Sound wave interference system based on bird behavior analysis

Abstract

The invention discloses a sound wave interference system based on bird behavior analysis, and relates to the technical field of bird behavior analysis sound wave interference. The system comprises a multi-mode ultra-high-definition monitoring module, bird behavior data are collected in all directions by means of various devices, data are processed through a deep space-time correlation analysis module and by means of a mixed deep learning architecture and a knowledge graph, and the bird behavior data are analyzed through a multi-mode ultra-high-definition monitoring module. The intelligent adaptive strategy generation module generates a personalized sound wave strategy according to bird hearing and an evolutionary game theory, the multi-beam directional transmitting module accurately transmits sound waves by using technologies such as a phased array, and the closed-loop feedback module evaluates and optimizes an interference effect. According to the invention, bird behaviors can be accurately analyzed, an adaptive sound wave interference strategy is generated, the risk that birds hit an airplane can be reduced, agricultural harvest is guaranteed, power failures are reduced, the system has the advantages of intelligent adaptation, accurate monitoring, convenient networking management and the like, and an efficient scheme is provided for the bird interference problem in multiple fields.

Description

Technical Field

[0001] The present invention relates to the technical field of bird behavior analysis sound wave interference, in particular to a sound wave interference system based on bird behavior analysis. Background Art

[0002] The problems caused by bird activity are becoming increasingly prominent in many areas. At airports, the frequent presence of birds poses a significant threat to flight safety. Collisions with birds during takeoff and landing can cause serious consequences, such as engine damage and windshield cracking, leading to accidents and endangering the lives of passengers and crew. According to statistics, global economic losses from bird strikes amount to hundreds of millions of dollars annually. Traditional bird repellent methods, such as setting off firecrackers and using scarecrows, are short-lived and easily adapt to birds, making them ineffective in ensuring long-term flight safety.

[0003] Agricultural production is also deeply impacted by bird activity. Birds peck at crops, such as grains and fruits, resulting in reduced or even complete crop failure, causing significant economic losses for farmers. To mitigate these losses, farmers often use pesticides to repel birds. However, this not only pollutes the environment but can also lead to a decrease in bird populations and disrupt the ecological balance. Furthermore, some existing agricultural bird repellent devices are limited in functionality and fail to tailor their repellent to the behavior and habits of individual birds, resulting in ineffective repelling.

[0004] In the field of power facilities, bird nesting and defecation can cause faults such as line short circuits and tripping, disrupting the normal operation of the power system and causing inconvenience to industrial production and residents. Currently, there are limited preventative measures for bird activity near power facilities, relying mainly on regular manual inspections and simple protective devices. These measures are unable to effectively prevent birds from approaching in real time and cannot fundamentally address the harm caused by bird activity to power facilities.

[0005] In summary, existing bird-repelling methods have many shortcomings, including a lack of a system that can accurately analyze bird behavior and implement effective interference. Therefore, developing an acoustic interference system based on bird behavior analysis has important practical significance and application value, providing a more scientific, efficient, and environmentally friendly bird interference solution for airports, agriculture, power generation, and other fields. Summary of the Invention

[0006] The present invention proposes a sound wave interference system based on bird behavior analysis to solve the problems mentioned in the above-mentioned prior art.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A sound wave jamming system based on bird behavior analysis, including the following modules:

[0009] Multimodal ultra-high-definition bird behavior monitoring module: Monitoring equipment is deployed in the target area to form a monitoring network. Cameras use advanced image recognition algorithms to identify birds, 3D lidar tracks bird coordinates, and microphone arrays combined with sound localization algorithms locate bird calls and collect characteristics. A new thermal imaging sensor is added to monitor bird activity in low-visibility environments.

[0010] Deep spatiotemporal correlation behavior data analysis module: This module uses a hybrid deep learning architecture of spatiotemporal convolution and long short-term memory networks to analyze multi-source data from the monitoring module, build a bird behavior knowledge base, and use knowledge graph technology to classify and predict bird behavior.

[0011] Intelligent adaptive sound wave strategy generation module: Based on the results of behavioral data analysis, the sound wave interference strategy is generated by combining the bird auditory physiological model and evolutionary game theory, and the optimized particle swarm algorithm is used to search for sound wave parameter combinations; based on the reinforcement learning algorithm, the sound wave strategy is optimized according to the interference effect feedback. The formula is A t+1 =f(A t ,R t ), where A t+1 is the strategy at time t+1, A t is the strategy at time t, R t is the interference effect feedback at time t, f is the update function, and at the same time, the cooperative sound wave strategy is generated according to the behavioral characteristics of the bird group;

[0012] Multi-beam directional adjustable acoustic wave transmitter module: It is composed of intelligent acoustic wave transmitters distributed in the target area. It uses phased array technology to achieve beam pointing and scanning by controlling the signal phase difference. The beamforming algorithm adjusts the beam shape according to the bird's position to concentrate the acoustic wave energy. The transmitter generates the acoustic wave waveform according to the interference strategy.

[0013] Closed-loop feedback intelligent optimization module: Build a real-time feedback mechanism, use the monitoring module to collect bird behavior data after interference, compare and analyze it with expectations, use the entropy weight method combined with grey correlation analysis to evaluate the effect, and when the interference effect does not meet expectations, use the Bayesian optimization algorithm to adjust the sound wave strategy parameters, and combine the expert system to analyze the cause of failure.

[0014] Furthermore, it also includes an environmental perception and compensation submodule, which uses a micro-weather station, terrain radar and environmental noise sensor to monitor the meteorological parameters, topography and environmental noise spectrum of the target area in real time. By building a physical model of sound wave propagation and combining it with a ray tracing algorithm, it simulates the sound wave propagation path and attenuation characteristics under different environmental conditions. The formula is I(d) = I0e -αd , where I(d) is the sound wave intensity at a distance d from the sound source, I0 is the initial intensity of the sound source, and α is the attenuation coefficient. The sound wave emission parameters are adjusted according to the simulation results.

[0015] Furthermore, it also includes a bird ecological protection assessment sub-module, which uses ecological footprint analysis and biodiversity indicator calculation methods, combined with bird behavior data and regional ecosystem information, to evaluate the impact of sound wave interference on the ecological balance of bird areas. By constructing an ecological impact assessment model, it predicts bird habitat selection, population changes and ecosystem service function changes under different interference strategies.

[0016] Furthermore, the multimodal ultra-high-definition bird behavior monitoring module adopts distributed self-organizing network technology. Each monitoring device self-organizes through wireless communication to form a stable network, with automatic node discovery and adaptive routing adjustment functions. At the same time, it adopts low-power hardware design and energy collection technology to reduce system maintenance costs and energy dependence.

[0017] Furthermore, the deep spatiotemporal correlation behavior data analysis module uses the Monte Carlo tree search algorithm to predict the future behavior trends of birds. The formula is

[0018] , where P(B t+n |B1:B t ) is the probability of predicting the behavior at time t+n based on the behavior before time t, S i represents different behavioral states, and N is the total number of states. Transfer learning technology is introduced to optimize the local model using bird behavior data and model parameters in other regions. At the same time, combined with the federated learning algorithm, multi-regional data joint analysis is achieved under the premise of protecting data privacy, thereby expanding the bird behavior knowledge base.

[0019] Furthermore, the intelligent adaptive sound wave strategy generation module combines the emotional computing theory to analyze the emotional characteristics of bird calls, generate sound wave signals with emotion-inducing effects, enhance the interference effect, and at the same time, use the generative adversarial network to generate diverse sound wave waveforms.

[0020] Furthermore, the multi-beam directional adjustable sound wave emission module uses quantum dot light-emitting diode technology to achieve sound wave visualization. By emitting sound waves of a specific frequency to interact with QLED materials, it produces visual light and shadow effects. At the same time, it introduces an artificial intelligence-assisted control interface to adjust the sound wave emission parameters through gesture recognition and voice commands.

[0021] Furthermore, the closed-loop feedback intelligent optimization module uses blockchain technology to build a distributed ledger to record the entire process data of the system operation, and realizes the automatic update of system parameters and strategy optimization task allocation functions through smart contracts, thereby improving the autonomy and security of the system.

[0022] Furthermore, the system also includes a remote collaborative management platform, which realizes remote real-time monitoring and management through 5G communication technology. The platform supports multi-user concurrent operation and has permission management functions. Different users view and operate corresponding system functions according to their responsibilities, and provide data visualization on a large screen. At the same time, it has remote diagnosis and fault warning functions, which can detect system faults in advance through data analysis and push maintenance suggestions.

[0023] Furthermore, in the multi-beam directional adjustable sound wave transmission module, nanomaterials are used to manufacture the sound wave transmission diaphragm, and the characteristics of nanomaterials are utilized to improve the sound wave transmission efficiency and frequency response range. At the same time, a metamaterial coating with sound insulation and noise reduction functions is coated on the surface of the diaphragm to reduce the noise interference generated by the transmitter itself.

[0024] Compared with the existing technology, the beneficial effects of the present invention are:

[0025] In terms of ensuring flight safety, the system can monitor bird behavior in real time, generate targeted acoustic interference strategies through precise analysis, effectively disperse birds near the airport, greatly reduce the probability of bird strikes, provide a safer and more reliable environment for air transportation, and reduce the huge economic losses and casualties caused by bird strikes.

[0026] For agricultural production, the system can flexibly adjust its acoustic interference strategy based on the different crop growth cycles and bird foraging habits, precisely repelling birds that peck at crops, preventing crop damage and improving crop yield and quality. Furthermore, using acoustic interference instead of traditional pesticides to repel birds reduces environmental pollution, protects ecological balance, and promotes sustainable agricultural development.

[0027] In terms of power facility protection, the system can promptly detect birds approaching power facilities and quickly emit appropriate sound waves for interference, preventing birds from nesting and staying near power facilities, reducing the incidence of line failures, ensuring the stable operation of the power system, reducing power outages caused by bird activities, and providing a stable power supply for industrial production and residents' lives.

[0028] Furthermore, the system is highly intelligent and adaptable. It automatically adjusts acoustic parameters and jamming strategies based on varying environmental conditions and changes in bird behavior, preventing birds from adapting and ensuring long-term, effective jamming. Furthermore, the system utilizes multimodal monitoring and advanced data analysis technologies, resulting in high-precision monitoring and accurate analysis, providing comprehensive, real-time insights into bird activity. Furthermore, the system's distributed ad hoc networking and remote collaborative management capabilities facilitate installation, maintenance, and management, reducing operational costs and labor investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1This is a schematic block diagram of the sound wave interference system based on bird behavior analysis proposed by the present invention;

[0030] Figure 2 A histogram showing the response intensity of different birds to specific sound wave frequencies in the sound wave jamming system based on bird behavior analysis proposed in the present invention;

[0031] Figure 3 This is a line graph showing the change in bird repellent effect over time under different application scenarios of the acoustic interference system based on bird behavior analysis proposed in the present invention;

[0032] Figure 4 A pie chart comparing the sound wave propagation attenuation coefficients under different environmental factors of the sound wave jamming system based on bird behavior analysis proposed in the present invention;

[0033] Figure 5 This is a radar chart comparing the stability of bird group behavior before and after interference by the sound wave interference system based on bird behavior analysis proposed by the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0035] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0036] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below with reference to the accompanying drawings.

[0037] Reference Figures 1 to 5 :A sound wave jamming system based on bird behavior analysis, including the following modules:

[0038] The multimodal ultra-high-definition bird behavior monitoring module comprises a comprehensive monitoring network consisting of ultra-high-definition cameras, 3D lidar, microphone arrays, and thermal imaging sensors. The ultra-high-definition cameras, equipped with zoom and anti-shake capabilities, are installed at a commanding height within the target area. The captured video is processed by an advanced image recognition algorithm. This algorithm utilizes deep learning technology, trained on a large number of samples of bird feather textures and body morphology, enabling precise identification of bird species. For example, within the airport perimeter, it can accurately distinguish between common birds such as sparrows and magpies. The 3D lidar emits a laser beam at a fixed frequency into the surrounding space, collecting thousands of point cloud data per second. Through analysis and processing of this data, it can track the three-dimensional spatial coordinates of birds in real time with sub-meter accuracy, precisely measuring their flight paths, speed, acceleration, and posture changes. Microphone arrays, distributed across the target area, utilize sound localization algorithms to locate bird calls with an accuracy of less than one meter, while also capturing multi-dimensional audio features such as the frequency spectrum, intensity, and rhythm of the sounds. Thermal imaging sensors operate at night or in low-visibility environments, exploiting the difference between a bird's body temperature and the ambient temperature to continuously monitor bird activity. The data collected by all monitoring devices will undergo preliminary feature extraction and cache to provide a basis for subsequent analysis.

[0039] Deep spatiotemporal correlation behavior data analysis module: Use a hybrid deep learning architecture that combines spatiotemporal convolutional networks (STCN) and long short-term memory networks (LSTM) to conduct in-depth analysis of multi-source data obtained by the monitoring module. STCN can effectively extract the characteristics of bird behavior in the spatial dimension, capture the positional relationships between birds, and group distribution patterns; LSTM focuses on processing time series data and learning the temporal evolution of bird behavior. By constructing a bird behavior knowledge base and using knowledge graph technology to associate different bird behavior characteristics, habits, and environmental factors, accurate classification and prediction of bird behavior can be achieved. Based on historical and real-time data, the Monte Carlo tree search algorithm is used to predict future bird behavior trends, presenting a variety of possible behaviors in the form of probability distribution. The formula is , where P(B t+n |B1:B t ) is the probability of predicting the behavior at time t+n based on the behavior before time t, S i are different behavioral states, and N is the total number of states. For example, based on the flight trajectories and aggregation situations of birds in different time periods, its possible flight direction and stopover location in the next time period can be predicted.

[0040] Intelligent adaptive sound wave strategy generation module: Based on the results of behavioral data analysis, combined with the bird auditory physiological model and evolutionary game theory, a personalized sound wave interference strategy is generated. In view of the differences in sensitivity of different birds to sound frequency, intensity, and rhythm, the optimized particle swarm algorithm is used to search for the optimal combination of sound wave parameters. For example, for granivorous birds, the high-frequency and rapid calls of birds of prey are simulated, and the masking effect of environmental noise is combined to adjust the sound wave intensity and frequency modulation method to achieve the best interference effect with minimal energy consumption. Taking into account the possible adaptability of birds, a dynamic strategy adjustment mechanism is introduced. Based on the reinforcement learning algorithm, the sound wave strategy is continuously optimized according to the feedback of the interference effect. The formula is A t+1 =f(A t ,R t ), where A t+1 is the sonic strategy at time t+1, A t is the strategy at time t, R t is the interference effect feedback at time t, and f is the strategy update function. At the same time, based on the behavioral characteristics of bird flocks, a coordinated sound wave strategy for dispersing or guiding the flock is generated, taking into account the phase and amplitude relationships between sound waves to avoid mutual cancellation of interference signals.

[0041] The multi-beam directional, adjustable acoustic transmitter module consists of multiple intelligent acoustic transmitters with multi-beam transmission capabilities, distributed across the target area. Each transmitter can independently control the direction, frequency, intensity, and phase of multiple transmission beams. Utilizing phased array technology, the module achieves precise pointing and flexible scanning of acoustic beams by controlling the signal phase differences between multiple transmitters, with a pointing accuracy of up to 0.1 degrees. A beamforming algorithm dynamically adjusts the beam shape based on the location and distribution of birds, concentrating acoustic energy on the target area and improving acoustic propagation efficiency and jamming effectiveness. For example, for flocks of birds, circular or fan-shaped beams are generated to cover the area. For flocks in flight, tracking directional beams are emitted for continuous jamming. The transmitter supports multiple acoustic modes, including frequency modulation, amplitude modulation, and pulse modulation, and can generate complex acoustic waveforms based on jamming strategies. It also features wideband transmission capabilities, covering the 20Hz-20kHz frequency band, which is sensitive to bird hearing.

[0042] Closed-Loop Feedback Intelligent Optimization Module: This module establishes a real-time feedback mechanism, utilizing a monitoring module to continuously collect various behavioral data on birds after acoustic interference. This includes key information such as flight trajectories, changes in roosting locations, and variations in song sounds. To evaluate the effectiveness of the interference, the module innovatively combines entropy weighting with gray correlation analysis. The entropy weighting method, based on the principle of information entropy, weights various bird behavioral indicators, assigning higher weights to indicators with high variability, such as flight altitude changes. Gray correlation analysis further explores the correlations and degree of change between bird behavioral patterns and flock stability before and after the interference, further granularly examining behavioral patterns such as foraging and migration, as well as stability indicators such as flock aggregation and dispersion. If the interference effect fails to meet expectations, a Bayesian optimization algorithm is swiftly activated. Based on Bayes' theorem, this algorithm efficiently searches through parameter space and rapidly adjusts strategy parameters such as sound frequency, intensity, and transmission duration. Furthermore, the expert system, drawing on knowledge from multiple fields, including ornithology and acoustics, comprehensively analyzes the causes of interference failure, such as the obstruction of sound propagation by industrial and traffic noise within the ambient noise, and the adaptive changes that birds undergo after repeated interference exposure. Based on these analyses, a strong decision-making basis is provided for strategy optimization, helping the system to continuously improve adaptability and interference effectiveness in different bird species, environments and behavioral scenarios, and accurately regulate bird behavior.

[0043] The present invention also includes an environmental perception and compensation submodule, which uses a micro-weather station, terrain radar, and environmental noise sensor to monitor the target area's meteorological parameters (wind speed, wind direction, temperature, humidity, air pressure), topography, and environmental noise spectrum in real time. By constructing a physical model of sound wave propagation and combining it with a ray tracing algorithm, the sound wave propagation path and attenuation characteristics under different environmental conditions are simulated. The formula is I(d) = I0e -αd, where I(d) is the sound wave intensity at a distance d from the sound source, I0 is the initial sound source intensity, and α is the attenuation coefficient related to the environment. Based on the simulation results, the acoustic emission parameters are automatically adjusted to compensate for the impact of environmental factors on sound wave propagation, ensuring the effective intensity and coverage of the interference sound wave in the target area.

[0044] The present invention also includes a bird ecological protection assessment submodule, which uses an ecological footprint analysis algorithm to carefully consider the resource occupation of bird survival, and at the same time uses a biodiversity indicator calculation method to accurately measure the richness and uniformity of bird species in the region. By deeply integrating bird behavior data, such as bird migration routes and foraging preferences, and regional ecosystem information, including vegetation distribution and water source location, a comprehensive assessment of the potential impact of sound wave interference on bird ecology and regional ecological balance is made. The constructed ecological impact assessment model is extremely sophisticated. It can accurately predict the dynamic changes in bird habitat selection under different interference strategies, such as whether certain sensitive birds will abandon their original habitats due to sound wave interference. At the same time, it can also estimate the trend of population changes and determine whether interference will lead to a decrease in bird reproduction rate or an increase in mortality rate. In addition, the model also focuses on changes in ecosystem service functions, such as whether functions such as bird seed dispersal and pest control are affected. These prediction results provide strict ecological protection constraints for optimizing sound wave interference strategies, helping to achieve a perfect balance between bird repellent needs and ecological protection.

[0045] The multimodal ultra-high-definition bird behavior monitoring module in this invention utilizes distributed self-organizing networking technology, enabling each monitoring device to demonstrate powerful autonomous collaboration capabilities. Each monitoring device acts as an intelligent entity, rapidly and automatically discovering surrounding nodes in a wireless communication environment and rapidly establishing a stable network connection through sophisticated algorithms. When environmental factors change, such as signal obstruction or node failure, adaptive routing adjustments are immediately activated, automatically finding the optimal data transmission path. This ensures real-time and reliable transmission of bird behavior data in complex environments, ensuring no critical information is missed. Regarding energy supply, the module utilizes low-power hardware design, minimizing energy consumption from chip selection to circuit layout. Furthermore, energy harvesting technologies are actively incorporated, such as solar panels that fully utilize sunlight to convert it into electricity, and vibration energy harvesting devices that convert subtle environmental vibrations into usable energy for the device. These measures not only reduce system maintenance costs but also reduce reliance on traditional energy sources, enabling more sustainable and stable monitoring operations.

[0046] In this paper, the deep spatiotemporal correlation behavior data analysis module incorporates transfer learning technology, leveraging bird behavior data and model parameters accumulated from other regions or similar ecological environments to accelerate local model training and optimization, improving the model's adaptability to new environments and new bird species. Furthermore, combined with a federated learning algorithm, this module enables joint analysis of data from multiple regions while protecting data privacy, expanding the bird behavior knowledge base and improving the accuracy of behavioral analysis and prediction.

[0047] In the present invention, the intelligent adaptive sound wave strategy generation module is combined with the theory of emotional computing. By conducting an in-depth analysis of the bird calls, it accurately identifies the emotional characteristics such as fear, vigilance, and pleasure, and then generates sound wave signals with specific emotion-inducing effects, which greatly enhances the interference effect on birds. Taking the simulated calls of birds in distress as an example, the realistic sound effects can quickly trigger a panic response in the flock of birds, effectively prompting them to fly away from the target area quickly. In addition, the module uses the powerful generation capability of the generative adversarial network (GAN) to continuously produce diversified sound wave waveforms, cleverly avoiding the adaptability of birds due to long-term exposure to a single waveform, and comprehensively improving the effectiveness of the bird-repelling strategy.

[0048] In this invention, the multi-beam directional adjustable sound wave emission module uses quantum dot light-emitting diode (QLED) technology to realize sound wave visualization. When emitting sound waves of a specific frequency, the sound waves and the QLED material will produce a wonderful interaction, thereby presenting a visual light and shadow effect. Operators can intuitively see the direction of sound wave propagation and clearly grasp the intensity distribution, which greatly facilitates the monitoring and debugging of the equipment. In addition, the module introduces an advanced artificial intelligence-assisted control interface that supports gesture recognition and voice command operation, allowing operators to quickly and conveniently adjust the sound wave emission parameters through simple gestures or spoken commands, greatly improving operational efficiency.

[0049] In the present invention, the closed-loop feedback intelligent optimization module uses blockchain technology to build a distributed ledger. From the bird behavior data collected by the monitoring module, to the accurate results obtained from the behavior analysis, to the formulated sound wave strategy and interference effect feedback, the entire process data of the system operation is recorded in detail in this ledger. The blockchain's unique encryption algorithm and consensus mechanism ensure that once these data are entered, they cannot be maliciously tampered with, and data changes in any link can be accurately traced, greatly enhancing the credibility of the data. Not only that, the module uses the powerful tool of smart contracts to automatically update system parameters. When the monitoring data shows environmental changes or new trends in bird behavior, the smart contract can automatically adjust the relevant system parameters according to preset rules without manual intervention. In terms of strategy optimization task allocation, the smart contract can reasonably allocate strategy optimization tasks based on the computing power and storage capacity of each node, ensuring the efficient operation of the entire system, comprehensively improving the system's autonomy and security, and ensuring the stable and reliable implementation of bird behavior regulation work.

[0050] The system also includes a remote collaborative management platform, which utilizes 5G communication technology to enable remote, real-time monitoring and management. The platform supports concurrent multi-user operation and includes permission management, allowing different users to view and operate system functions based on their responsibilities. It also provides a large-screen data visualization display, presenting bird behavior distribution, acoustic interference effects, and system operating status in intuitive charts and maps to assist management decision-making. Furthermore, it features remote diagnosis and fault warning capabilities, enabling early detection of potential system failures through data analysis and prompt delivery of repair recommendations.

[0051] In the present invention, in the multi-beam directional adjustable sound wave transmitting module, nanomaterials are used to manufacture the sound wave transmitting diaphragm, giving full play to the unique advantages of nanomaterials in terms of high toughness and low mass. The high toughness enables the diaphragm to withstand high-intensity vibrations without being easily damaged during the sound wave transmission process, and the low mass reduces the inertia of the diaphragm, allowing it to respond to electrical signals more quickly, thereby significantly improving the efficiency of sound wave transmission and greatly broadening the frequency response range, covering a wide frequency band from low frequency to high frequency, meeting the needs of different bird-repelling scenarios. At the same time, to further improve the performance of the system, a metamaterial coating with sound insulation and noise reduction functions is carefully coated on the surface of the diaphragm. This coating can effectively block the excess noise generated inside the transmitter from propagating outward, reduce interference with the target sound waves, ensure that the emitted sound waves are pure and accurate, and comprehensively optimize the overall performance of the system.

[0052] The above are only preferred specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solutions and inventive concepts of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A sound wave jamming system based on bird behavior analysis, characterized in that: Includes the following modules: Multimodal ultra-high-definition bird behavior monitoring module: Monitoring equipment is deployed in the target area to form a monitoring network. Cameras use advanced image recognition algorithms to identify birds, 3D lidar tracks bird coordinates, and microphone arrays combined with sound localization algorithms locate bird calls and collect characteristics. A new thermal imaging sensor is added to monitor bird activity in low-visibility environments. Deep spatiotemporal correlation behavior data analysis module: This module uses a hybrid deep learning architecture of spatiotemporal convolution and long short-term memory networks to analyze multi-source data from the monitoring module, build a bird behavior knowledge base, and use knowledge graph technology to classify and predict bird behavior. Intelligent adaptive sound wave strategy generation module: Based on the results of behavioral data analysis, the sound wave interference strategy is generated by combining the bird auditory physiological model and evolutionary game theory, and the optimized particle swarm algorithm is used to search for sound wave parameter combinations; based on the reinforcement learning algorithm, the sound wave strategy is optimized according to the interference effect feedback. The formula is A t+1 =f(A t , R t ), where A t+1 is the strategy at time t+1, A t is the strategy at time t, R t is the interference effect feedback at time t, f is the update function, and at the same time, the cooperative sound wave strategy is generated according to the behavioral characteristics of the bird group; Multi-beam directional adjustable acoustic wave transmitter module: It is composed of intelligent acoustic wave transmitters distributed in the target area. It uses phased array technology to achieve beam pointing and scanning by controlling the signal phase difference. The beamforming algorithm adjusts the beam shape according to the bird's position to concentrate the acoustic wave energy. The transmitter generates the acoustic wave waveform according to the interference strategy. Closed-loop feedback intelligent optimization module: Build a real-time feedback mechanism, use the monitoring module to collect bird behavior data after interference, compare and analyze it with expectations, use the entropy weight method combined with grey correlation analysis to evaluate the effect, and when the interference effect does not meet expectations, use the Bayesian optimization algorithm to adjust the sound wave strategy parameters, and combine the expert system to analyze the cause of failure.

2. The sound wave interference system based on bird behavior analysis according to claim 1 is characterized in that: It also includes an environmental perception and compensation submodule, which uses a micro-weather station, terrain radar, and environmental noise sensor to monitor the meteorological parameters, topography, and environmental noise spectrum of the target area in real time. By building a physical model of sound wave propagation and combining it with a ray tracing algorithm, it simulates the sound wave propagation path and attenuation characteristics under different environmental conditions. The formula is I(d) = I0e -αd , where I(d) is the sound wave intensity at a distance d from the sound source, I0 is the initial intensity of the sound source, and α is the attenuation coefficient. The sound wave emission parameters are adjusted according to the simulation results.

3. The sound wave interference system based on bird behavior analysis according to claim 1 is characterized in that: It also includes a bird ecological protection assessment sub-module, which uses ecological footprint analysis and biodiversity indicator calculation methods, combined with bird behavior data and regional ecosystem information, to evaluate the impact of sound wave interference on the ecological balance of bird areas. By constructing an ecological impact assessment model, it predicts bird habitat selection, population changes and ecosystem service function changes under different interference strategies.

4. The sound wave interference system based on bird behavior analysis according to claim 1 is characterized in that: The multimodal ultra-high-definition bird behavior monitoring module adopts distributed self-organizing network technology. Each monitoring device self-organizes through wireless communication to form a stable network. It has the functions of automatic node discovery and adaptive routing adjustment. At the same time, it adopts low-power hardware design and energy harvesting technology to reduce system maintenance costs and energy dependence.

5. The sound wave interference system based on bird behavior analysis according to claim 1 is characterized in that: The deep spatiotemporal correlation behavior data analysis module uses the Monte Carlo tree search algorithm to predict the future behavior trends of birds. The formula is Where P(B t+n |B1:B t ) is the probability of predicting the behavior at time t+n based on the behavior before time t, S i represents different behavioral states, and N is the total number of states. Transfer learning technology is introduced to optimize the local model using bird behavior data and model parameters in other regions. At the same time, combined with the federated learning algorithm, multi-regional data joint analysis is achieved under the premise of protecting data privacy, thereby expanding the bird behavior knowledge base.

6. The sound wave interference system based on bird behavior analysis according to claim 1 is characterized in that: The intelligent adaptive sound wave strategy generation module combines the theory of affective computing to analyze the emotional characteristics of bird calls, generate sound wave signals with emotion-inducing effects, enhance the interference effect, and at the same time, use generative adversarial networks to generate diverse sound wave waveforms.

7. The sound wave interference system based on bird behavior analysis according to claim 1 is characterized in that: The multi-beam directional adjustable sound wave emission module uses quantum dot light-emitting diode technology to achieve sound wave visualization. By emitting sound waves of a specific frequency and interacting with QLED materials, it produces visual light and shadow effects. At the same time, it introduces an artificial intelligence-assisted control interface to adjust the sound wave emission parameters through gesture recognition and voice commands.

8. The sound wave interference system based on bird behavior analysis according to claim 1 is characterized in that: The closed-loop feedback intelligent optimization module uses blockchain technology to build a distributed ledger to record data from the entire system operation process. Through smart contracts, it realizes automatic updates of system parameters and strategy optimization task allocation functions, thereby improving the autonomy and security of the system.

9. The sound wave interference system based on bird behavior analysis according to claim 1, characterized in that: The system also includes a remote collaborative management platform, which uses 5G communication technology to achieve remote real-time monitoring and management. The platform supports concurrent multi-user operations and has permission management functions. Different users can view and operate corresponding system functions according to their responsibilities, and provide data visualization on a large screen. At the same time, it has remote diagnosis and fault warning functions, which can detect system faults in advance through data analysis and push maintenance suggestions.

10. The sound wave interference system based on bird behavior analysis according to claim 1, characterized in that: In the multi-beam directional adjustable sound wave transmission module, nanomaterials are used to manufacture the sound wave transmission diaphragm. The characteristics of nanomaterials are utilized to improve the sound wave transmission efficiency and frequency response range. At the same time, a metamaterial coating with sound insulation and noise reduction functions is coated on the surface of the diaphragm to reduce the noise interference generated by the transmitter itself.

Images