Equipment deployment strategy optimization system and method based on artificial intelligence

Abstract

The invention discloses an equipment deployment strategy optimization system and method based on artificial intelligence, relates to the technical field of artificial intelligence, and aims to obtain position information of all bird activity monitoring equipment and determine the bird activity monitoring equipment according to the working radius of the bird activity monitoring equipment and the distance between the bird activity monitoring equipment and unit monitoring. The equipment coverage rate in the bird activity monitoring area is calculated, the coverage rate of each time is recalculated after multiple independent simulations are executed, the ratio of the standard deviation to the average value is recorded as a relative fluctuation coefficient, and an evaluation index of the total energy consumption is established; combining the equipment coverage rate, the total energy consumption and the relative fluctuation coefficient to establish an energy efficiency evaluation model of the bird activity monitoring area, based on the optimal solution of the energy efficiency evaluation model, obtaining the recommended position and the operation state of the bird activity monitoring equipment, and obtaining the actual configuration of the current unit detection period; when the difference value between the actual energy efficiency value and the maximum energy efficiency value corresponds to a threshold value, the position and the running state of the bird activity monitoring equipment are updated.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to an artificial intelligence-based system and method for optimizing device deployment strategies. Background Technology

[0002] In scenarios involving proactive prevention and control of specific biological activities, such as bird intrusion, traditional equipment deployment strategies often rely on human experience or static rule settings. These strategies struggle to dynamically respond to changes in the environment and the spatiotemporal evolution of target behavior, and lack the ability to deeply mine and quantitatively model historical behavioral data. This results in redundant equipment deployment locations, excessive energy consumption, or frequent blind spots in prevention and control.

[0003] Existing technologies typically employ simple statistical frequency or heatmap overlay methods for equipment location, failing to establish an explicit functional relationship between activity patterns and equipment performance. This results in lagging strategy adjustments and a lack of theoretical support. Furthermore, most methods neglect constraints such as equipment radius of influence, terrain obstruction, and the periodicity of activity patterns, making accurate coverage modeling impossible in complex environments. Therefore, a method for generating equipment deployment strategies that integrates spatiotemporal data analysis and automatic optimization mechanisms is needed. Summary of the Invention

[0004] The purpose of this invention is to provide an artificial intelligence-based device deployment strategy optimization system and method to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a device deployment strategy optimization method based on artificial intelligence, the method comprising: Step S1: Divide the bird activity monitoring area into several unit monitoring areas, obtain the location information of all bird activity monitoring devices, and calculate the device coverage rate in the bird activity monitoring area by combining the working radius of the bird activity monitoring devices and the distance between the bird activity monitoring devices and the unit monitoring areas. Step S2: Apply simulated offset perturbation to each bird activity monitoring device, perform several independent simulations, and recalculate the coverage rate for each simulation to obtain the average and standard deviation of the simulated coverage rate. The ratio of the standard deviation to the average is recorded as the relative fluctuation coefficient. Step S3: Obtain the operating indicators and operating status of each bird activity monitoring device, establish an evaluation index for total energy consumption, and establish an energy efficiency evaluation model for the bird activity monitoring area by combining the device coverage, total energy consumption and relative fluctuation coefficient. Based on the optimal solution of the energy efficiency evaluation model, obtain the recommended location and operating status of the bird activity monitoring devices. Step S4: Obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, and compare it with the optimized maximum energy efficiency value. When the difference between the actual energy efficiency value and the maximum energy efficiency value is within a threshold, update the position and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value.

[0006] Furthermore, step S1 includes: Step S1-1: Divide the bird activity monitoring area into N unit monitoring areas, obtain the location information of all bird activity monitoring devices in the bird activity monitoring area, and obtain the distance from the center of the i-th unit monitoring area to the m-th bird activity monitoring device, denoted as dim; Step S1-2: Obtain the working radius rm of the m-th bird activity monitoring device, calculate the ratio of dim to rm, and normalize the ratio using an exponential function to obtain the relationship coefficient fim between the i-th unit monitoring area and the m-th bird activity monitoring device. Where k1 is the proportionality constant, 0 < k1 < 1; Step S1-3: Calculate the association strength value Pi between the i-th unit monitoring area and all bird activity monitoring devices. , where M is the total number of bird activity monitoring devices; Steps S1-4: Calculate the coverage C of the bird activity monitoring area. , where AT represents the total area of ​​the bird activity monitoring area, and Ai represents the area of ​​the i-th unit monitoring area.

[0007] When dim=0, fim=1, indicating that the device is facing the center of the area and makes the greatest contribution to coverage; as the center of the area gets closer to the edge of the working device's range, the fim value decreases, reflecting the characteristic that coverage effectiveness decreases non-linearly with distance; Furthermore, since the coverage effects of each device on the same unit area are independent, the probability that the i-th unit monitoring area is not covered by any device is: Therefore, Pi represents the correlation strength value when the i-th unit monitoring area is effectively covered by at least one device.

[0008] Furthermore, step S2 includes: Step S2-1: Perform a simulated offset of the position of each bird activity monitoring device in the bird activity monitoring area by a random distance, wherein the offset distance for any bird activity monitoring device is less than or equal to one-tenth of the working radius; Step S2-2: Calculate the simulated coverage of the bird activity monitoring area after the simulated offset. After performing h simulations, aggregate all simulated coverages and calculate the mean CR and standard deviation Cstd of all simulated coverages. Step S2-3: Calculate the relative volatility coefficient η, η=Cstd / CR, and obtain the stability coefficient R, R=1-η.

[0009] To assess the impact of minor changes in equipment location on coverage, a random disturbance simulation mechanism is introduced; A Cartesian coordinate system is established within the bird activity monitoring area. Simulated coordinates are generated by perturbing the existing coordinate positions of the bird monitoring equipment. In the j-th simulation, the new position of the m-th bird monitoring equipment is... ,in This indicates the initial position of the m-th bird monitoring device. This indicates coordinate perturbation, based on which the distance between the center of the i-th unit monitoring area and the m-th bird monitoring device in the j-th simulation is recalculated. The relationship coefficient between the i-th monitoring area and the m-th bird activity monitoring device Correlation strength value and coverage ; Collect the results of h simulations and calculate the sample mean of the coverage rate. with sample standard deviation : , ; Define relative volatility coefficient The ratio of standard deviation to mean: ; Then, the stability coefficient R is defined as follows: , A larger stability coefficient R value indicates that the strategy is less sensitive to positional disturbances and has stronger robustness to surface device distribution. During implementation, a cutoff mechanism for the R value can be introduced. When R=0, it indicates that the strategy is extremely unstable.

[0010] Furthermore, step S3 includes: Step S3-1: Obtain the power of each bird activity monitoring device and normalize the power of the bird activity monitoring devices. The normalized power of the m-th bird activity monitoring device is denoted as pm. Set the indication parameter sm for the m-th bird activity monitoring device: sm=1 when the m-th bird activity monitoring device is on, and sm=0 when the m-th bird activity monitoring device is off. Calculate the total energy consumption E of the devices in the bird activity monitoring area. ; Step S3-2: Establish the energy efficiency model U of the bird activity monitoring equipment, U=ω1×C-ω2×E+ω3×R, where ω1, ω2 and ω3 represent the coefficients of coverage, total energy consumption and stability coefficient, respectively, ω1>0, ω2>0, ω3>0, ω1+ω2+ω3=1; Step S3-3: Obtain the location information and indication parameters of each bird activity monitoring device in the bird activity monitoring area. With the goal of maximizing the value of U, generate updated location information and updated indication parameters for each bird activity monitoring device. The conditions to be met in the process of calculating the maximum value of U are: the number of bird activity monitoring devices is less than or equal to M, the distance between any two bird activity monitoring devices is greater than the distance threshold Dmin, the location of each bird activity monitoring device is within the bird activity monitoring area, and the set of values ​​for the indication parameters of the bird activity monitoring devices is {0,1}.

[0011] The coordinates of all bird activity monitoring devices are collected to obtain the set of bird activity monitoring device locations B, B = (b1, b2, b3, ..., bk), where b1, b2, b3, ..., bk represent the coordinates of the 1st, 2nd, 3rd, ..., and kth bird activity monitoring devices, respectively. For example, the coordinates of the kth bird activity monitoring device include the abscissa and ordinate of the monitoring device in the Cartesian coordinate system. In the energy efficiency model U, the location of the bird activity monitoring equipment affects the coverage of the bird detection area, and the on / off status of the bird activity monitoring equipment affects the total energy consumption. Therefore, it is necessary to solve for the maximum value of U by using the location information and status information of the bird activity monitoring equipment. Further obtain the on / off status of the bird activity monitoring equipment to obtain the working state vector V, V=(s1,s2,s3,...,sk), where s1,s2,s3,... and sk represent the indication parameters of the 1st, 2nd, 3rd,... and kth bird activity monitoring equipment, respectively. The indication parameters indicate the on / off status, and the set of values ​​for the indication parameters of any bird activity monitoring equipment is {0,1}. Constraints for constructing energy efficiency model U: k≤M, where M is the total number of bird activity monitoring devices; , bi∈B, bj∈B, and bi≠bj; A multi-objective genetic algorithm is used to solve the above multi-objective problem; Construct a chromosome with a coding length of 3k. The first 2k codes include the planar abscissa and ordinate of k bird activity monitoring devices, and the last k codes are the working status vectors of k bird activity monitoring devices. Randomly generate an initial population of size Q=100; Calculate the energy efficiency assessment value for the status of bird activity monitoring equipment corresponding to each individual chromosome; Offspring are generated by simulating binary crossover and polynomial mutation; The parent and offspring populations are merged, resulting in a total of 2Q individuals. A rapid non-dominated sorting is performed, and Q individuals are selected to enter the next generation based on frontier level and crowding. The optimization result is output after the maximum number of iterations.

[0012] Furthermore, step S4 includes: Step S4-1: Set the unit detection cycle. Based on the operation records, location information and indication parameters of each bird activity monitoring device in the bird activity monitoring area in the current unit detection cycle, calculate the actual energy efficiency value Ureal according to the energy efficiency model. Step S4-2: Generate the maximum energy efficiency prediction value Upre based on the location information and indication parameters in the current unit detection cycle, as well as the updated location information and updated indication parameters corresponding to the maximum energy efficiency prediction value; Step S4-3: When If the location information and indication parameters of the bird activity monitoring equipment remain unchanged in the next unit detection cycle, then the location information and indication parameters of the bird activity monitoring equipment in the next unit detection cycle will be adjusted to update the location information and update the indication parameters. τ represents the resolution threshold, and the condition 0 < τ < 0.5 must be met.

[0013] By introducing a sliding time window mechanism, new activity data is continuously incorporated, and the deployment strategy is re-optimized every unit detection cycle. When the difference in effectiveness between the new and old solutions exceeds a threshold, the system automatically switches. For example, when bird activity patterns shift from the "east side of the runway" to the "north side of the terminal" due to seasonal changes, the system can promptly adjust equipment positions and operating status to avoid effectiveness degradation caused by "outdated deployment strategies."

[0014] To better implement the above methods, an AI-based device deployment strategy optimization system is also proposed. The system includes: a device coverage management module, a disturbance analysis module, an energy efficiency assessment module, and a strategy optimization module. The equipment coverage management module is used to obtain the location information of bird activity monitoring equipment, and calculate the equipment coverage in the bird activity monitoring area by combining the working radius of the bird activity monitoring equipment and the distance between the bird activity monitoring equipment and the unit monitoring area. The disturbance analysis module is used to apply simulated offset disturbance to each bird activity monitoring equipment, and recalculate the coverage for each simulation after performing several independent simulations. The ratio of the standard deviation to the mean is recorded as the relative fluctuation coefficient. The energy efficiency assessment module is used to obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, compare it with the optimized maximum energy efficiency value, and update the location and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value; the strategy optimization module is used to obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, compare it with the optimized maximum energy efficiency value, and update the location and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value.

[0015] Furthermore, the equipment coverage management module includes: a unit area management unit, a relationship coefficient management unit, a correlation strength value management unit, and a coverage management unit; the unit area management unit is used to manage unit monitoring areas within the bird activity monitoring area; the relationship coefficient management unit is used to obtain the working radius of the bird activity monitoring equipment and the distance from the center of the unit monitoring area to the bird activity monitoring equipment, and calculate the relationship coefficient; the correlation strength value management unit is used to calculate the correlation strength value between each unit monitoring area and all bird activity monitoring equipment; and the coverage management unit is used to calculate the coverage of the bird activity monitoring area. Furthermore, the disturbance analysis module includes: a simulated disturbance unit and a relative fluctuation coefficient management unit; the simulated disturbance unit is used to apply simulated offset disturbances to each bird activity monitoring device, and the relative fluctuation coefficient management unit is used to acquire data from the disturbance records and calculate the relative fluctuation coefficient based on the average and standard deviation of the simulated coverage of the simulated data. Furthermore, the energy efficiency assessment module includes: an energy consumption management unit, an energy efficiency model management unit, and an optimization management unit; the energy consumption management unit is used to acquire the energy consumption and working status of the bird activity monitoring equipment and calculate the total energy consumption of the equipment in the bird activity monitoring area; the energy efficiency model management unit is used to manage the energy efficiency model; and the optimization management unit is used to output the optimal solution for the energy efficiency model based on relevant conditions. Furthermore, the strategy optimization module includes a state management unit and a strategy suggestion unit. The state management unit is used to calculate the actual energy efficiency value and the maximum energy efficiency prediction value in each unit detection cycle according to the energy efficiency model. The strategy suggestion unit is used to output the corresponding strategy optimization results according to the strategy optimization conditions.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. By using a multi-objective optimization model and constraint design, while ensuring coverage, we strictly control the cost of equipment and total energy consumption. At the same time, we avoid signal interference and functional redundancy by using minimum distance constraints between equipment. We achieve the best overall benefits with the least resource investment and reduce ineffective investment and equipment redundancy. 2. Introducing robustness indicators and Monte Carlo simulations ensures that the solution maintains stable performance even under random disturbances such as equipment location shifts. At the same time, constraints such as installable area and equipment spacing mitigate implementation risks from the outset, reduce the cost of frequent adjustments by maintenance personnel, and ensure long-term stable operation of the solution. 3. Through mathematical modeling and algorithmic implementation, a three-in-one optimization framework integrating coverage, energy consumption, and stability was constructed. Coverage and stability were quantified, and an energy efficiency objective function was used to ensure the deployment strategy possesses physical realism, robustness, and engineering feasibility. The overall solution improves the ability to perceive and automatically match scenes during bird monitoring. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the structure of an artificial intelligence-based device deployment strategy optimization system according to the present invention; Figure 2 This is a flowchart illustrating an artificial intelligence-based device deployment strategy optimization method according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example: Figures 1-2 As shown, the present invention provides a technical solution: a device deployment strategy optimization system and method based on artificial intelligence.

[0020] The methods include: Step S1: Divide the bird activity monitoring area into several unit monitoring areas, obtain the location information of all bird activity monitoring devices, and calculate the device coverage rate in the bird activity monitoring area by combining the working radius of the bird activity monitoring devices and the distance between the bird activity monitoring devices and the unit monitoring areas. Step S1 includes: Step S1-1: Divide the bird activity monitoring area into N unit monitoring areas, obtain the location information of all bird activity monitoring devices in the bird activity monitoring area, and obtain the distance from the center of the i-th unit monitoring area to the m-th bird activity monitoring device, denoted as dim; Step S1-2: Obtain the working radius rm of the m-th bird activity monitoring device, calculate the ratio of dim to rm, and normalize the ratio using an exponential function to obtain the relationship coefficient fim between the i-th unit monitoring area and the m-th bird activity monitoring device. Where k1 is the proportionality constant, 0 < k1 < 1; Step S1-3: Calculate the association strength value Pi between the i-th unit monitoring area and all bird activity monitoring devices. , where M is the total number of bird activity monitoring devices; Steps S1-4: Calculate the coverage C of the bird activity monitoring area. , where AT represents the total area of ​​the bird activity monitoring area, and Ai represents the area of ​​the i-th unit monitoring area.

[0021] Step S2: Apply simulated offset perturbation to each bird activity monitoring device, perform several independent simulations, and recalculate the coverage rate for each simulation to obtain the average and standard deviation of the simulated coverage rate. The ratio of the standard deviation to the average is recorded as the relative fluctuation coefficient. Step S2 includes: Step S2-1: Perform a simulated offset of the position of each bird activity monitoring device in the bird activity monitoring area by a random distance, wherein the offset distance for any bird activity monitoring device is less than or equal to one-tenth of the working radius; Step S2-2: Calculate the simulated coverage of the bird activity monitoring area after the simulated offset. After performing h simulations, aggregate all simulated coverages and calculate the mean CR and standard deviation Cstd of all simulated coverages. Step S2-3: Calculate the relative volatility coefficient η, η=Cstd / CR, and obtain the stability coefficient R, R=1-η.

[0022] Step S3: Obtain the operating indicators and operating status of each bird activity monitoring device, establish an evaluation index for total energy consumption, and establish an energy efficiency evaluation model for the bird activity monitoring area by combining the device coverage, total energy consumption and relative fluctuation coefficient. Based on the optimal solution of the energy efficiency evaluation model, obtain the recommended location and operating status of the bird activity monitoring devices. Step S3 includes: Step S3-1: Obtain the power of each bird activity monitoring device and normalize the power of the bird activity monitoring devices. The normalized power of the m-th bird activity monitoring device is denoted as pm. Set the indication parameter sm for the m-th bird activity monitoring device: sm=1 when the m-th bird activity monitoring device is on, and sm=0 when the m-th bird activity monitoring device is off. Calculate the total energy consumption E of the devices in the bird activity monitoring area. ; Step S3-2: Establish the energy efficiency model U of the bird activity monitoring equipment, U=ω1×C-ω2×E+ω3×R, where ω1, ω2 and ω3 represent the coefficients of coverage, total energy consumption and stability coefficient, respectively, ω1>0, ω2>0, ω3>0, ω1+ω2+ω3=1; Step S3-3: Obtain the location information and indication parameters of each bird activity monitoring device in the bird activity monitoring area. With the goal of maximizing the value of U, generate updated location information and updated indication parameters for each bird activity monitoring device. The conditions to be met in the process of calculating the maximum value of U are: the number of bird activity monitoring devices is less than or equal to M, the distance between any two bird activity monitoring devices is greater than the distance threshold Dmin, the location of each bird activity monitoring device is in the bird activity monitoring area, and the set of values ​​for the indication parameters of the bird activity monitoring devices is {0,1}. Step S4: Obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, and compare it with the optimized maximum energy efficiency value. When the difference between the actual energy efficiency value and the maximum energy efficiency value is within a threshold, update the position and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value. Step S4 includes: Step S4-1: Set the unit detection cycle. Based on the operation records, location information and indication parameters of each bird activity monitoring device in the bird activity monitoring area in the current unit detection cycle, calculate the actual energy efficiency value Ureal according to the energy efficiency model. Step S4-2: Generate the maximum energy efficiency prediction value Upre based on the location information and indication parameters in the current unit detection cycle, as well as the updated location information and updated indication parameters corresponding to the maximum energy efficiency prediction value; Step S4-3: When If the location information and indication parameters of the bird activity monitoring equipment remain unchanged in the next unit detection cycle, then the location information and indication parameters of the bird activity monitoring equipment in the next unit detection cycle will be adjusted to update the location information and update the indication parameters. τ represents the resolution threshold, and the condition 0 < τ < 0.5 must be met.

[0023] The following implementation examples illustrate each step; Scene setup for the bird monitoring area: Monitoring area: A square with sides of 500 m, total area ; Grid division: Each unit area ; Number of devices: M=8 units, all bird monitoring devices have a working radius of 100m; Power: The rated power of the equipment is [10W, 12W, 8W, 10W, 15W, 9W, 11W, 10W]. The maximum power of 15W is used as the normalization reference standard. After normalization ; Current configuration: Enabled on all devices ( ), their positions are evenly distributed within the area; Weight: ; , , , ; Calculate coverage : Obtain the center coordinates of the i-th grid and calculate the distances to the 8 devices respectively; The distance from the center of the i-th grid to the nearest device is 40 m. but ; The area was covered by three devices. The rest are 0; but ; ; For all Summation ; Calculate stability : After 100 perturbation simulations, we obtain , ; , ; Calculate energy consumption : , Calculate energy efficiency value : ; ; Optimized prediction: It is recommended to turn off the 5th device in the bird monitoring area. The rated power of the corresponding device is 15W. After adjustment, s5=0, and fine-tune the position of other devices according to the output coordinates. New configuration: , ; ; ; Difference judgment: , The adjustment is triggered, and the new configuration will be executed in the next cycle.

[0024] The system includes: equipment coverage management module, disturbance analysis module, energy efficiency assessment module, and strategy optimization module; The equipment coverage management module is used to obtain the location information of bird activity monitoring equipment, and calculate the equipment coverage in the bird activity monitoring area by combining the working radius of the bird activity monitoring equipment and the distance between the bird activity monitoring equipment and the unit monitoring area. The equipment coverage management module includes: a unit area management unit, a relationship coefficient management unit, a correlation strength value management unit, and a coverage management unit. The unit area management unit is used to manage the unit monitoring areas in the bird activity monitoring area. The relationship coefficient management unit is used to obtain the working radius of the bird activity monitoring equipment and the distance from the center of the unit monitoring area to the bird activity monitoring equipment, and calculate the relationship coefficient. The correlation strength value management unit is used to calculate the correlation strength value between each unit monitoring area and all bird activity monitoring equipment. The coverage management unit is used to calculate the coverage of the bird activity monitoring area. The disturbance analysis module is used to apply simulated offset disturbances to each bird activity monitoring device, and after performing several independent simulations, the coverage is recalculated for each simulation. The ratio of the standard deviation to the mean is recorded as the relative fluctuation coefficient. The disturbance analysis module includes a simulated disturbance unit and a relative fluctuation coefficient management unit. The simulated disturbance unit is used to apply simulated offset disturbances to each bird activity monitoring device, and the relative fluctuation coefficient management unit is used to acquire data from the disturbance records and calculate the relative fluctuation coefficient based on the average value and standard deviation of the simulated coverage of the simulated data. The energy efficiency assessment module is used to obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, compare it with the optimized maximum energy efficiency value, and update the location and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value. The energy efficiency assessment module includes an energy consumption management unit, an energy efficiency model management unit, and an optimization management unit. The energy consumption management unit is used to obtain the energy consumption and working status of the bird activity monitoring equipment and calculate the total energy consumption of the equipment in the bird activity monitoring area. The energy efficiency model management unit is used to manage the energy efficiency model. The optimization management unit is used to output the optimal solution for the energy efficiency model based on relevant conditions. The strategy optimization module is used to obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, compare it with the optimized maximum energy efficiency value, and update the position and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value. The strategy optimization module includes a state management unit and a strategy suggestion unit. The state management unit is used to calculate the actual energy efficiency value and the maximum predicted energy efficiency value in each unit detection cycle according to the energy efficiency model. The strategy suggestion unit is used to output the corresponding strategy optimization results according to the strategy optimization conditions.

[0025] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for optimizing device deployment strategies based on artificial intelligence, characterized in that: The method includes the following steps: Step S1: Divide the bird activity monitoring area into several unit monitoring areas, obtain the location information of all bird activity monitoring devices, and calculate the device coverage rate in the bird activity monitoring area by combining the working radius of the bird activity monitoring devices and the distance between the bird activity monitoring devices and the unit monitoring areas. Step S2: Apply simulated offset perturbation to each bird activity monitoring device, perform several independent simulations, and recalculate the coverage rate for each simulation to obtain the average and standard deviation of the simulated coverage rate. The ratio of the standard deviation to the average is recorded as the relative fluctuation coefficient. Step S3: Obtain the operating indicators and operating status of each bird activity monitoring device, establish an evaluation index for total energy consumption, and establish an energy efficiency evaluation model for the bird activity monitoring area by combining the device coverage, total energy consumption and relative fluctuation coefficient. Based on the optimal solution of the energy efficiency evaluation model, obtain the recommended location and operating status of the bird activity monitoring devices. Step S4: Obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, and compare it with the optimized maximum energy efficiency value. When the difference between the actual energy efficiency value and the maximum energy efficiency value is within a threshold, update the position and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value.

2. The method for optimizing device deployment strategy based on artificial intelligence according to claim 1, characterized in that: Step S1 includes: Step S1-1: Divide the bird activity monitoring area into N unit monitoring areas, obtain the location information of all bird activity monitoring devices in the bird activity monitoring area, and obtain the distance from the center of the i-th unit monitoring area to the m-th bird activity monitoring device, denoted as dim; Step S1-2: Obtain the working radius rm of the m-th bird activity monitoring device, calculate the ratio of dim to rm, and normalize the ratio using an exponential function to obtain the relationship coefficient fim between the i-th unit monitoring area and the m-th bird activity monitoring device; Where k1 is the proportionality constant, 0 < k1 < 1; Step S1-3: Calculate the association strength value Pi between the i-th unit monitoring area and all bird activity monitoring devices. , where M is the total number of bird activity monitoring devices; Steps S1-4: Calculate the coverage C of the bird activity monitoring area. , where AT represents the total area of ​​the bird activity monitoring area, and Ai represents the area of ​​the i-th unit monitoring area.

3. The method for optimizing device deployment strategy based on artificial intelligence according to claim 2, characterized in that: Step S2 includes: Step S2-1: Perform a simulated offset of the position of each bird activity monitoring device in the bird activity monitoring area by a random distance, wherein the offset distance for any bird activity monitoring device is less than or equal to one-tenth of the working radius; Step S2-2: Calculate the simulated coverage of the bird activity monitoring area after the simulated offset. After performing h simulations, aggregate all simulated coverages and calculate the mean CR and standard deviation Cstd of all simulated coverages. Step S2-3: Calculate the relative volatility coefficient η, η=Cstd / CR, and obtain the stability coefficient R, R=1-η.

4. The method for optimizing device deployment strategy based on artificial intelligence according to claim 3, characterized in that: Step S3 includes: Step S3-1: Obtain the power of each bird activity monitoring device and normalize the power of the bird activity monitoring devices. The normalized power of the m-th bird activity monitoring device is denoted as pm. Set the indication parameter sm for the m-th bird activity monitoring device: sm=1 when the m-th bird activity monitoring device is on, and sm=0 when the m-th bird activity monitoring device is off. Calculate the total energy consumption E of the devices in the bird activity monitoring area. ; Step S3-2: Establish the energy efficiency model U of the bird activity monitoring equipment; U = ω1 × C - ω2 × E + ω3 × R, where ω1, ω2 and ω3 represent the coefficients of coverage, total energy consumption and stability coefficient, respectively, ω1 > 0, ω2 > 0, ω3 > 0, ω1 + ω2 + ω3 = 1; Step S3-3: Obtain the location information and indication parameters of each bird activity monitoring device in the bird activity monitoring area. With the goal of maximizing the value of U, generate updated location information and updated indication parameters for each bird activity monitoring device. The conditions to be met in the process of calculating the maximum value of U are: the number of bird activity monitoring devices is less than or equal to M, the distance between any two bird activity monitoring devices is greater than the distance threshold Dmin, the location of each bird activity monitoring device is within the bird activity monitoring area, and the set of values ​​for the indication parameters of the bird activity monitoring devices is {0,1}.

5. The method for optimizing device deployment strategy based on artificial intelligence according to claim 4, characterized in that: Step S4 includes: Step S4-1: Set the unit detection cycle. Based on the operation records, location information and indication parameters of each bird activity monitoring device in the bird activity monitoring area in the current unit detection cycle, calculate the actual energy efficiency value Ureal according to the energy efficiency model. Step S4-2: Generate the maximum energy efficiency prediction value Upre based on the location information and indication parameters in the current unit detection cycle, as well as the updated location information and updated indication parameters corresponding to the maximum energy efficiency prediction value; Step S4-3: When If the location information and indication parameters of the bird activity monitoring equipment remain unchanged in the next unit detection cycle, then the location information and indication parameters of the bird activity monitoring equipment in the next unit detection cycle will be adjusted to update the location information and update the indication parameters. τ represents the resolution threshold, and the condition 0 < τ < 0.5 must be met.

6. An AI-based device deployment strategy optimization system, used to execute the AI-based device deployment strategy optimization method according to any one of claims 1-5, characterized in that: The system includes: The system includes a device coverage management module, a disturbance analysis module, an energy efficiency assessment module, and a strategy optimization module. The equipment coverage management module is used to obtain the location information of bird activity monitoring equipment, and calculate the equipment coverage in the bird activity monitoring area by combining the working radius of the bird activity monitoring equipment and the distance between the bird activity monitoring equipment and the unit monitoring area. The disturbance analysis module is used to apply simulated offset disturbances to each bird activity monitoring device, and after performing several independent simulations, the coverage is recalculated for each simulation. The ratio of the standard deviation to the mean is recorded as the relative fluctuation coefficient. The energy efficiency assessment module is used to obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, compare it with the optimized maximum energy efficiency value, and update the location and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value. The strategy optimization module is used to obtain the actual configuration of the current unit detection cycle, calculate the actual energy efficiency value, compare it with the optimized maximum energy efficiency value, and update the location and operating status of the bird activity monitoring equipment to match the maximum energy efficiency value.

7. The device deployment strategy optimization system based on artificial intelligence according to claim 6, characterized in that: The equipment coverage management module includes: a unit area management unit, a relationship coefficient management unit, a correlation strength value management unit, and a coverage management unit; The unit area management unit is used to manage the unit monitoring areas in the bird activity monitoring area. The relationship coefficient management unit is used to obtain the working radius of the bird activity monitoring equipment and the distance from the center of the unit monitoring area to the bird activity monitoring equipment, and calculate the relationship coefficient. The association strength value management unit is used to calculate the association strength value between each unit monitoring area and all bird activity monitoring equipment. The coverage management unit is used to calculate the coverage of the bird activity monitoring area.

8. The device deployment strategy optimization system based on artificial intelligence according to claim 6, characterized in that: The disturbance analysis module includes: a simulated disturbance unit and a relative fluctuation coefficient management unit; The simulated disturbance unit is used to apply simulated offset disturbances to each bird activity monitoring device, and the relative fluctuation coefficient management unit is used to acquire data from the disturbance records and calculate the relative fluctuation coefficient based on the average and standard deviation of the simulated coverage of the simulated data.

9. The device deployment strategy optimization system based on artificial intelligence according to claim 6, characterized in that: The energy efficiency assessment module includes: an energy consumption management unit, an energy efficiency model management unit, and an optimization management unit; The energy consumption management unit is used to acquire the energy consumption and working status of the bird activity monitoring equipment and calculate the total energy consumption of the equipment in the bird activity monitoring area. The energy efficiency model management unit is used to manage the energy efficiency model, and the optimization management unit is used to output the optimal solution of the energy efficiency model based on relevant conditions.

10. The device deployment strategy optimization system based on artificial intelligence according to claim 6, characterized in that: The strategy optimization module includes: a status management unit and a strategy suggestion unit; The state management unit is used to calculate the actual energy efficiency value and the maximum energy efficiency prediction value in each unit detection cycle according to the energy efficiency model, and the strategy suggestion unit is used to output the corresponding strategy optimization results according to the strategy optimization conditions.

Images