trained in the following way: Acquire a sample set, wherein the samples in the sample set include: a second signal domain set, and a sample label set corresponding to the second signal domain set; For each sample in the sample set, the following training steps are performed: Inputting the second signal domain of the sample into a second initial radiation source individual identification model to obtain a radiation source individual identification result corresponding to the sample; Comparing the radiation source individual identification result with the sample label corresponding to the corresponding second signal domain; Determining whether the second initial radiation source individual identification model reaches a preset optimization goal according to the comparison result; In response to determining that the second initial radiation source individual recognition model achieves the optimization target, the second initial radiation source individual recognition model is used as the trained second radiation source individual recognition model.

5. The method according to claim 4, in, The method further comprises: In response to determining that the second initial radiation source individual identification model does not achieve the optimization goal, the relevant parameters of the second initial radiation source individual identification model are adjusted, and samples are reselected from the sample set, and the adjusted second initial radiation source individual identification model is used as the second initial radiation source individual identification model, and the training step is performed again.

6. A radiation source individual information identification device, include: An acquisition unit, configured to acquire an intermediate frequency signal set of a radiation source; A segmentation unit is configured to perform signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate a first signal domain and a second signal domain, and obtain a first signal domain set and a second signal domain set, wherein the signal segmentation on each intermediate frequency signal in the intermediate frequency signal set of the radiation source to generate the first signal domain and the second signal domain includes: detecting the intermediate frequency signal to obtain an intermediate frequency signal envelope sequence; for each intermediate frequency signal envelope in the intermediate frequency signal envelope sequence, performing a segmentation step: performing a signal domain search on the intermediate frequency signal envelope to obtain a starting point and an ending point of a pulse signal; determining the pulse signal data near the starting point and the ending point of the pulse signal as the first signal domain; and determining the pulse signal data between the starting point and the ending point of the pulse signal as the second signal domain; The processing unit is configured to execute processing steps for each first signal domain in the first signal domain set and the second signal domain corresponding to the first signal domain in the second signal domain set: performing individual identification on the first signal domain according to a preset first radiation source individual identification model, and obtaining an individual identification result and a first confidence level corresponding to the first signal domain; performing individual identification on the second signal domain according to a preset second radiation source individual identification model, and obtaining an individual identification result and a second confidence level corresponding to the second signal domain; and determining the individual identification result corresponding to the confidence level with the largest value between the first confidence level and the second confidence level as the radiation source individual information corresponding to the intermediate frequency signal of the radiation source.

7. An electronic device, include: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, in, When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images