A precise jamming method and system for pilot signals of remote controllers of unmanned aerial vehicles

Abstract

The present invention provides a precise interference method and system for a pilot signal of a remote controller of an unmanned aerial vehicle. The method receives and processes a picture transmission signal and a remote control signal of the unmanned aerial vehicle, parses the starting time and transmission period of the picture transmission signal and classification results of different types of picture transmission protocols; extracts the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal; uses a reinforcement learning algorithm to generate an optimized interference signal parameter configuration, uses a long short-term memory network to analyze historical data, obtains historical analysis results, and predicts the best interference time; uses real-time spectrum sensing technology to monitor the wireless communication environment around the unmanned aerial vehicle to identify potential conflicting frequency bands, and uses frequency agility technology to select a target interference frequency band; and determines a precise interference method based on the historical analysis results, the best interference time, and the target interference frequency band. The present invention improves the interference accuracy and effect of the pilot signal of the remote controller of the unmanned aerial vehicle.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of wireless communication technology, and in particular to a method and system for accurately jamming a pilot signal of a drone remote controller. Background Art

[0002] In recent years, the drone industry has developed rapidly, not only showing its prowess in industry applications, but also creating a craze among individual enthusiasts. Then, the problems that followed became increasingly prominent. UFOs broke into sensitive areas, interfered with the normal flight of civil aircraft, caused aircraft to be forced to land, and affected people's normal lives. In order to prevent such incidents of drones from happening again, it is necessary to restrict and control drones. In order to interfere with the remote control signals of drones, prevent illegal flights, and ensure people's normal lives, it is necessary to develop a technical solution that can accurately interfere with the pilot signals of drone remote controls.

[0003] At present, there are some technical solutions for drone signal interference on the market, such as frequency band blocking, which prevents drones from receiving or sending control commands by sending strong interference signals on a specific frequency band. This method lacks specificity and is likely to interfere with other legitimate communication equipment. Existing solutions usually use broad-spectrum interference or simple frequency agility, which cannot accurately identify and interfere with specific signals of drones, resulting in a greater impact on legitimate communication equipment. Summary of the invention

[0004] The embodiments of the present invention provide a method and system for accurately jamming the pilot signal of a drone remote controller, so as to solve the problem that the specific signal of the drone cannot be accurately identified and jammed in the prior art, which has a great impact on legitimate communication equipment.

[0005] In a first aspect, an embodiment of the present invention provides a precise jamming method for a pilot signal of a drone remote controller, comprising:

[0006] Receive the image transmission signal and remote control signal of the drone, detect and process the image transmission signal, and parse the start time, transmission period and classification results of different types of image transmission protocols of the image transmission signal;

[0007] Based on the image transmission protocol classification result and the remote control signal, the start time and the transmission period are compared with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal;

[0008] Based on the time period and the appearance time of the pilot symbol, the existing time feature recognition standard is adjusted by using a reinforcement learning algorithm to generate an optimized interference signal parameter configuration, based on the optimized interference signal parameter configuration, the historical data is analyzed by using a long short-term memory network to obtain a historical analysis result, and the optimal interference time is predicted in combination with the historical analysis result;

[0009] Real-time spectrum sensing technology is used to monitor the wireless communication environment around the drone to obtain wireless communication monitoring results, and a convolutional neural network is used to perform a first classification process on the real-time spectrum graph in the wireless communication monitoring results to distinguish between legitimate communication signals and potential conflict signals; an autoencoder is introduced to perform anomaly detection on the potential conflict signals, identify abnormal frequency band activities, and obtain potential conflict frequency bands; based on the potential conflict frequency bands, a dynamic spectrum map is generated in combination with the geographic positioning data of the drone to visualize the frequency band occupancy; according to predefined frequency band risk assessment indicators, the risk level of each frequency band is evaluated to generate risk warning information; based on the wireless communication monitoring results, the dynamic spectrum map and the risk warning information, a target candidate frequency band pool is constructed, and based on the target candidate frequency band pool, the identified conflicting frequency bands are removed to confirm the target interference frequency band;

[0010] Based on the historical analysis results, the optimal interference timing and the target interference frequency band, a precise interference method is determined.

[0011] Optionally, based on the wireless communication monitoring result, the dynamic spectrum map and the risk warning information, a target candidate frequency band pool is constructed, and based on the target candidate frequency band pool, an identified conflicting frequency band is removed to confirm a target interference frequency band, including:

[0012] Based on the wireless communication monitoring result, the dynamic spectrum map and the risk warning information, removing the identified conflicting frequency bands and generating a preliminary candidate frequency band pool;

[0013] Using multi-sensor data fusion technology, the image transmission signal, the remote control signal, the wireless communication monitoring result and the geographic positioning data are fused and processed to obtain a comprehensive frequency band evaluation result;

[0014] Based on the comprehensive frequency band evaluation result, a Bayesian classifier is used to perform a second classification process on the frequency bands in the preliminary candidate frequency band pool to obtain an optimized classification result;

[0015] Based on the optimized classification results and the frequency band availability evaluation index, the preliminary candidate frequency band pool is optimized using a genetic algorithm to obtain a target candidate frequency band pool, and a multi-objective optimization algorithm is introduced in the optimization process using the genetic algorithm to simultaneously optimize multiple objectives, wherein the multiple objectives include an interference effect objective, a legitimate communication protection objective, and a resource utilization efficiency objective;

[0016] The electromagnetic environment simulation model is used to simulate the actual electromagnetic environment to evaluate the performance of each frequency band in the target candidate frequency band pool under different conditions to obtain a performance evaluation result, generate a target frequency band combination based on the performance evaluation result, and confirm the target interference frequency band based on the target frequency band combination.

[0017] Optionally, using an electromagnetic environment simulation model to simulate an actual electromagnetic environment to evaluate the performance of each frequency band in the target candidate frequency band pool under different conditions to obtain a performance evaluation result, generating a target frequency band combination based on the performance evaluation result, and confirming a target interference frequency band based on the target frequency band combination, including:

[0018] Based on the image transmission signal, the remote control signal and the multi-dimensional parameters of the electromagnetic environment around the drone, simulation parameters are set, and an electromagnetic environment simulation model is constructed by combining random variables and probability distribution;

[0019] Using the electromagnetic environment simulation model, different scenarios are set to simulate the actual electromagnetic environment. In the process of simulating the actual electromagnetic environment, multi-physics field coupling simulation technology is introduced to combine multiple physical phenomena to generate simulation result data. Based on the simulation result data, performance evaluation indicators are defined. The different scenarios include cities, mountainous areas, and open areas.

[0020] Based on the performance evaluation index and the actual electromagnetic environment, the performance of each frequency band in the target candidate frequency band pool under different conditions is evaluated to obtain a performance evaluation result, wherein the performance evaluation index includes an interference effect index, a legal communication protection index, and a resource utilization efficiency index;

[0021] Based on the performance evaluation results, a multi-criteria decision analysis method is applied to determine the priority of each frequency band to generate a preliminary frequency band combination, and a Monte Carlo simulation is introduced to evaluate the performance of the preliminary frequency band combination under random disturbance to obtain a random disturbance performance result, and based on the random disturbance performance result, a target frequency band combination is generated, and based on the target frequency band combination, a target interference frequency band is confirmed.

[0022] Optionally, the risk level of each frequency band is evaluated according to a predefined frequency band risk assessment indicator to generate risk warning information, including:

[0023] Based on the wireless communication monitoring results and dynamic spectrum map, combined with geographic positioning data, and using geographic information system technology, multi-dimensional modeling of frequency band occupancy is performed to obtain a frequency band occupancy model;

[0024] Based on the frequency band occupancy model and predefined frequency band risk assessment indicators, a multi-criteria decision analysis method is applied, combined with a hierarchical analysis method and a fuzzy comprehensive evaluation method, to conduct a risk assessment on each frequency band, calculate a risk score corresponding to each frequency band, divide each frequency band into different risk levels based on the risk score, and generate a preliminary risk assessment result based on the risk level. The frequency band risk assessment indicators include interference intensity, frequency band utilization, geographic location sensitivity, and frequency band protection priority;

[0025] A Bayesian network is used to perform risk propagation analysis on the high-risk level frequency bands in the preliminary risk assessment results to refine the risk sources, potential impact scope and response measures to obtain refined risk information, and risk warning information is generated based on the preliminary risk assessment results and the refined risk information.

[0026] Optionally, based on the image transmission protocol classification result and the remote control signal, comparing the start time and the transmission period with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal, including:

[0027] Extracting target features of the remote control signal to obtain key feature parameters of the remote control signal, wherein the target features include frequency, modulation mode, and coding format;

[0028] Based on the image transmission protocol classification result and the key characteristic parameters of the remote control signal, a dynamic time warping algorithm is used to compare and analyze the timing relationship between the start time and the transmission period and the remote control signal, so as to identify the time synchronization point and periodic characteristics between the transmission period and the remote control signal;

[0029] Based on the time synchronization point and the periodicity characteristics, a hidden Markov model is applied to perform state sequence analysis on the remote control signal to extract the time period of the remote control signal and identify the appearance time of the pilot symbol in the remote control signal.

[0030] Optionally, based on the optimized interference signal parameter configuration, using a long short-term memory network, historical data is analyzed to obtain historical analysis results, and combined with the historical analysis results, the best interference timing is predicted, including:

[0031] Based on the optimized interference signal parameter configuration, the long-term dependencies and pattern changes in the historical data are deeply analyzed using the long-term short-term memory network to obtain historical analysis results;

[0032] Combined with the historical analysis results, the long short-term memory network is used to analyze the key elements in the historical data. Based on the key elements, the optimal interference time is predicted. The attention mechanism is introduced in the process of analysis using the long short-term memory network. By calculating the attention weight of each time step, the attention weight is used to identify the key elements of the historical data, which include periodic characteristics, abnormal events and environmental changes.

[0033] In a second aspect, an embodiment of the present invention provides a precise jamming system for a pilot signal of a drone remote controller, comprising:

[0034] A receiving module is used to receive the image transmission signal and remote control signal of the drone, detect and process the image transmission signal, and parse the start time, transmission period and classification results of different types of image transmission protocols of the image transmission signal;

[0035] An extraction module, configured to compare the start time and the transmission period with the remote control signal based on the image transmission protocol classification result and the remote control signal, so as to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal;

[0036] An adjustment module is used to adjust the existing time feature recognition standard based on the time period and the appearance time of the pilot symbol by using a reinforcement learning algorithm to generate an optimized interference signal parameter configuration, and based on the optimized interference signal parameter configuration, use a long short-term memory network to analyze historical data to obtain historical analysis results, and combine the historical analysis results to predict the best interference time;

[0037] An identification module is used to use real-time spectrum sensing technology to monitor the wireless communication environment around the drone, obtain wireless communication monitoring results, apply a convolutional neural network to perform a first classification process on the real-time spectrum graph in the wireless communication monitoring results to distinguish between legitimate communication signals and potential conflict signals; introduce an autoencoder to perform anomaly detection on the potential conflict signal, identify abnormal frequency band activities, and obtain potential conflict frequency bands; based on the potential conflict frequency bands, combined with the geographic positioning data of the drone, generate a dynamic spectrum map to visualize the frequency band occupancy; according to predefined frequency band risk assessment indicators, evaluate the risk level of each frequency band to generate risk warning information; based on the wireless communication monitoring results, the dynamic spectrum map and the risk warning information, construct a target candidate frequency band pool, and based on the target candidate frequency band pool, remove the identified conflicting frequency bands to confirm the target interference frequency band;

[0038] A determination module is used to determine a precise interference method based on the historical analysis results, the optimal interference timing and the target interference frequency band.

[0039] In a third aspect, an embodiment of the present invention provides a computing device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a precise interference method for a pilot signal of a drone remote control as described in any one of the first aspects.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement a precise interference method for a pilot signal of a drone remote controller as described in any one of the first aspects.

[0041] In an embodiment of the present invention, an image transmission signal and a remote control signal of a drone are received, the image transmission signal is detected and processed, and the starting time, the transmission period, and classification results of different types of image transmission protocols of the image transmission signal are parsed; based on the image transmission protocol classification results and the remote control signal, the starting time and the transmission period are compared with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal; based on the time period and the appearance time of the pilot symbol, the existing time feature recognition standard is adjusted using a reinforcement learning algorithm to generate an optimized interference signal parameter configuration; based on the optimized interference signal parameter configuration, historical data is analyzed using a long short-term memory network to obtain historical analysis results, and the optimal interference time is predicted in combination with the historical analysis results; real-time spectrum sensing technology is used to monitor the wireless communication environment around the drone , obtain wireless communication monitoring results, apply convolutional neural networks to perform first classification processing on the real-time spectrum graph in the wireless communication monitoring results to distinguish legitimate communication signals from potential conflict signals; introduce an autoencoder to perform anomaly detection on the potential conflict signals, identify abnormal frequency band activities, and obtain potential conflict frequency bands; based on the potential conflict frequency bands, combined with the geographic positioning data of the drone, generate a dynamic spectrum map to visualize the frequency band occupancy; according to predefined frequency band risk assessment indicators, evaluate the risk level of each frequency band to generate risk warning information; based on the wireless communication monitoring results, the dynamic spectrum map and the risk warning information, construct a target candidate frequency band pool, and based on the target candidate frequency band pool, remove the identified conflicting frequency bands to confirm the target interference frequency band; based on the historical analysis results, the optimal interference time and the target interference frequency band, determine the precise interference method. The technical solution provided by the present invention can accurately identify the time period of the remote control signal and the appearance time of the pilot symbol, so that the interference operation can be targeted at a specific time point and frequency, thereby improving the accuracy of the interference and reducing the impact on legal communications; the reinforcement learning algorithm and attention mechanism not only ensure that the interference operation can be carried out at the most appropriate time point, but also improve the robustness and adaptability of the overall system; the processing of real-time spectrum sensing technology and frequency agility technology enables the system to adaptively select the optimal interference frequency band in a complex and changeable electromagnetic environment, avoiding conflicts with other legal communications, and enhancing the system's dynamic environment adaptability; the precise interference method takes into account multiple key factors to ensure that the interference operation can be carried out at the most appropriate time and frequency, maximizing the interference effect while reducing the risk of misoperation. In addition, by continuously updating and optimizing model parameters, the system can continuously improve performance and adapt to new interference scenarios and environmental changes.Among them, by comprehensively considering multiple factors, the target candidate frequency band pool is constructed and optimized to ensure that the target interference frequency band finally confirmed is both effective and safe; through detailed simulation parameter settings and the introduction of random variables and probability distribution, a simulation model that accurately reflects the actual electromagnetic environment is constructed; using multi-physics field coupling simulation technology, different scenarios are set and reliable simulation result data is generated, and comprehensive performance evaluation indicators are defined; furthermore, based on performance evaluation indicators and actual electromagnetic environment, the performance of each frequency band is evaluated to ensure a comprehensive understanding of the performance of each frequency band; through multi-criteria decision analysis methods and Monte Carlo simulation, target frequency band combinations are generated and the final target interference frequency band is confirmed. The entire solution not only improves the overall performance and reliability of the system, but also ensures the safety and effectiveness of interference operations, maximizing the interference effect while reducing the impact on legitimate communications.

[0042] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A flowchart of a method for accurately jamming a pilot signal of a drone remote controller provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of the structure of a precise jamming system for a pilot signal of a drone remote controller provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0048] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0050] Figure 1 A flowchart of a method for accurately jamming a pilot signal of a drone remote controller is provided in an embodiment of the present invention. Figure 1 As shown, the method includes:

[0051] With the rapid development of drone technology, its application in military, civil and commercial fields is becoming more and more extensive, but it also brings security risks caused by unauthorized use, such as illegal surveillance, privacy infringement and potential security threats. In order to meet these challenges, a technical solution that can accurately interfere with the pilot signal of the drone remote control is urgently needed to ensure the safety and order of the legal airspace. Based on this, the present invention provides a precise interference method for the pilot signal of the drone remote control, such as Figure 1 ,include:

[0052] Step 101: receiving an image transmission signal and a remote control signal of a drone, detecting and processing the image transmission signal, parsing the start time and transmission period of the image transmission signal, and classification results of different types of image transmission protocols;

[0053] In this step, the image transmission signal refers to the image data stream transmitted by the drone, which is usually used for real-time monitoring. The remote control signal refers to the control command sent by the ground control station to the drone, such as flight direction, speed, etc. Start time: the time point when the image transmission signal starts to be transmitted. The transmission cycle refers to the period of repeated transmission of the image transmission signal at a certain time interval. The image transmission protocol classification result refers to the classification of the image transmission signal according to different communication protocols (such as Wi-Fi, LoRa, etc.).

[0054] For example, a high-performance RF receiver is used to receive the image transmission signal and remote control signal transmitted by the drone in real time. To ensure signal quality, a high-sensitivity antenna array and a low-noise amplifier are used to minimize signal attenuation and interference. The received signal undergoes preliminary preprocessing, including denoising and filtering, and an adaptive filter is applied to remove background noise and other non-related signal components, retaining the effective image transmission and remote control signal parts. Subsequently, frequency domain analysis methods such as fast Fourier transform and short-time Fourier transform are used to identify the key elements of the image transmission signal, such as the starting time and the transmission period. At the same time, a machine learning model is introduced to automatically classify the image transmission signal, identify different types of image transmission protocols, and parse the specific parameters of each protocol. For example, for a drone using the Wi-Fi protocol, the system can accurately parse out that the starting time of its image transmission signal is 0 seconds and the transmission period is 50 milliseconds.

[0055] Step 102: Based on the image transmission protocol classification result and the remote control signal, the start time and the transmission period are compared with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal;

[0056] In this step, the time period refers to the repetition period of a specific event (such as pilot symbol transmission) in the remote control signal. Pilot symbols are special signals used for synchronization and calibration, usually appearing at a fixed position in each communication cycle.

[0057] This step combines the image transmission protocol classification results and the received remote control signal, and uses the dynamic time warping algorithm to compare and analyze the timing relationship between the image transmission signal and the remote control signal to identify the synchronization points and periodic characteristics of the two. This helps to more accurately locate key events in the remote control signal, such as the appearance time of the pilot symbol. In addition, cross-correlation analysis is applied to further verify the time synchronization relationship between the image transmission signal and the remote control signal to ensure the accuracy of the analysis results. For example, if the transmission period of the image transmission signal is 50 milliseconds, the system finds through comparison that the period of the remote control signal is also 50 milliseconds, and the pilot symbol appears every 10th millisecond.

[0058] Step 103: Based on the time period and the appearance time of the pilot symbol, the existing time feature recognition standard is adjusted by using a reinforcement learning algorithm to generate an optimized interference signal parameter configuration; based on the optimized interference signal parameter configuration, the historical data is analyzed by using a long short-term memory network to obtain a historical analysis result; and the optimal interference time is predicted in combination with the historical analysis result;

[0059] In this step, the temporal feature recognition criteria refer to the rules and parameters used to recognize the temporal characteristics of the signal.

[0060] This step uses the reinforcement learning algorithm to adjust the existing time feature recognition standard based on the extracted time period and the appearance time of the pilot symbol to generate the optimized interference signal parameter configuration. The reinforcement learning algorithm learns the optimal time feature recognition standard through continuous trial and error and feedback to ensure that the key features of the remote control signal can be accurately captured under different environmental conditions. Subsequently, the long short-term memory network is applied to conduct in-depth analysis of historical data to obtain historical analysis results. For example, by analyzing the communication records of the same drone in the past month, the long short-term memory network can identify abnormal activities and environmental changes in certain time periods, and then predict the most likely time for effective interference in the future.

[0061] Step 104: using real-time spectrum sensing technology to monitor the wireless communication environment around the UAV, obtain wireless communication monitoring results, apply convolutional neural network to perform first classification processing on the real-time spectrum map in the wireless communication monitoring results to distinguish between legitimate communication signals and potential conflict signals; introduce autoencoder to perform abnormality detection on the potential conflict signal, identify abnormal frequency band activities, and obtain potential conflict frequency bands; based on the potential conflict frequency bands, combined with the geographic positioning data of the UAV, generate a dynamic spectrum map to visualize the frequency band occupancy; according to predefined frequency band risk assessment indicators, evaluate the risk level of each frequency band to generate risk warning information; based on the wireless communication monitoring results, the dynamic spectrum map and the risk warning information, construct a target candidate frequency band pool, and based on the target candidate frequency band pool, remove the identified conflicting frequency bands to confirm the target interference frequency band;

[0062] In this step, potential conflicting frequency bands refer to frequency bands that may conflict with other legitimate communication devices. Wireless communication monitoring results refer to data about wireless communication activities around the drone obtained through spectrum sensing technology. Legitimate communication signals refer to signals transmitted by legitimate devices in authorized frequency bands. Potential conflicting signals refer to signals that may conflict with other legitimate communication devices. Abnormal frequency band activity refers to frequency band activity that is significantly different from normal communication patterns and may indicate illegal or interfering signals. Dynamic spectrum map refers to a map that shows frequency band occupancy at different geographic locations and time points. Geolocation data refers to information describing the location of the drone, usually obtained through GPS. Frequency band risk assessment indicators refer to a series of criteria used to assess frequency band risks, such as interference intensity, frequency band utilization, geographic location sensitivity, etc. Risk warning information refers to warning information generated based on risk assessment results, which prompts users of potential high-risk frequency bands. Target candidate frequency band pool refers to a set of frequency bands that contain all possible interference targets.

[0063] This step uses real-time spectrum sensing technology (such as software-defined radio SDR) to continuously monitor the wireless communication environment around the drone and obtain wireless communication monitoring results. These results include real-time spectrum diagrams that show the occupancy of different frequency bands. Subsequently, a convolutional neural network is applied to perform the first classification processing on the real-time spectrum diagram. For example, in a certain monitoring, the system detected multiple signal sources in the 2.4GHz frequency band. Through convolutional neural network analysis, the system can distinguish which signals belong to legitimate Wi-Fi communications and which may be potential conflict signals. This step ensures the effectiveness and accuracy of the initial screening. The autoencoder is introduced to further detect anomalies of the identified potential conflict signals. By learning the characteristics of normal communication signals, the autoencoder can identify abnormal frequency band activities that are significantly different from the normal mode. For example, the system detects that the signal strength in a certain frequency band suddenly increases significantly and lasts for a short time. This abnormal activity is marked as a potential conflict frequency band. In this way, the system can more accurately identify the frequency bands that may cause conflicts. Based on the identified potential conflict frequency bands, combined with the drone's geolocation data, a dynamic spectrum map is generated. This map not only shows the occupancy of each frequency band in different geographical locations, but also can be updated in real time over time. For example, the system can show which frequency bands are frequently used and which frequency bands may conflict in a specific area during a certain period of time. By visualizing the frequency band occupancy, users can intuitively understand the current state of the electromagnetic environment and assist in decision-making. According to the predefined frequency band risk assessment indicators (such as interference intensity, frequency band utilization, geographic location sensitivity, etc.), detailed risk assessment is performed on each frequency band and its risk score is calculated. Based on these scores, each frequency band is divided into different risk levels (such as low, medium, and high). For example, if a frequency band frequently has abnormal activities in a densely populated area and the interference intensity is large, the frequency band will be rated as a high risk level and corresponding risk warning information will be generated. This information helps users take measures in advance to avoid potential communication conflicts. Combining wireless communication monitoring results, dynamic spectrum maps, and risk warning information, a target candidate frequency band pool is constructed. This pool contains all frequency bands that may be interference targets. Subsequently, the system removes the identified conflicting frequency bands, that is, those that have been confirmed as high-risk or abnormal, from the target candidate frequency band pool. For example, if the 2.4GHz band is widely used and presents a high risk, the system will remove it from the candidate pool and select a less used suboptimal band (such as 5.8GHz) as the final target interference band. In this way, the system ensures that the interference operation can be carried out at the most appropriate time and frequency, maximizing the interference effect while reducing the impact on legitimate communications.

[0064] Step 105: Determine a precise interference method based on the historical analysis results, the optimal interference timing and the target interference frequency band;

[0065] This step takes all factors into consideration based on historical analysis results, the best jamming time, and the target jamming frequency band to determine the precise jamming method. For example, assuming that historical data analysis shows that a drone communicates most frequently between 2pm and 4pm every day, and the surrounding electromagnetic environment is relatively stable at this time, the system will choose to jam the 5.8GHz frequency band during this time period. In this way, the system ensures that the jamming operation can be carried out at the most appropriate time and frequency, maximizing the jamming effect while reducing the impact on legitimate communications.

[0066] The embodiment of the present invention ensures high-quality original signal reception and key information extraction through high-precision analysis of image transmission signals and remote control signals, laying a solid foundation for subsequent operations; by accurately synchronizing image transmission signals and remote control signals, the system can accurately extract the time period of the remote control signal and the appearance time of the pilot symbol, providing a key time reference; the reinforcement learning algorithm is used to optimize the time feature recognition standard, and the long short-term memory network is combined to perform historical data analysis, and the best interference time is intelligently predicted to ensure that the interference operation is performed at the most appropriate time point, maximizing the interference effect while reducing the risk of misoperation; through real-time spectrum sensing technology and convolutional neural networks, efficient monitoring and preliminary classification of the wireless communication environment are achieved; anomaly detection is performed using autoencoders to enhance the sensitivity and accuracy of the system; a dynamic spectrum map is generated to visualize the frequency band occupancy and improve the transparency of the system; through scientific risk assessment and early warning mechanisms, it is ensured that users can understand and respond to high-risk frequency bands in a timely manner; by comprehensively considering multiple factors, a target candidate frequency band pool is constructed and optimized to ensure that the target interference frequency band finally confirmed is both effective and safe. The entire solution not only improves the accuracy and speed of data integration, but also enhances the system's adaptability, ensuring that the best data support can be provided in complex and ever-changing application scenarios, maximizing the interference effect while reducing the impact on legitimate communications; comprehensively considering historical analysis results, the best interference time and target interference frequency bands, determining precise interference methods, ensuring the safety and reliability of interference operations, and improving the performance and adaptability of the overall system.

[0067] In order to ensure that interference is performed at the most appropriate time and frequency, and to maximize the interference effect while reducing the impact on legitimate communications, based on this, the present invention provides a specific embodiment, step 104, based on the wireless communication monitoring results, the dynamic spectrum map and the risk warning information, constructing a target candidate frequency band pool, based on the target candidate frequency band pool, removing the identified conflicting frequency bands to confirm the target interference frequency band, specifically comprising the following steps:

[0068] Step 401: Based on the wireless communication monitoring result, the dynamic spectrum map and the risk warning information, the identified conflicting frequency bands are removed to generate a preliminary candidate frequency band pool;

[0069] In this step, the conflicting frequency band refers to a frequency band that has been confirmed to have conflict or interference.

[0070] In this step, the system removes the identified conflicting frequency bands based on the wireless communication monitoring results, dynamic spectrum maps, and risk warning information. For example, in one monitoring, the 2.4GHz band was marked as a high-risk band because it frequently had abnormal activities in densely populated areas and had high interference intensity. Therefore, this band will be removed from the candidate pool. The remaining bands constitute the preliminary candidate band pool, which are considered to be relatively safe and potentially suitable candidates for interference operations.

[0071] Step 402: using multi-sensor data fusion technology to fuse the image transmission signal, the remote control signal, the wireless communication monitoring result, and the geographic positioning data to obtain a comprehensive frequency band evaluation result;

[0072] This step uses multi-sensor data fusion technology to fuse the image transmission signal, remote control signal, wireless communication monitoring results, and geolocation data. For example, the system can combine the transmission period of the image transmission signal, the time characteristics of the remote control signal, the spectrum occupancy in the wireless communication monitoring results, and the current location of the drone to generate a comprehensive frequency band assessment result. This process not only improves the accuracy of the data, but also enables a more comprehensive understanding of the actual use of each frequency band and its potential impact.

[0073] Step 403: Based on the comprehensive frequency band evaluation result, a Bayesian classifier is applied to perform a second classification process on the frequency bands in the preliminary candidate frequency band pool to obtain an optimized classification result;

[0074] This step is based on the comprehensive frequency band evaluation results, and the Bayesian classifier is used to perform a second classification process on the frequency bands in the preliminary candidate frequency band pool. For example, the system can calculate the probability of each frequency band being effective interference or legal communication protection based on historical data and current environmental conditions, and classify it accordingly. Assuming that a certain frequency band has shown good interference effects in multiple past monitorings and has not significantly affected legal communications, it will be classified as an effective interference band. In this way, the system can more accurately screen out the most suitable frequency bands.

[0075] Step 404: Based on the optimized classification result and the frequency band availability evaluation index, the preliminary candidate frequency band pool is optimized using a genetic algorithm to obtain a target candidate frequency band pool, and a multi-objective optimization algorithm is introduced in the optimization process using the genetic algorithm to simultaneously optimize multiple objectives, wherein the multiple objectives include an interference effect objective, a legitimate communication protection objective, and a resource utilization efficiency objective;

[0076] In this step, the frequency band availability assessment index refers to the criteria used to assess whether the frequency band is suitable for use, such as interference effect, legal communication protection, etc.

[0077] This step uses a genetic algorithm to optimize the preliminary candidate frequency band pool based on the optimized classification results and frequency band availability evaluation indicators. In this process, a multi-objective optimization algorithm is introduced to simultaneously optimize the three goals of interference effect, legal communication protection, and resource utilization efficiency. For example, the system can iteratively select the optimal frequency band combination through a genetic algorithm to ensure that each frequency band can maximize the interference effect while minimizing the impact on legal communications and making efficient use of existing resources. In the end, the generated target candidate frequency band pool contains multiple optimized frequency bands, ensuring the best interference method.

[0078] Step 405: Simulate the actual electromagnetic environment using the electromagnetic environment simulation model to evaluate the performance of each frequency band in the target candidate frequency band pool under different conditions, obtain a performance evaluation result, generate a target frequency band combination based on the performance evaluation result, and confirm the target interference frequency band based on the target frequency band combination;

[0079] This step uses the electromagnetic environment simulation model to simulate the actual electromagnetic environment and evaluate the performance of each frequency band in the target candidate frequency band pool under different conditions. For example, the system can test the interference effect of a certain frequency band in a simulated urban environment, taking into account factors such as building reflections and multipath effects. Through simulation testing, the system obtains detailed performance evaluation results and selects the best frequency band combination. Finally, based on these performance evaluation results, the target frequency band combination is generated and the final target interference frequency band is confirmed. For example, the system may select the 5.8GHz frequency band as the target interference frequency band because it performs well in simulation tests and can effectively interfere with drone communications without significantly affecting legitimate communications.

[0080] The embodiment of the present invention ensures that the frequency bands in the preliminary candidate frequency band pool are both effective and safe by removing the identified conflicting frequency bands; uses multi-sensor data fusion technology to enhance the system's perception ability and decision-making basis; applies the Bayesian classifier to further improve the accuracy of frequency band classification; realizes multiple optimizations of frequency bands through genetic algorithms and multi-objective optimization algorithms to ensure the best interference method; uses the electromagnetic environment simulation model to ensure that the selection of the target interference frequency band is based on the real electromagnetic environment conditions. The entire solution not only improves the overall performance and reliability of the system, but also ensures the safety and effectiveness of the interference operation, maximizing the interference effect while reducing the impact on legal communications.

[0081] In order to ensure that the interference frequency band finally selected can effectively interfere with the communication of the UAV in a complex environment without causing negative impact on the legitimate communication, based on this, the present invention provides a specific embodiment, in which step 405 uses an electromagnetic environment simulation model to simulate the actual electromagnetic environment to evaluate the performance of each frequency band in the target candidate frequency band pool under different conditions, obtain a performance evaluation result, generate a target frequency band combination based on the performance evaluation result, and confirm the target interference frequency band based on the target frequency band combination, which specifically includes the following steps:

[0082] Step 411: Based on the image transmission signal, the remote control signal and the multi-dimensional parameters of the electromagnetic environment around the UAV, simulation parameters are set, and an electromagnetic environment simulation model is constructed by combining random variables and probability distribution;

[0083] In this step, simulation parameters refer to various input parameters used to simulate the actual environment. Random variables and probability distributions are used to introduce uncertainty factors to make the simulation closer to the actual situation.

[0084] This step sets the simulation parameters based on the multi-dimensional parameters of the image transmission signal, remote control signal, and the electromagnetic environment around the drone (such as spectrum occupancy, signal strength, noise level, etc.). For example, in an urban environment, the system will consider factors such as building reflection and multipath effects; in a mountainous environment, it will consider the effects of terrain shielding and propagation attenuation. Then, combining random variables and probability distribution, an electromagnetic environment simulation model is constructed. For example, the system can introduce random variables to simulate the uncertainty of signal interference and probability distribution to describe the changes in signal strength under different conditions, ensuring that the simulation results are closer to the actual situation.

[0085] Step 412: using the electromagnetic environment simulation model, setting different scenarios to simulate the actual electromagnetic environment, introducing multi-physics field coupling simulation technology in the process of simulating the actual electromagnetic environment, combining multiple physical phenomena, generating simulation result data, and defining performance evaluation indicators based on the simulation result data, wherein the different scenarios include urban, mountainous, and open areas;

[0086] In this step, different scenes refer to different geographical environments including cities, mountainous areas, and open areas.

[0087] This step uses the constructed electromagnetic environment simulation model to set different scenarios (such as cities, mountainous areas, and open areas) to simulate the actual electromagnetic environment. During the simulation process, multi-physics field coupling simulation technology is introduced to combine various physical phenomena such as electromagnetic wave propagation, thermal effects, and mechanical vibrations to generate simulation result data. For example, in an urban environment, the system simulates the reflection and multipath effects of signals from high-rise buildings; in a mountainous environment, the effects of terrain shielding and signal attenuation are simulated; in an open area, the signal propagation characteristics in open space are simulated. Based on these simulation result data, performance evaluation indicators are defined, such as interference effect indicators, legal communication protection indicators, and resource utilization efficiency indicators. This step ensures the comprehensiveness and accuracy of the simulation results.

[0088] Step 413: Based on the performance evaluation index and the actual electromagnetic environment, the performance of each frequency band in the target candidate frequency band pool under different conditions is evaluated to obtain a performance evaluation result, wherein the performance evaluation index includes an interference effect index, a legal communication protection index, and a resource utilization efficiency index;

[0089] In this step, the actual electromagnetic environment refers to the actual electromagnetic environment conditions, such as spectrum occupancy, signal strength, etc.

[0090] This step evaluates the performance of each frequency band in the target candidate frequency band pool under different conditions based on defined performance evaluation indicators (such as interference effect indicators, legal communication protection indicators, and resource utilization efficiency indicators) and actual electromagnetic environment conditions. For example, in an urban environment, the system evaluates whether a certain frequency band can effectively interfere with drone communications between high-rise buildings without significantly affecting legal Wi-Fi networks. In this way, the system obtains detailed performance evaluation results to ensure that the advantages and disadvantages of each frequency band can be accurately identified.

[0091] Step 414: Based on the performance evaluation result, a multi-criteria decision analysis method is applied to determine the priority of each frequency band to generate a preliminary frequency band combination, a Monte Carlo simulation is introduced to evaluate the performance of the preliminary frequency band combination under random disturbance, and a random disturbance performance result is obtained, a target frequency band combination is generated based on the random disturbance performance result, and a target interference frequency band is confirmed based on the target frequency band combination;

[0092] In this step, the priority refers to the importance ranking of the frequency bands determined according to the performance evaluation results. The preliminary frequency band combination refers to a preliminary combination consisting of frequency bands with higher priorities.

[0093] This step is based on the performance evaluation results, and the multi-criteria decision analysis method is applied to determine the priority of each frequency band and generate a preliminary frequency band combination. For example, the system may rank the 5.8GHz band first based on the three indicators of interference effect, legal communication protection, and resource utilization efficiency. Subsequently, Monte Carlo simulation is introduced to evaluate the performance of the preliminary frequency band combination under random disturbances. For example, the system simulates different electromagnetic environment changes through a large number of random samplings and evaluates the stability of the frequency band combination under these changes. Based on these random disturbance performance results, the target frequency band combination is generated, and the target interference frequency band is finally confirmed. For example, if a frequency band combination performs well and stably in all simulated scenarios, it will be selected as the target interference frequency band.

[0094] In the process of selecting UAV jammer frequency bands, it is crucial to ensure that the selected frequency bands can work effectively in complex electromagnetic environments and will not cause unnecessary impact on legitimate communications. In order to achieve this goal, the present invention provides a method based on multi-objective optimization and random perturbation simulation to determine the optimal target frequency band combination. The specific calculation formula is as follows:

[0095] ;

[0096] ;

[0097] ;

[0098] in, Indicates the target frequency band combination; Indicates finding the objective function among all candidate frequency band combinations The smallest candidate frequency band combination ,in Belongs to the target candidate band pool ; represents a candidate frequency band combination; Indicates the random perturbation performance results; Represents the Pareto frontier function, which is used to screen out the candidate frequency band combinations that are not inferior to other candidate frequency band combinations in multiple objectives. The target candidate frequency band pool; represents a preliminary candidate frequency band pool; Represents a multi-objective optimization function used to measure candidate frequency band combinations Comprehensive performance; Indicates that there is no symbol, indicating that there are no other candidate frequency band combinations Not inferior to candidate band combinations on multiple targets ; Represents a multi-objective optimization function, which is used to measure other candidate frequency band combinations Comprehensive performance; Indicates that there are no other candidate frequency band combinations Non-inferior to candidate band combinations on all objectives , and performed better on at least one objective; represents the number of Monte Carlo simulations; Indicates Random perturbations in sub-simulations; Represents random disturbance The probability density function of , used for importance sampling; Represents the loss function used to evaluate the target candidate band pool In random perturbations The performance below; Express The results of the simulations are accumulated.

[0099] The calculation formula of the above target frequency band combination improves the accuracy and robustness of the target frequency band combination selection. Through the multi-objective optimization function, key factors such as interference effect, protection of legal communications and resource utilization efficiency are comprehensively considered to ensure that the selected frequency band can maximize the interference effect while minimizing the impact on legal communications in practical applications. In addition, the Pareto frontier selection method effectively screens out a pool of target frequency bands that are not inferior to other candidate frequency bands in multiple objectives, avoiding the suboptimal solution problem that may be caused by single-objective optimization. The calculation of random perturbation performance results not only improves the efficiency and accuracy of the simulation, but also enhances the solution's ability to cope with complex electromagnetic environments. Finally, by minimizing the loss function, the target frequency band combination with the best comprehensive performance is found, providing a reliable basis for frequency band selection for drone jamming missions.

[0100] The embodiment of the present invention constructs a simulation model that accurately reflects the actual electromagnetic environment through detailed simulation parameter settings and the introduction of random variables and probability distributions; uses multi-physics field coupling simulation technology to set different scenarios and generate reliable simulation result data, and defines comprehensive performance evaluation indicators; furthermore, based on performance evaluation indicators and the actual electromagnetic environment, the performance of each frequency band is evaluated to ensure a comprehensive understanding of the performance of each frequency band; through multi-criteria decision analysis methods and Monte Carlo simulation, a target frequency band combination is generated, and the final target interference frequency band is confirmed. The entire solution not only improves the overall performance and reliability of the system, but also ensures the safety and effectiveness of the interference operation, maximizing the interference effect while reducing the impact on legitimate communications.

[0101] In order to timely discover high-risk frequency bands and provide a scientific basis for precise interference operations, the present invention provides a specific embodiment, based on which, step 104, according to predefined frequency band risk assessment indicators, assesses the risk level of each frequency band to generate risk warning information, specifically comprising the following steps:

[0102] Step 421: Based on the wireless communication monitoring results and the dynamic spectrum map, combined with the geographic positioning data, and using geographic information system technology, multi-dimensional modeling of the frequency band occupancy is performed to obtain a frequency band occupancy model;

[0103] This step uses the GIS technology to model the frequency band occupancy in multiple dimensions based on the wireless communication monitoring results and dynamic spectrum maps, combined with the drone's geolocation data. For example, in a certain monitoring, the system recorded the use of the 2.4GHz frequency band in a certain urban area, and combined with the geographical characteristics of the area (such as building density, population distribution, etc.) to generate a frequency band occupancy model. This model not only shows the occupancy of each frequency band in different geographical locations, but also updates in real time over time, providing a comprehensive view of frequency band occupancy.

[0104] Step 422: Based on the frequency band occupancy model and the predefined frequency band risk assessment indicators, a multi-criteria decision analysis method is applied, combined with a hierarchical analysis method and a fuzzy comprehensive evaluation method, to perform risk assessment on each frequency band, calculate a risk score corresponding to each frequency band, divide each frequency band into different risk levels based on the risk score, and generate a preliminary risk assessment result based on the risk level. The frequency band risk assessment indicators include interference intensity, frequency band utilization, geographic location sensitivity, and frequency band protection priority.

[0105] In this step, the frequency band risk assessment index refers to the criteria used to assess the frequency band risk, including interference intensity, frequency band utilization, geographical location sensitivity, and frequency band protection priority. The risk score refers to the score calculated based on the frequency band risk assessment index, which is used to quantify the risk level of the frequency band.

[0106] This step is based on the frequency band occupancy model and predefined frequency band risk assessment indicators (such as interference intensity, frequency band utilization, geographic location sensitivity, and frequency band protection priority). The multi-criteria decision analysis method is combined with the hierarchical analysis method and the fuzzy comprehensive evaluation method to conduct risk assessment on each frequency band. For example, for a certain frequency band, the system determines the weight of each indicator through the hierarchical analysis method, and uses the fuzzy comprehensive evaluation method to deal with uncertainty and ambiguity, and finally calculates the risk score of the frequency band. According to the risk score, each frequency band is divided into different risk levels (such as low, medium, and high). For example, if a frequency band frequently experiences abnormal activities in a densely populated area and the interference intensity is high, the frequency band will be rated as a high risk level. Based on these risk levels, a preliminary risk assessment result is generated to ensure that the risk status of each frequency band can be accurately identified.

[0107] Step 423: applying a Bayesian network to perform risk propagation analysis on the high-risk frequency bands in the preliminary risk assessment results to refine the risk sources, potential impact scope, and response measures to obtain refined risk information, and generating risk warning information based on the preliminary risk assessment results and the refined risk information;

[0108] In this step, the Bayesian network is used to perform risk propagation analysis on the high-risk frequency bands in the preliminary risk assessment results, and to refine the risk sources, potential impact scope, and response measures. For example, for a frequency band rated as high risk, the system uses the Bayesian network to analyze its risk sources (such as abnormal activities in a specific area), predict its potential impact scope (such as legal communication equipment that may be affected), and propose specific response measures (such as selecting alternative frequency bands or adjusting interference strategies). Based on this refined risk information, combined with the preliminary risk assessment results, risk warning information is generated. For example, the system may issue a warning that a certain frequency band is at high risk and recommends taking emergency measures to avoid potential communication conflicts.

[0109] The embodiment of the present invention integrates the frequency band occupancy and geographic information through multi-dimensional modeling and geographic information system technology, ensuring the accuracy and comprehensiveness of the frequency band occupancy model; applies multi-criteria decision analysis method, hierarchical analysis method and fuzzy comprehensive evaluation method to ensure a comprehensive assessment of the risks of each frequency band, improving the scientificity and accuracy of risk assessment; conducts risk propagation analysis through Bayesian network, refines the risk information of high-risk frequency bands, and ensures the detail and pertinence of risk warning information. The entire solution not only improves the overall performance and reliability of the system, but also ensures the timeliness and effectiveness of risk warnings, maximizing the ability to prevent potential threats.

[0110] In order to accurately capture the key time features of the remote control signal and provide a reliable basis for subsequent interference decisions, the present invention provides a specific embodiment, based on which, step 102, based on the image transmission protocol classification result and the remote control signal, compares the start time and the transmission period with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal, specifically comprising the following steps:

[0111] Step 201: extracting target features of the remote control signal to obtain key feature parameters of the remote control signal, wherein the target features include frequency, modulation mode, and coding format;

[0112] In this step, the target features refer to the key attributes used to describe the characteristics of the remote control signal, such as frequency, modulation mode and coding format. Frequency refers to the carrier frequency of the remote control signal, which determines the frequency band of signal transmission. Modulation mode refers to the method of signal modulation, such as ASK (amplitude shift keying), FSK (frequency shift keying) or PSK (phase shift keying). Coding format refers to the method of signal encoding, such as Manchester coding, NRZ (non-return to zero code), etc. Key feature parameters refer to specific parameters extracted from the remote control signal for subsequent analysis.

[0113] This step extracts the features of the remote control signal in detail to obtain its key feature parameters. For example, in a certain monitoring, the system detected that the remote control signal frequency used by the drone was 2.4GHz, using GFSK (Gaussian Frequency Shift Keying) modulation and Manchester coding format. These key feature parameters not only describe the basic characteristics of the remote control signal, but also provide an important basis for subsequent comparative analysis. In this way, the system can accurately identify and analyze the remote control signal to ensure the accuracy of subsequent processing.

[0114] Step 202: Based on the image transmission protocol classification result and the key characteristic parameters of the remote control signal, a dynamic time warping algorithm is used to compare and analyze the timing relationship between the start time and the transmission period and the remote control signal, so as to identify the time synchronization point and periodic characteristics between the transmission period and the remote control signal;

[0115] In this step, the timing relationship refers to the time correspondence between two signals. The time synchronization point refers to the point where two signals are synchronized in time. The periodic feature refers to the time interval feature of the repeated occurrence of the signal.

[0116] This step is based on the classification results of the image transmission protocol and the key characteristic parameters of the remote control signal. The dynamic time bending algorithm is used to compare and analyze the timing relationship between the start time and transmission period of the image transmission signal and the remote control signal. For example, the system detects that the transmission period of the image transmission signal is 50 milliseconds, and the period of the remote control signal is also 50 milliseconds, and the pilot symbol appears at the 10th millisecond each time. Through the dynamic time bending algorithm, the system can accurately identify the synchronization points and periodic characteristics of the two to ensure the accuracy of the analysis results. This comparative analysis not only improves the accuracy of time synchronization, but also captures subtle periodic changes, providing reliable timing information for subsequent state sequence analysis.

[0117] Step 203: Based on the time synchronization point and the periodicity characteristics, a hidden Markov model is applied to perform state sequence analysis on the remote control signal to extract the time period of the remote control signal and identify the appearance time of the pilot symbol in the remote control signal;

[0118] This step applies the hidden Markov model to perform state sequence analysis on the remote control signal based on the identified time synchronization points and periodic features. For example, the system decomposes the remote control signal into a series of hidden states through the hidden Markov model, and infers the time period of the remote control signal based on the known time synchronization points and periodic features. Furthermore, the system can identify the time when the pilot symbol appears in the remote control signal. Assuming that a pilot symbol appears once every 50 milliseconds in a remote control signal, and each time it appears at the 10th millisecond, the hidden Markov model can accurately extract this periodic feature and identify the specific time when the pilot symbol appears. In this way, the system can fully analyze the time characteristics of the remote control signal to ensure the accuracy and effectiveness of the interference operation.

[0119] The embodiment of the present invention ensures the accuracy of key characteristic parameters by performing detailed feature extraction on the remote control signal; uses a dynamic time warping algorithm to achieve accurate comparative analysis of the timing relationship between the image transmission signal and the remote control signal, ensuring accurate identification of the time synchronization point and periodic characteristics; and uses a hidden Markov model to perform state sequence analysis, which not only extracts the time period of the remote control signal, but also accurately identifies the appearance time of the pilot symbol. The entire solution not only improves the overall performance and reliability of the system, but also ensures a comprehensive analysis of the time characteristics of the remote control signal, providing a scientific basis for subsequent precise interference operations, maximizing the interference effect while reducing the risk of misoperation.

[0120] In order to intelligently select the most appropriate interference time point according to the pattern changes in the historical data, maximize the interference effect while reducing the impact on legitimate communications. Based on this, the present invention provides a specific embodiment, step 103, based on the optimized interference signal parameter configuration, using a long short-term memory network, analyzes the historical data to obtain historical analysis results, and combines the historical analysis results to predict the best interference time, specifically including the following steps:

[0121] Step 301: Based on the optimized interference signal parameter configuration, a long short-term memory network is used to deeply analyze the long-term dependencies and pattern changes in the historical data to obtain historical analysis results;

[0122] In this step, long-term dependency refers to the fact that in time series data, a data point at a certain moment is affected not only by recent data points, but also by earlier data points. Pattern change refers to the trend or regularity of change that occurs over time in time series data.

[0123] This step uses the long short-term memory network to conduct an in-depth analysis of the long-term dependencies and pattern changes in historical data based on the optimized interference signal parameter configuration. For example, in a certain monitoring, the system recorded the historical data of drone communications in the past month, including changes in image transmission signals, remote control signals, and the surrounding electromagnetic environment. Through the long short-term memory network, the system can capture the long-term dependencies in this data, such as the frequent use patterns of certain frequency bands in a specific time period, as well as periodic characteristics. The long short-term memory network can not only process data with short time intervals, but also identify complex pattern changes across multiple time steps, ensuring the comprehensiveness and accuracy of the analysis results.

[0124] Step 302: Combine the historical analysis results, use the long short-term memory network to analyze the key elements in the historical data, and predict the best interference time based on the key elements. In the process of using the long short-term memory network for analysis, an attention mechanism is introduced, and the attention weight of each time step is calculated. The attention weight is used to identify the key elements of the historical data, and the key elements include periodic characteristics, abnormal events, and environmental changes.

[0125] In this step, key elements refer to important factors that affect the interference effect, such as periodic characteristics, abnormal events, and environmental changes. Attention weight refers to the value representing the importance of a certain time step, which is used to highlight key elements. Abnormal events refer to events that are significantly different from the normal pattern and may indicate illegal activities or interference. Environmental changes refer to changes in the surrounding electromagnetic environment, such as fluctuations in noise levels.

[0126] This step combines the historical analysis results and uses the long short-term memory network to further analyze the key elements in the historical data, and predicts the best time to interfere based on these key elements. In this process, the attention mechanism is introduced to identify the key elements in the historical data by calculating the attention weight of each time step. For example, the system detects that a certain frequency band frequently appears with periodic characteristics between 3 pm and 5 pm every Tuesday, while it is relatively quiet at other times. At the same time, the system also identifies some abnormal events, such as the sudden appearance of high-intensity interference signals on a certain day, and environmental changes, such as a significant decrease in background noise levels on weekends. Through the attention mechanism, the system can focus on these key elements to ensure the accuracy and reliability of the prediction. Finally, based on these key elements, the system predicts the best time to interfere, such as choosing to start the interference operation at 3 pm every Tuesday to maximize the interference effect.

[0127] The embodiment of the present invention uses a long short-term memory network to conduct in-depth analysis of long-term dependencies and pattern changes in historical data, ensuring the comprehensiveness and accuracy of historical analysis results; combined with historical analysis results, an attention mechanism is introduced to identify key elements such as periodic features, abnormal events, and environmental changes by calculating attention weights, thereby predicting the best time for interference. The entire solution not only improves the intelligence and adaptability of the system, but also ensures the safety and effectiveness of interference operations, maximizing the interference effect while reducing the impact on legitimate communications.

[0128] Figure 2 The present invention provides a structural schematic diagram of a precise jamming system for a pilot signal of a drone remote controller, such as Figure 2 As shown, the system includes:

[0129] The receiving module 21 is used to receive the image transmission signal and the remote control signal of the drone, detect and process the image transmission signal, and parse the start time, transmission period and classification results of different types of image transmission protocols of the image transmission signal;

[0130] An extraction module 22, configured to compare the start time and the transmission period with the remote control signal based on the image transmission protocol classification result and the remote control signal, so as to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal;

[0131] An adjustment module 23 is used to adjust the existing time feature recognition standard based on the time period and the appearance time of the pilot symbol by using a reinforcement learning algorithm to generate an optimized interference signal parameter configuration, and based on the optimized interference signal parameter configuration, use a long short-term memory network to analyze historical data to obtain historical analysis results, and combine the historical analysis results to predict the best interference time;

[0132] The identification module 24 is used to use real-time spectrum sensing technology to monitor the wireless communication environment around the drone, obtain wireless communication monitoring results, apply convolutional neural networks to perform a first classification process on the real-time spectrum graph in the wireless communication monitoring results to distinguish between legitimate communication signals and potential conflict signals; introduce an autoencoder to perform anomaly detection on the potential conflict signals, identify abnormal frequency band activities, and obtain potential conflict frequency bands; based on the potential conflict frequency bands, combined with the geographic positioning data of the drone, generate a dynamic spectrum map to visualize the frequency band occupancy; according to predefined frequency band risk assessment indicators, evaluate the risk level of each frequency band to generate risk warning information; based on the wireless communication monitoring results, the dynamic spectrum map and the risk warning information, construct a target candidate frequency band pool, and based on the target candidate frequency band pool, remove the identified conflicting frequency bands to confirm the target interference frequency band;

[0133] The determination module 25 is used to determine a precise interference method based on the historical analysis results, the optimal interference timing and the target interference frequency band.

[0134] Figure 2 The precise jamming system for the pilot signal of the remote control of the UAV can be executed Figure 1 The implementation principle and technical effect of the precise jamming method for the pilot signal of the remote control of the UAV described in the embodiment shown are not repeated here. The specific way in which each module and unit performs the operation of the precise jamming system for the pilot signal of the remote control of the UAV in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0135] In one possible design, Figure 2 The precise jamming system for the pilot signal of the remote controller of the UAV in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0136] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0137] The processing component 32 is used to: receive the image transmission signal and remote control signal of the drone, detect and process the image transmission signal, and parse the starting time, transmission period and classification results of different types of image transmission protocols of the image transmission signal; based on the image transmission protocol classification results and the remote control signal, compare the starting time and the transmission period with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal; based on the time period and the appearance time of the pilot symbol, use the reinforcement learning algorithm to adjust the existing time feature recognition standard to generate an optimized interference signal parameter configuration, based on the optimized interference signal parameter configuration, use the long short-term memory network to analyze the historical data to obtain the historical analysis results, and combine the historical analysis results to predict the best interference time; use real-time spectrum sensing technology to monitor the wireless communications around the drone environment, obtain wireless communication monitoring results, apply convolutional neural network to perform first classification processing on the real-time spectrum diagram in the wireless communication monitoring results to distinguish legitimate communication signals from potential conflict signals; introduce autoencoder to perform anomaly detection on the potential conflict signal, identify abnormal frequency band activities, and obtain potential conflict frequency bands; based on the potential conflict frequency bands, combined with the geographic positioning data of the drone, generate a dynamic spectrum map to visualize the frequency band occupancy; according to the predefined frequency band risk assessment indicators, evaluate the risk level of each frequency band to generate risk warning information; based on the wireless communication monitoring results, the dynamic spectrum map and the risk warning information, construct a target candidate frequency band pool, based on the target candidate frequency band pool, remove the identified conflicting frequency bands to confirm the target interference frequency band; based on the historical analysis results, the optimal interference time and the target interference frequency band, determine the precise interference method.

[0138] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0139] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0140] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0141] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0142] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0143] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0144] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The illustrated embodiment is a method for accurately jamming the pilot signal of a drone remote controller.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0146] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0147] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A precise jamming method for the pilot signal of a drone remote controller, characterized in that: include: Receive the image transmission signal and remote control signal of the drone, detect and process the image transmission signal, and parse the start time, transmission period and classification results of different types of image transmission protocols of the image transmission signal; Based on the image transmission protocol classification result and the remote control signal, the start time and the transmission period are compared with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal; Based on the time period and the appearance time of the pilot symbol, the existing time feature recognition standard is adjusted by using a reinforcement learning algorithm to generate an optimized interference signal parameter configuration, based on the optimized interference signal parameter configuration, the historical data is analyzed by using a long short-term memory network to obtain a historical analysis result, and the optimal interference time is predicted in combination with the historical analysis result; Real-time spectrum sensing technology is used to monitor the wireless communication environment around the drone to obtain wireless communication monitoring results. A convolutional neural network is used to perform the first classification process on the real-time spectrum graph in the wireless communication monitoring results to distinguish between legitimate communication signals and potential conflicting signals. An autoencoder is introduced to perform anomaly detection on the potential conflicting signals, identify abnormal frequency band activities, and obtain potential conflicting frequency bands. Based on the potential conflicting frequency bands, combined with the geographic positioning data of the drone, a dynamic spectrum map is generated to visualize the frequency band occupancy; based on the predefined frequency band risk assessment indicators, the risk level of each frequency band is assessed to generate risk warning information; Based on the wireless communication monitoring result, the dynamic spectrum map and the risk warning information, a target candidate frequency band pool is constructed, and based on the target candidate frequency band pool, the identified conflicting frequency bands are removed to confirm the target interference frequency band; Based on the historical analysis results, the optimal interference timing and the target interference frequency band, a precise interference method is determined.

2. The method according to claim 1, characterized in that Based on the wireless communication monitoring result, the dynamic spectrum map and the risk warning information, a target candidate frequency band pool is constructed, and based on the target candidate frequency band pool, the identified conflicting frequency bands are removed to confirm the target interference frequency band, including: Based on the wireless communication monitoring result, the dynamic spectrum map and the risk warning information, removing the identified conflicting frequency bands and generating a preliminary candidate frequency band pool; Using multi-sensor data fusion technology, the image transmission signal, the remote control signal, the wireless communication monitoring result and the geographic positioning data are fused and processed to obtain a comprehensive frequency band evaluation result; Based on the comprehensive frequency band evaluation result, a Bayesian classifier is used to perform a second classification process on the frequency bands in the preliminary candidate frequency band pool to obtain an optimized classification result; Based on the optimized classification results and the frequency band availability evaluation index, the preliminary candidate frequency band pool is optimized using a genetic algorithm to obtain a target candidate frequency band pool, and a multi-objective optimization algorithm is introduced in the optimization process using the genetic algorithm to simultaneously optimize multiple objectives, wherein the multiple objectives include an interference effect objective, a legitimate communication protection objective, and a resource utilization efficiency objective; The electromagnetic environment simulation model is used to simulate the actual electromagnetic environment to evaluate the performance of each frequency band in the target candidate frequency band pool under different conditions to obtain a performance evaluation result, generate a target frequency band combination based on the performance evaluation result, and confirm the target interference frequency band based on the target frequency band combination.

3. The method according to claim 2, characterized in that The electromagnetic environment simulation model is used to simulate the actual electromagnetic environment to evaluate the performance of each frequency band in the target candidate frequency band pool under different conditions to obtain a performance evaluation result, generate a target frequency band combination based on the performance evaluation result, and confirm the target interference frequency band based on the target frequency band combination, including: Based on the image transmission signal, the remote control signal and the multi-dimensional parameters of the electromagnetic environment around the drone, simulation parameters are set, and an electromagnetic environment simulation model is constructed by combining random variables and probability distribution; Using the electromagnetic environment simulation model, different scenarios are set to simulate the actual electromagnetic environment. In the process of simulating the actual electromagnetic environment, multi-physics field coupling simulation technology is introduced to combine multiple physical phenomena to generate simulation result data. Based on the simulation result data, performance evaluation indicators are defined. The different scenarios include cities, mountainous areas, and open areas. Based on the performance evaluation index and the actual electromagnetic environment, the performance of each frequency band in the target candidate frequency band pool under different conditions is evaluated to obtain a performance evaluation result, wherein the performance evaluation index includes an interference effect index, a legal communication protection index, and a resource utilization efficiency index; Based on the performance evaluation results, a multi-criteria decision analysis method is applied to determine the priority of each frequency band to generate a preliminary frequency band combination, and a Monte Carlo simulation is introduced to evaluate the performance of the preliminary frequency band combination under random disturbance to obtain a random disturbance performance result, and based on the random disturbance performance result, a target frequency band combination is generated, and based on the target frequency band combination, a target interference frequency band is confirmed.

4. The method according to claim 1, characterized in that: According to the predefined frequency band risk assessment indicators, the risk level of each frequency band is evaluated to generate risk warning information, including: Based on the wireless communication monitoring results and dynamic spectrum map, combined with geographic positioning data, the frequency band occupancy is modeled in multiple dimensions using geographic information system technology to obtain a frequency band occupancy model; Based on the frequency band occupancy model and predefined frequency band risk assessment indicators, a multi-criteria decision analysis method is applied, combined with a hierarchical analysis method and a fuzzy comprehensive evaluation method, to conduct a risk assessment on each frequency band, calculate a risk score corresponding to each frequency band, divide each frequency band into different risk levels based on the risk score, and generate a preliminary risk assessment result based on the risk level. The frequency band risk assessment indicators include interference intensity, frequency band utilization, geographic location sensitivity, and frequency band protection priority; A Bayesian network is used to perform risk propagation analysis on the high-risk level frequency bands in the preliminary risk assessment results to refine the risk sources, potential impact scope and response measures to obtain refined risk information, and risk warning information is generated based on the preliminary risk assessment results and the refined risk information.

5. The method according to claim 1, characterized in that Based on the image transmission protocol classification result and the remote control signal, the start time and the transmission period are compared with the remote control signal to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal, including: Extracting target features of the remote control signal to obtain key feature parameters of the remote control signal, wherein the target features include frequency, modulation mode, and coding format; Based on the image transmission protocol classification result and the key characteristic parameters of the remote control signal, a dynamic time warping algorithm is used to compare and analyze the timing relationship between the start time and the transmission period and the remote control signal, so as to identify the time synchronization point and periodic characteristics between the transmission period and the remote control signal; Based on the time synchronization point and the periodicity characteristics, a hidden Markov model is applied to perform state sequence analysis on the remote control signal to extract the time period of the remote control signal and identify the appearance time of the pilot symbol in the remote control signal.

6. The method according to claim 1, characterized in that Based on the optimized interference signal parameter configuration, the historical data is analyzed using a long short-term memory network to obtain historical analysis results, and the optimal interference timing is predicted in combination with the historical analysis results, including: Based on the optimized interference signal parameter configuration, the long-term dependencies and pattern changes in the historical data are deeply analyzed using the long-term short-term memory network to obtain historical analysis results; Combined with the historical analysis results, the long short-term memory network is used to analyze the key elements in the historical data. Based on the key elements, the optimal interference time is predicted. The attention mechanism is introduced in the process of analysis using the long short-term memory network. By calculating the attention weight of each time step, the attention weight is used to identify the key elements of the historical data, which include periodic characteristics, abnormal events and environmental changes.

7. A precise jamming system for the pilot signal of a drone remote controller, characterized in that: include: A receiving module is used to receive the image transmission signal and remote control signal of the drone, detect and process the image transmission signal, and parse the start time, transmission period and classification results of different types of image transmission protocols of the image transmission signal; An extraction module, configured to compare the start time and the transmission period with the remote control signal based on the image transmission protocol classification result and the remote control signal, so as to extract the time period of the remote control signal and the appearance time of the pilot symbol in the remote control signal; An adjustment module is used to adjust the existing time feature recognition standard based on the time period and the appearance time of the pilot symbol by using a reinforcement learning algorithm to generate an optimized interference signal parameter configuration, and based on the optimized interference signal parameter configuration, use a long short-term memory network to analyze historical data to obtain historical analysis results, and combine the historical analysis results to predict the best interference time; The identification module is used to use real-time spectrum sensing technology to monitor the wireless communication environment around the UAV, obtain wireless communication monitoring results, apply convolutional neural network to perform first classification processing on the real-time spectrum graph in the wireless communication monitoring results to distinguish legitimate communication signals from potential conflict signals; introduce autoencoder to perform abnormality detection on the potential conflict signal, identify abnormal frequency band activities, and obtain potential conflict frequency bands; Based on the potential conflicting frequency bands, combined with the geographic positioning data of the drone, a dynamic spectrum map is generated to visualize the frequency band occupancy; based on the predefined frequency band risk assessment indicators, the risk level of each frequency band is assessed to generate risk warning information; Based on the wireless communication monitoring result, the dynamic spectrum map and the risk warning information, a target candidate frequency band pool is constructed, and based on the target candidate frequency band pool, the identified conflicting frequency bands are removed to confirm the target interference frequency band; A determination module is used to determine a precise interference method based on the historical analysis results, the optimal interference timing and the target interference frequency band.

8. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a precise interference method for a pilot signal of a drone remote controller as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a precise interference method for a pilot signal of a drone remote controller as described in any one of claims 1 to 6 is implemented.

Images