Interference scheme determination method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses an interference scheme determination method and device, electronic equipment and a storage medium. The method comprises the following steps: under the condition that a target radar signal sent by a radar system is received, determining description word information of a radar pulse description word of the target radar signal; based on the descriptor information and a feature extraction layer of a pre-constructed interference decision network, extracting signal feature information corresponding to the target radar signal; and determining a target interference scheme for coping with the target radar signal based on the interference decision layer and the signal feature information of the interference decision network, so as to transmit the target interference signal according to the target interference scheme. According to the technical scheme provided by the embodiment of the invention, the target interference scheme corresponding to the target radar information can be flexibly determined so as to deal with variable radar signals; meanwhile, the radar system is interfered through the target interference scheme corresponding to the target radar signal, so that the accuracy of interference operation is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of radar jamming technology, and in particular, to a method, device, electronic device, and storage medium for determining an jamming scheme. Background Art

[0002] In modern radar electronic game technology, jammers can transmit jamming signals according to the jamming scheme, making it difficult for radar to accurately detect and track targets, playing a very important role in the electronic game process.

[0003] In the prior art, a pre-set fixed interference scheme is usually used to generate an interference signal to interfere with the radar. However, in the process of implementing the present invention, it is found that the prior art has at least the following technical problems: using a fixed interference scheme, it is difficult to effectively identify and respond to variable radar signals, which reduces the accuracy and flexibility of the interference operation on the radar. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, electronic device and storage medium for determining an interference scheme, so as to flexibly determine a target interference scheme corresponding to target radar information, and interfere with a radar system through a target interference scheme corresponding to a target radar signal, thereby helping to improve the accuracy of the interference operation.

[0005] According to one aspect of the present invention, a method for determining an interference scheme is provided, comprising:

[0006] In case of receiving a target radar signal sent by a radar system, determining descriptor information of a radar pulse descriptor of the target radar signal;

[0007] Extracting signal feature information corresponding to the target radar signal based on the descriptor information and a feature extraction layer of a pre-constructed interference decision network;

[0008] Based on the interference decision layer of the interference decision network and the signal characteristic information, a target interference scheme for dealing with the target radar signal is determined to transmit a target interference signal according to the target interference scheme.

[0009] According to another aspect of the present invention, there is provided an interference scheme determination device, the device comprising:

[0010] a descriptor information determination module, configured to determine the descriptor information of the radar pulse descriptor of the target radar signal when receiving the target radar signal sent by the radar system;

[0011] A signal feature information extraction module, used to extract the signal feature information corresponding to the target radar signal based on the descriptor information and the feature extraction layer of the pre-constructed interference decision network;

[0012] A target interference scheme determination module is used to determine a target interference scheme for dealing with the target radar signal based on the interference decision layer of the interference decision network and the signal characteristic information, so as to transmit a target interference signal according to the target interference scheme.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the interference scheme determination method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the interference scheme determination method described in any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention determines the descriptor information of the radar pulse descriptor of the target radar signal when the target radar signal sent by the radar system is received; based on the descriptor information and the feature extraction layer of the pre-constructed interference decision network, the signal feature information corresponding to the target radar signal is extracted; through the interference decision layer of the interference decision network and the signal feature information, a target interference scheme for dealing with the target radar signal is determined, so as to transmit the target interference signal according to the target interference scheme, so as to flexibly determine the target interference scheme corresponding to the target radar information according to the signal feature information of the received target radar signal each time, so as to deal with the changeable radar signal; at the same time, the radar system is interfered with by the target interference scheme corresponding to the target radar signal, which helps to improve the accuracy of the interference operation.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 these drawings without creative work.

[0021] Figure 1 is a flow chart of a method for determining an interference scheme provided according to an embodiment of the present invention;

[0022] Figure 2 is a flow chart of another interference scheme determination method provided by an embodiment of the present invention;

[0023] Figure 3 is a structural schematic diagram of an interference scheme determination device provided according to an embodiment of the present invention;

[0024] Figure 4 It is a structural schematic diagram of an electronic device for implementing the interference scheme determination method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "etc." and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0028] Figure 1 1 is a flow chart of a method for determining an interference scheme according to an embodiment of the present invention. This embodiment is applicable to a case where a jammer generates a target interference scheme based on a received target radar signal. The method can be performed by an interference scheme determination device, which can be implemented in the form of hardware and / or software.

[0029] like Figure 1 As shown, the method of this embodiment may specifically include:

[0030] S110 . When receiving a target radar signal sent by a radar system, determine descriptor information of a radar pulse descriptor of the target radar signal.

[0031] It should be noted that the target radar signal includes a radar transmission signal sent by the radar system and a background noise signal. In order to reduce noise interference, after receiving the target radar signal, a signal preprocessing operation may be performed on the target radar signal.

[0032] Specifically, determining the descriptor information of the radar pulse descriptor of the target radar signal includes: performing a signal preprocessing operation on the target radar signal, and updating the target radar signal based on the signal obtained after the preprocessing operation; wherein the signal preprocessing operation includes at least one of bandpass filtering, normalization and adaptive filtering.

[0033] In a specific implementation, the target radar signal can be bandpass filtered by a pre-built bandpass filter, and the target radar signal can be updated based on the signal obtained after the bandpass filtering. Furthermore, in order to ensure that the signal amplitude of the target radar signal is within the standard range and facilitate signal processing, the updated target radar signal can be normalized to obtain a normalized signal. The calculation formula of the normalized signal is:

[0034]

[0035] Wherein, s"(t) represents the normalized signal, s'(t) represents the updated target radar signal, and max(|s'(t)|) represents the maximum value of the absolute value of the updated target radar signal.

[0036] Furthermore, in order to reduce residual noise in the signal, the normalized signal may be adaptively filtered by an adaptive filtering algorithm, and the target radar signal may be updated based on the signal after the adaptive filtering. The descriptor information of the radar pulse descriptor may be determined by the updated target radar signal.

[0037] Among them, the radar pulse descriptor includes at least one item of pulse width, pulse amplitude, pulse repetition interval and carrier frequency. Pulse width is used to reflect the time duration of the pulse in the target radar signal; pulse amplitude is used to reflect the peak strength of the pulse in the target radar signal; pulse repetition interval is used to reflect the repetition period of the pulse in the target radar signal; carrier frequency is used to reflect the frequency of the target radar signal. The descriptor information includes the specific value of the radar pulse descriptor and the classification corresponding to the radar pulse descriptor. Exemplarily, when the descriptor information is a specific value, the radar pulse descriptor is pulse amplitude, and the descriptor information is the pulse amplitude value. When the descriptor information reflects the classification, the radar pulse descriptor is pulse width, and the descriptor information corresponding to the pulse width may include narrow pulse, medium pulse or wide pulse.

[0038] In this embodiment, bandwidth filtering and adaptive filtering are performed on the target radar signal to minimize the influence of noise on the target radar signal; and normalization is performed to ensure that the amplitude of the target radar signal is within a standard range, so as to facilitate subsequent signal processing operations.

[0039] In this embodiment, a specific implementation method for determining the descriptor information of the radar pulse descriptor of the target radar signal includes: performing short-time Fourier transform processing on the target radar signal to obtain a frequency domain signal corresponding to the target radar signal; performing logarithmic transform processing on the frequency domain signal to obtain a logarithmic amplitude spectrum corresponding to the target radar signal; and determining the descriptor information of the radar pulse descriptor of the target radar signal based on the logarithmic amplitude spectrum.

[0040] In order to fully capture the information contained in the target radar signal, the target radar signal can be processed by short-time Fourier transform, thereby reflecting the time-frequency characteristics of the target radar signal. Specifically, the Hamming window function can be used to perform short-time Fourier transform processing to reduce spectrum leakage and reduce the influence of spectrum side lobes.

[0041] It should be noted that the time-frequency distribution of the frequency domain signal is a complex spectrum, including four parts: real part, imaginary part, modulus and phase. Among them, the real part reflects the time-frequency information of the real part of the target radar signal. The imaginary part is used to reflect the time-frequency information of the imaginary part of the target radar signal, the modulus is used to reflect the energy intensity of the target radar signal, and the phase is used to reflect the phase angle of the target radar signal.

[0042] In a specific implementation, in order to enhance the ability of feature recognition, the frequency domain signal can be converted into a logarithmic amplitude spectrum, that is, the frequency domain signal is subjected to logarithmic transformation. Specifically, the process of logarithmic transformation is:

[0043] X log (t,f)=20×log 10 (|X(t,f)|+∈)

[0044] Among them, X log (t,f) represents the logarithmic amplitude spectrum, and X(t,f) represents the frequency domain signal. ∈ represents a positive integer whose value is less than the preset threshold. ∈ is used to avoid the situation where the true number is zero in the logarithmic operation, ensuring the stability of the calculation.

[0045] In this embodiment, in order to facilitate the subsequent effective determination of signal feature information, the logarithmic amplitude spectrum can be normalized to generate a time-frequency image of a preset standard size. The time-frequency image contains multi-dimensional features. By extracting the image features in the time-frequency image, the descriptor information of the radar pulse descriptor of the target radar signal is determined.

[0046] This embodiment determines the time-frequency characteristics of the target radar signal through short-time Fourier transform processing; and the logarithmic transform processing is conducive to enhancing the feature recognition capability and facilitating the effective determination of the signal feature information in the target radar signal.

[0047] Optionally, based on the logarithmic amplitude spectrum, the descriptive word information of the radar pulse descriptor of the target radar signal is determined, including: inputting the logarithmic amplitude spectrum into pre-constructed real part sub-classifier, imaginary part sub-classifier, modulus value sub-classifier and phase sub-classifier respectively, extracting the real part feature information, imaginary part feature information, total energy feature information and phase frequency information of the logarithmic amplitude spectrum; based on preset sub-classifier weights, performing a weighted summation operation on the real part feature information, imaginary part feature information, total energy feature information and phase frequency information, and determining the descriptive word information of the radar pulse word of the target radar signal based on the sum value obtained by the weighted summation operation.

[0048] Among them, the real part sub-classifier, the imaginary part sub-classifier, the modulus sub-classifier and the phase sub-classifier include a convolutional layer, a pooling layer and a fully connected layer, respectively.

[0049] It should be noted that the preset description category is a preset category of radar signals. Different radar pulse descriptors correspond to different preset description categories. Exemplarily, if the pulse descriptor is pulse width, the preset description category includes at least one of narrow pulse, medium pulse and wide pulse. If the pulse descriptor is carrier frequency, the preset description category may include a conventional frequency signal and a frequency agile signal. If the pulse descriptor is pulse repetition interval, the preset description category includes at least one of a fixed pulse repetition interval, a staggered pulse repetition interval, a jittered pulse repetition interval and a slipped pulse repetition interval.

[0050] In a specific implementation, the logarithmic amplitude spectrum is input into a pre-constructed real part sub-classifier, and the first association probability between the real part feature and the preset description category corresponding to each radar pulse descriptor is output, and the first association probability is used as the real part feature information. The logarithmic amplitude spectrum is input into the imaginary part sub-classifier, and the second association probability between the imaginary part feature and the preset description category corresponding to each radar pulse descriptor is output, and the second association probability is used as the imaginary part feature information. The logarithmic amplitude spectrum is input into the modulus sub-classifier, and the third association probability between the modulus feature and the preset description category corresponding to each radar pulse descriptor is output, and the third association probability is used as the total energy feature information; the logarithmic amplitude spectrum is input into the phase sub-classifier, and the fourth association probability between the phase frequency feature and the preset description category corresponding to each radar pulse descriptor is output, and the fourth association probability is used as the phase frequency information.

[0051] In this embodiment, during the training process of the real sub-classifier, the imaginary sub-classifier, the modulus sub-classifier and the phase sub-classifier, the weights corresponding to the real sub-classifier, the imaginary sub-classifier, the modulus sub-classifier and the phase sub-classifier, i.e., the sub-classifier weights, can be determined. Specifically, the sub-classifier weights can be determined based on the accuracy of each sub-classifier on the validation set. Optionally, the real sub-classifier, the imaginary sub-classifier, the modulus sub-classifier and the phase sub-classifier can be sorted, and the formula for determining the sub-classifier weight corresponding to each sub-classifier can be:

[0052]

[0053] Among them, Acc i is the classification accuracy of the i-th subclassifier in the ranking on the validation set used for classifier training. i represents the subclassifier weight of the ith subclassifier. S represents the sum of the classification accuracy of the real subclassifier, imaginary subclassifier, modulus subclassifier, and phase subclassifier on the validation set. Determining the subclassifier weights in this way ensures that the contribution of each subclassifier matches its performance during the integration process.

[0054] In this embodiment, based on the preset sub-classifier weights, a weighted sum operation is performed on the real feature information, the imaginary feature information, the total energy feature information, and the phase frequency information, that is, for each preset description category corresponding to each radar pulse descriptor, a weighted sum operation is performed on the first association probability, the second association probability, the third association probability, and the fourth association probability based on the sub-classifier weights to obtain a total score; finally, for each preset description category corresponding to each radar pulse descriptor, a total score is corresponding. The maximum total score in the total score corresponding to each radar pulse descriptor can be screened out, and each maximum total score forms a probability classification vector.

[0055] Exemplarily, the pulse width corresponds to 100 preset description categories, each preset description category obtains a total score, and the maximum total score is a; the pulse amplitude corresponds to 100 preset description categories, each preset description category obtains a total score, and the maximum total score is b; the maximum total score corresponding to the pulse repetition interval is c, and the maximum total score corresponding to the carrier frequency is d, then the probability classification vector is composed of [a, b, c, d].

[0056] Furthermore, for each radar pulse descriptor, the category information of the preset description category corresponding to the maximum total score may be determined. It should be noted that the target radar signal may include multiple frames of data, and the descriptor information may be composed based on the category information corresponding to each frame of data. The category information includes information such as the name and number of the preset description category.

[0057] In this embodiment, the features of each dimension of the spectrum are fully utilized through the real part sub-classifier, imaginary part sub-classifier, modulus sub-classifier and phase sub-classifier; the weighted integration operation is conducive to improving the accuracy of the determined descriptor information. In addition, the probability classification vector provides quantized radar signal features for subsequent interference decisions, so that the jammer can specify the corresponding interference scheme according to the specific characteristics of the target radar signal.

[0058] S120, extracting signal feature information corresponding to the target radar signal based on the descriptor information and the feature extraction layer of the pre-built interference decision network.

[0059] In order to make more full and effective use of the description word information, the description word information can be split and processed into multiple description segments. By performing feature extraction on each description segment, more detailed information can be extracted. Specifically, each description segment can be input into the feature extraction layer of the pre-constructed interference decision network, and based on the information corresponding to each description segment output by the feature extraction layer, the signal feature information corresponding to the target radar signal is determined. Optionally, the feature extraction layer includes a Transformer layer. The feature extraction layer includes a spatial feature extraction network layer and / or a temporal feature extraction network layer. The spatial feature extraction network layer is used to extract the potential correlation between different radar pulse descriptors in each description segment; the temporal feature extraction network layer is used to capture the dynamic characteristics of the target radar signal that change over time.

[0060] S130, determining a target interference scheme for dealing with the target radar signal based on the interference decision layer and signal characteristic information of the interference decision network, so as to transmit the target interference signal according to the target interference scheme.

[0061] In this embodiment, the signal characteristic information can be input into the interference decision layer of the interference decision network, and the target interference scheme can be determined from multiple preset interference schemes through the output information of the interference decision layer, and the target interference signal can be transmitted according to the target interference scheme.

[0062] The technical solution of the embodiment of the present invention determines the descriptor information of the radar pulse descriptor of the target radar signal when the target radar signal sent by the radar system is received; based on the descriptor information and the feature extraction layer of the pre-constructed interference decision network, the signal feature information corresponding to the target radar signal is extracted; through the interference decision layer of the interference decision network and the signal feature information, a target interference scheme for dealing with the target radar signal is determined, so as to transmit the target interference signal according to the target interference scheme, so as to flexibly determine the target interference scheme corresponding to the target radar information according to the signal feature information of the received target radar signal each time, so as to deal with the changeable radar signal; at the same time, the radar system is interfered with by the target interference scheme corresponding to the target radar signal, which helps to improve the accuracy of the interference operation.

[0063] Figure 2It is a flowchart of another interference scheme determination method provided according to an embodiment of the present invention. Based on the above embodiment, this embodiment proposes that the feature extraction layer includes a spatial feature extraction network layer, a temporal feature extraction network layer and a mask network layer; based on the descriptive word information and the feature extraction layer of the pre-constructed interference decision network, the implementation method of extracting the signal feature information corresponding to the target radar signal includes: inputting the descriptive word information into the spatial feature extraction network layer, and extracting the spatial feature information of the descriptive word information through the spatial feature extraction network layer; inputting the spatial feature information into the temporal feature extraction network layer to obtain the spatiotemporal feature information corresponding to the descriptive word information; inputting the spatiotemporal feature information into the mask network layer to obtain the signal feature information corresponding to the target radar signal. Among them, the explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 2 As shown, the method includes:

[0064] S210 . When receiving a target radar signal sent by a radar system, determine descriptor information of a radar pulse descriptor of the target radar signal.

[0065] S220 , inputting the description word information into the spatial feature extraction network layer, and extracting the spatial feature information of the description word information through the spatial feature extraction network layer.

[0066] Optionally, the description word information may be split into multiple description segments, and each description segment may be input into the spatial feature extraction network layer. Alternatively, the description word information may be directly input into the spatial feature extraction network layer. In the case where each description segment is input into the spatial feature extraction network layer, the spatial feature extraction network layer may process each description segment using a self-attention mechanism.

[0067] In this embodiment, the output information of the spatial feature extraction network layer can be determined as the spatial feature information. Exemplarily, for the case where each description segment is input into the spatial feature extraction network layer, after each description segment is input into the spatial feature extraction network layer, the spatial features between each radar pulse descriptor in each description segment are extracted through space, thereby identifying the potential association between different radar pulse descriptors. For example, the relationship between pulse width and pulse repetition interval is identified. The output information corresponding to each description segment is combined to obtain the spatial feature information. For the case where the description word information is directly input into the spatial feature extraction network layer, the output information of the spatial feature extraction network layer can be directly used as the spatial feature information.

[0068] S230, inputting the spatial feature information into the temporal feature extraction network layer to obtain the temporal and spatial feature information corresponding to the description word information; inputting the temporal and spatial feature information into the mask network layer to obtain the signal feature information corresponding to the target radar signal.

[0069] The mask network layer is used to perform element-by-element multiplication of spatiotemporal feature information based on a preset mask matrix. The mask network layer includes a feedforward network layer, a mask layer, and an activation function layer.

[0070] In this embodiment, the spatial feature information can be input into the temporal feature extraction network layer, and the output information of the temporal feature extraction network layer is used as the temporal and spatial feature information. It should be noted that the main task of the temporal feature extraction network layer is to process continuous features in the time dimension, so as to capture the dynamic characteristics of the target radar signal changing over time. Since the key characteristics of the target radar signal usually show certain regularities in time, the temporal feature extraction network layer identifies these regularities through the self-attention mechanism and generates a high-dimensional representation with temporal characteristics.

[0071] Furthermore, after completing the joint characterization of the spatiotemporal features, the obtained spatiotemporal feature information is input into the mask network layer. The main function of the mask network layer is to selectively highlight the features related to the decision and suppress irrelevant interference factors according to the current state of the radar. Specifically, the mask matrix can be set according to the current state of the radar. After the spatiotemporal feature information is input into the mask network layer, the spatiotemporal feature information is multiplied element by element with the mask matrix, and the result obtained after the multiplication is used as the signal feature information.

[0072] In this embodiment, a more abundant and accurate time-frequency feature is extracted from the target radar signal through a hierarchical feature extraction method, so that the target radar signal can be analyzed more clearly from both time and space aspects. In addition, the features related to decision-making are selectively highlighted through the mask network layer.

[0073] S240, determining a target interference scheme for dealing with the target radar signal based on the interference decision layer and signal characteristic information of the interference decision network, so as to transmit the target interference signal according to the target interference scheme.

[0074] In this embodiment, the signal characteristic information can be input into the interference decision layer to obtain the output information of the interference decision layer. Optionally, the output information may be the target scheme information of the target interference scheme; for example, the target scheme information includes the name and number of the target scheme. The preset interference scheme corresponding to the target scheme information is used as the target interference scheme to transmit the target interference signal according to the target interference scheme. Alternatively, the output information may also be the matching degree value between the target radar signal and each preset interference scheme. Based on the interference decision layer and signal characteristic information of the interference decision network, the specific implementation method of determining the target interference scheme for dealing with the target radar signal includes: inputting the signal characteristic information into the interference decision layer to determine the matching degree value between at least one preset interference scheme and the target radar signal through the interference decision layer, and determining the target interference scheme based on the matching degree value.

[0075] Specifically, after the signal characteristic information is input into the interference decision layer, the matching degree value between the target radar signal and each preset interference scheme is output, and the preset interference scheme with the highest matching degree value can be determined as the target interference scheme. Alternatively, any preset interference scheme with a matching degree value greater than a preset matching degree threshold can be determined as the target interference scheme.

[0076] This embodiment determines the target interference scheme by the matching degree value, so that the interference scheme that is more suitable for the target radar signal can be screened out as the target interference scheme, thereby improving the accuracy of the interference operation.

[0077] The embodiments corresponding to the method for determining the interference scheme are described in detail above. In order to make the technical scheme of the present method further clear to those skilled in the art, the method for determining the interference scheme is described below in combination with the scenario of performing a penetration mission.

[0078] In order to ensure that the interference decision network continues to maintain high efficiency in a complex and changing radar environment, the network parameters of the interference decision network can be continuously optimized through reinforcement learning. Optionally, the interference decision network is obtained through reinforcement learning. In the scenario of performing a penetration mission, the interference decision network is trained through reinforcement learning based on the interaction data between the radar system and the jammer in the penetration mission.

[0079] Optionally, the reinforcement learning process of the interference decision network includes: after transmitting the target interference signal according to the target interference scheme, receiving a radar feedback signal corresponding to the target interference signal; determining a target reward value of the interference decision network based on the signal change between the radar feedback signal and the target radar signal, and adjusting the network parameters of the interference decision network based on the target reward value, so as to determine the next interference scheme for the next radar signal based on the interference decision network after adjusting the network parameters.

[0080] In this embodiment, the signal change between the target radar signal and the radar feedback signal can be determined. Exemplarily, the signal change includes at least one of a pulse width change, an amplitude change, a repetition interval change, and a carrier frequency change. The target reward value of the interference decision network is determined based on the signal change. Specifically, the greater the change between the target radar signal and the radar feedback signal reflected by the signal change, the higher the target reward value; conversely, the smaller the change between the target radar signal and the radar feedback signal reflected by the signal change, the smaller the target reward value. Through the proximal strategy optimization algorithm and the target reward value, the network parameters of the interference network are adjusted to determine the next interference scheme for the next radar signal based on the interference network after adjusting the network parameters. Among them, the next radar signal is the radar signal received in the next penetration mission. The next interference scheme is an interference scheme for interfering with the next radar signal.

[0081] Furthermore, the target reward value can also be determined based on the working mode adopted by the radar feedback signal, and the network parameters in the interference decision network can be adjusted based on the target reward value. Exemplarily, if the target radar signal adopts the first working mode, the radar feedback signal adopts the second working mode. The target reward value can be determined based on the first signal-to-noise ratio corresponding to the first working mode and the second signal-to-noise ratio corresponding to the second working mode. For example, the larger the change value between the first signal-to-noise ratio and the second signal-to-noise ratio, the more effective the target interference scheme is, and the higher the target reward value is; conversely, if the change value is smaller, the target reward value is lower.

[0082] In addition, the target reward value can also be determined based on the interference information corresponding to the target interference scheme. Specifically, the interference information includes the interference duration and / or interference power of the target interference signal. The longer the interference duration, the lower the target reward value; conversely, the higher the target reward value. The higher the interference power, the lower the target reward value; conversely, the higher the target reward value.

[0083] In this embodiment, the interference decision network is trained by reinforcement learning, so as to more accurately identify and adapt to the complex and changing radar environment, thereby improving the interference effect. In addition, when adjusting the network parameters in the interference decision network, the interference duration and output power of the intelligent agent when performing the interference action are taken into account, and the factors considered are more comprehensive.

[0084] Figure 3 1 is a schematic diagram of the structure of an interference scheme determination device provided according to an embodiment of the present invention, and the device is used to execute the interference scheme determination method provided in any of the above embodiments. The device and the interference scheme determination method of the above embodiments belong to the same inventive concept, and the details not described in detail in the embodiments of the interference scheme determination device can refer to the embodiments of the above interference scheme determination method. Figure 3 As shown, the device comprises:

[0085] A descriptor information determination module 10 is used to determine the descriptor information of the radar pulse descriptor of the target radar signal when receiving the target radar signal sent by the radar system;

[0086] A signal feature information extraction module 11 is used to extract signal feature information corresponding to the target radar signal based on the descriptor information and the feature extraction layer of the pre-built interference decision network;

[0087] The target interference scheme determination module 12 is used to determine the target interference scheme for dealing with the target radar signal based on the interference decision layer and signal characteristic information of the interference decision network, so as to transmit the target interference signal according to the target interference scheme.

[0088] Based on any optional technical solution in the embodiment of the present invention, optionally, the description word information determination module 10 includes:

[0089] A Fourier transform unit, used for performing short-time Fourier transform processing on the target radar signal to obtain a frequency domain signal corresponding to the target radar signal;

[0090] A logarithmic transformation unit is used to perform logarithmic transformation processing on the frequency domain signal to obtain a logarithmic amplitude spectrum corresponding to the target radar signal;

[0091] The descriptor information determining unit is used to determine the descriptor information of the radar pulse descriptor of the target radar signal based on the logarithmic amplitude spectrum.

[0092] Based on any optional technical solution in the embodiments of the present invention, optionally, the description word information determining unit includes:

[0093] The information extraction subunit is used to input the logarithmic amplitude spectrum into the pre-built real part sub-classifier, imaginary part sub-classifier, modulus sub-classifier and phase sub-classifier respectively, and extract the real part feature information, imaginary part feature information, total energy feature information and phase frequency information of the logarithmic amplitude spectrum; wherein the real part sub-classifier, imaginary part sub-classifier, modulus sub-classifier and phase sub-classifier respectively include a convolution layer, a pooling layer and a fully connected layer;

[0094] The descriptor information determination subunit is used to perform a weighted sum operation on the real feature information, the imaginary feature information, the total energy feature information, and the phase frequency information based on a preset subclassifier weight, and determine the descriptor information of the radar pulse word of the target radar signal based on the sum value obtained by the weighted sum operation.

[0095] On the basis of any optional technical solution in the embodiment of the present invention, optionally, the feature extraction layer includes a spatial feature extraction network layer, a temporal feature extraction network layer and a mask network layer;

[0096] The signal feature information extraction module 11 includes:

[0097] A spatial feature information extraction unit, used to input the description word information into the spatial feature extraction network layer, and extract the spatial feature information of the description word information through the spatial feature extraction network layer;

[0098] A spatial feature information input unit, used to input the spatial feature information into the temporal feature extraction network layer to obtain the temporal and spatial feature information corresponding to the description word information;

[0099] The spatiotemporal feature information input unit is used to input the spatiotemporal feature information into the mask network layer to obtain the signal feature information corresponding to the target radar signal; wherein the mask network layer is used to perform element-by-element multiplication of the spatiotemporal feature information based on a pre-set mask matrix.

[0100] On the basis of any optional technical solution in the embodiment of the present invention, optionally, the target interference solution determination module 12 includes:

[0101] The signal characteristic information input unit is used to input the signal characteristic information into the interference decision layer, so as to determine the matching degree value between at least one preset interference scheme and the target radar signal through the interference decision layer, and determine the target interference scheme based on the matching degree value.

[0102] On the basis of any optional technical solution in the embodiments of the present invention, optionally, the interference decision network is obtained through reinforcement learning, and the device further includes:

[0103] The reinforcement learning module is used to receive a radar feedback signal corresponding to the target interference signal after transmitting the target interference signal according to the target interference scheme; determine the target reward value of the interference decision network based on the signal change between the radar feedback signal and the target radar signal, and adjust the network parameters of the interference decision network based on the target reward value to determine the next interference scheme for the next radar signal based on the interference decision network after adjusting the network parameters.

[0104] Based on any optional technical solution in the embodiment of the present invention, optionally, the description word information determination module 10 includes:

[0105] A signal preprocessing unit, used to perform a signal preprocessing operation on the target radar signal, and update the target radar signal based on the signal obtained after the preprocessing operation;

[0106] The signal preprocessing operation includes at least one of bandpass filtering, normalization and adaptive filtering.

[0107] The technical solution of the embodiment of the present invention determines the descriptor information of the radar pulse descriptor of the target radar signal when the target radar signal sent by the radar system is received; based on the descriptor information and the feature extraction layer of the pre-constructed interference decision network, the signal feature information corresponding to the target radar signal is extracted; through the interference decision layer of the interference decision network and the signal feature information, a target interference scheme for dealing with the target radar signal is determined, so as to transmit the target interference signal according to the target interference scheme, so as to flexibly determine the target interference scheme corresponding to the target radar information according to the signal feature information of the received target radar signal each time, so as to deal with the changeable radar signal; at the same time, the radar system is interfered with by the target interference scheme corresponding to the target radar signal, which helps to improve the accuracy of the interference operation.

[0108] It is worth noting that in the embodiment of the above-mentioned interference scheme determination device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0109] Figure 4 It is a structural diagram of an electronic device that implements the interference scheme determination method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0110] like Figure 4 As shown, the electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 21 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 23. In RAM23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, ROM22 and RAM23 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0111] A number of components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0112] The processor 21 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as the interference scheme determination method.

[0113] In some embodiments, the interference scheme determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps of the interference scheme determination method described above may be performed. Alternatively, in other embodiments, the processor 21 may be configured to perform the interference scheme determination method in any other appropriate manner (e.g., by means of firmware).

[0114] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0116] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by 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), a blockchain network, and the Internet.

[0119] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0120] This embodiment also provides a computer program product, including a computer program, which, when executed by a processor, implements the interference scheme determination method provided in any embodiment of the present application.

[0121] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can 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 the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0122] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0123] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining an interference scheme, characterized in that: include: In case of receiving a target radar signal sent by a radar system, determining descriptor information of a radar pulse descriptor of the target radar signal; Extracting signal feature information corresponding to the target radar signal based on the descriptor information and a feature extraction layer of a pre-constructed interference decision network; Based on the interference decision layer of the interference decision network and the signal characteristic information, a target interference scheme for dealing with the target radar signal is determined to transmit a target interference signal according to the target interference scheme.

2. The method according to claim 1, characterized in that The determining of the descriptor information of the radar pulse descriptor of the target radar signal includes: Performing short-time Fourier transform processing on the target radar signal to obtain a frequency domain signal corresponding to the target radar signal; Performing logarithmic transformation on the frequency domain signal to obtain a logarithmic amplitude spectrum corresponding to the target radar signal; Descriptor information of a radar pulse descriptor of the target radar signal is determined based on the logarithmic amplitude spectrum.

3. The method according to claim 2, characterized in that The step of determining the descriptor information of the radar pulse descriptor of the target radar signal based on the logarithmic amplitude spectrum includes: The logarithmic magnitude spectrum is input into a pre-constructed real part sub-classifier, an imaginary part sub-classifier, a modulus value sub-classifier and a phase sub-classifier respectively, and the real part feature information, imaginary part feature information, total energy feature information and phase frequency information of the logarithmic magnitude spectrum are extracted; wherein the real part sub-classifier, the imaginary part sub-classifier, the modulus value sub-classifier and the phase sub-classifier respectively include a convolutional layer, a pooling layer and a fully connected layer; Based on preset sub-classifier weights, a weighted summation operation is performed on the real part feature information, the imaginary part feature information, the total energy feature information, and the phase frequency information, and the descriptive word information of the radar pulse word of the target radar signal is determined based on the sum value obtained by the weighted summation operation.

4. The method according to claim 1, characterized in that: The feature extraction layer includes a spatial feature extraction network layer, a temporal feature extraction network layer and a mask network layer; The feature extraction layer based on the descriptor information and the pre-built interference decision network extracts the signal feature information corresponding to the target radar signal, including: Inputting the description word information into the spatial feature extraction network layer, and extracting the spatial feature information of the description word information through the spatial feature extraction network layer; Inputting the spatial feature information into the temporal feature extraction network layer to obtain the temporal and spatial feature information corresponding to the descriptive word information; The spatiotemporal feature information is input into the mask network layer to obtain signal feature information corresponding to the target radar signal; wherein the mask network layer is used to perform element-by-element multiplication of the spatiotemporal feature information based on a pre-set mask matrix.

5. The method according to claim 1, characterized in that: The determining, based on the interference decision layer of the interference decision network and the signal characteristic information, a target interference scheme for dealing with the target radar signal comprises: The signal characteristic information is input into the interference decision layer, so as to determine the matching degree value between at least one preset interference scheme and the target radar signal through the interference decision layer, and determine the target interference scheme based on the matching degree value.

6. The method according to claim 1, characterized in that The interference decision network is obtained through reinforcement learning, and the reinforcement learning process of the interference decision network includes: After transmitting the target jamming signal according to the target jamming scheme, receiving a radar feedback signal corresponding to the target jamming signal; Based on the signal change between the radar feedback signal and the target radar signal, a target reward value of the interference decision network is determined, and network parameters of the interference decision network are adjusted based on the target reward value to determine a next interference scheme for a next radar signal based on the interference decision network after adjusting the network parameters.

7. The method according to claim 1, characterized in that The determining of the descriptor information of the radar pulse descriptor of the target radar signal includes: Performing a signal preprocessing operation on the target radar signal, and updating the target radar signal based on a signal obtained after the preprocessing operation; The signal preprocessing operation includes at least one of bandpass filtering, normalization and adaptive filtering.

8. An interference scheme determination device, characterized in that: include: a descriptor information determination module, configured to determine the descriptor information of the radar pulse descriptor of the target radar signal when receiving the target radar signal sent by the radar system; A signal feature information extraction module, used to extract the signal feature information corresponding to the target radar signal based on the descriptor information and the feature extraction layer of the pre-constructed interference decision network; A target interference scheme determination module is used to determine a target interference scheme for dealing with the target radar signal based on the interference decision layer of the interference decision network and the signal characteristic information, so as to transmit a target interference signal according to the target interference scheme.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the interference scheme determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the interference scheme determination method according to any one of claims 1 to 7 when executed.

Images