A site selection optimization method for low-altitude flight service stations and related products

Abstract

The present application relates to the field of general aviation technology, and in particular to a method for optimizing the site selection of low-altitude flight service stations and related products. The method predefines target continuous decision variables based on factors such as the characteristics of the low-altitude flight service stations, evaluation priorities, and data availability; utilizes multi-objective decision analysis to comprehensively and accurately evaluate the performance of each low-altitude flight service station to be selected in the target site selection area in different performance dimensions, and determines the low-altitude flight service stations whose comprehensive performance meets the requirements; and then forms a unified evaluation standard by combining multiple indicators of different dimensions and dimensions, so as to facilitate more intuitive and scientific selection decisions for flight service stations, provide a strong basis for comprehensive evaluation and ultimately accurately and effectively determining the optimal flight service station, and be conducive to the rapid development of the low-altitude industry.

Description

Technical Field

[0001] The present invention relates to the field of general aviation technology, and in particular to a site selection optimization method for a low-altitude flight service station and related products. Background Art

[0002] As the main provider of low-altitude flight services, the site selection of low-altitude flight service stations involves infrastructure construction, operation service models and low-altitude flight service guarantee capabilities. It determines the convenience of users in obtaining services, and even more so the safety and economy of the services. It is also a comprehensive decision-making work.

[0003] Since 2020, the number of low-altitude flights and hours in my country has seen double-digit annual growth, showing a surge in the number of flights reaching hundreds of millions. However, low-altitude flight service stations are scarce, and most are administratively designated based on a "self-operated, self-supported, and self-sufficient" approach. These lack systematic basic data and a mature system for optimizing flight service site selection, making them unable to adapt to the rapid growth of the low-altitude industry.

[0004] Therefore, establishing a scientific and efficient low-altitude flight service station site selection optimization system has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] This application aims to provide a low-altitude flight service station site selection optimization method and related products to solve the technical problem that the existing low-altitude flight service station site selection method is immature and cannot adapt to the rapid development of the low-altitude industry. This is achieved specifically through the following technical solutions:

[0006] In a first aspect, the present application provides a method for optimizing the site selection of a low-altitude flight service station, comprising: determining at least one first low-altitude flight service station to be evaluated within a target site selection area; determining at least one second low-altitude flight service station from the at least one first low-altitude flight service station using a Benders decomposition algorithm based on predefined target continuous decision variables, wherein the index values ​​of each target continuous decision variable corresponding to the second low-altitude flight service station make the Benders decomposition algorithm meet the convergence conditions, and the target continuous decision variables are used to characterize the performance level of the service station; determining the variable weights of each target continuous decision variable corresponding to the second low-altitude flight service station; and performing dimensionless processing on the index values ​​of each target continuous decision variable corresponding to the second low-altitude flight service station to obtain the dimensionless values ​​of each target continuous decision variable index corresponding to the second low-altitude flight service station; calculating the comprehensive evaluation index I of the second low-altitude flight service station based on the variable weights of each target continuous decision variable and the dimensionless values ​​of each target continuous decision variable index; and determining the final optimized target low-altitude flight service station from the second low-altitude flight service station based on the comprehensive evaluation index I.

[0007] In the second aspect, the present application provides a site selection optimization system for low-altitude flight service stations, including: a candidate service station module, used to determine at least one first low-altitude flight service station to be evaluated in the target site selection area; a Benders calculation module, used to determine at least one second low-altitude flight service station from the at least one first low-altitude flight service station based on a predefined target continuous decision variable and using a Benders decomposition algorithm, wherein the index values ​​of each target continuous decision variable corresponding to the second low-altitude flight service station make the Benders decomposition algorithm meet the convergence conditions, and the target continuous decision variables are used to characterize the performance level of the service station; variable weights A weight module is used to determine the variable weights of each target continuous decision variable corresponding to the second low-altitude flight service station; a dimensionless module is used to perform dimensionless processing on the index values ​​of each target continuous decision variable corresponding to the second low-altitude flight service station to obtain the dimensionless values ​​of each target continuous decision variable index corresponding to the second low-altitude flight service station; a comprehensive evaluation module is used to calculate the comprehensive evaluation index I of the second low-altitude flight service station based on the variable weights of each target continuous decision variable and the dimensionless values ​​of each target continuous decision variable index; and determine the final optimized target low-altitude flight service station from the second low-altitude flight service station based on the comprehensive evaluation index I.

[0008] In a third aspect, the present application provides an electronic device comprising: at least one processor; a memory communicatively connected to the at least one processor; and a computer program stored on the memory and running on the at least one processor; wherein, when the at least one processor executes the computer program, it is used to implement the site selection optimization method for a low-altitude flight service station described in the first aspect above.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer program contained in the computer-readable storage medium is used to implement the site selection optimization method for a low-altitude flight service station described in the first aspect when executed by a computer device.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a computer device, it is used to implement the site selection optimization method of a low-altitude flight service station described in the first aspect above.

[0011] From the above, it can be seen that this application predefines each target continuous decision variable based on factors such as the characteristics of low-altitude flight service stations, evaluation focus, and data availability; uses multi-objective decision analysis to comprehensively and accurately evaluate the performance of each candidate low-altitude flight service station in the target site selection area in different performance dimensions, and determines the second low-altitude flight service station with better comprehensive performance; and then forms a unified evaluation standard by combining multiple indicators of different dimensions and dimensions, which facilitates more intuitive and scientific flight service station selection decisions, and provides a strong basis for comprehensive evaluation and the final accurate and effective determination of the optimal flight service station; it is conducive to the rapid development of the low-altitude industry.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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 creative work.

[0014] Figure 1 A flowchart of a method for optimizing the site selection of a low-altitude flight service station provided in an embodiment of the present application;

[0015] Figure 2 A schematic diagram of the structure of a site selection optimization system for a low-altitude flight service station provided in an embodiment of the present application;

[0016] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] Example 1

[0019] See also Figure 1 , Figure 1 The following is a flow chart of a method for optimizing the location of a low-altitude flight service station provided in an embodiment of the present application. Figure 1As shown, the method includes the following contents:

[0020] 101. Determine at least one first low-altitude flight service station to be evaluated within the target site selection area.

[0021] Low-altitude flight service stations can be established independently or based on the existing transport airport air traffic control unit or general aviation airport. In the embodiment of this application, the situation of being established based on the existing transport airport air traffic control unit or general aviation airport is mainly considered. In the target site selection area, several first low-altitude flight service stations to be evaluated are determined based on civil aviation policies and low-altitude flight service needs. Low-altitude flight service stations are divided into Class A and Class B according to their service scope and functions. Among them, Class B low-altitude flight service stations should have functions such as flight plan processing, aviation intelligence services, aviation meteorological services, warning and assistance rescue services, provide services to general aviation flight activities within the service scope, and regularly provide information related to flight plans and implementation status to the regional information processing system; Class A low-altitude flight service stations, in addition to the above functions, should also have functions such as monitoring and in-flight services.

[0022] However, according to the civil aviation administration's layout plan for low-altitude flight service stations, each provincial-level administrative region will, in principle, establish one to three Class A low-altitude flight service stations, and several Class B low-altitude flight service stations as needed. The provincial (autonomous region, or municipality) people's government will coordinate with military and civil aviation units to coordinate the demarcation of low-altitude airspace and flight plan management within its administrative region. It will formulate a flight service station layout plan for its administrative region based on the low-altitude airspace classification, general airport layout plan, and actual general aviation development. Flight service stations should clearly define their service scope, determine specific functional modules based on operational needs, and configure appropriate facilities and equipment. They should deploy information collection systems at relevant general airports and general aviation activity areas; monitor and report on general aviation flight plans and implementation status within the region, distributing the flight plans and implementation status within the region to relevant flight service stations; monitor and report on the management and use of low-altitude airspace within the region; coordinate with flight service stations to provide warnings and assist in rescue services; and integrate various types of service information to provide basic products and information services to flight service stations. Therefore, for the civil aviation management department, in the absence of systematic basic data, a mature flight service site selection optimization system has not yet been formed, and it is unable to provide a scientific and efficient decision-making method for the site selection of low-altitude flight service stations, and is unable to adapt to the rapid development of the low-altitude industry.

[0023] In an embodiment of the present application, several first low-altitude flight service stations to be evaluated are selected according to their functionality. As mentioned above, the first low-altitude flight service stations may include several Class A first low-altitude flight service stations to be evaluated and / or several Class B first low-altitude flight service stations to be evaluated.

[0024] 102. Based on predefined target continuous decision variables, using Benders decomposition algorithm, determine at least one second low-altitude flight service station from the at least one first low-altitude flight service station.

[0025] Among them, the index values ​​of each target continuous decision variable corresponding to the second low-altitude flight service station make the Benders decomposition algorithm meet the convergence condition, and the target continuous decision variables are used to characterize the performance level of the service station.

[0026] For several Class A first low-altitude flight service stations, a corresponding weight coefficient is assigned to each first low-altitude flight service station according to a predefined target continuous decision variable; wherein, the target continuous decision variable includes an effective coverage radius variable, coverage area overlap, average response time, response success rate, equipment resource adequacy, unit operating cost, flight accident warning accuracy and air traffic conflict resolution efficiency; according to the target continuous decision variable and the weight coefficient of the first low-altitude flight service station, an objective function is determined; the minimum number of service stations required to cover the target site selection area and the pre-set total amount of operating resources required for each service station are used as constraints; a main problem solving function is constructed according to the objective function and the constraints, and a number of initial solutions are obtained by using the main problem solving function; according to the effective A coverage quality sub-problem solving function is constructed based on the coverage radius variable and the coverage area overlap index; and a response capability sub-problem solving function is constructed based on the average response time and response success rate indicators; and a cost-effectiveness sub-problem solving function is constructed based on the equipment resource adequacy and unit operating cost indicators; and a safety assurance sub-problem solving function is constructed based on the flight accident warning accuracy and the air traffic conflict resolution efficiency; using several initial solutions obtained by solving the main problem solving function, the coverage quality sub-problem solving function, the response capability sub-problem solving function, the cost-effectiveness sub-problem solving function and the safety assurance sub-problem solving function are iteratively solved, and when the convergence condition is met, the iteration is stopped to obtain the optimal solution of the main problem solving function, and the second low-altitude flight service station is determined based on the optimal solution of the main problem solving function.

[0027] For example, suppose To select The binary decision variables for the first low-altitude flight service station, where Indicates choice, Indicates not to select. Assume that the number of Class A first low-altitude flight service stations to be evaluated (i.e., to be selected) is ,but . According to the evaluation requirements (i.e., the evaluation requirements as a Class A low-altitude flight service station), define target continuous decision variables used to characterize the performance level of the service station, including effective coverage radius variables, coverage area overlap, average response time, response success rate, equipment resource adequacy, unit operating cost, flight accident warning accuracy, and air traffic conflict resolution efficiency; assign corresponding weight coefficients to each first low-altitude flight service station based on these target continuous decision variable indicators, which are specifically determined according to the actual evaluation dimensions. Determine the objective function based on the target continuous decision variables and the weight coefficients of the first low-altitude flight service station; the objective function can be a function form that maximizes the service station evaluation coefficient (or minimizes corresponding indicators such as related costs) after comprehensively considering multiple factors, as shown in the following formula:

[0028]

[0029] in, represents the service station evaluation coefficient; Indicates the The first low-altitude flight service station is assigned a weight coefficient; the objective function is to optimize To make the service station evaluation coefficient Reach the best.

[0030] Identify the constraints:

[0031] (1) Coverage constraints:

[0032] Ensure that the selected low-altitude flight service station can cover the required low-altitude flight area, which can be expressed mathematically as follows:

[0033]

[0034] in, Indicates the coverage area Gather at the first service station; Indicates coverage area Minimum number of low-altitude flight service stations required.

[0035] (2) Resource constraints:

[0036] It mainly involves the operating resource limitations of low-altitude flight service stations, such as manpower and equipment, which can be expressed mathematically as follows:

[0037]

[0038] in, Indicates the The amount of resources consumed by the first low-altitude flight service station; Indicates the total amount of available resources.

[0039] A main problem solving function is constructed based on the objective function and the constraint conditions. The main problem solving function is a mixed integer programming problem, which contains the binary decision variables defined above. , the objective function and the constraints, the mathematical formula is as follows:

[0040]

[0041] Initially, it can be based on some simple rules or experience The algorithm is started by finding a feasible solution to or by obtaining a relaxed linear programming solution by relaxing the integer constraints.

[0042] For a given main problem, find the initial solution of the function, such as the one obtained in a certain round of iteration. If the value of , initial solution , and then construct sub-problems. Sub-problems are usually based on detailed service station operation characteristics, indicator calculations, etc. to further analyze the feasibility and quality of the solution selected by the main problem solution function. For example, considering the coverage quality of service stations for low-altitude flight service needs, the sub-problem can be to determine which service stations to select (i.e. Based on the value of ), according to the effective coverage radius and coverage area overlap of the service station, a coverage quality sub-problem solving function is constructed to calculate the coverage quality index of the first low-altitude flight service station. For example, after determining which service stations to select (i.e. Based on the value of ), according to the average response time and response success rate indicators of the service station, a response capability sub-problem solving function is constructed to calculate the response capability indicator of the first low-altitude flight service station. For another example, after determining which service stations to select (i.e. Based on the value of ), according to the equipment resource sufficiency and unit operating cost index of the service station, a cost-effectiveness sub-problem solving function is constructed to calculate the cost-effectiveness index of the first low-altitude flight service station. For another example, after determining which service stations to select (i.e. ), based on the flight accident warning accuracy and air traffic conflict resolution efficiency of the service station, a safety assurance sub-problem solving function is constructed to calculate the safety assurance index of the first low-altitude flight service station.

[0043] The initial solution of the given main problem-solving function is passed to the constructed sub-problem-solving function. The sub-problem-solving function is then solved to obtain its optimal solution and corresponding optimal value (including the coverage quality, responsiveness, cost-effectiveness, and safety assurance indicators of the first low-altitude flight service station). The optimal solution and corresponding optimal value of the sub-problem-solving function are then determined to be feasible. If so, an optimization cutting plane is generated based on its optimal value (for example, if there is a gap between the sub-problem objective value and the current main problem objective value, an optimization cutting plane is constructed based on this gap). This cutting plane is then fed back to the main problem-solving function to improve subsequent solutions of the main problem-solving function, moving the main problem objective value towards a more optimal solution. Otherwise, a feasibility cutting plane is generated and fed back to the main problem-solving function to further constrain the feasible region of the main problem-solving function. The solution is then iterated. Convergence is determined by comparing the changes in the main problem objective value (or combining other evaluation indicators, such as the generation of cutting planes) over consecutive iterations to determine whether convergence conditions (such as whether the change in the objective value is less than a set threshold) have been met. If convergence occurs, the iteration stops; if not, the iteration continues.

[0044] After the algorithm converges, the final optimal solution obtained by the main problem solving function is , which determines which ones are selected in the first low-altitude flight service station, i.e. The first low-altitude flight service station, in the embodiment of this application, these The first low-altitude flight service station is used as the second low-altitude flight service station. By adding the above effective constraints to tighten the main problem solving function, the number of iterations is reduced, which is conducive to improving the efficiency of the comprehensive performance evaluation of the service station.

[0045] For several Class B first low-altitude flight service stations, a corresponding weight coefficient is assigned to each first low-altitude flight service station according to a predefined target continuous decision variable; wherein the target continuous decision variable includes an effective coverage radius variable, coverage area overlap, equipment resource adequacy, and unit operating cost; an objective function is determined according to the target continuous decision variable and the weight coefficient of the first low-altitude flight service station; the minimum number of service stations required to cover the target site selection area and the pre-set total amount of operating resources required for each service station are used as constraints; a target function is constructed according to the target function and the constraints. A main problem solving function is used to obtain several initial solutions; a coverage quality sub-problem solving function is constructed according to the effective coverage radius variable and the coverage area overlap index; and a cost-effectiveness sub-problem solving function is constructed according to the equipment resource adequacy and the unit operating cost index; the coverage quality sub-problem solving function and the cost-effectiveness sub-problem solving function are iteratively solved using the several initial solutions obtained by solving the main problem solving function, and when the convergence condition is met, the iteration is stopped to obtain the optimal solution of the main problem solving function, and the second low-altitude flight service station is determined according to the optimal solution of the main problem solving function.

[0046] It should be noted that for several Class B first low-altitude flight service stations, the specific implementation methods can refer to the above-mentioned implementation methods for several Class A first low-altitude flight service stations. The two only have different sub-problem solving functions due to different functionality. Therefore, they will not be repeated here.

[0047] 103. Determine the variable weight of each target continuous decision variable corresponding to the second low-altitude flight service station.

[0048] A specific implementation method can use a deep learning neural network to collect historical operating data corresponding to each target continuous decision variable of the second low-altitude flight service station; preprocess the historical operating data; divide the preprocessed historical operating data into a training set, a validation set, and a test set; establish a variable weight estimation model based on a multi-layer perceptron, and train the variable weight estimation model using the divided training set; define a mean square error loss function, and use an optimizer to iteratively update the parameters of the variable weight estimation model multiple times in combination with the validation set and the test set; the iterative convergence condition of the variable weight estimation model is to minimize the difference between the weight estimate value and the weight label value pre-annotated for the training set; use the trained variable weight estimation model output to obtain the estimated weight of each target continuous decision variable corresponding to the second low-altitude flight service station; determine the correlation between each target continuous decision variable and the service station performance level; convert the estimated weight of each target continuous decision variable output by the variable weight estimation model into a probability distribution, and adjust the estimated weight based on the correlation between each target continuous decision variable and the service station performance level to obtain the variable weight of each target continuous decision variable corresponding to the second low-altitude flight service station.

[0049] Specifically, a large amount of various historical operational data on the aforementioned second low-altitude flight service station will be collected, including but not limited to historical effective coverage radius data, historical coverage area overlap data, historical average response time data, historical response success rate data, historical equipment resource adequacy data, historical unit operating cost data, historical flight accident warning accuracy data, and historical air traffic conflict resolution efficiency data. This data should cover the performance information of different service stations at different times and under different circumstances, providing sufficient training samples for subsequent deep learning models. Data sources can be the operation logs, monitoring systems, sensor networks, flight management systems, etc. of each low-altitude flight service station to ensure data accuracy and completeness. The collected historical operational data will then be preprocessed, such as processing missing values, outliers, and duplicate data.

[0050] The historical operation data after the above preprocessing is then divided into a training set, a validation set and a test set; wherein the training set is used to train the model, the validation set is used to adjust the model hyperparameters (such as learning rate, number of layers, number of neurons, etc.), and the test set is used to finally evaluate the model performance. A variable weight estimation model is established based on a multi-layer perceptron, which consists of an input layer, multiple hidden layers and an output layer, and defines the dimension of the input feature (input_size), the number of neurons in the hidden layer (hidden_size), and the output dimension (output_size), wherein the output dimension is the estimated weight dimension of each target continuous decision variable corresponding to the second low-altitude flight service station in the embodiment of the present application. ReLU is used as the activation function. For example, it can be implemented using a python library to define a multi-layer perceptron model:

[0051] import torch

[0052] import torch.nn as nn

[0053] class MLP(nn.Module):

[0054] def __init__(self, input_size, hidden_size, output_size):

[0055] super(MLP, self).__init__()

[0056] self.layers = nn.Sequential(

[0057] nn.Linear(input_size, hidden_size),

[0058] nn.ReLU(),

[0059] nn.Linear(hidden_size, hidden_size),

[0060] nn.ReLU(),

[0061] nn.Linear(hidden_size, output_size) )

[0063] def forward(self, x):

[0064] return self.layers(x)

[0065] Define a mean squared error loss function, combine the validation set and the test set, and use an optimizer to iteratively update the parameters of the variable weight estimation model multiple times; the iterative convergence condition of the variable weight estimation model is to minimize the difference between the weight estimate value and the weight label value pre-annotated for the training set. The specific implementation code example is as follows:

[0066] input_size = 10 # Assume the dimension of input features

[0067] hidden_size = 20

[0068] output_size = 5 # Assume the weight dimension to be predicted

[0069] model = MLP(input_size, hidden_size, output_size)

[0070] criterion = nn.MSE()

[0071] optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

[0072] # Assume x_train and y_train are training data and labels

[0073] for epoch in range(epochs):

[0074] optimizer.zero_grad()

[0075] outputs = model(x_train)

[0076] loss = criterion(outputs, y_train)

[0077] loss.backward()

[0078] optimizer.step()

[0079] Among them, x_train is the preprocessed historical running data, and y_train is the corresponding label (such as the pre-set ideal weight, which can be obtained based on expert experience).

[0080] Using association rule mining algorithms (such as the Apriori algorithm), we can identify correlations between historical data indicators and between each indicator and the overall performance level of the Second Low-Altitude Flight Service Station. For example, we can find a correlation between sufficient equipment resources and strong responsiveness, or a correlation between a large effective coverage radius and high cost-effectiveness. These association rules can provide auxiliary information for determining weights, revealing the inherent connections between certain indicators and thus influencing weight allocation. In Python, we can use the mlxtend library to perform association rule mining. The sample code is as follows:

[0081] from mlxtend.frequent_patterns import apriori, association_rules

[0082] import pandas as pd

[0083] # Assume df is a DataFrame containing service station features

[0084] df = pd.DataFrame(...)

[0085] frequent_itemsets=apriori(df,min_support=0.05, use_colnames=True)

[0086] rules=association_rules(frequent_itemsets,metric="lift", min_threshold=1.0)

[0087] The trained variable weight estimation model output is used to obtain the estimated weights of each target continuous decision variable corresponding to the second low-altitude flight service station; for the output results, some post-processing methods, such as the softmax function, can be used to convert the output results into a reasonable weight range.

[0088] import torch.nn.functional as F

[0089] weights = F.softmax(outputs, dim=1)

[0090] Among them, outputs is the original output of the variable weight estimation model, which is converted into a probability distribution through the softmax function as a preliminary weight estimation.

[0091] The weight estimates output by the variable weight estimation model and the association rule mining results are comprehensively considered. The weight estimates output by the variable weight estimation model are fine-tuned, and the weights are adjusted based on the important associations discovered by the association rules. Through the combination of deep learning and big data analysis, the variable weights of each target continuous decision variable of the low-altitude flight service station can be determined more comprehensively and accurately. The weights can also be dynamically updated and optimized based on the latest collected update data, improving the adaptability and rationality of the weights, thereby more scientifically determining the indicator weights of each target continuous decision variable of the low-altitude flight service station, providing strong support for the evaluation and site selection decisions of the service station.

[0092] In another feasible implementation, the following technical solution may be used:

[0093] Collect historical operation data corresponding to each target continuous decision variable of the second low-altitude flight service station; preprocess the historical operation data; standardize the preprocessed historical operation data according to the dimension of each target continuous decision variable to obtain a historical data matrix of each target continuous decision variable; calculate the information entropy of each target continuous decision variable based on the historical data matrix; and calculate the variable weight of each target continuous decision variable based on the information entropy.

[0094] For example, suppose there is The second low-altitude flight service station to be evaluated, for the A target continuous decision variable (such as the average response time indicator), whose data sequence is , ,..., .

[0095] In order to eliminate the influence of different dimensions, the data is standardized. If the target continuous decision variable corresponding to the data is a positive indicator, such as the effective coverage radius variable, the larger the indicator value, the better the coverage quality. The calculation formula for the standardized processing is as follows:

[0096]

[0097] in, Represents the first samples (i.e., in the evaluation of low-altitude flight service stations, it can be understood as Low-altitude flight service station) The standardized values ​​of the target continuous decision variable indicators are obtained. The purpose of standardization is to convert the raw data into dimensionless values ​​within the range [0, 1] to facilitate the subsequent calculation of information entropy and weights. Standardized data can eliminate the influence of different dimensions and orders of magnitude between different indicators, allowing them to be compared and calculated on the same scale.

[0098] Indicates the number of the historical running data set before standardization. samples (i.e., in the evaluation of low-altitude flight service stations, it can be understood as Low-altitude flight service station) The original observation value of the target continuous decision variable indicator.

[0099] Indicates the The target continuous decision variable index is in all samples (such as the data series set mentioned above , ,..., ). In the entire data set, for The target continuous decision variable index is used to find its minimum original observation value. When calculating the normalization of positive indicators, it serves as a benchmark so that the minimum original observation value is normalized to 0; when calculating the normalization of negative indicators, it is used as a benchmark so that the minimum original observation value is normalized to 0. Together we determined the scope of the data.

[0100] Indicates the The target continuous decision variable index is in all samples (such as the data series set mentioned above , ,..., ). In the entire data set, for The target continuous decision variable index is used to find its maximum original observation value. When calculating the normalization of the positive index, it is the same as Together they constitute the range of the data, so that the maximum original observation value is standardized to 1; when calculating the standardization of negative indicators, it serves as a benchmark, so that the maximum original observation value is standardized to 0.

[0101] Standardization transforms raw data, providing a unified data foundation for subsequent information entropy calculations and weight determination, ensuring fairness and comparability across different indicators in weight calculations. Through standardization, indicator data of varying types and ranges can be more scientifically incorporated into the information entropy and weight calculations, ultimately resulting in more reasonable indicator weights and enabling comprehensive evaluation of multiple continuous decision-making variable indicators.

[0102] If the target continuous decision variable corresponding to the data is a negative indicator, such as average response time, the smaller the indicator value, the better the response ability. The calculation formula for standardization is as follows:

[0103]

[0104] After the above standardization process, the historical data matrix of each target continuous decision variable is obtained ,in, Indicates the number of the second low-altitude flight service stations to be evaluated, Indicates the number of defined target continuous decision variables. This number It can be set according to the actual application scenario. For example, as mentioned above, when evaluating a Class A low-altitude flight service station, ; When evaluating Class B low-altitude flight service stations, .

[0105] The information entropy of each target continuous decision variable is calculated based on the historical data matrix, and the calculation formula is as follows:

[0106]

[0107] in, Indicates the The information entropy of the target continuous decision variable indicator; Indicates the number of the second low-altitude flight service station.

[0108] Finally, the variable weight of each target continuous decision variable is calculated according to the information entropy of each target continuous decision variable. The calculation formula is as follows:

[0109]

[0110] The variable weight distribution of each target continuous decision variable is obtained by calculation.

[0111] 104. Perform dimensionless processing on the index values ​​of each target continuous decision variable corresponding to the second low-altitude flight service station to obtain the dimensionless value of each target continuous decision variable index corresponding to the second low-altitude flight service station.

[0112] As described above, the collected target continuous decision variable index values ​​corresponding to the second low-altitude flight service station are standardized, and the collected target continuous decision variable index values ​​corresponding to the second low-altitude flight service station are converted into dimensionless values, that is, the purpose of dimensionless processing of the target continuous decision variable index values ​​corresponding to the second low-altitude flight service station is achieved, and the dimensionless values ​​of the target continuous decision variable indexes corresponding to the second low-altitude flight service station are obtained, that is, the historical data matrix as described above is obtained. .

[0113] 105. Calculate the comprehensive evaluation index I of the second low-altitude flight service station based on the variable weights of each target continuous decision variable and the dimensionless values ​​of each target continuous decision variable index.

[0114] As mentioned above, for For the second low-altitude flight service station, according to the variable weights of each target continuous decision variable Hedi The dimensionless values ​​of each target continuous decision variable index corresponding to the second low-altitude flight service station , calculate the The comprehensive evaluation index I of the second low-altitude flight service station is calculated as follows:

[0115]

[0116] in, Indicates the The variable weights of the target continuous decision variables, Indicates the The second low-altitude flight service station corresponds to the The dimensionless value of the target continuous decision variable indicator.

[0117] It should be noted that when evaluating a Class A low-altitude flight service station, , the target continuous decision variables include: effective coverage radius variable, coverage area overlap, average response time, response success rate, equipment resource adequacy, unit operating cost, flight accident warning accuracy and air traffic conflict resolution efficiency, then for the first For the second low-altitude flight service station, the variable weights of each target continuous decision variable include: (variable weights of effective coverage radius variables), (variable weights for coverage area overlap), (variable weights for average response time), (variable weight of response success rate), (variable weight of equipment resource adequacy), (variable weights of unit operating costs), (Variable weight of flight accident warning accuracy), (Variable weights of air traffic conflict resolution efficiency); The dimensionless values ​​of each target continuous decision variable index corresponding to the second low-altitude flight service station include: (No. the dimensionless value of the effective coverage radius variable index corresponding to the second low-altitude flight service station), (No. the dimensionless value of the coverage area overlap variable index corresponding to the second low-altitude flight service station), (No. the dimensionless value of the average response time variable indicator corresponding to the second low-altitude flight service station), (No. The dimensionless value of the response success rate variable indicator corresponding to the second low-altitude flight service station), (No. The dimensionless value of the equipment resource adequacy variable indicator corresponding to the second low-altitude flight service station), (No. the dimensionless value of the unit operating cost variable indicator corresponding to the second low-altitude flight service station), (No. The dimensionless value of the flight accident warning accuracy variable indicator corresponding to the second low-altitude flight service station) (No. The dimensionless value of the air traffic conflict resolution efficiency variable index corresponding to the second low-altitude flight service station)

[0118] When evaluating a Class B low-altitude flight service station, , each target continuous decision variable includes: effective coverage radius variable, coverage area overlap, equipment resource adequacy and unit operating cost, then for the first For the second low-altitude flight service station, the variable weights of each target continuous decision variable include: (variable weights of effective coverage radius variables), (variable weights for coverage area overlap), (variable weight of equipment resource adequacy), (Variable weight of unit operating cost); The dimensionless values ​​of each target continuous decision variable index corresponding to the second low-altitude flight service station include: (No. the dimensionless value of the effective coverage radius variable index corresponding to the second low-altitude flight service station), (No. the dimensionless value of the coverage area overlap variable index corresponding to the second low-altitude flight service station), (No. The dimensionless value of the equipment resource adequacy variable indicator corresponding to the second low-altitude flight service station), (No. The dimensionless value of the unit operating cost variable indicator corresponding to the second low-altitude flight service station).

[0119] 106. Determine a target low-altitude flight service station to be finally optimized from the second low-altitude flight service stations based on the comprehensive evaluation index I.

[0120] For each second low-altitude flight service station to be selected, its corresponding comprehensive evaluation index I can be calculated using the above formula. Finally, the I values ​​of each second low-altitude flight service station can be compared. The larger the I value, the better the comprehensive performance level of the service station. Therefore, the second low-altitude flight service stations can be sorted from large to small according to the comprehensive evaluation index I. Therefore, several second low-altitude service stations with the largest I value (front) or front I values ​​can be selected as the target low-altitude flight service stations for final optimization.

[0121] By using multi-objective decision analysis, the performance of each candidate low-altitude flight service station in the target site selection area in different performance dimensions is comprehensively and accurately evaluated. Finally, the low-altitude flight service station is comprehensively evaluated based on the comprehensive evaluation index I. In this way, multiple indicators of different dimensions and dimensions are integrated to form a unified evaluation standard, which facilitates more intuitive and scientific service station selection decisions; provides a strong basis for comprehensive evaluation and the final accurate and effective determination of the optimal flight service station; and is conducive to the rapid development of the low-altitude industry.

[0122] Example 2

[0123] Combination of the above Figure 1 The following describes in detail a method for optimizing the location of a low-altitude flight service station provided by an embodiment of the present application. Figure 2 A detailed description is given of a low-altitude flight service station site selection optimization system for executing a low-altitude flight service station site selection optimization method provided in an embodiment of the present application. Figure 2 This is a structural diagram of a low-altitude flight service station site selection optimization system provided in an embodiment of the present application; please refer to Figure 2 , the system comprises:

[0124] The candidate service station module 201 is used to determine at least one first low-altitude flight service station to be evaluated within the target site selection area;

[0125] A Benders calculation module 202 is configured to determine at least one second low-altitude flight service station from the at least one first low-altitude flight service station using a Benders decomposition algorithm based on predefined target continuous decision variables, wherein the index values ​​of the target continuous decision variables corresponding to the second low-altitude flight service station make the Benders decomposition algorithm meet a convergence condition, and the target continuous decision variables are used to characterize the performance level of the service station;

[0126] a variable weight module 203, configured to determine a variable weight of each target continuous decision variable corresponding to the second low-altitude flight service station;

[0127] A dimensionless conversion module 204 is configured to perform dimensionless processing on the index values ​​of the target continuous decision variables corresponding to the second low-altitude flight service station to obtain dimensionless values ​​of the index values ​​of the target continuous decision variables corresponding to the second low-altitude flight service station;

[0128] The comprehensive evaluation module 205 is used to calculate the comprehensive evaluation index I of the second low-altitude flight service station based on the variable weights of each target continuous decision variable and the dimensionless value of each target continuous decision variable indicator; and determine the final optimized target low-altitude flight service station from the second low-altitude flight service station based on the comprehensive evaluation index I.

[0129] Preferably, the Benders calculation module 202 is specifically used to: assign a corresponding weight coefficient to each first low-altitude flight service station according to a predefined target continuous decision variable; wherein the target continuous decision variable includes an effective coverage radius variable, coverage area overlap, average response time, response success rate, equipment resource adequacy, unit operating cost, flight accident warning accuracy and air traffic conflict resolution efficiency; determine an objective function according to the target continuous decision variable and the weight coefficient of the first low-altitude flight service station; take the minimum number of service stations required to cover the target site selection area and the predetermined total amount of operating resources required for each service station as constraints; construct a main problem solving function according to the objective function and the constraints, and use the main problem solving function to solve and obtain a number of initial solutions; based on A coverage quality sub-problem solving function is constructed based on the effective coverage radius variable and the coverage area overlap index; and a response capability sub-problem solving function is constructed based on the average response time and response success rate index; and a cost-effectiveness sub-problem solving function is constructed based on the equipment resource adequacy and unit operating cost index; and a safety assurance sub-problem solving function is constructed based on the flight accident warning accuracy and the air traffic conflict resolution efficiency; using several initial solutions obtained by solving the main problem solving function, the coverage quality sub-problem solving function, the response capability sub-problem solving function, the cost-effectiveness sub-problem solving function and the safety assurance sub-problem solving function are iteratively solved, and when the convergence condition is met, the iteration is stopped to obtain the optimal solution of the main problem solving function, and the second low-altitude flight service station is determined based on the optimal solution of the main problem solving function.

[0130] Preferably, the Benders calculation module 202 is specifically used to: assign a corresponding weight coefficient to each first low-altitude flight service station according to a predefined target continuous decision variable; wherein the target continuous decision variable includes an effective coverage radius variable, coverage area overlap, equipment resource adequacy and unit operating cost; determine an objective function according to the target continuous decision variable and the weight coefficient of the first low-altitude flight service station; minimize the number of service stations required to cover the target site selection area, and meet the pre-set limit on the total amount of operating resources required for each service station as constraints; and calculate the target service station based on the objective function and the constraints. A main problem-solving function is constructed by using the main problem-solving function to obtain several initial solutions; a coverage quality sub-problem-solving function is constructed according to the effective coverage radius variable and the coverage area overlap index; and a cost-effectiveness sub-problem-solving function is constructed according to the equipment resource adequacy and the unit operating cost index; the coverage quality sub-problem-solving function and the cost-effectiveness sub-problem-solving function are iteratively solved using the several initial solutions obtained by using the main problem-solving function. When the convergence condition is met, the iteration is stopped to obtain the optimal solution of the main problem-solving function, and the second low-altitude flight service station is determined according to the optimal solution of the main problem-solving function.

[0131] Preferably, the variable weight module 203 is specifically configured to: collect historical operating data corresponding to each target continuous decision variable of the second low-altitude flight service station; preprocess the historical operating data; divide the preprocessed historical operating data into a training set, a validation set, and a test set; establish a variable weight estimation model based on a multi-layer perceptron, and train the variable weight estimation model using the divided training set; define a mean square error loss function, and update the parameters of the variable weight estimation model using an optimizer in multiple iterations in combination with the validation set and the test set; the iterative convergence condition of the variable weight estimation model is to minimize the difference between the weight estimate value and the weight label value pre-annotated for the training set; obtain the estimated weight of each target continuous decision variable corresponding to the second low-altitude flight service station using the output of the trained variable weight estimation model; determine the correlation between each target continuous decision variable and the service station performance level; convert the estimated weight of each target continuous decision variable output by the variable weight estimation model into a probability distribution, and adjust the estimated weight based on the correlation between each target continuous decision variable and the service station performance level to obtain the variable weight of each target continuous decision variable corresponding to the second low-altitude flight service station.

[0132] Preferably, the variable weight module 203 is specifically used to: collect historical operation data corresponding to each target continuous decision variable of the second low-altitude flight service station; and preprocess the historical operation data; standardize the preprocessed historical operation data according to the dimension of each target continuous decision variable to obtain a historical data matrix of each target continuous decision variable; calculate the information entropy of each target continuous decision variable based on the historical data matrix; and calculate the variable weight of each target continuous decision variable based on the information entropy.

[0133] Preferably, the information entropy is calculated as follows:

[0134]

[0135] in, Indicates the The information entropy of the target continuous decision variable indicator; Indicates the number of the second low-altitude flight service station; Represents the first The second low-altitude flight service station corresponds to the The standardized value of the target continuous decision variable indicator.

[0136] The specific implementation method and technical effects of the site selection optimization system for the low-altitude flight service station are referred to the aforementioned site selection optimization method for the low-altitude flight service station, and will not be repeated here.

[0137] Example 3

[0138] An embodiment of the present invention further provides an electronic device, Figure 3 FIG. 1 is a structural diagram of an electronic device according to an embodiment of the present invention, Figure 3As shown, this electronic device includes a central processing unit (CPU) 701, which can execute various appropriate actions and processes according to programs stored in a read-only memory (ROM) 702 or programs loaded from a storage unit 708 into a random access memory (RAM) 703. RAM 703 also stores various programs and data required for system operation. CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to bus 704. The following components are connected to I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 708 including a hard disk; and a communication section 709 including a network interface card such as a LAN card or modem. Communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is mounted on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as combinations of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.

[0140] Example 4

[0141] An embodiment of the present invention further provides a computer-readable storage medium. This computer-readable storage medium may be included in the random path verification code-based security verification device described in the above embodiment, or may be a standalone computer-readable storage medium not incorporated into an electronic device. The computer-readable storage medium stores one or more programs, which are used by one or more processors to execute the method for optimizing the location of a low-altitude flight service station described in the present invention.

[0142] Example 5

[0143] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a computer device, it is used to implement a method for optimizing the site selection of a low-altitude flight service station of the present invention.

[0144] The above description is merely a preferred embodiment of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. A method for optimizing the site selection of a low-altitude flight service station, characterized in that: include: Identify at least one first low-altitude flight service station to be evaluated within the target site selection area; Assigning corresponding weight coefficients to each first low-altitude flight service station based on predefined target continuous decision variables; wherein the target continuous decision variables include effective coverage radius variable, coverage area overlap, average response time, response success rate, equipment resource adequacy, unit operating cost, flight accident warning accuracy, and air traffic conflict resolution efficiency; Determining an objective function based on the target continuous decision variable and the weight coefficient of the first low-altitude flight service station; using as constraints the minimum number of service stations required to cover the target site selection area and the satisfaction of a predetermined limit on the total amount of operating resources required for each service station; Constructing a main problem-solving function according to the objective function and the constraint conditions, and using the main problem-solving function to obtain a number of initial solutions; A function for solving the coverage quality sub-problem is constructed based on the effective coverage radius variable and the coverage area overlap index; a function for solving the response capability sub-problem is constructed based on the average response time and response success rate indicators; a function for solving the cost-effectiveness sub-problem is constructed based on the equipment resource adequacy and unit operating cost indicators; and a function for solving the safety assurance sub-problem is constructed based on the flight accident warning accuracy and air traffic conflict resolution efficiency. Using several initial solutions obtained by solving the main problem-solving function, the coverage quality sub-problem-solving function, the responsiveness sub-problem-solving function, the cost-effectiveness sub-problem-solving function, and the safety assurance sub-problem-solving function are iteratively solved. When a convergence condition is met, the iteration is stopped to obtain an optimal solution to the main problem-solving function. The second low-altitude flight service station is determined based on the optimal solution to the main problem-solving function. The index values ​​of the target continuous decision variables corresponding to the second low-altitude flight service station make the Benders decomposition algorithm meet the convergence condition, and the target continuous decision variables are used to characterize the performance level of the service station. Determining a variable weight for each target continuous decision variable corresponding to the second low-altitude flight service station; and performing dimensionless processing on the index value of each target continuous decision variable corresponding to the second low-altitude flight service station to obtain a dimensionless index value of each target continuous decision variable corresponding to the second low-altitude flight service station; According to the variable weights of each target continuous decision variable and the dimensionless values ​​of each target continuous decision variable index, the comprehensive evaluation index I of the second low-altitude flight service station is calculated; according to the comprehensive evaluation index I, the final optimized target low-altitude flight service station is determined from the second low-altitude flight service station.

2. The method for optimizing the site selection of a low-altitude flight service station according to claim 1, wherein: Determining the variable weights of each target continuous decision variable corresponding to the second low-altitude flight service station includes: Collecting historical operation data corresponding to each target continuous decision variable of the second low-altitude flight service station; preprocessing the historical operation data; and dividing the preprocessed historical operation data into a training set, a validation set, and a test set; A variable weight estimation model is established based on a multi-layer perceptron, and the variable weight estimation model is trained using a divided training set; a mean square error loss function is defined, and the parameters of the variable weight estimation model are updated multiple times iteratively using an optimizer in combination with the validation set and the test set; the iterative convergence condition of the variable weight estimation model is minimizing the difference between the weight estimate value and the weight label value pre-annotated for the training set; and the estimated weight of each target continuous decision variable corresponding to the second low-altitude flight service station is obtained using the output of the trained variable weight estimation model; Determine the correlation between each target continuous decision variable and the performance level of the service station; The estimated weights of each target continuous decision variable output by the variable weight estimation model are converted into a probability distribution. Combined with the correlation between each target continuous decision variable and the performance level of the service station, the estimated weights are adjusted to obtain the variable weights of each target continuous decision variable corresponding to the second low-altitude flight service station.

3. The method for optimizing the site selection of a low-altitude flight service station according to claim 1, wherein: Determining the variable weights of each target continuous decision variable corresponding to the second low-altitude flight service station includes: collecting historical operation data corresponding to each target continuous decision variable of the second low-altitude flight service station; and preprocessing the historical operation data; Normalizing the preprocessed historical operation data according to the dimensions of each target continuous decision variable to obtain a historical data matrix of each target continuous decision variable; Calculating the information entropy of each target continuous decision variable according to the historical data matrix; The variable weight of each target continuous decision variable is calculated according to the information entropy.

4. The method for optimizing the site selection of a low-altitude flight service station according to claim 3, wherein: The information entropy is calculated as follows: ； in, Indicates the The information entropy of the target continuous decision variable indicator; Indicates the number of the second low-altitude flight service station; Represents the first The second low-altitude flight service station corresponds to the The standardized value of the target continuous decision variable indicator.

5. A site selection optimization system for low-altitude flight service stations, characterized in that: include: A service station to be selected module, used to determine at least one first low-altitude flight service station to be evaluated in a target site selection area; A Benders calculation module is used to determine at least one second low-altitude flight service station from the at least one first low-altitude flight service station based on predefined target continuous decision variables and using a Benders decomposition algorithm, wherein the index values ​​of each target continuous decision variable corresponding to the second low-altitude flight service station make the Benders decomposition algorithm meet the convergence conditions, and the target continuous decision variables are used to characterize the performance level of the service station; the Benders calculation module is specifically used to: assign corresponding weight coefficients to each first low-altitude flight service station according to the predefined target continuous decision variables; wherein the target continuous decision variables include effective coverage radius variables, coverage area overlap, average response time, response success rate, equipment resource adequacy, unit operating cost, flight accident warning accuracy and air traffic conflict resolution efficiency; determine the objective function based on the target continuous decision variables and the weight coefficients of the first low-altitude flight service station; minimize the number of service stations required to cover the target site selection area, and meet the pre-set a limit on the total amount of operating resources required for each service station as a constraint; constructing a main problem-solving function based on the objective function and the constraint conditions, and using the main problem-solving function to obtain a number of initial solutions; constructing a coverage quality sub-problem-solving function based on the effective coverage radius variable and the coverage area overlap index; and constructing a response capability sub-problem-solving function based on the average response time and response success rate index; and constructing a cost-effectiveness sub-problem-solving function based on the equipment resource adequacy and the unit operating cost index; and constructing a safety assurance sub-problem-solving function based on the flight accident warning accuracy and the air traffic conflict resolution efficiency; using the several initial solutions obtained by solving the main problem-solving function, iteratively solving the coverage quality sub-problem-solving function, the response capability sub-problem-solving function, the cost-effectiveness sub-problem-solving function, and the safety assurance sub-problem-solving function, and stopping the iteration when the convergence condition is met to obtain the optimal solution of the main problem-solving function, and determining the second low-altitude flight service station based on the optimal solution of the main problem-solving function; a variable weight module, configured to determine a variable weight of each target continuous decision variable corresponding to the second low-altitude flight service station; a dimensionless conversion module, configured to perform dimensionless processing on the index values ​​of the target continuous decision variables corresponding to the second low-altitude flight service station to obtain dimensionless values ​​of the index values ​​of the target continuous decision variables corresponding to the second low-altitude flight service station; A comprehensive evaluation module is used to calculate the comprehensive evaluation index I of the second low-altitude flight service station based on the variable weights of each target continuous decision variable and the dimensionless value of each target continuous decision variable indicator; and determine the final optimized target low-altitude flight service station from the second low-altitude flight service station based on the comprehensive evaluation index I.

6. An electronic device, characterized in that: The electronic device includes: at least one processor; a memory communicatively connected to the at least one processor; and a computer program stored on the memory and running on the at least one processor; wherein, when the at least one processor executes the computer program, it is used to implement the site selection optimization method for a low-altitude flight service station as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer program in the computer-readable storage medium is used to implement the site selection optimization method for a low-altitude flight service station as described in any one of claims 1 to 4 when executed by a computer device.

8. A computer program product, comprising a computer program, characterized in that: When executed by a computer device, the computer program is used to implement the site selection optimization method for a low-altitude flight service station as described in any one of claims 1 to 4.

Images