Aviation route opening matching method and system

Abstract

The invention relates to an airline opening matching method and system. The method comprises the following steps: acquiring airport demand information and airline company supply information; constructing a demand matching strategy and a demand matching algorithm model; screening out initially matched airport demand information and airline company supply information by using a demand matching strategy; the matching degree of the airport demand information and the airline company supply information which are preliminarily matched is calculated through a demand matching algorithm model, and a matching result is obtained; the airport operation company and the airline company carry out online matchmaking negotiation through the Internet according to the matching result to obtain an airline opening result; according to the invention, by integrating the resource information of the airport and the airline company, accurate matching of the demands of the two parties is realized, rapid opening of a new airline is promoted, the communication efficiency is remarkably improved, the opening cost is reduced, and optimal configuration of resources is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of informatization of air transportation management, and specifically relates to a method and system for matching the opening of air routes. Background Art

[0002] With the rapid development of the air transportation industry, the cooperation demand between airports and airlines has been increasing day by day. However, in the traditional mode, there are problems such as information asymmetry, high communication costs, and low resource matching efficiency in opening new routes, which seriously restrict the rapid response and deployment of opening new routes, resulting in a long cycle and high cost for opening new routes. Summary of the Invention

[0003] In order to solve the technical problems of information asymmetry, high communication costs, and low resource matching efficiency in opening new routes in the prior art, the present invention provides a method and system for matching the opening of air routes.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] A method for matching the opening of air routes includes the following steps:

[0006] Collect airport demand information and airline supply information;

[0007] Construct a demand matching strategy and a demand matching algorithm model;

[0008] Use the demand matching strategy to initially match the airport demand information and the airline supply information to screen out the initially matched airport demand information and airline supply information;

[0009] Use the demand matching algorithm model to calculate the matching degree of the initially matched airport demand information and airline supply information to obtain a matching result;

[0010] According to the matching result, conduct online matching negotiation through the Internet to obtain the result of route opening.

[0011] The beneficial effects of the present invention are as follows: By performing two matches on the supply information of airports and the demand information of airlines, it can significantly improve the matching and efficient cooperation between airports and airlines in the process of opening new routes, improve the efficiency of route opening, and optimize resource allocation. At the same time, by constructing an efficient communication channel and progress tracking mechanism, it helps both parties to promptly discover problems and take measures to ensure the smooth progress of opening new routes. In addition, the implementation of data security and encryption protection measures effectively improves the security of the system and protects the sensitive information of route opening from being infringed.

[0012] On the basis of the above technical solutions, the present invention can also be improved as follows.

[0013] Furthermore, the airport demand information is provided by the airport operation company;

[0014] The airline supply information is provided by the airline;

[0015] After collecting the airport demand information and the airline supply information, the following steps are further included:

[0016] Construct a demand database;

[0017] Encrypt the airport demand information and the airline supply information through a data encryption algorithm;

[0018] Store the encrypted airport demand information and the airline supply information in the demand database.

[0019] Furthermore, constructing a demand database specifically includes the following steps:

[0020] Construct a blockchain;

[0021] Set the demand database on the blockchain.

[0022] Furthermore, the demand matching strategy includes a model - runway compatibility matching strategy and a flight schedule conflict strategy. The airport demand information includes airport runway data and airport runway usage time data, and the airline supply information includes flight model data and flight schedule data;

[0023] Use the demand matching strategy to initially match the airport demand information and the airline supply information to screen out the initially matched airport demand information and airline supply information, which specifically includes the following steps:

[0024] Use the model - runway compatibility matching strategy to initially match the airport runway data and the flight model data to screen out the initially matched airport runway data and flight model data;

[0025] Use the flight schedule conflict strategy to initially match the airport runway usage time data and the flight schedule data to screen out the initially matched airport runway usage time data and flight schedule data.

[0026] Furthermore, the demand matching algorithm model includes a route network optimization model, a time - series prediction model, and a reinforcement learning model;

[0027] Use the demand matching algorithm model to calculate the matching degree of the initially matched airport demand information and airline supply information, and obtain a matching result, which specifically includes the following steps:

[0028] Construct a directed graph of the route network for all airports; wherein, the directed graph of the route network includes multiple nodes, each node represents an airport, the in-degree of each node in the directed graph of the route network represents the number of flights flowing to the airport corresponding to the node, the out-degree of each node represents the number of flights flowing out of the airport corresponding to the node, and each link in the directed graph of the route network represents a flight route;

[0029] Construct an optimization model for the route network based on graph theory algorithms;

[0030] Use the optimization model of the route network to calculate the edge weights of each node in the directed graph of the route network;

[0031] Screen out the airport demand information corresponding to the airports of the nodes in the directed graph of the route network whose initially matched edge weights are higher than the preset edge weight threshold;

[0032] Construct a time series prediction model;

[0033] Use the time series prediction model to predict potentially valuable flight routes based on the screened airport demand information;

[0034] Construct a reinforcement learning model;

[0035] Use the reinforcement learning model to calculate the matching degree of potentially valuable flight routes based on the screened airport demand information and the airline supply information to obtain the matching result.

[0036] Further, the airport demand information also includes airport operation data and airport subsidy data;

[0037] Use the time series prediction model to predict potentially valuable flight routes based on the screened airport demand information. The specific steps are as follows:

[0038] Substitute the airport operation data and the airport subsidy data of the screened airport demand information into the time series prediction model to predict potentially valuable flight routes and obtain potentially valuable flight routes.

[0039] Further, the airline supply information includes shipping intensity data, and the airport demand information also includes route planning data;

[0040] Use the reinforcement learning model to calculate the matching degree of potentially valuable flight routes based on the screened airport demand information and the airline supply information to obtain the matching result. The specific steps are as follows:

[0041] Using the reinforcement learning model, according to the weight values of the airport operation data and airport subsidy data corresponding to the calculated potential value routes, the airport operation weight value and the airport subsidy weight value are correspondingly obtained;

[0042] Using the reinforcement learning model, according to the weight values of the shipping intensity data of the airline supply information and the route planning data of the airport demand information selected by calculation, the shipping intensity weight value and the route planning weight value are correspondingly obtained;

[0043] According to the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value, and the route planning weight value, the matching degree of the potentially valuable routes is calculated to obtain the matching result.

[0044] Further, according to the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value, and the route planning weight value, the matching degree of the potentially valuable routes is calculated to obtain the matching result. The specific steps are as follows:

[0045] Sum the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value, and the route planning weight value to obtain a matching degree score value; wherein, the matching result includes the matching degree score value.

[0046] Further, the airport operation company and the airline conduct online matching and negotiation through the Internet according to the matching result to obtain the route opening result. The specific steps are as follows:

[0047] Generate route economic measurement data according to the matching result;

[0048] The airport operation company and the airline share the route economic measurement data through the Internet for online matching and negotiation to obtain the route opening result.

[0049] To solve the above technical problems, the present invention also provides an air route opening matching system. The specific technical content is as follows:

[0050] An air route opening matching system adopting the above air route opening matching method, including:

[0051] A demand release module, used to collect airport demand information and airline supply information;

[0052] An intelligent matching module, which is used to construct a demand matching strategy and a demand matching algorithm model; to initially match the airport demand information and the airline supply information by using the demand matching strategy, so as to screen out the initially matched airport demand information and airline supply information; to calculate the matching degree of the initially matched airport demand information and airline supply information by using the demand matching algorithm model, and obtain a matching result;

[0053] An online negotiation module, which is used to conduct online matchmaking negotiation through the Internet according to the matching result, and obtain a route opening result;

[0054] A progress tracking module, which is used to display the progress of route opening in real time. Description of the Drawings

[0055] Figure 1 It is a flowchart of a method for matchmaking the opening of an airline route in an embodiment of the present invention;

[0056] Figure 2 It is a schematic structural diagram of a system for matchmaking the opening of an airline route in an embodiment of the present invention. Detailed Embodiment

[0057] The principles and features of the present invention will be described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0058] As Figure 1 shown, this embodiment provides a method for matchmaking the opening of an airline route, including the following steps:

[0059] S1. Collect airport demand information and airline supply information;

[0060] Collecting airport demand information and airline supply information specifically includes the following steps:

[0061] S101. The airport operating company releases the airport demand information;

[0062] S102. The airline releases the airline supply information;

[0063] S103. Construct a demand database;

[0064] Constructing a demand database specifically includes the following steps:

[0065] Construct a blockchain;

[0066] Set the demand database on the blockchain; wherein, the airport operating company and the airline access the demand database through a smart contract.

[0067] The setting of the data protection solution based on blockchain technology can achieve the following functions:

[0068] (1) Data encryption: Use advanced encryption algorithms (such as AES, RSA, etc.) to encrypt and store sensitive data during storage and transmission.

[0069] (2) Blockchain construction: Build a blockchain network, store the encrypted data on the blockchain, and utilize the immutability and decentralization characteristics of the blockchain to improve data security.

[0070] (3) Access control: Combine smart contracts to achieve fine-grained access control, and only authorized users can access and modify relevant data.

[0071] (4) Audit and monitoring: Conduct real-time auditing and monitoring of data access behaviors. Once abnormal access or data leakage risks are detected, immediately take measures for prevention and disposal. Conduct real-time monitoring of all data operation behaviors in the enterprise internal network environment, record and generate audit logs, and promptly detect and handle abnormal behaviors.

[0072] S104. Encrypt the airport demand information and the airline supply information through a data encryption algorithm;

[0073] S105. Store the encrypted airport demand information and the airline supply information in the demand database.

[0074] S2. Construct a demand matching strategy and a demand matching algorithm model;

[0075] The demand matching strategy includes a model runway compatibility matching strategy and a flight schedule conflict strategy. The airport demand information includes airport runway data and airport runway usage time data. The airline supply information includes flight model data and flight schedule data. The demand matching algorithm model includes a route network optimization model, a time series prediction model, and a reinforcement learning model.

[0076] The route network optimization model is specifically a PageRank algorithm model based on graph theory. The basic idea of the PageRank algorithm is to define a random walk model on a directed graph Q, that is, a first-order Markov chain, to describe the behavior of a random walker randomly visiting each node along the directed graph. Under certain conditions, in the limit case, the probability of visiting each node converges to a stationary distribution. At this time, the stationary probability value of each node is its PageRank value, representing the importance of the node. PageRank is defined recursively for Q, and the calculation of PageRank can be carried out through an iterative algorithm. It is necessary to first construct a route network diagram of the airport; the route network diagram includes multiple nodes, and each node represents an airport.

[0077] The time series prediction model specifically uses the LSTM model or the Prophet model. LSTM and Prophet are two commonly used time series prediction models, each with its own advantages and disadvantages and applicable to different scenarios. LSTM (Long Short-Term Memory) is a special type of recurrent neural network (RNN) designed to address the problem of vanishing or exploding gradients that standard RNNs often encounter when dealing with long sequence data. Through its unique cell structure, including forget gates, input gates, and output gates, LSTM can effectively capture and maintain long-term dependencies.

[0078] The time series prediction model is a route matching model based on multi-factor weights, which specifically includes:

[0079] Data preprocessing: Collect and clean the historical operation data of airports and airlines, including flight frequencies, load factors, aircraft type distributions, route networks, operating costs, etc.

[0080] Feature engineering: Extract key features such as airport capacity, airline capacity, market demand (such as population mobility data), route competition situation, etc., and standardize these features.

[0081] Weight assignment: Assign weights to each feature to reflect its importance in the new route matching.

[0082] Matching degree calculation: For each combination of airport and airline, calculate its comprehensive matching degree based on feature weights. Methods such as weighted average method, analytic hierarchy process (AHP), etc. can be used for calculation.

[0083] Optimal solution screening: According to the matching degree ranking, select the groups of airport and airline combinations with the highest matching degree as the recommended new route opening solutions.

[0084] The reinforcement learning model specifically uses the PPO (Proximal Policy Optimization) algorithm model to dynamically adjust weights. Proximal Policy Optimization (PPO) is a reinforcement learning algorithm designed to ensure both performance improvement and algorithm stability and efficiency in complex tasks. The following introduces its core concepts and processes in an easy-to-understand way. Among them, the state space of the reinforcement learning model: current market supply-demand ratio, historical matching success rate, user feedback. Action space: Adjust the weight values of α, β, γ. Reward function: R = 0.6; matching success rate + 0.3; matching score - 0.1; resource waste rate.

[0085] S3. Use the demand matching strategy to initially match the airport demand information and the airline supply information to screen out the initially matched airport demand information and airline supply information;

[0086] Using the demand matching strategy to initially match the airport demand information and the airline supply information to screen out the initially matched airport demand information and airline supply information specifically includes the following steps:

[0087] S301. Use the aircraft - runway compatibility matching strategy to initially match the airport runway data and the flight aircraft type data to screen out the initially matched airport runway data and flight aircraft type data;

[0088] S302. Use the flight schedule conflict strategy to initially match the airport runway usage time data and the flight schedule data to screen out the initially matched airport runway usage time data and flight schedule data.

[0089] S4. Use the demand matching algorithm model to calculate the matching degree of the initially matched airport demand information and airline supply information to obtain a matching result;

[0090] Using the demand matching algorithm model to calculate the matching degree of the initially matched airport demand information and airline supply information to obtain a matching result specifically includes the following steps:

[0091] S401. Construct a directed graph of the route network for all airports; wherein, the directed graph of the route network includes multiple nodes, each node represents an airport, the in - link number of each node in the directed graph of the route network represents the number of flights flowing to the airport corresponding to the node, the out - link number of each node represents the number of flights flowing out from the airport corresponding to the node, and each link in the directed graph of the route network represents a route;

[0092] S402. Construct a route network optimization model based on graph theory algorithms;

[0093] S403. Use the route network optimization model to calculate the edge weights of each node in the directed graph of the route network;

[0094] S404. Screen out the airport demand information of the airports corresponding to the nodes in the directed graph of the route network whose initially matched edge weights are higher than the preset edge weight threshold; the airport demand information also includes airport operation data and airport subsidy data;

[0095] Use the time - series prediction model to predict potential - value routes based on the screened - out airport demand information. The specific steps are as follows:

[0096] Substitute the airport operation data and the airport subsidy data of the screened airport demand information into the time series prediction model to predict the routes with potential value, and obtain the routes with potential value.

[0097] S405. Construct a time series prediction model;

[0098] S406. Use the time series prediction model to predict the routes with potential value according to the screened airport demand information;

[0099] S407. Construct a reinforcement learning model;

[0100] S408. Use the reinforcement learning model to calculate the matching degree of the routes with potential value according to the screened airport demand information and the airline supply information, and obtain the matching result.

[0101] The airline supply information includes shipping intensity data, and the airport demand information further includes route planning data;

[0102] Using the reinforcement learning model to calculate the matching degree of the routes with potential value according to the screened airport demand information and the airline supply information, and obtaining the matching result specifically includes the following steps:

[0103] Using the reinforcement learning model, according to the weight values of the airport operation data and the airport subsidy data corresponding to the calculated routes with potential value, obtain the airport operation weight value and the airport subsidy weight value correspondingly;

[0104] Using the reinforcement learning model, according to the weight values of the shipping intensity data of the screened airline supply information and the route planning data of the airport demand information, obtain the shipping intensity weight value and the route planning weight value correspondingly; wherein, the route planning data represents the airports corresponding to the routes during route planning.

[0105] Calculate the matching degree of the routes with potential value according to the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value and the route planning weight value, and obtain the matching result.

[0106] Furthermore, calculating the matching degree of the routes with potential value according to the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value and the route planning weight value, and obtaining the matching result, the specific steps are:

[0107] Sum the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value, and the route planning weight value to obtain the matching degree score value; among them, the matching result includes the matching degree score value.

[0108] The calculation method of the matching degree score value is as follows:

[0109] The data preprocessing data includes: airport data, airline shipping intensity data, subsidy intensity data, and route planning data.

[0110] Output: Matching degree score (0 - 10).

[0111] Route matching degree: N = N1 * X1 + N2 * X2 + N3 * X3;

[0112] For example, average revenue per available seat kilometer: N1 (average revenue per available seat kilometer) = ∑ average revenue per available seat kilometer in the past 3 years / 3;

[0113] As shown in Table 1, the following is a case of the weight value of a certain route opened in the past (the weight value adopts a dynamic algorithm)

[0114]

[0115] Table 1 Case of the weight value of a certain route opened

[0116] Such as Figure 1 As shown, the airport operation weight value includes the weight value of the average revenue per available seat kilometer index, the average discount rate index weight value, the average load factor index weight value, the airfield grade index weight value, the airport on-time rate index weight value, and the available slot index weight value. Each index corresponds to a weight value.

[0117] The airport subsidy weight value includes the fixed subsidy index weight value, the differential subsidy index weight value, the other subsidy policy index weight value, and the historical route subsidy timeliness index weight value;

[0118] The shipping intensity weight value includes the aircraft type index weight value, the number of seats index weight value, and the intended flight area index weight value; it should be noted that the shipping intensity in the present invention mainly refers to the idle transport capacity of the airline. For example, if an airline has an aircraft and has completed the planned flights in the morning and is idle in the afternoon, it means that the aircraft of this airline has idle transport capacity in the afternoon.

[0119] The route planning weight value includes the weight value of the area or flight point of the proposed route, the schedule index weight value, and the proposed flight season index weight value.

[0120] S5. The airport operation company and the airline conduct online matchmaking and negotiation through the Internet according to the matching result to obtain the route opening result.

[0121] The airport operation company and the airline conduct online matchmaking negotiations via the Internet based on the matching result to obtain the route opening result. The specific steps are as follows:

[0122] S501. Generate route economic calculation data according to the matching result;

[0123] S502. The airport operation company and the airline share the route economic calculation data via the Internet for online matchmaking negotiations to obtain the route opening result.

[0124] A full-link tracking mechanism is also set up, that is, by setting a Gantt chart dashboard and an exception warning mechanism;

[0125] (1) Gantt chart dashboard: Automatically generate route opening milestones (approval by the aviation authority, schedule coordination, first flight date).

[0126] (2) Exception warning: Trigger a reminder based on the process time limit threshold (such as "The schedule coordination has exceeded the average processing cycle by 3 days").

[0127] By matching the supply information of the airport and the demand information of the airline twice, it can significantly improve the matchmaking and efficient cooperation between the airport and the airline during the process of opening a new route, enhance the route opening efficiency, and optimize resource allocation. At the same time, by building an efficient communication channel and progress tracking mechanism, it helps both parties to discover problems in a timely manner and take measures to ensure the smooth progress of the new route opening. In addition, the implementation of data security and encryption protection measures effectively improves the security of the system and protects the sensitive information of the route opening from being infringed.

[0128] As Figure 2 shown, in some other embodiments, an airline route opening matchmaking system is also provided, including:

[0129] A demand release module, which is used to collect airport demand information and airline supply information;

[0130] An intelligent matching module, which is used to build a demand matching strategy and a demand matching algorithm model; use the demand matching strategy to initially match the airport demand information and the airline supply information to screen out the initially matched airport demand information and airline supply information; calculate the matching degree of the initially matched airport demand information and airline supply information using the demand matching algorithm model to obtain the matching result;

[0131] An online consultation module, which is used to enable the airport operation company and the airline to conduct online matchmaking negotiations via the Internet based on the matching result to obtain the route opening result;

[0132] A progress tracking module, which is used to display the progress of the route opening in real time.

[0133] The demand release module includes an airport demand release module and an airline demand release module;

[0134] The airport demand release module, the airline demand release module, the intelligent matching module, the online consultation module, and the progress tracking module.

[0135] 1). The intelligent matching module is built with an intelligent algorithm that can automatically perform matching analysis based on the demand information released by airports and airlines and recommend the optimal route opening plan.

[0136] 2). The online consultation module provides a real-time communication function to support online consultations between airports and airlines.

[0137] 3). The progress tracking module can display the progress of new route openings in real time, including the completion of tasks at each stage and the estimated completion time, etc.

[0138] System process:

[0139] 1. Demand collection stage:

[0140] The airport uploads the timetable in the IATA standard format, and the system automatically parses the available time windows.

[0141] The airline synchronizes capacity data through the API (such as the Sabre flight schedule system).

[0142] 2. Intelligent matching stage:

[0143] First round of screening: The rules engine eliminates hard conflicts (mismatches between airline and airport demands).

[0144] Second round of matching: Hybrid collaborative filtering algorithm (multi-algorithm model screening and matching).

[0145] 3. Simulation and deduction stage:

[0146] Monte Carlo simulation predicts the three-year revenue of the new route and generates a risk heat map.

[0147] 4. Agreement signing stage:

[0148] Key terms of blockchain evidence storage (subsidy amount, default terms) are generated into a smart contract.

[0149] System technical deployment:

[0150] (1) Database:

[0151] Use Debezium to achieve real-time capture of MySQL binlog and synchronize it to the ClickHouse columnar database.

[0152] (2) Algorithm Deployment:

[0153] Model Service-ization: TensorFlow Serving is used to deploy the route prediction model, supporting AB test traffic allocation.

[0154] (3) Security Design:

[0155] The sensitive data (fare strategy) of the airline is encrypted and calculated using the SGX trusted execution environment.

[0156] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the concept and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for matching the opening of an aviation route, characterized in that, It includes the following steps: Collect airport demand information and airline supply information; Construct a demand matching strategy and a demand matching algorithm model; Use the demand matching strategy to initially match the airport demand information and the airline supply information to screen out the initially matched airport demand information and airline supply information; Use the demand matching algorithm model to calculate the matching degree of the initially matched airport demand information and airline supply information to obtain a matching result; Based on the matching result, conduct online matchmaking negotiation through the Internet to obtain a route opening result.

2. The method for matching and facilitating the opening of an air route according to claim 1, wherein The airport demand information is provided by the airport operation company The airline supply information is provided by the airline; After collecting the airport demand information and the airline supply information, it further includes the following steps: Construct a demand database; Encrypt the airport demand information and the airline supply information through a data encryption algorithm; Store the encrypted airport demand information and airline supply information in the demand database.

3. The aviation route opening matching method according to claim 2, characterized in that Construct a demand database, which specifically includes the following steps: Construct a blockchain; Set the demand database on the blockchain.

4. The air route opening matching method according to claim 2, wherein The demand matching strategy includes a model-runway compatibility matching strategy and a flight schedule conflict strategy. The airport demand information includes airport runway data and airport runway usage time data. The airline supply information includes flight model data and flight schedule data; Use the demand matching strategy to initially match the airport demand information and the airline supply information to screen out the initially matched airport demand information and airline supply information, which specifically includes the following steps: Use the model-runway compatibility matching strategy to initially match the airport runway data and the flight model data to screen out the initially matched airport runway data and flight model data; Use the flight schedule conflict strategy to initially match the airport runway usage time data and the flight schedule data to screen out the initially matched airport runway usage time data and flight schedule data.

5. The aviation route opening matchmaking method according to claim 4, wherein The demand matching algorithm model includes a route network optimization model, a time series prediction model, and a reinforcement learning model; Use the demand matching algorithm model to calculate the matching degree of the initially matched airport demand information and airline supply information to obtain a matching result, which specifically includes the following steps: Construct a directed graph of the route network of all airports; among them, the directed graph of the route network includes multiple nodes, and each node represents an airport; Construct a route network optimization model based on graph theory algorithms; Use the route network optimization model to calculate the edge weights of each node in the directed graph of the route network; Screen out the airport demand information of the airports corresponding to the nodes in the directed graph of the route network whose initially matched edge weights are higher than the preset edge weight threshold; Construct a time series prediction model; Use the time series prediction model to predict potential valuable routes based on the screened airport demand information; Construct a reinforcement learning model; Using the reinforcement learning model, calculate the matching degree of the potentially valuable routes based on the selected airport demand information and the airline supply information to obtain the matching result.

6. The air route opening matching method according to claim 5, wherein The airport demand information further includes airport operation data and airport subsidy data; Using the time series prediction model, predict the potentially valuable routes based on the selected airport demand information. The specific steps are as follows: Substitute the airport operation data and the airport subsidy data of the selected airport demand information into the time series prediction model to predict the potentially valuable routes and obtain the potentially valuable routes.

7. The aviation route opening matching method according to claim 6, characterized in that The airline supply information includes shipping intensity data, and the airport demand information further includes route planning data; Using the reinforcement learning model, calculate the matching degree of the potentially valuable routes based on the selected airport demand information and the airline supply information to obtain the matching result. The specific steps include the following: Using the reinforcement learning model, obtain the airport operation weight value and the airport subsidy weight value corresponding to the weight values of the airport operation data and the airport subsidy data corresponding to the calculated potentially valuable routes; Using the reinforcement learning model, obtain the shipping intensity weight value and the route planning weight value corresponding to the weight values of the shipping intensity data of the selected airline supply information and the route planning data of the airport demand information; Calculate the matching degree of the potentially valuable routes based on the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value, and the route planning weight value to obtain the matching result.

8. The aviation route opening matching method according to claim 7, characterized in that Calculate the matching degree of the potentially valuable routes based on the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value, and the route planning weight value to obtain the matching result. The specific steps are as follows: Sum the airport operation weight value, the airport subsidy weight value, the shipping intensity weight value, and the route planning weight value to obtain the matching degree score value; wherein, the matching result includes the matching degree score value.

9. The air route opening matchmaking method according to claim 1, wherein According to the matching result, conduct online matchmaking negotiation through the Internet to obtain the route opening result. The specific steps are as follows: Generate route economic calculation data according to the matching result; Share the route economic calculation data through the Internet for online matchmaking negotiation to obtain the route opening result.

10. An air route opening matchmaking system adopting the air route opening matchmaking method according to any one of claims 1 to 9, characterized in that, Including: A demand release module for collecting airport demand information and airline supply information; An intelligent matching module for constructing a demand matching strategy and a demand matching algorithm model; for initially matching the airport demand information and the airline supply information using the demand matching strategy to screen out the initially matched airport demand information and airline supply information; Calculate the matching degree of the initially matched airport demand information and airline supply information using the demand matching algorithm model to obtain the matching result; An online negotiation module for conducting online matchmaking negotiation through the Internet according to the matching result to obtain the route opening result; Progress tracking module, used to display the progress of route opening in real time.

Images