Intrusion identification processing method and device and readable storage medium
Through multimodal data fusion and artificial intelligence algorithms, acoustics, airflow and optical sensors are integrated, accurate identification and real-time intervention of flight equipment intrusion behavior are achieved, the problem of identifying blind spots in complex environments is solved, and the intelligence level of monitoring systems is improved.
Patent Information
- Application Number
- CN202510504405.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-21
- Publication Date
- 2025-08-08
AI Technical Summary
The prior art poorly recognizes silent flight and low-noise targets when monitoring flight equipment intrusions, especially in complex environments, resulting in airspace security threats, privacy violations and public safety hazards.
The multimodal data fusion method is adopted, combining acoustic features, environmental perturbation characteristics and dynamic intervention results, and the intrusion recognition processing is optimized through convolutional neural networks and reinforcement learning algorithms, and sensors such as acoustic sensors, breeze perturbation sensors and lidars are integrated to achieve accurate classification and trajectory prediction of flight equipment.
It improves monitoring accuracy in complex environments, makes up for the blind spots of silent flight and low-noise targets, and achieves real-time, accurate and efficient governance of flight equipment intrusion behavior.
Smart Images
Figure CN120448775A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of flight equipment technology, and in particular to an intrusion identification and processing method, device, and readable storage medium. Background Art
[0002] With the rapid development and widespread application of flight equipment technology, flight equipment has demonstrated important value in logistics and transportation, agricultural monitoring, entertainment shooting, emergency rescue and other fields.
[0003] However, due to inadequate regulation and improper operation, the illegal flight of aircraft is becoming increasingly serious, bringing multiple social problems, including threats to airspace security, privacy violations, and public safety hazards. For example, aircraft "intrusion" into airport clear zones can cause aviation accidents, entering military restricted areas can lead to information leaks, and even flying in densely populated urban areas can cause accidental injuries.
[0004] Therefore, how to improve the identification effect of flight equipment intrusion has become a problem that needs to be solved. Summary of the Invention
[0005] The technical problem to be solved by this application is to provide an intrusion identification processing method, device and readable storage medium to solve the problems existing in the prior art in view of the above-mentioned deficiencies in the prior art.
[0006] In a first aspect, the present application provides an intrusion identification and processing method, the method comprising:
[0007] S1. Obtain the acoustic characteristics within the monitoring area;
[0008] S2. Acquire environmental disturbance characteristics within the monitoring area, wherein the environmental disturbance characteristics include airflow disturbance characteristics and optical reflection characteristics;
[0009] S3. Obtain dynamic intervention results for flight equipment within the monitoring area;
[0010] S4. Obtain an intrusion identification processing result within the monitoring area according to the acoustic characteristics, environmental disturbance characteristics, and dynamic intervention results.
[0011] In some embodiments, S1 includes:
[0012] Acquiring noise within a monitoring area, where the noise is measured by an acoustic sensor deployed within the monitoring area;
[0013] Feature extraction is performed on the noise to obtain acoustic features in the monitoring area.
[0014] In some embodiments, S2 includes:
[0015] Obtaining airflow changes in the monitoring area, where the airflow changes are measured by breeze disturbance sensors deployed in the monitoring area;
[0016] Obtaining air disturbances and reflection changes within a monitoring area, wherein the air disturbances and reflection changes are measured by a laser radar deployed within the monitoring area;
[0017] The airflow disturbance characteristic is obtained based on the airflow change, and the optical reflection characteristic is obtained based on the air disturbance and reflection change.
[0018] In some embodiments, S3 includes:
[0019] Perform flight equipment positioning, radio frequency interference, buzzer induction, and signal tracking processing within the monitoring area to obtain dynamic intervention results for the flight equipment.
[0020] In some embodiments, S4 includes:
[0021] The acoustic features, environmental disturbance features and dynamic intervention results are input into an artificial intelligence model, and the intrusion identification processing results in the monitoring area are obtained through the artificial intelligence model.
[0022] In some embodiments, the artificial intelligence model is constructed based on a convolutional neural network (CNN) and / or a reinforcement learning algorithm;
[0023] The convolutional neural network (CNN) is used to extract high-dimensional features and classify targets based on fused data, wherein the fused data is obtained by fusing the acoustic features, environmental disturbance features, and dynamic intervention results.
[0024] Among them, the reinforcement learning algorithm is used to optimize the monitoring and intervention strategies based on the target classification results obtained by CNN.
[0025] In some embodiments, the target classification result obtained by the CNN is whether the target is an intrusion behavior;
[0026] Optimize monitoring and intervention strategies based on target classification results obtained by CNN, including:
[0027] If the target is an intrusion behavior, the flight trajectory prediction results of the intruding flight device are output through the reinforcement learning algorithm, and the monitoring and intervention strategies are optimized based on the flight trajectory prediction results.
[0028] In a second aspect, the present application provides an intrusion identification and processing device, the device comprising:
[0029] A first acquisition module is configured to acquire acoustic characteristics within a monitoring area;
[0030] a second acquisition module configured to acquire environmental disturbance characteristics within the monitoring area, wherein the environmental disturbance characteristics include airflow disturbance characteristics and optical reflection characteristics;
[0031] A third acquisition module is configured to obtain dynamic intervention results for flight equipment within the monitoring area;
[0032] The intrusion identification module is configured to obtain an intrusion identification processing result within the monitoring area based on the acoustic characteristics, environmental disturbance characteristics and dynamic intervention results.
[0033] In a third aspect, the present application provides an intrusion identification and processing device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the intrusion identification and processing method described in the first aspect above.
[0034] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the intrusion identification and processing method described in the first aspect is implemented.
[0035] The intrusion identification and processing method, device and readable storage medium provided by the present application include: obtaining acoustic features within the monitoring area; obtaining environmental disturbance features within the monitoring area, the environmental disturbance features including airflow disturbance features and optical reflection features; obtaining dynamic intervention results for flight equipment within the monitoring area; and obtaining intrusion identification and processing results within the monitoring area based on the acoustic features, environmental disturbance features and dynamic intervention results. The present application provides an intrusion identification and processing method based on multimodal data fusion and artificial intelligence analysis, integrating multiple data sources such as acoustic feature monitoring, environmental disturbance detection and optical reflection analysis, achieving accurate target classification through convolutional neural networks, and combining reinforcement learning to optimize target trajectory prediction and response strategies. Through the synergistic effect of multimodal data and in-depth analysis of intelligent algorithms, the system not only improves the monitoring accuracy in complex environments, but also makes up for the blind spots of existing technologies in monitoring silent flights and low-noise targets, ultimately achieving real-time, accurate and efficient comprehensive management of flight equipment intrusion behaviors. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0037] Figure 1 A flowchart of an intrusion identification and processing method provided in an embodiment of the present application;
[0038] Figure 2 A schematic diagram of the structure of an intrusion identification and processing device provided in an embodiment of the present application;
[0039] Figure 3 A schematic diagram of the structure of another intrusion identification and processing device provided in an embodiment of the present application.
[0040] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION
[0041] In order to enable those skilled in the art to better understand the technical solution of the present application, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0042] It should be understood that the specific embodiments and drawings described herein are only used to explain the present application, rather than to limit the present application.
[0043] It can be understood that, in the absence of conflict, the various embodiments and features in the embodiments of the present application can be combined with each other.
[0044] It will be understood that, for the sake of ease of description, the drawings of this application only show the parts related to this application, while the parts not related to this application are not shown in the drawings.
[0045] It can be understood that each unit and module involved in the embodiments of the present application may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.
[0046] It can be understood that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.
[0047] It is understandable that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present application may occur in an order different from that marked in the drawings.
[0048] It is understood that the flowcharts and block diagrams of the present application illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present application. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or by a combination of hardware and computer instructions.
[0049] It can be understood that the units and modules involved in the embodiments of the present application can be implemented by software or hardware, for example, the units and modules can be located in a processor.
[0050] To combat intrusions into flight equipment, a variety of monitoring technologies have been developed and applied, including radar monitoring, visual recognition, and radio spectrum monitoring. Following is a description of the working principles, advantages, and disadvantages of existing intrusion monitoring technologies:
[0051] 1. Radar monitoring technology
[0052] How it works: Radar detects the range, speed, and direction of a flying target by transmitting radio waves and receiving reflected signals. This technology is widely used in traditional airspace monitoring, such as detecting aircraft and missiles.
[0053] Advantages: Can cover targets in a wide range. Applicable to various weather and lighting conditions.
[0054] Disadvantages: Radar has low resolution for small targets (such as aircraft), especially in the 0-600m range, and is easily obstructed by buildings and limited target size. In complex environments such as cities, radar monitoring is easily interfered with by factors such as signal reflections and terrain changes, leading to target identification errors.
[0055] 2. Visual recognition technology
[0056] Working principle: Use cameras or optical sensors to capture target images, and use computer vision algorithms (such as target detection and motion analysis) to identify the shape, trajectory, and motion characteristics of the flying device.
[0057] Advantages: Can be used to accurately identify the target's shape. Relatively low cost and easy to deploy quickly.
[0058] Disadvantages: Camera performance degrades significantly in rain, snow, fog, haze, or low-light conditions at night, resulting in reduced recognition accuracy. Vision technology typically requires close-range acquisition of clear images, making it less effective for monitoring distant targets or high-speed aircraft. Vision algorithms require significant computing resources to process images and video streams, making them difficult to meet real-time requirements in multi-target tracking scenarios.
[0059] 3. Radio spectrum monitoring technology
[0060] Working Principle: Identify and locate the aircraft by monitoring the wireless communication signals (such as Wi-Fi, Bluetooth or dedicated radio frequency signals) between the aircraft and its remote controller.
[0061] Advantages: Can directly identify the operating frequency and communication protocol of aircraft through signal characteristics. Independent of target shape, suitable for concealed target detection.
[0062] Disadvantages: Ineffective against passive targets: This technology relies primarily on communication signals between the aircraft and ground control equipment, and cannot detect autonomous aircraft that do not transmit signals. In urban or complex electromagnetic environments, wireless signals are complex, and aircraft signals are easily interfered with or misidentified.
[0063] Based on the above shortcomings, this application provides an intrusion identification and processing method, which uses multimodal fusion to improve the target recognition rate, introduces artificial intelligence algorithms, optimizes data processing and real-time analysis capabilities, enhances the dynamic response capabilities of the monitoring system, including target interception and risk disposal, expands the coverage capabilities of complex environments, and solves blind spot problems.
[0064] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0065] The present application provides an intrusion identification and processing method, the working process of which can be implemented by electronic devices, such as computers, handheld smart terminals, etc. For the convenience of explanation, the embodiments of the present application are described with the method execution subject being a computer.
[0066] Figure 1 A schematic diagram of an intrusion identification and processing method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the present application provides an intrusion identification and processing method, which includes S1-S4, as follows:
[0067] S1. Obtain the acoustic characteristics within the monitoring area;
[0068] In some embodiments, S1 includes:
[0069] Acquiring noise within a monitoring area, where the noise is measured by an acoustic sensor deployed within the monitoring area;
[0070] Feature extraction is performed on the noise to obtain acoustic features in the monitoring area.
[0071] Specifically, acoustic sensors are used to capture the noise generated by aircraft during flight. This noise is usually characteristic within a certain frequency range (such as the rotation frequency of the propeller and motor noise). Therefore, distributed acoustic sensors (such as array microphones) are deployed in the monitoring area. These sensors can cover different terrains and complex environments to collect the noise characteristics of aircraft. By analyzing the acoustic characteristics, the aircraft can be quickly located and identified. In addition, acoustic feature monitoring has non-contact, all-weather monitoring capabilities, and can effectively capture aircraft signals even in obstructed areas. Then, the collected noise is subjected to feature extraction.
[0072] For example, discrete wavelet transform is used to decompose the collected sound signal and extract key features (such as rotation frequency and amplitude change), as follows:
[0073]
[0074] Where x(t) is the original noise signal; ψ j,k (t) is the wavelet basis function; c j,k is the wavelet coefficient, and t is the time.
[0075] Optionally, a machine learning algorithm (such as a support vector machine (SVM)) can be used to classify noise as either aircraft noise or background noise. During training, aircraft noise samples (including different models of common aircraft) are input, and the model outputs whether it is an aircraft signal. This method is suitable for detecting targets at medium and short distances and in high noise levels.
[0076] S2. Acquire environmental disturbance characteristics within the monitoring area, wherein the environmental disturbance characteristics include airflow disturbance characteristics and optical reflection characteristics;
[0077] In some embodiments, S2 includes:
[0078] Obtaining airflow changes in the monitoring area, where the airflow changes are measured by breeze disturbance sensors deployed in the monitoring area;
[0079] Obtaining air disturbances and reflection changes within a monitoring area, wherein the air disturbances and reflection changes are measured by a laser radar deployed within the monitoring area;
[0080] The airflow disturbance characteristic is obtained based on the airflow change, and the optical reflection characteristic is obtained based on the air disturbance and reflection change.
[0081] Specifically, since flying devices disturb their surroundings (for example, airflow disturbances caused by rotor blades and the movement of tiny dust particles), monitoring these disturbance parameters can detect the presence of flying devices, thus addressing the blind spots in monitoring targets operating in "silent flight" or with communications disabled. A set of sensors monitoring environmental physical parameters will be deployed, including highly sensitive breeze disturbance sensors to capture airflow changes, and lidar to monitor air disturbances and reflection changes caused by flying devices.
[0082] Among them, the characteristic analysis formula of airflow disturbance is:
[0083]
[0084] Where v(x, y, z, t) is the disturbance velocity distribution, x, y, z are spatial coordinates, t is time, and Φ is the disturbance potential field, which comes from the force exerted by the rotor of the flight equipment on the air.
[0085] Optical reflection detection involves the laser radar emitting laser pulses toward the target area and constructing a reflection image after receiving the return signal. By comparing dynamic image changes, it can identify small flying targets (flying equipment).
[0086] This application combines airflow disturbance data and optical reflection signals through a comprehensive analysis using a correlation model to determine the presence of flying equipment. Environmental disturbance monitoring complements acoustic monitoring, improving detection coverage and accuracy in complex scenarios. Providing airflow and optical signatures, it is suitable for detecting silent targets or at long distances.
[0087] S3. Obtain dynamic intervention results for flight equipment within the monitoring area;
[0088] In some embodiments, S3 includes:
[0089] Perform flight equipment positioning, radio frequency interference, buzzer induction, and signal tracking processing within the monitoring area to obtain dynamic intervention results for the flight equipment.
[0090] Specifically, a dynamic intervention system can be built within the monitoring area. This system includes an aircraft positioning module, a radio frequency jamming module, a buzzer induction module, and a signal tracking module, enabling real-time intervention and disposal of intruding aircraft. Upon confirming an intrusion, the intelligent intervention system immediately implements jamming and tracking measures, preventing the aircraft from continuing to fly or forcing it to land.
[0091] The flight equipment positioning module uses the Time Difference of Arrival (TDOA) method of the sensor array to locate the flight equipment. The specific formula is:
[0092]
[0093] Where, Δt ij is the time difference between sensors i and j receiving signals, d ij : The distance difference between the flight equipment and the two sensors, c is the speed of sound wave propagation.
[0094] The RF interference module dynamically adjusts the RF interference signal frequency to match the aircraft's communication frequency, causing the aircraft to lose connection with its control device. The interference signal generation formula is:
[0095] S jam (t)=A sin(2πf j t+φ)
[0096] Among them, S jam (t) is the interference signal, A is the signal amplitude, f j is the interference frequency, t is the time, and φ is the initial phase.
[0097] Among them, the buzzer induction module uses acoustic equipment to emit high-frequency noise to simulate the sound of obstacles, so that the flight equipment can automatically avoid to a safe area or forced landing point.
[0098] Among them, the signal tracking module calculates the path of the flight equipment through the legacy signal (such as radio frequency signal) and dynamically updates the target position.
[0099] In this application, dynamic intervention can effectively control intrusion behavior and assist relevant processing departments in further processing through tracking means.
[0100] S4. Obtain an intrusion identification processing result within the monitoring area according to the acoustic characteristics, environmental disturbance characteristics, and dynamic intervention results.
[0101] In some embodiments, S4 includes:
[0102] The acoustic features, environmental disturbance features and dynamic intervention results are input into an artificial intelligence model, and the intrusion identification processing results in the monitoring area are obtained through the artificial intelligence model.
[0103] Specifically, this application integrates multimodal data such as acoustics, airflow, optics, and radio frequency, and uses artificial intelligence models for in-depth analysis, which can improve the recognition accuracy and anti-interference ability of the monitoring system and achieve precise monitoring of multiple targets in complex scenarios.
[0104] The acoustic sensor array in step S1 captures noise data of the flight equipment during flight, including propeller rotation sound, motor sound, etc. The output feature data includes:
[0105] Frequency domain features: noise frequency, amplitude, etc. extracted through wavelet transform.
[0106] Time domain features: noise changes extracted through the time series characteristics of the signal.
[0107] The above feature data becomes the acoustic feature input for multimodal data fusion (step S4).
[0108] The airflow disturbance sensor and lidar in step S2 capture environmental change data during flight of the flight device, including:
[0109] Airflow disturbance characteristics: air flow speed, direction and disturbance range caused by the rotor of the flight equipment.
[0110] Optical reflection characteristics: target reflection signals and changing images detected by lidar.
[0111] The above feature data becomes the disturbance feature input of multimodal data fusion (step S4).
[0112] Acoustic data is standardized and fused together with data such as airflow disturbances and optical reflections to form a complete multimodal feature vector. Feature fusion can improve the accuracy of identifying flight equipment. For example: If the acoustic features show that there is noise anomaly in a certain area, but the noise intensity or frequency is not enough to identify the target alone, multimodal fusion can be combined with other features (such as disturbances) for further confirmation. For example, if the lidar captures a small target, but it is impossible to determine whether it is a flight device or other object alone, the airflow disturbance and acoustic features can provide additional information, thereby improving the accuracy of target classification.
[0113] In this application:
[0114] Step S1 provides acoustic features suitable for detecting targets at medium and short distances and in high noise levels.
[0115] Step S2 provides airflow and optical characteristics, which are suitable for silent target or long-distance detection.
[0116] Step S3 provides dynamic intervention results for the flight equipment.
[0117] Step S4 utilizes these data to fuse and achieve information complementarity, thus making up for the deficiency of a single data source.
[0118] The raw data from steps S1 and S2 needs to undergo feature extraction (such as time-frequency domain feature extraction and optical image processing) and normalization. Step S4 receives the normalized feature data and combines it with artificial intelligence to classify the target and predict its trajectory.
[0119] In some embodiments, the artificial intelligence model is constructed based on Convolutional Neural Networks (CNN) and / or Reinforcement Learning (RL) algorithms;
[0120] The convolutional neural network (CNN) is used to extract high-dimensional features and classify targets based on fused data obtained by fusing the acoustic features, environmental disturbance features, and dynamic intervention results. The target classification is used to distinguish between legitimate and intrusion targets.
[0121] Among them, the reinforcement learning algorithm is used to optimize the monitoring and intervention strategies based on the target classification results obtained by CNN.
[0122] In this application, the specific implementation process of high-dimensional feature extraction and target classification is as follows:
[0123] First, features are extracted separately for each mode of data. For acoustic data, frequency and time domain features are extracted through wavelet transform. For airflow disturbance data, features such as disturbance velocity distribution and amplitude change are extracted. For optical data, lidar is used to obtain the two-dimensional reflection image or point cloud features of the target.
[0124] Then, the modal data is normalized to ensure that the numerical range of the eigenvalues is similar, avoiding the dominant effect of large numerical modes on the model. The normalized multimodal features are spliced into a high-dimensional vector for input into the subsequent AI model.
[0125] Then, CNN is used to extract the spatial and pattern relationships of high-dimensional features to achieve classification and identification of intrusion targets.
[0126] Among them, the network structure design of CNN is as follows:
[0127] Input layer: takes the fused multimodal features as input, with a shape of n×m, where n is the number of modalities and m is the feature dimension of each modality.
[0128] Convolutional layer: Use multiple convolution kernels to extract local pattern relationships:
[0129]
[0130] Among them, f i,j is the convolution output value, w k,l is the convolution kernel weight, x i+k,j+l is the local value of the input feature, and b is the bias.
[0131] Pooling layer: Reduce feature dimensions through max pooling and retain important features.
[0132] Fully connected layer: Flattens the convolutional features and maps them to the classification output, which is the probability of intrusion behavior.
[0133] In some embodiments, the target classification result obtained by the CNN is whether the target is an intrusion behavior;
[0134] Optimize monitoring and intervention strategies based on target classification results obtained by CNN, including:
[0135] If the target is an intrusion behavior, the flight trajectory prediction results of the intruding flight device are output through the reinforcement learning algorithm, and the monitoring and intervention strategies are optimized based on the flight trajectory prediction results.
[0136] In this application, based on historical trajectory data, reinforcement learning is used to predict the trajectory of the flight equipment and optimize the response strategy of the monitoring system. The details are as follows:
[0137] 1. Reinforcement Learning Environment Modeling:
[0138] Define the state space S: including real-time information such as the current position, speed, and flight direction of the aircraft.
[0139] Define the action space A: including operations such as tracking the target path, updating the interception strategy, switching monitoring nodes, etc.
[0140] Define a reward function R: This function is used to evaluate the effectiveness of the system behavior. For example, a positive reward is given when the target path is successfully predicted or an intruding flight device is intercepted; a negative reward is given when the target path is successfully predicted and an intrusion is intercepted.
[0141]
[0142] 2. Reinforcement Learning Algorithm:
[0143] Using Deep Q-network (DQN) as the reinforcement learning algorithm, the Q value update formula is:
[0144]
[0145] Among them, s t ,a t is the current state and action, r t is the current reward, α is the learning rate, and γ is the discount factor.
[0146] This application combines the CNN classification results with the RL prediction results to generate the final decision, including:
[0147] Classification output: The output of CNN is used to determine whether the target is an intrusion behavior.
[0148] Trajectory prediction: The reinforcement learning model outputs the next trajectory of the flight device so that the system can formulate an interception strategy.
[0149] System response: Trigger dynamic intervention measures based on classification and trajectory results, such as radio frequency interference, buzzer induction, or real-time tracking.
[0150] In this application, convolutional neural networks are used to classify and identify intruder targets, providing high-precision multimodal feature analysis capabilities. Reinforcement learning is used for trajectory prediction and response optimization. Dynamic adaptation to target behavior enhances system intelligence. CNNs achieve precise classification, while RL optimizes intervention and tracking strategies, enabling closed-loop control of global monitoring and dynamic response.
[0151] This application provides an intrusion identification and processing method based on multimodal data fusion and artificial intelligence analysis. It integrates multiple data sources such as acoustic feature monitoring, environmental disturbance detection, and optical reflection analysis, achieves accurate target classification through convolutional neural networks, and combines reinforcement learning to optimize target trajectory prediction and response strategies. Through the synergy of multimodal data and in-depth analysis of intelligent algorithms, the system not only improves monitoring accuracy in complex environments, but also fills the blind spots of existing technologies in monitoring silent flights and low-noise targets, ultimately achieving real-time, accurate, and efficient comprehensive management of flight equipment intrusion behaviors.
[0152] It should be understood that, although the various steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they may be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times, and their execution order is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of sub-steps or stages of other steps.
[0153] Figure 2 A schematic diagram of an intrusion identification and processing device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the present application provides an intrusion identification and processing device, the device comprising:
[0154] A first acquisition module 11 is configured to acquire acoustic characteristics within the monitoring area;
[0155] A second acquisition module 12 is configured to acquire environmental disturbance characteristics within the monitoring area, wherein the environmental disturbance characteristics include airflow disturbance characteristics and optical reflection characteristics;
[0156] A third acquisition module 13 is configured to obtain dynamic intervention results for flight equipment within the monitoring area;
[0157] The intrusion identification module 14 is configured to obtain an intrusion identification processing result within the monitoring area according to the acoustic characteristics, environmental disturbance characteristics and dynamic intervention results.
[0158] Regarding the limitation of the intrusion identification and processing device, reference may be made to the limitation of the intrusion identification and processing method in the above embodiments of the present application, which will not be repeated in this embodiment.
[0159] Figure 3 Another schematic diagram of the intrusion identification and processing device provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the device includes a memory 22 and a processor 21, the memory stores a computer program, and the processor is configured to run the computer program to execute the methods in the above embodiments of the present application.
[0160] The memory is connected to the processor, the memory may be a flash memory, a read-only memory or other memory, and the processor may be a central processing unit or a single-chip microcomputer.
[0161] In some embodiments, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the methods in the above embodiments of the present application are implemented.
[0162] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.
[0163] It is understood that the above embodiments are merely exemplary embodiments for illustrating the principles of the present application, and the present application is not limited thereto. Those skilled in the art may make various modifications and improvements without departing from the spirit and substance of the present application, and such modifications and improvements are also considered to be within the scope of protection of the present application.
Claims
1. A method for intrusion identification and processing, characterized in that: The method comprises: S1. Obtain the acoustic characteristics within the monitoring area; S2. Acquire environmental disturbance characteristics within the monitoring area, wherein the environmental disturbance characteristics include airflow disturbance characteristics and optical reflection characteristics; S3. Obtain dynamic intervention results for flight equipment within the monitoring area; S4. Obtain an intrusion identification processing result within the monitoring area according to the acoustic characteristics, environmental disturbance characteristics, and dynamic intervention results.
2. The intrusion identification and processing method according to claim 1, characterized in that: S1, including: Acquiring noise within a monitoring area, where the noise is measured by an acoustic sensor deployed within the monitoring area; Feature extraction is performed on the noise to obtain acoustic features in the monitoring area.
3. The intrusion identification and processing method according to claim 1, characterized in that: S2, including: Obtaining airflow changes in the monitoring area, where the airflow changes are measured by breeze disturbance sensors deployed in the monitoring area; Obtaining air disturbances and reflection changes within a monitoring area, wherein the air disturbances and reflection changes are measured by a laser radar deployed within the monitoring area; The airflow disturbance characteristic is obtained based on the airflow change, and the optical reflection characteristic is obtained based on the air disturbance and reflection change.
4. The intrusion identification and processing method according to claim 1, characterized in that: S3, including: Perform flight equipment positioning, radio frequency interference, buzzer induction, and signal tracking processing within the monitoring area to obtain dynamic intervention results for the flight equipment.
5. The intrusion identification and processing method according to any one of claims 1 to 4, characterized in that: S4, including: The acoustic features, environmental disturbance features and dynamic intervention results are input into an artificial intelligence model, and the intrusion identification processing results in the monitoring area are obtained through the artificial intelligence model.
6. The intrusion identification and processing method according to claim 5, characterized in that: The artificial intelligence model is constructed based on a convolutional neural network (CNN) and / or a reinforcement learning algorithm; The convolutional neural network (CNN) is used to extract high-dimensional features and classify targets based on fused data, wherein the fused data is obtained by fusing the acoustic features, environmental disturbance features, and dynamic intervention results. Among them, the reinforcement learning algorithm is used to optimize the monitoring and intervention strategies based on the target classification results obtained by CNN.
7. The intrusion identification and processing method according to claim 6, characterized in that: The target classification result obtained by CNN is whether the target is an intrusion behavior; Optimize monitoring and intervention strategies based on target classification results obtained by CNN, including: If the target is an intrusion behavior, the flight trajectory prediction results of the intruding flight device are output through the reinforcement learning algorithm, and the monitoring and intervention strategies are optimized based on the flight trajectory prediction results.
8. An intrusion identification and processing device, characterized in that: The device comprises: A first acquisition module is configured to acquire acoustic characteristics within a monitoring area; a second acquisition module configured to acquire environmental disturbance characteristics within the monitoring area, wherein the environmental disturbance characteristics include airflow disturbance characteristics and optical reflection characteristics; A third acquisition module is configured to obtain dynamic intervention results for flight equipment within the monitoring area; The intrusion identification module is configured to obtain an intrusion identification processing result within the monitoring area based on the acoustic characteristics, environmental disturbance characteristics and dynamic intervention results.
9. An intrusion identification and processing device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the intrusion identification and processing method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the intrusion identification and processing method according to any one of claims 1 to 7 is implemented.