Method for optimally arranging low-altitude aircrafts on expressway

Abstract

The invention relates to the technical field of aircraft optimization, and discloses an expressway low-altitude aircraft optimization arrangement method, which comprises the following steps: constructing an evaluation index system, determining the comprehensive weight of each evaluation index by using an analytic hierarchy process and an entropy weight method, and identifying the importance of the evaluation indexes; constructing a low-altitude aircraft optimization arrangement model, and solving by utilizing a simulated annealing algorithm to obtain static optimal quantity configuration of the low-altitude aircrafts of the service site; dynamically adjusting the static optimal number configuration of the low-altitude aircrafts of the service site by using a social emotion resonance avoidance algorithm; and according to the final number configuration of the low-altitude aircrafts of the service site, combining the social emotion data to optimize the flight path of the low-altitude aircrafts. According to the method, various complex factors are comprehensively considered, efficient arrangement and path optimization of the low-altitude aircraft are achieved, investment of the low-altitude aircraft is more global and economical, and important technical support is provided for application of the low-altitude aircraft industry.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft optimization, and in particular to a method for optimizing the arrangement of low-altitude aircraft on a highway. Background Art

[0002] As a strategic emerging economic sector, the low-altitude economy has experienced rapid growth in the past two years. By 2024, the scale of my country's low-altitude economy has exceeded 500 billion yuan. Low-altitude aircraft, such as drones and eVTOLs (electric vertical take-off and landing vehicles), are rapidly being adopted in logistics, emergency response, and passenger transport scenarios. However, lagging infrastructure has become a major bottleneck. Expressways offer natural airspace resources and ground infrastructure (such as service areas and monitoring systems), but existing technologies lack a systematic, integrated solution for aircraft takeoff and landing, route planning, and energy refueling.

[0003] Planning low-altitude flight service stations or take-off and landing hubs along highways allows the use of low-altitude aircraft for applications such as road inspections, logistics distribution, tourism, emergency rescue, and low-altitude passenger transport. However, as a new economic phenomenon, the low-altitude economy currently lacks a basic understanding of its meaning and how to develop it. In particular, the construction of low-altitude road network infrastructure requires planning based on the number of low-altitude aircraft to be deployed. However, there is no theoretical basis for how to allocate a reasonable number of low-altitude aircraft at take-off and landing hubs based on actual needs and taking into account various influencing factors.

[0004] When low-altitude aircraft are deployed excessively, organization and scheduling become complicated and equipment cannot be fully utilized. When low-altitude aircraft are deployed too few, mission efficiency and completion are affected. Therefore, there are currently no mature technical standards for the optimal deployment of low-altitude aircraft, which leads to the following shortcomings:

[0005] 1) Insufficient consideration of influencing factors: The number of low-altitude aircraft deployed is affected by many factors, including population size, traffic conditions, airspace resources, economic development, consumption capacity, application scenarios, and social sentiment. Currently, there is a lack of methods to determine the number of low-altitude aircraft deployed based on influencing factors, resulting in blind determination of the number of low-altitude aircraft deployed;

[0006] 2) No reasonable assessment of influencing factors: There is a lack of scientific and reasonable assessment of the role played by each influencing factor, resulting in inaccurate number of low-altitude aircraft determined accordingly.

[0007] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0008] In response to the problems in the related art, the present invention proposes a method for optimizing the layout of low-altitude aircraft on highways to overcome the above-mentioned technical problems existing in the existing related art.

[0009] To this end, the specific technical solutions adopted in the present invention are as follows:

[0010] A method for optimizing the layout of low-altitude aircraft on a highway comprises the following steps:

[0011] S1. Construct an evaluation index system based on influencing factors, and use the analytic hierarchy process and entropy weight method to determine the comprehensive weight of each evaluation index and identify the importance of the evaluation index;

[0012] S2. Based on the importance of the evaluation indicators, a low-altitude aircraft optimization layout model is constructed, and the simulated annealing algorithm is used to solve the static optimal number configuration of low-altitude aircraft at the service station;

[0013] S3. Using the social emotion resonance avoidance algorithm, dynamically adjust the static optimal number configuration of low-altitude aircraft at the service site to obtain the final number configuration of low-altitude aircraft at the service site;

[0014] S4. Based on the final number of low-altitude aircraft at the service site, the flight paths of low-altitude aircraft are optimized in combination with social sentiment data.

[0015] Furthermore, the evaluation index system is constructed based on the influencing factors, and the comprehensive weight of each evaluation index is determined by using the analytic hierarchy process and the entropy weight method. The importance of the evaluation index is identified by the following steps:

[0016] S11. Construct an evaluation index system based on the target highway area's population size, traffic conditions, airspace resources, economic development, consumption capacity, application scenarios, and radiation range;

[0017] S12. Determine the subjective weight of each evaluation indicator using the analytic hierarchy process, and analyze the objective weight of each evaluation indicator using the entropy weight method;

[0018] S13. Based on the weighted average method, the subjective weight and objective weight of each evaluation indicator are combined to calculate the comprehensive weight of each evaluation indicator, and the importance of each evaluation indicator is identified according to the comprehensive weight.

[0019] Furthermore, the construction of a low-altitude aircraft optimization layout model based on the importance of the evaluation index and the use of a simulated annealing algorithm to solve the static optimal number configuration of low-altitude aircraft at the service site include the following steps:

[0020] S21. Based on the evaluation indicators and their corresponding comprehensive weights, the objective function is constructed with minimizing the comprehensive cost as the optimization goal, and the number of service stations, the distance between service stations, and airspace resources as constraints;

[0021] S22. Randomly generate an initial solution as the number of low-altitude aircraft to be configured at each service station, and set the initial temperature, cooling factor, and maximum number of iterations;

[0022] S23, adjusting the number of low-altitude aircraft configurations by randomly perturbing the current solution, generating a new neighborhood solution, and calculating the objective function value of the new neighborhood solution according to the objective function;

[0023] S24, determining whether the objective function value of the new neighborhood solution is greater than the objective function value of the current solution, if so, accepting the new neighborhood solution, if not, accepting the new neighborhood solution according to the acceptance probability;

[0024] S25. Reduce the probability of accepting an inferior solution according to the decrease in temperature, so as to gradually guide the search process to converge to the global optimal solution;

[0025] S26. When the maximum number of iterations is reached or the temperature drops to the set minimum value, the iteration is stopped and the optimal solution is output to obtain the static optimal number of low-altitude aircraft at the service station that minimizes the objective function.

[0026] Furthermore, the objective function is expressed as:

[0027] Z=α1·C 人口规模 +α2·C 交通条件 +α3·C 空域资源 +α4·C 经济发展

[0028] +α5·C 消费能力 +α6·C 应用场景 +α7·C 辐射范围

[0029] Where Z represents comprehensive cost; C 人口规模 represents the cost measure of the population size indicator, α1 represents the comprehensive weight of the population size indicator, C 交通条件 represents the cost measure of traffic condition indicators, α2 represents the comprehensive weight of traffic condition indicators, C 空域资源 represents the cost measurement of airspace resource indicators, α3 represents the comprehensive weight of airspace resource indicators, C 经济发展 represents the cost measurement of economic development indicators, α4 represents the comprehensive weight of economic development indicators, C 消费能力 represents the cost measure of consumption capacity index, α5 represents the comprehensive weight of consumption capacity index, C 应用场景 represents the cost metric of the application scenario indicator, α6 represents the comprehensive weight of the application scenario indicator, and C 辐射范围 It represents the cost measure of the radiation range indicator, and α7 represents the comprehensive weight of the radiation range indicator.

[0030] Furthermore, the method of dynamically adjusting the static optimal number configuration of low-altitude aircraft at the service site by using the social emotion resonance avoidance algorithm to obtain the final number configuration of low-altitude aircraft at the service site includes the following steps:

[0031] S31. Obtain public sentiment feedback data on low-altitude aircraft in various regions based on social media, and use sentiment analysis technology to extract the sentiment polarity and sentiment intensity of public sentiment feedback data in various regions;

[0032] S32. Correcting the sentiment intensity data of each region using demographic weights, and constructing a sentiment distribution map of each region based on the corrected sentiment intensity data;

[0033] S33. Based on the emotional intensity and geographical information of each region, a group psychological field strength model is constructed to quantify the public acceptance of low-altitude aircraft deployment in each region;

[0034] S34. Based on the public acceptance of low-altitude aircraft deployment in various regions, combined with evolutionary game theory and resonance avoidance mechanism, optimize the static optimal number configuration of low-altitude aircraft at each service station and determine the final number configuration of low-altitude aircraft at each service station.

[0035] Furthermore, the method of modifying the emotion intensity data of each region by using demographic weights and constructing the emotion distribution map of each region according to the modified emotion intensity data includes the following steps:

[0036] S321. Extracting geographic location information related to public sentiment feedback data through social media, and attributing the public sentiment feedback data to specific regions based on the geographic information;

[0037] S322. Obtain basic demographic data for each region, and determine the demographic weight of each region based on its population characteristics and social media activity;

[0038] S323. Correct the emotion intensity data of each region according to the demographic weight of each region, and construct an emotion distribution map of each region based on the corrected emotion intensity data.

[0039] Furthermore, the calculation formula for sentiment intensity data correction is:

[0040] S′(x)=S(x)·W(x)

[0041] The formula for calculating demographic weight is:

[0042]

[0043] Where S'(x) represents the corrected sentiment score of region x, S(x) represents the sentiment score of region x, W(x) represents the demographic weight of region x, P(x) represents the total population of region x, and P(T) represents the total population of all regions in the service station.

[0044] Furthermore, the method of constructing a group psychological field strength model based on the emotional intensity and geographical information of each region to quantify the public acceptance of the deployment of low-altitude aircraft in each region includes the following steps:

[0045] S331. Construct a group psychological field strength model based on the emotional intensity and geographical information of each region. The expression of the group psychological field strength model is:

[0046]

[0047] In the formula, Ψ(x) represents the psychological field strength of region x, n represents the number of regions, S(x) represents the emotional score of region x, k represents the adjustment coefficient used to control the decay speed of emotional intensity with distance, r i represents the distance between the service site and region x, R i Indicates the maximum coverage distance of low-altitude aircraft services;

[0048] S332. Use the group psychological field strength model to calculate the psychological field strength of each region to quantify the public acceptance of low-altitude aircraft deployment in each region.

[0049] Furthermore, the optimization of the static optimal number of low-altitude aircraft at each service site based on the public acceptance of low-altitude aircraft deployment in each region and the combination of evolutionary game theory and resonance avoidance mechanism to determine the final number of low-altitude aircraft at each service site includes the following steps:

[0050] S341. Obtain the static optimal quantity configuration and public acceptance of low-altitude aircraft deployment in each region, and calculate the public acceptance of all regions within each service site using the weighted average method to obtain the public acceptance of low-altitude aircraft deployment at each service site;

[0051] S342. Define the low-altitude aircraft quantity strategy for each service site. Consider the service site as a participant in the game, select the quantity configuration of low-altitude aircraft, and design the fitness function of the service site based on public acceptance, operating costs, and service efficiency.

[0052] The expression of the fitness function is:

[0053] F i =β1·Ψ i -β2·C i +β3·O i

[0054] Where, F i represents the fitness function value of the i-th service station, Ψ i represents the psychological field strength of the i-th service site, C i represents the operating cost of the i-th service site, O i represents the service capability of the i-th service station, β1, β2, and β3 represent the psychological field strength weight, operating cost weight, and service capability weight of the i-th service station, respectively;

[0055] S342. Each service station updates its strategy based on the fitness difference between itself and the fitness of neighboring service stations, and dynamically adjusts the number of aircraft configurations through replication;

[0056] The policy update formula is:

[0057]

[0058] Where, represents the number of low-altitude aircraft at the i-th service station in the t+1 round, represents the number of low-altitude aircraft at the i-th service station in the t-th round, λ represents the learning rate, represents the average fitness of all service sites;

[0059] S343. In each iteration, monitor the fluctuations in public acceptance at all service sites, calculate the resonance index, identify potential emotional resonance risks, and adjust the update strategy when the resonance index exceeds the set threshold;

[0060] The calculation formula of resonance index is:

[0061]

[0062] The adjusted update formula is:

[0063]

[0064] Where E represents the resonance index, m represents the number of service sites, and x′ i (t+1) represents the number of low-altitude aircraft at the i-th service station in the t+1 round after adjustment, and η represents the resonance avoidance coefficient;

[0065] S344. Perform multiple rounds of strategy updates based on the game dynamics and resonance suppression mechanism to gradually optimize the low-altitude aircraft quantity configuration of each service site until the configuration quantity change of all service sites is less than the preset configuration quantity threshold or the maximum number of iterations is reached. The iteration ends and the final aircraft quantity configuration of each service site is obtained.

[0066] Furthermore, the optimization of the flight paths of low-altitude aircraft based on the final number configuration of low-altitude aircraft at the service site and in combination with social sentiment data includes the following steps:

[0067] S41. Obtain the final number of low-altitude aircraft at each service site, social sentiment data, and geographic information data related to flight paths;

[0068] S42. Build a flight path optimization model with minimizing the flight time of the aircraft path and maximizing public acceptance as optimization objectives, and with flight path restrictions, public sentiment fluctuations, and aircraft service range as constraints;

[0069] S43. Use the shortest path algorithm to optimize the flight path of low-altitude aircraft, and overlay the optimized flight path with the emotion distribution map of each region to intuitively display the flight route, service range and emotion area of low-altitude aircraft.

[0070] The beneficial effects of the present invention are:

[0071] 1) The present invention achieves efficient layout and path optimization of low-altitude aircraft by comprehensively considering multiple complex factors such as population size, traffic conditions, airspace resources, economic development, consumption capacity, application scenarios, radiation range and social sentiment, making the investment in low-altitude aircraft more global and economical, ensuring the feasibility, social acceptance and sustainable development of the technology, and providing important technical support for the application of the low-altitude aircraft industry.

[0072] 2) This invention comprehensively considers multiple influencing factors through the Analytic Hierarchy Process (AHP) and entropy weighting, and identifies the importance of each factor by calculating the overall weight. This multi-dimensional optimization approach ensures that the placement of low-altitude aircraft not only meets traditional service requirements but also adapts to social, economic, and emotional changes in different regions.

[0073] 3) This invention optimizes the number of aircraft using a simulated annealing algorithm, efficiently finding the static optimal number of service stations, thereby reducing aircraft vacancy rates and over-deployment. Furthermore, this method dynamically adjusts the aircraft configuration based on changes in the number of configured aircraft to adapt to evolving demand and sentiment.

[0074] 4) By incorporating a social-emotional resonance avoidance algorithm and a group psychological field strength model, this invention effectively mitigates the negative impact of public sentiment fluctuations during aircraft deployment. The optimized aircraft placement and flight paths better align with public acceptance and social-psychological needs, improving aircraft operational efficiency and reducing the risk of emotional resonance.

[0075] 5) This invention optimizes flight paths based on aircraft configuration and sentiment data, ensuring that aircraft efficiently execute their missions while avoiding areas of negative public sentiment. This optimized path not only improves aircraft operational efficiency but also effectively enhances the user experience and reduces public backlash and protests. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0077] Figure 1 The present invention is a flowchart of a method for optimizing the layout of low-altitude aircraft on highways according to an embodiment of the present invention. DETAILED DESCRIPTION

[0078] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0079] According to an embodiment of the present invention, a method for optimizing the layout of low-altitude aircraft on a highway is provided.

[0080] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, the method for optimizing the layout of low-altitude aircraft on highways according to an embodiment of the present invention includes the following steps:

[0081] S1. Construct an evaluation index system based on influencing factors, and use the analytic hierarchy process and entropy weight method to determine the comprehensive weight of each evaluation index and identify the importance of the evaluation index;

[0082] The evaluation index system is constructed based on the influencing factors, and the comprehensive weight of each evaluation index is determined by using the analytic hierarchy process and the entropy weight method. The importance of the evaluation index is identified by the following steps:

[0083] S11. Construct an evaluation index system based on the target highway area's population size, traffic conditions, airspace resources, economic development, consumption capacity, application scenarios, and radiation range;

[0084] Specifically, population size (such as population density and total population in a certain area), traffic conditions (such as traffic flow, road density, traffic congestion, etc.), airspace resources (such as the degree of airspace openness, restricted areas, flight difficulty, etc.), economic development (such as regional GDP, industry development, number of enterprises, etc.), consumption capacity (such as per capita income, consumer payment ability, consumption trends, etc.), application scenarios (such as logistics demand, urban air travel demand, etc.), radiation range (such as the service radius and coverage area of the aircraft, etc.). These indicators must be closely related to the optimization goals of aircraft deployment and can be obtained through data collection, surveys, etc.

[0085] S12. Determine the subjective weight of each evaluation indicator using the analytic hierarchy process, and analyze the objective weight of each evaluation indicator using the entropy weight method;

[0086] Specifically, the analytic hierarchy process (AHP) is mainly used to determine the relative importance of each evaluation indicator. The specific steps are as follows:

[0087] 1) Establish a hierarchical model:

[0088] Target layer: Determine the ultimate goal, which is “optimizing the layout of low-altitude aircraft.”

[0089] Criteria layer: Select the first-level criteria, which are usually several key factors that affect aircraft deployment, such as population size, traffic conditions, airspace resources, economic development, consumption capacity, etc.

[0090] Indicator layer: Under each criterion, list the relevant specific evaluation indicators.

[0091] For example:

[0092] Target layer: Optimized placement of low-altitude aircraft;

[0093] Criteria layer: population size, transportation conditions, airspace resources, economic development, consumption capacity, application scenarios, and radiation range;

[0094] Indicator layer: specific indicators under each criterion (e.g., “population density” is an indicator under “population size”);

[0095] 2) Construct a pairwise comparison matrix:

[0096] For each pair of criteria (or indicators), a pairwise comparison is performed. Experts judge the relative importance of each pair of factors based on their experience and knowledge, and the scores are usually on a scale of 1 to 9:

[0097] 1 means that the two factors are equally important; 3 means that one factor is slightly more important than the other; 5 means that one factor is obviously more important than the other; 7 means that one factor is very important than the other; 9 means that one factor is extremely important than the other; the results of pairwise comparison can generate a symmetric matrix in which each element represents the relative importance between the two.

[0098] 3) Calculate weight:

[0099] Eigenvalue method: Calculate the weight of each factor (i.e., the contribution of each factor to the final goal) using the eigenvalue method of the matrix. By calculating the maximum eigenvalue, the normalized weight value is obtained.

[0100] Specifically, the entropy weight method is an objective weight determination method that calculates the weight of each indicator by evaluating the data dispersion of the indicator. The higher the dispersion, the greater the contribution of the indicator to the evaluation result. The specific steps are as follows:

[0101] 1) Data standardization: Standardize the data of each indicator so that they can be compared on the same scale. Common standardization methods include minimum-maximum standardization and Z-score standardization;

[0102] 2) Calculate entropy value: Calculate the information entropy of each indicator based on the standardized data;

[0103] 3) Calculate weight: Calculate the weight of each indicator based on the entropy value. The larger the weight, the more information the indicator contains and the greater its impact on the final evaluation.

[0104] S13. Based on the weighted average method, the subjective weight and objective weight of each evaluation indicator are combined to calculate the comprehensive weight of each evaluation indicator, and the importance of each evaluation indicator is identified according to the comprehensive weight;

[0105] After completing the analysis of AHP and entropy weight method, the results of these two methods are combined to finally obtain the comprehensive weight of each evaluation index. The specific method is as follows:

[0106] Synthesis of subjective weights and objective weights: The subjective weights obtained by the AHP method and the objective weights obtained by the entropy weight method can be synthesized into the final weights by weighted averaging.

[0107] Identification of key influencing factors: Based on the comprehensive weights, key influencing factors can be identified, i.e., those factors that have the greatest impact and the heaviest weight on the aircraft layout optimization.

[0108] S2. Based on the importance of the evaluation indicators, a low-altitude aircraft optimization layout model is constructed, and the simulated annealing algorithm is used to solve the static optimal number configuration of low-altitude aircraft at the service station;

[0109] The process of constructing a low-altitude aircraft optimization layout model based on the importance of the evaluation indicators and solving the static optimal number configuration of low-altitude aircraft at the service site using a simulated annealing algorithm includes the following steps:

[0110] S21. Based on the evaluation indicators and their corresponding comprehensive weights, the objective function is constructed with minimizing the comprehensive cost as the optimization goal, and the number of service stations, the distance between service stations, and airspace resources as constraints;

[0111] The expression of the objective function is:

[0112] Z=α1·C 人口规模 +α2·C 交通条件 +α3·C 空域资源 +α4·C 经济发展

[0113] +α5·C 消费能力 +α6·C 应用场景 +α7·C 辐射范围

[0114] Where Z represents comprehensive cost; C 人口规模 represents the cost measure of the population size indicator, α1 represents the comprehensive weight of the population size indicator, C 交通条件 represents the cost measure of traffic condition indicators, α2 represents the comprehensive weight of traffic condition indicators, C 空域资源 represents the cost measurement of airspace resource indicators, α3 represents the comprehensive weight of airspace resource indicators, C 经济发展 represents the cost measurement of economic development indicators, α4 represents the comprehensive weight of economic development indicators, C 消费能力 represents the cost measure of consumption capacity index, α5 represents the comprehensive weight of consumption capacity index, C 应用场景 represents the cost metric of the application scenario indicator, α6 represents the comprehensive weight of the application scenario indicator, and C 辐射范围 represents the cost measure of the radiation range indicator, and α7 represents the comprehensive weight of the radiation range indicator;

[0115] Population size cost: Population size cost measures the impact of population size on the demand and cost of low-altitude aircraft deployment in the service area. Areas with larger populations require more aircraft to meet service demand. The calculation method is: This cost can be calculated based on the relationship between the total population and the service area. Assuming that the service capacity of the aircraft is proportional to the population, it can be calculated as follows: C 人口规模 =k 人口 ×P, where P is the population of the area, k 人口 is a cost coefficient related to population size, which can be determined based on the service efficiency and deployment requirements of the aircraft;

[0116] Traffic Condition Cost: Traffic condition cost measures the impact of factors such as traffic congestion and road construction in the service area on the deployment of aircraft. Areas with severe traffic congestion may require more aircraft to provide more efficient service. The calculation method is to estimate the cost based on the traffic volume and road conditions in the area. Traffic congestion index or road density can be used to quantify traffic condition cost: C 交通条件 =k 交通 ×T 拥堵 ×D, where T 拥堵 represents the traffic congestion index of the area (such as traffic delay time during peak hours), D is the road density or traffic flow in the area, and k 交通 is the cost coefficient of traffic conditions, adjusted based on the service efficiency of the aircraft;

[0117] Airspace resource cost: Airspace resource cost measures the impact of airspace resource restrictions on aircraft deployment. The tighter the airspace resources, the higher the deployment and operation costs of aircraft may be. The calculation method is: Airspace resources can be measured by the total area of available airspace, flight altitude restrictions, or the number of aircraft. The cost of airspace resources can be expressed as the cost of airspace occupation or the resource scheduling costs caused by airspace resource restrictions: C 空域资源 =k 空域 ×R 空域 , where R 空域 Indicates the degree of airspace resource tension, which can be quantified by the ratio of the available capacity of the airspace to the actual capacity used, k 空域 is the cost coefficient of airspace resources, taking into account the restrictiveness of airspace and the requirements of aircraft deployment;

[0118] Economic Development Cost: This cost considers the impact of the service area's economic development on aircraft deployment. Regions with better economic development may have higher affordability, and aircraft operations may be more cost-effective. The calculation method is: Economic development level can be measured by indicators such as GDP and per capita income. The economic development cost can be calculated based on the relative cost of regional economic level and aircraft operations: C 经济发展 =k 经济 ×GDP, where GDP is the total economic output of the region or GDP per capita, k 经济 is the cost coefficient of the economic development level;

[0119] Consumption capacity cost: Consumption capacity cost measures the impact of the purchasing power of consumers in a region on the demand for aircraft services. Regions with higher purchasing power may be more willing to pay higher fees to enjoy aircraft services. The calculation method is: Consumption capacity is usually related to the region's income level, consumer expenditure, etc., and can be calculated based on per capita income or total regional consumption: C 消费能力 =k消费 ×C 人均消费 , where C 人均消费 is the consumption capacity indicator of the region (e.g. per capita consumption), k 消费 is the cost coefficient of consumption capacity;

[0120] Application scenario cost: The application scenario cost takes into account the specific requirements of different application scenarios (such as express delivery, agricultural monitoring, etc.) for aircraft deployment. For example, some application scenarios require the aircraft to fly for a long time or require a higher load capacity. The calculation method is: the requirements of each application scenario may be different, and the cost of the application scenario can be evaluated based on the specific requirements of the aircraft: C 应用场景 =k 场景 ×S 场景需求 , where S 场景需求 is the demand level of the aircraft in this application scenario (such as flight time, load capacity, etc.), k 场景 is the cost coefficient of the application scenario;

[0121] Range Cost: Range cost measures the impact of an aircraft's service range on costs. Larger service areas require more aircraft to cover, thus increasing costs. Range cost can be calculated as: The range cost can be proportional to the aircraft's maximum service radius or the area covered: C 辐射范围 =k 辐射 ×A 覆盖面积 , where A 覆盖面积 is the service area or the maximum coverage distance of the aircraft, k 辐射 is the cost coefficient of the radiation range;

[0122] S22. Randomly generate an initial solution as the number of low-altitude aircraft to be configured at each service site, and set the initial temperature, cooling factor, and maximum number of iterations;

[0123] S23, adjusting the number of low-altitude aircraft configurations by randomly perturbing the current solution, generating a new neighborhood solution, and calculating the objective function value of the new neighborhood solution according to the objective function;

[0124] In the simulated annealing algorithm, randomly perturbing the current solution to generate new neighborhood solutions is a core operation. The goal is to explore the space of possible solutions to find the optimal solution to the objective function. For the low-altitude aircraft configuration problem, perturbing the current solution and generating new neighborhood solutions involves changing the number of aircraft configurations and then evaluating whether the cost (objective function value) of the new configuration is more optimal.

[0125] Perturbation operation (generating new neighborhood solutions):

[0126] The method of randomly perturbing the current solution is to make some random adjustments to the current solution to generate a new solution, called a neighborhood solution. In the aircraft number configuration problem, the neighborhood solution can be generated in the following ways:

[0127] Increase or decrease the number of aircraft at a certain station: For example, select a service station, randomly increase or decrease its number of aircraft, and ensure that the number of aircraft remains within the allowed range (for example, it cannot be negative).

[0128] Swap the number of aircraft between two sites: Select two sites and swap their aircraft number configurations.

[0129] Randomly select a site and adjust the ratio of its aircraft numbers: make small changes to the number of aircraft through some random factors (for example, increase or decrease the number of aircraft by 5%).

[0130] The operation of generating neighborhood solutions is generally generated by random numbers and has a certain degree of randomness.

[0131] S24, determining whether the objective function value of the new neighborhood solution is greater than the objective function value of the current solution, if so, accepting the new neighborhood solution, if not, accepting the new neighborhood solution according to the acceptance probability;

[0132] The formula for calculating the probability of acceptance is:

[0133]

[0134] Where P(ΔZ) represents the acceptance probability, ΔZ represents the difference in the objective function, and T represents the current temperature;

[0135] S25. Reduce the probability of accepting an inferior solution according to the decrease in temperature, so as to gradually guide the search process to converge to the global optimal solution;

[0136] The expression for cooling is:

[0137] T new =ω·T old

[0138] Where, T new represents the temperature after cooling, ω represents the cooling factor, T old Indicates the temperature before cooling.

[0139] S26. When the maximum number of iterations is reached or the temperature drops to the set minimum value, the iteration is stopped and the optimal solution is output to obtain the static optimal number of low-altitude aircraft at the service station that minimizes the objective function;

[0140] S3. Using the social emotion resonance avoidance algorithm, dynamically adjust the static optimal number configuration of low-altitude aircraft at the service site to obtain the final number configuration of low-altitude aircraft at the service site;

[0141] The method of dynamically adjusting the static optimal number configuration of low-altitude aircraft at the service site by using the social emotion resonance avoidance algorithm to obtain the final number configuration of low-altitude aircraft at the service site includes the following steps:

[0142] S31. Obtain public sentiment feedback data on low-altitude aircraft in various regions based on social media, and use sentiment analysis technology to extract the sentiment polarity and sentiment intensity of public sentiment feedback data in various regions;

[0143] Specifically, capturing public sentiment feedback data and conducting sentiment analysis based on social media is a crucial step in considering social sentiment when optimizing the deployment of low-altitude aircraft. By capturing discussions and feedback about low-altitude aircraft from social media platforms such as Weibo, we can quantify public attitudes, emotions, and acceptance of low-altitude aircraft. This process can be divided into several steps: data collection, sentiment analysis, and extraction of sentiment polarity and intensity.

[0144] 1) Data Collection:

[0145] First, collect relevant data about low-altitude aircraft from social media platforms. This data may include but is not limited to:

[0146] Social media posts (e.g., Weibo tweets, etc.): content related to low-altitude aircraft, such as discussions, comments, feedback, news, advertisements, etc.

[0147] Comments and forwarding information: Users’ comments, discussions, and forwarding about low-altitude aircraft can provide direct clues about public sentiment.

[0148] Geographic location information: Social media posts often include geographic location information, which can be used to bind sentiment data to specific regions, providing support for subsequent sentiment analysis and mood map creation.

[0149] Common techniques for data acquisition:

[0150] API calls: Many social media platforms provide APIs that allow developers to crawl public posts and comments. For example, Twitter's API or Weibo's open platform provide a rich set of interfaces for obtaining data.

[0151] Web crawling technology: Use crawling technology to capture public data on social media pages, especially those social platforms that do not directly provide APIs.

[0152] 2) Data cleaning and preprocessing:

[0153] After obtaining social media data, it is usually necessary to perform some cleaning and preprocessing to ensure data quality and consistency. These steps include:

[0154] Remove irrelevant data: Eliminate discussions or irrelevant content that are not related to low-altitude aircraft.

[0155] De-noising: Remove noise from comments, such as meaningless symbols, garbled characters, advertisements, etc.

[0156] Word segmentation and tagging: Especially in Chinese texts, comments need to be segmented and tagged with parts of speech so that sentiment analysis can identify words related to emotions.

[0157] 3) Sentiment Analysis Technology:

[0158] The purpose of sentiment analysis is to extract the polarity and intensity of public sentiment from text. It can be divided into the following steps:

[0159] Polarity

[0160] Sentiment polarity indicates the basic direction of public sentiment, which can be:

[0161] Positive emotions: express approval, likes, support, and positive emotional attitudes, such as "low-altitude aircraft are very convenient."

[0162] Negative emotions: express opposition, dislike, worry, and negative emotional attitudes, such as "low-altitude aircraft are noisy and affect the quality of life."

[0163] Neutral sentiment: refers to an attitude that is neither particularly positive nor particularly negative, such as "The development of low-altitude aircraft may bring changes, but it is uncertain."

[0164] In sentiment analysis, the identification of sentiment polarity is usually based on lexicon methods, machine learning methods, or deep learning methods:

[0165] Dictionary method: Use sentiment dictionaries (such as SentiWordNet, sentiment lexicon, etc.) to judge the sentiment polarity based on the positive and negative words that appear in the text.

[0166] Machine learning method: Train sentiment classification models (such as Naive Bayes, Support Vector Machine, etc.) to predict the sentiment polarity of text.

[0167] Deep learning methods: Use deep neural networks (such as LSTM, BERT, etc.) to perform sentiment classification on text. These models can learn the complex context in the text and thus identify the sentiment polarity.

[0168] Sentiment Intensity:

[0169] Emotional intensity measures the intensity of an emotion. It reflects the intensity of the emotion and can be categorized as follows:

[0170] High-intensity emotion: Indicates a strong emotional reaction, such as "This low-altitude aircraft is amazing and so convenient!"

[0171] Low-intensity emotion: Indicates a weak emotion, such as "The low-altitude aircraft is okay, but not particularly good."

[0172] Calculation method of emotion intensity:

[0173] Dictionary method: By using a sentiment dictionary with sentiment intensity scores (such as the VADER sentiment dictionary), each sentiment word is assigned an intensity score.

[0174] Machine learning methods: Use regression models or classification models to predict the sentiment intensity in text.

[0175] Deep learning method: Based on neural network models (such as BERT), multi-level analysis of text is performed to output the sentiment intensity of the text.

[0176] S32. Correcting the sentiment intensity data of each region using demographic weights, and constructing a sentiment distribution map of each region based on the corrected sentiment intensity data;

[0177] Specifically, the method of correcting the emotion intensity data of each region by using demographic weights and constructing the emotion distribution map of each region according to the corrected emotion intensity data includes the following steps:

[0178] S321. Extracting geographic location information related to public sentiment feedback data through social media, and attributing the public sentiment feedback data to specific regions based on the geographic information;

[0179] S322. Obtain basic demographic data for each region, and determine the demographic weight of each region based on its population characteristics and social media activity;

[0180] To obtain basic demographic data for each region and determine demographic weights based on the region's demographic characteristics and social media activity, the following steps are required:

[0181] 1) Obtain basic demographic data: such as total population: the total population of each region, which can reflect the population size of the region.

[0182] Data sources include:

[0183] Government statistical yearbooks or public data: Governments or local governments usually publish annual statistical data, including population, income, education level, etc.

[0184] Data from social media platforms: Obtain active user data on social platforms through APIs and other means, and associate demographic information through regional tags.

[0185] 2) Obtaining social media activity data:

[0186] Social media activity generally reflects the level of activity of users in a region on social platforms, which has a significant impact on sentiment analysis and the credibility of public opinion feedback. Social media activity includes the following indicators:

[0187] Active users: The number of users in a region who post content or engage in social media activities on a daily or monthly basis.

[0188] Posting frequency: The average posting frequency and interaction frequency (likes, comments, shares, etc.) of social media users in the region.

[0189] Penetration rate of social media platforms: for example, the ratio of the number of users of a certain platform to the total population of a certain region.

[0190] Content engagement: The number of discussions, comments, and reposts about low-altitude aircraft on social media can reflect the region's attention to low-altitude aircraft.

[0191] Data source:

[0192] Social media platform APIs: Obtain social media data for a specific region through APIs (such as the Weibo Open Platform API).

[0193] Social media analytics tools: Tools such as Brandwatch, Hootsuite, and BuzzSumo can help collect social media activity data and conduct regional analysis.

[0194] Social media reports: Some market research companies (such as Statista and eMarketer) also publish reports that provide statistics on social media usage in various regions.

[0195] 3) Calculate demographic weights:

[0196] Demographic weights are assigned based on each region's demographic characteristics (such as population size) and social media activity. These weights reflect the influence of a region's public sentiment feedback and its importance in sentiment analysis.

[0197] The formula for calculating demographic weight is:

[0198]

[0199] Where W(x) represents the demographic weight of region x, P(x) represents the total population of region x, and P(T) represents the total population of all regions in the service station.

[0200] S323, correcting the emotion intensity data of each region according to the demographic weight of each region, and constructing an emotion distribution map of each region based on the corrected emotion intensity data;

[0201] Specifically, constructing the emotion distribution map includes:

[0202] 1) Prepare geographic information data:

[0203] In order to construct the sentiment distribution map, it is necessary to associate the corrected sentiment intensity data with geographic locations (e.g., regions, cities, or administrative divisions). Common geographic data may include:

[0204] Latitude and longitude data: The longitude and latitude of each region, used for drawing maps.

[0205] Regional boundary data: such as administrative divisions or provincial and municipal boundary data, can be obtained in GeoJSON or Shapefile format.

[0206] 2) Visualized emotional distribution map:

[0207] Based on the corrected sentiment intensity data and geographic information, use visualization tools to generate sentiment distribution maps. Common tools and libraries include:

[0208] Python's Matplotlib and Geopandas libraries: for map visualization.

[0209] QGIS or ArcGIS: Professional Geographic Information System software that can be used to generate complex sentiment heatmaps.

[0210] Google Maps API or Leaflet.js: for interactive map display.

[0211] 3) Analysis and optimization:

[0212] Through the sentiment distribution map, you can analyze the sentiment trends in different regions:

[0213] Hot Regions: Which regions have strong emotional reactions (positive or negative) to low-altitude aircraft?

[0214] Areas with less attention: Areas with weaker emotional feedback may require more public communication and education to improve public acceptance.

[0215] Based on this information, you can optimize the deployment strategy of low-altitude aircraft, select areas with higher emotional intensity for priority deployment, and adjust the number of aircraft configurations through the objective function.

[0216] Specifically, the calculation formula for sentiment intensity data correction is:

[0217] S′(x)=S(x)·W(x)

[0218] Where S'(x) represents the corrected sentiment score of region x, and S(x) represents the sentiment score of region x.

[0219] For example, suppose the sentiment intensity data is as follows (assuming there are 3 regions): Sentiment intensity of region A = 0.7, Sentiment intensity of region B = 0.4, Sentiment intensity of region C = 0.9;

[0220] The demographic weights for each region are: Region A weight = 0.25, Region B weight = 0.35, Region C weight = 0.4;

[0221] Therefore, the corrected emotional intensity data are: corrected emotional intensity of region A = 0.7×0.25 = 0.175, corrected emotional intensity of region B = 0.4×0.35 = 0.14, and corrected emotional intensity of region C = 0.9×0.4 = 0.36.

[0222] S33. Based on the emotional intensity and geographical information of each region, a group psychological field strength model is constructed to quantify the public acceptance of low-altitude aircraft deployment in each region;

[0223] Specifically, the method of constructing a group psychological field strength model based on the emotional intensity and geographical information of each region to quantify the public acceptance of the deployment of low-altitude aircraft in each region includes the following steps:

[0224] S331. Construct a group psychological field strength model based on the emotional intensity and geographical information of each region. The expression of the group psychological field strength model is:

[0225]

[0226] In the formula, Ψ(x) represents the psychological field strength of region x, n represents the number of regions, S(x) represents the emotional score of region x, k represents the adjustment coefficient used to control the decay speed of emotional intensity with distance, r i represents the distance between the service site and region x, R i Indicates the maximum coverage distance of low-altitude aircraft services;

[0227] S332. Use the group psychological field strength model to calculate the psychological field strength of each region to quantify the public acceptance of low-altitude aircraft deployment in each region.

[0228] S34. Based on the public acceptance of low-altitude aircraft deployment in various regions, combined with evolutionary game theory and resonance avoidance mechanism, optimize the static optimal number configuration of low-altitude aircraft at each service station and determine the final number configuration of low-altitude aircraft at each service station.

[0229] Specifically, the method of optimizing the static optimal number configuration of low-altitude aircraft at each service site based on the public acceptance of low-altitude aircraft deployment in each region and combining evolutionary game theory and resonance avoidance mechanism to determine the final number configuration of low-altitude aircraft at each service site includes the following steps:

[0230] S341. Obtain the static optimal quantity configuration and public acceptance of low-altitude aircraft deployment in each region, and calculate the public acceptance of all regions within each service site using the weighted average method to obtain the public acceptance of low-altitude aircraft deployment at each service site;

[0231] S342. Define the low-altitude aircraft quantity strategy for each service site. Consider the service site as a participant in the game, select the quantity configuration of low-altitude aircraft, and design the fitness function of the service site based on public acceptance, operating costs, and service efficiency.

[0232] The expression of the fitness function is:

[0233] F i =β1·Ψ i -β2·C i +β3·O i

[0234] Where, F i represents the fitness function value of the i-th service station, Ψ i represents the psychological field strength of the i-th service site, C i represents the operating cost of the i-th service site, O i represents the service capacity of the i-th service station. In addition, due to the inconsistent dimensions of psychological field strength, operating cost, and service capacity, normalization is required during calculation in this embodiment. At the same time, normalization is also required for the inconsistent dimensions in other formulas of this embodiment. β1, β2, and β3 represent the psychological field strength weight, operating cost weight, and service capacity weight of the i-th service station, respectively.

[0235] S342. Each service station updates its strategy based on the fitness difference between itself and the fitness of neighboring service stations, and dynamically adjusts the number of aircraft configurations through replication;

[0236] The policy update formula is:

[0237]

[0238] Where, represents the number of low-altitude aircraft at the i-th service station in the t+1 round, represents the number of low-altitude aircraft at the i-th service station in the t-th round, λ represents the learning rate, represents the average fitness of all service sites;

[0239] S343. In each iteration, monitor the fluctuations in public acceptance at all service sites, calculate the resonance index, identify potential emotional resonance risks, and adjust the update strategy when the resonance index exceeds the set threshold;

[0240] The calculation formula of resonance index is:

[0241]

[0242] The adjusted update formula is:

[0243]

[0244] Where E represents the resonance index, m represents the number of service sites, represents the number of low-altitude aircraft at the i-th service station in the t+1 round after adjustment, and η represents the resonance avoidance coefficient;

[0245] Specifically, setting the resonance index threshold and adjusting the update strategy include:

[0246] After calculating the resonance index (RI) for each iteration, it can be compared with a preset resonance index threshold. When the RI exceeds the threshold, it indicates a potential risk of emotional resonance and requires appropriate adjustment strategies.

[0247] Strategy adjustment mechanism:

[0248] 1) The resonance index is lower than the threshold:

[0249] If the RI is less than the set threshold, it means that public sentiment is relatively stable, with low emotional fluctuations and emotional consistency. The current deployment strategy can be continued and the normal low-altitude aircraft configuration can be maintained.

[0250] 2) The resonance index exceeds the threshold:

[0251] Identifying Potential Emotional Resonance Areas: When the RI exceeds the threshold, the first step is to identify regions experiencing significant emotional fluctuations and consider whether specific communication or deployment strategies are warranted. For example, if public sentiment in certain areas is particularly intense, more intensive publicity, education, and communication efforts may be necessary to alleviate public sentiment.

[0252] Reduce emotional fluctuations: After discovering the risk of emotional resonance, it may be necessary to adjust the configuration or flight path of low-altitude aircraft to avoid overly drastic service deployment in areas with large emotional fluctuations, thereby reducing possible conflicts and anxiety.

[0253] Increase public participation: If sentiment is highly consistent across multiple regions (for example, negative sentiment is expressed across multiple regions), consider increasing public engagement, such as through online surveys, feedback, or interactive platforms, to understand the public's specific concerns and respond promptly to them, thereby enhancing public participation and identification.

[0254] Strengthen communication and feedback mechanisms: Strengthen communication with local communities, explain the purpose and safety of low-altitude aircraft, and reduce the negative emotions caused by uncertainty. Promote public acceptance through positive media publicity, special lectures, and other means.

[0255] Adjust the update strategy. When the resonance index exceeds the set threshold, you can choose the following adjustment strategies:

[0256] Adjust the configuration of low-altitude aircraft: reduce or increase the configuration of low-altitude aircraft at certain service stations, and flexibly adjust according to fluctuations in public sentiment.

[0257] Adjust flight paths and frequencies: Avoid aircraft flying over areas with large emotional fluctuations or adjust flight frequencies to alleviate public emotional stress.

[0258] Implement a slow deployment strategy: If sentiment fluctuates significantly, consider temporarily slowing down the deployment of low-altitude aircraft, gradually expanding to various regions, and observing changes in sentiment feedback.

[0259] S344. Perform multiple rounds of strategy updates based on the game dynamics and resonance suppression mechanism to gradually optimize the low-altitude aircraft quantity configuration of each service site until the configuration quantity change of all service sites is less than the preset configuration quantity threshold or the maximum number of iterations is reached. The iteration ends and the final aircraft quantity configuration of each service site is obtained.

[0260] S4. Based on the final number of low-altitude aircraft at the service site, the flight paths of low-altitude aircraft are optimized in combination with social sentiment data.

[0261] The step of optimizing the flight paths of low-altitude aircraft based on the final number of low-altitude aircraft at the service site and combining social sentiment data includes the following steps:

[0262] S41. Obtain the final number of low-altitude aircraft at each service site, social sentiment data, and geographic information data related to flight paths;

[0263] S42. Build a flight path optimization model with minimizing the flight time of the aircraft path and maximizing public acceptance as optimization objectives, and with flight path restrictions, public sentiment fluctuations, and aircraft service range as constraints;

[0264] S43. Use the shortest path algorithm to optimize the flight path of low-altitude aircraft, and overlay the optimized flight path with the emotion distribution map of each region to intuitively display the flight route, service range and emotion area of low-altitude aircraft.

[0265] To sum up, with the help of the above-mentioned technical scheme of the present invention, the present invention has achieved efficient layout and path optimization of low-altitude aircraft by comprehensively considering multiple complex factors such as population size, traffic conditions, airspace resources, economic development, consumption capacity, application scenarios, radiation range and social sentiment, making the investment in low-altitude aircraft more global and economical, ensuring the feasibility, social acceptance and sustainable development of the technology, and providing important technical support for the application of the low-altitude aircraft industry.

[0266] At the same time, the present invention comprehensively considers multiple influencing factors through the hierarchical analysis method and entropy weight method, and identifies the importance of each factor by calculating the comprehensive weight. This multi-dimensional optimization method ensures that the layout of low-altitude aircraft not only meets traditional service requirements but also adapts to social, economic and emotional changes in different regions.

[0267] The present invention also optimizes the number of aircraft using a simulated annealing algorithm, efficiently finding the static optimal number of service stations, thereby reducing issues such as aircraft vacancy or over-deployment. Furthermore, the method dynamically adjusts the layout based on changes in the number of aircraft configured, adapting to evolving demand and sentiment.

[0268] Furthermore, by incorporating a social-emotional resonance avoidance algorithm and a group psychological field strength model, this invention effectively mitigates the negative impact of public sentiment fluctuations during aircraft deployment. The optimized aircraft placement and flight paths better meet public acceptance and social-psychological needs, improving aircraft operational efficiency and reducing the risk of emotional resonance.

[0269] Furthermore, the present invention optimizes flight paths based on aircraft configuration and sentiment data, ensuring that aircraft can efficiently execute their missions while avoiding areas of negative public sentiment. This optimized path not only improves aircraft operational efficiency but also effectively enhances the user experience, reducing public dissatisfaction and protests against aircraft.

[0270] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing the layout of low-altitude aircraft on a highway, characterized in that: The following steps are involved: S1. Construct an evaluation index system based on influencing factors, and use the analytic hierarchy process and entropy weight method to determine the comprehensive weight of each evaluation index and identify the importance of the evaluation index; S2. Based on the importance of the evaluation indicators, a low-altitude aircraft optimization layout model is constructed, and the simulated annealing algorithm is used to solve the static optimal number configuration of low-altitude aircraft at the service station; S3. Using the social emotion resonance avoidance algorithm, dynamically adjust the static optimal number configuration of low-altitude aircraft at the service site to obtain the final number configuration of low-altitude aircraft at the service site; S4. Based on the final number of low-altitude aircraft at the service site, the flight paths of low-altitude aircraft are optimized in combination with social sentiment data.

2. The method for optimizing the layout of low-altitude aircraft on highways according to claim 1, characterized in that: The evaluation index system is constructed based on the influencing factors, and the comprehensive weight of each evaluation index is determined by using the hierarchical analysis method and the entropy weight method. The importance of the evaluation index is identified by the following steps: S11. Construct an evaluation index system based on the target highway area's population size, traffic conditions, airspace resources, economic development, consumption capacity, application scenarios, and radiation range; S12. Determine the subjective weight of each evaluation indicator using the analytic hierarchy process, and analyze the objective weight of each evaluation indicator using the entropy weight method; S13. Based on the weighted average method, the subjective weight and objective weight of each evaluation indicator are combined to calculate the comprehensive weight of each evaluation indicator, and the importance of each evaluation indicator is identified according to the comprehensive weight.

3. The method for optimizing the layout of low-altitude aircraft on highways according to claim 1, characterized in that: The method of constructing a low-altitude aircraft optimization layout model based on the importance of the evaluation index and using a simulated annealing algorithm to solve the static optimal number configuration of low-altitude aircraft at the service site includes the following steps: S21. Based on the evaluation indicators and their corresponding comprehensive weights, the objective function is constructed with minimizing the comprehensive cost as the optimization goal, and the number of service stations, the distance between service stations, and airspace resources as constraints; S22. Randomly generate an initial solution as the number of low-altitude aircraft to be configured at each service site, and set the initial temperature, cooling factor, and maximum number of iterations; S23, adjusting the number of low-altitude aircraft configurations by randomly perturbing the current solution, generating a new neighborhood solution, and calculating the objective function value of the new neighborhood solution according to the objective function; S24, determining whether the objective function value of the new neighborhood solution is greater than the objective function value of the current solution, if so, accepting the new neighborhood solution, if not, accepting the new neighborhood solution according to the acceptance probability; S25. Reduce the probability of accepting an inferior solution according to the decrease in temperature, so as to gradually guide the search process to converge to the global optimal solution; S26. When the maximum number of iterations is reached or the temperature drops to the set minimum value, the iteration is stopped and the optimal solution is output to obtain the static optimal number of low-altitude aircraft at the service station that minimizes the objective function.

4. The method for optimizing the layout of low-altitude aircraft on highways according to claim 3, characterized in that: The expression of the objective function is: Z=α1·C 人口规模 +α2·C 交通条件 +α3·C 空域资源 +α4·C 经济发展 +α5·C 消费能力 +α6·C 应用场景 +α7·C 辐射范围 Where Z represents comprehensive cost; C 人口规模 represents the cost measure of the population size indicator, α1 represents the comprehensive weight of the population size indicator, C 交通条件 represents the cost measure of traffic condition indicators, α2 represents the comprehensive weight of traffic condition indicators, C 空域资源 represents the cost measurement of airspace resource indicators, α3 represents the comprehensive weight of airspace resource indicators, C 经济发展 represents the cost measurement of economic development indicators, α4 represents the comprehensive weight of economic development indicators, C 消费能力 represents the cost measure of consumption capacity index, α5 represents the comprehensive weight of consumption capacity index, C 应用场景 represents the cost metric of the application scenario indicator, α6 represents the comprehensive weight of the application scenario indicator, and C 辐射范围 It represents the cost measure of the radiation range indicator, and α7 represents the comprehensive weight of the radiation range indicator.

5. The method for optimizing the layout of low-altitude aircraft on highways according to claim 1, characterized in that: The method of dynamically adjusting the static optimal number configuration of low-altitude aircraft at the service site by using the social emotion resonance avoidance algorithm to obtain the final number configuration of low-altitude aircraft at the service site includes the following steps: S31. Obtain public sentiment feedback data on low-altitude aircraft in various regions based on social media, and use sentiment analysis technology to extract the sentiment polarity and sentiment intensity of public sentiment feedback data in various regions; S32. Correcting the sentiment intensity data of each region using demographic weights, and constructing a sentiment distribution map of each region based on the corrected sentiment intensity data; S33. Based on the emotional intensity and geographical information of each region, a group psychological field strength model is constructed to quantify the public acceptance of low-altitude aircraft deployment in each region; S34. Based on the public acceptance of low-altitude aircraft deployment in various regions, combined with evolutionary game theory and resonance avoidance mechanism, optimize the static optimal number configuration of low-altitude aircraft at each service station and determine the final number configuration of low-altitude aircraft at each service station.

6. The method for optimizing the layout of low-altitude aircraft on highways according to claim 5, characterized in that: The method of modifying the emotion intensity data of each region by using demographic weights and constructing the emotion distribution map of each region according to the modified emotion intensity data includes the following steps: S321. Extracting geographic location information related to public sentiment feedback data through social media, and attributing the public sentiment feedback data to specific regions based on the geographic information; S322. Obtain basic demographic data for each region, and determine the demographic weight of each region based on its population characteristics and social media activity; S323. Correct the emotion intensity data of each region according to the demographic weight of each region, and construct an emotion distribution map of each region based on the corrected emotion intensity data.

7. The method for optimizing the layout of low-altitude aircraft on highways according to claim 6, characterized in that: The calculation formula for sentiment intensity data correction is: S′(x)=S(x)·W(x) The formula for calculating demographic weight is: Where S'(x) represents the corrected sentiment score of region x, S(x) represents the sentiment score of region x, W(x) represents the demographic weight of region x, P(x) represents the total population of region x, and P(T) represents the total population of all regions in the service station.

8. The method for optimizing the layout of low-altitude aircraft on highways according to claim 5, characterized in that: The method of constructing a group psychological field strength model based on the emotional intensity and geographical information of each region to quantify the public acceptance of low-altitude aircraft deployment in each region includes the following steps: S331. Construct a group psychological field strength model based on the emotional intensity and geographical information of each region. The expression of the group psychological field strength model is: In the formula, Ψ(x) represents the psychological field strength of region x, n represents the number of regions, S(x) represents the emotional score of region x, k represents the adjustment coefficient used to control the decay speed of emotional intensity with distance, r i represents the distance between the service site and region x, R i Indicates the maximum coverage distance of low-altitude aircraft services; S332. Use the group psychological field strength model to calculate the psychological field strength of each region to quantify the public acceptance of low-altitude aircraft deployment in each region.

9. The method for optimizing the layout of low-altitude aircraft on highways according to claim 5, characterized in that: The method of optimizing the static optimal number of low-altitude aircraft at each service site based on public acceptance of low-altitude aircraft deployment in each region and combining evolutionary game theory and resonance avoidance mechanism to determine the final number of low-altitude aircraft at each service site includes the following steps: S341. Obtain the static optimal quantity configuration and public acceptance of low-altitude aircraft deployment in each region, and calculate the public acceptance of all regions within each service site using the weighted average method to obtain the public acceptance of low-altitude aircraft deployment at each service site; S342. Define the low-altitude aircraft quantity strategy for each service site. Consider the service site as a participant in the game, select the quantity configuration of low-altitude aircraft, and design the fitness function of the service site based on public acceptance, operating costs, and service efficiency. The expression of the fitness function is: F i =β1·Ψ i -β2·C i +β3·O i Where, F i represents the fitness function value of the i-th service station, Ψ i represents the psychological field strength of the i-th service site, C i represents the operating cost of the i-th service site, O i represents the service capability of the i-th service station, β1, β2, and β3 represent the psychological field strength weight, operating cost weight, and service capability weight of the i-th service station, respectively; S342. Each service station updates its strategy based on the fitness difference between itself and the fitness of neighboring service stations, and dynamically adjusts the number of aircraft configurations through replication; The policy update formula is: Where, represents the number of low-altitude aircraft at the i-th service station in the t+1 round, represents the number of low-altitude aircraft at the i-th service station in the t-th round, λ represents the learning rate, represents the average fitness of all service sites; S343. In each iteration, monitor the fluctuations in public acceptance at all service sites, calculate the resonance index, identify potential emotional resonance risks, and adjust the update strategy when the resonance index exceeds the set threshold; The calculation formula of resonance index is: The adjusted update formula is: Where E represents the resonance index, m represents the number of service sites, represents the number of low-altitude aircraft at the i-th service station in the t+1 round after adjustment, and η represents the resonance avoidance coefficient; S344. Perform multiple rounds of strategy updates based on the game dynamics and resonance suppression mechanism to gradually optimize the low-altitude aircraft quantity configuration of each service site until the configuration quantity change of all service sites is less than the preset configuration quantity threshold or the maximum number of iterations is reached. The iteration ends and the final aircraft quantity configuration of each service site is obtained.

10. The method for optimizing the layout of low-altitude aircraft on a highway according to claim 1, characterized in that: Optimizing the flight paths of low-altitude aircraft based on the final number of low-altitude aircraft at the service site and combining social sentiment data includes the following steps: S41. Obtain the final number of low-altitude aircraft at each service site, social sentiment data, and geographic information data related to flight paths; S42. Build a flight path optimization model with minimizing the flight time of the aircraft path and maximizing public acceptance as optimization objectives, and with flight path restrictions, public sentiment fluctuations, and aircraft service range as constraints; S43. Use the shortest path algorithm to optimize the flight path of low-altitude aircraft, and overlay the optimized flight path with the emotion distribution map of each region to intuitively display the flight route, service range and emotion area of low-altitude aircraft.

Images