System and method for allocating boarding gates based on historical data and transfer passenger information

By combining historical data and transit passenger information, the boarding gate allocation plan is optimized, and the problem of inconsistent with the actual situation in the existing technology is solved, and more efficient flight and passenger services are achieved, especially in flight delay processing. It provides real-time adjustment capabilities.

CN114330971BActive Publication Date: 2024-12-06QINGDAO CIVIL AVIATION KAIYA SYST INTEGRATION CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111281403.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-01
Publication Date
2024-12-06
Estimated Expiration
2041-11-01

AI Technical Summary

Technical Problem

The existing technology has not achieved a good combination of specific historical data and algorithm models, and has not reflected the service concept well at the level of the transit service business model, resulting in the inconsistent gate allocation results that are not consistent with the actual situation and flight delays Not real-time enough.

Method used

By obtaining historical data of flights and boarding gates, analyzing the boarding gates periodically allocated by flights, and based on the predicted flight delays and transit passenger information, the transfer efficiency and historical allocation fit indicators are used to pre-allocate the boarding gates and Adjust and use technologies such as LSTM and genetic algorithms to optimize the gate allocation plan.

Benefits of technology

It improves the compatibility of boarding gate allocation, alleviates the adjustment efforts between flights and boarding gates, realizes real-time dynamic adjustments to flight delays, and improves passenger satisfaction and transit efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114330971B_ABST
    Figure CN114330971B_ABST
Patent Text Reader

Abstract

The present invention discloses a system and method for allocating boarding gates based on historical data and transfer passenger information, including: obtaining historical data of flights and boarding gates, as well as transfer passenger information and corresponding transfer flights; analyzing and obtaining boarding gates periodically allocated to flights, and predicting flight delays based on flight historical data, and calculating pre-allocated boarding gates; using indicators including transfer efficiency and fit of historically allocated boarding gates to evaluate pre-allocated check-in gates. The present invention improves the fit between the allocated boarding gates and the actual situation, conforms to the flight's stop habits, and alleviates the large-scale adjustment of flights and boarding gates; and through rolling predictions of flight delays, real-time dynamic adjustments to flights can be achieved; and evaluation indicators for transfer passengers are added so that the obtained boarding gate allocation plan can better improve passenger satisfaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of civil aviation technology, and in particular to a system and method for allocating boarding gates based on historical data and transfer passenger information. Background Art

[0002] The intelligent boarding gate allocation system studies the reasonable allocation of boarding gates for incoming flights based on the existing airport airspace resources, runway resources, taxiway resources, apron boarding gate resources and terminal resources, formulates flight plans, and improves resource utilization and work efficiency. The research on the intelligent boarding gate allocation system is a typical integer programming problem. Compared with general integer programming problems, the intelligent boarding gate allocation problem is special and has a complex application environment due to the influence of factors such as many variables, many constraints, and many optimization objectives.

[0003] Existing research results on boarding gate allocation can be roughly divided into three categories according to different methods: one is the mathematical programming of boarding gate allocation; the mathematical model represents the business model, the constraints are summarized, the relationship is quantified, and then the optimization solution algorithm is further studied from the perspective of mathematics and operations research. The other is the artificial intelligence method; the artificial intelligence method of boarding gate allocation is the introduction of expert systems, which simulates the ability of domain experts to analyze and solve complex problems. Usually, flight and boarding gate information is converted into "knowledge expression", and a "knowledge base" of flight and boarding gate information is constructed. Then, the inference boarding gate is used to set different boarding gate allocation rules to obtain the boarding gate allocation plan. The third is the system simulation method. System simulation analyzes the airport's boarding gate resources and flight schedules, establishes an airport operation model, and implements boarding gate allocation through the simulation model.

[0004] In the existing boarding gate allocation algorithm, the boarding gate allocation result obtained by the algorithm has a significantly better effect than manual allocation. However, the existing patents do not achieve a good combination of specific historical data and algorithm models, and the existing patents do not well reflect the service concept at the business model level of transfer services. Summary of the invention

[0005] The present invention overcomes the shortcomings of the prior art and provides a system and method for allocating boarding gates based on historical data and transfer passenger information. One of the technical problems it aims to solve is that the prior art does not achieve a good combination of specific historical data and algorithm models.

[0006] In view of the above problems in the prior art, according to one aspect of the present invention, in order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] A method for allocating boarding gates based on historical data and transfer passenger information, comprising:

[0008] Obtain historical data of flights and boarding gates, as well as transfer passenger information and corresponding transfer flights;

[0009] Analyze the acquired historical data of flights and boarding gates to obtain boarding gates that are periodically assigned to flights;

[0010] and predicting flight delays based on historical flight data;

[0011] The pre-assigned boarding gate is calculated based on the periodically assigned boarding gate of the flight, the predicted flight delays, the transfer passenger information and the corresponding transfer flight;

[0012] The pre-assigned check-in gates are evaluated using indicators including transfer efficiency and fit with historically assigned gates;

[0013] If the evaluation indicators are met, the aircraft stand allocation plan will be output; if the evaluation indicators are not met, the boarding gates of the connecting flights will be adjusted.

[0014] In order to better realize the present invention, a further technical solution is:

[0015] Furthermore, KPI evaluation indicators are used to evaluate the pre-assigned registration points.

[0016] Furthermore, the acquired historical data of the flight and boarding gate, the transfer passenger information and the corresponding transfer flight information are pre-processed by data cleaning and normalization.

[0017] Furthermore, MSE is used as the loss function in the process of calculating the pre-allocated boarding gate.

[0018] Furthermore, it also includes using LSTM to obtain historical data of flights and boarding gates for training and learning.

[0019] Furthermore, for normal flights, a genetic algorithm is used to obtain pre-assigned boarding gates.

[0020] Furthermore, for delayed flights, a recommendation algorithm is used to obtain a pre-assigned boarding gate.

[0021] The present invention may also be a system for allocating boarding gates based on historical data and transfer passenger information, comprising:

[0022] The data acquisition module is used to obtain historical data of flights and boarding gates, as well as transfer passenger information and corresponding transfer flights;

[0023] A data analysis module, configured to obtain boarding gates periodically allocated to flights based on the acquired historical data of flights and boarding gates;

[0024] The rolling prediction module is used to predict flight delays based on historical flight data;

[0025] The boarding gate calculation output module is used to calculate the pre-assigned boarding gate according to the boarding gates periodically assigned by the flight, the predicted flight delays, the transfer passenger information and the corresponding transfer flights;

[0026] The evaluation module is used to evaluate the pre-allocated check-in gates using indicators including transfer efficiency and the degree of fit with historically allocated boarding gates; if the evaluation indicators are met, the aircraft stand allocation plan is output; if the evaluation indicators are not met, the boarding gates of the transfer flights are adjusted.

[0027] Furthermore, the boarding gate calculation output module includes a transfer passenger optimization model, and the transfer passenger optimization model includes:

[0028] Assume that within a time period T, there are m boarding gates at an airport, and the gate set is G = {G(j)|j = 1, 2, L, m}, j ∈ [1, m] represents the number of the boarding gate; within a fixed time period, there are n flights, and the flight set is J = {J(i)|i = 1, 2, L, n}, i ∈ [1, n] represents the flight number, m < n; the gate allocation model that minimizes the total transfer process time of transfer passengers is as follows:

[0029]

[0030]

[0031]

[0032]

[0033] L ij +ΔT≤A ij (4)

[0034] A ij >L ij (5)

[0035]

[0036] x ij ∈{0,1} (7)

[0037] The objective function represents the total transfer process time of transfer passengers, where there are n flights and m boarding gates; f ik represents the passenger flow from inbound flight i to outbound flight m; x ij is a 0-1 variable, which takes 1 if flight i is assigned to gate j, and 0 otherwise; x klis a 0-1 variable, which takes 1 if flight k is assigned to gate l, and 0 otherwise; D jl is the transfer process time for passengers from arrival gate j to departure gate l. The total transfer process time required for passengers from arrival flight i to departure flight l is x ij D jl , G j Indicates the gate size type; Q i F is the flight size type; j To represent the gate attribute with a numerical value, F j =1,2 represent domestic flight boarding gate and international flight boarding gate respectively; E i is the flight attribute, E i =1,2 respectively indicates that the flight is a domestic flight or an international flight; A ij is the time for flight i to arrive at gate j; L ij is the time when flight i leaves gate j; ΔT is the minimum time interval for two consecutive take-off and landing flights to use the same boarding gate; Formula (1) is the uniqueness of the boarding gate used by the flight, and any flight can only be assigned to one boarding gate; Formula (2) is in line with the principle of matching flight type with boarding gate; Formula (3) is in line with the principle of matching flight nature with boarding gate; Formula (4) is the minimum time interval constraint for consecutive take-off and landing flights to use the same boarding gate; Formula (5) is that when two consecutive take-off and landing flights stop at the same boarding gate, the landing time of the latter flight should be greater than the take-off time of the former flight; Formula (6) U j is a 0-1 variable, which takes the value 1 if gate j is used and 0 otherwise. Formula (7) is a 0-1 decision variable, which takes the value 1 if flight i is assigned to gate j and 0 otherwise.

[0038] Compared with the prior art, one of the beneficial effects of the present invention is:

[0039] The system and method for allocating boarding gates based on historical data and transfer passenger information of the present invention improves the fit between the allocated boarding gates and the actual situation, conforms to the flight's stop habits, and alleviates the intensity of large-scale adjustments of flights and boarding gates; and through rolling predictions of flight delays, real-time dynamic adjustments of flights are achieved; and evaluation indicators for transfer passengers are added, so that the obtained boarding gate allocation plan can better improve passenger satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application document or the technical solutions in the prior art, the drawings required for use in the description of the embodiments or the prior art are briefly introduced below. Obviously, the drawings described below are only references to some embodiments in the present application document. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 The figure is a schematic diagram of the overall design process of an intelligent boarding gate allocation algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The present invention is further described in detail below in conjunction with examples, but the embodiments of the present invention are not limited thereto.

[0043] See also Figure 1 As shown, Figure 1 The overall process of an intelligent boarding gate allocation algorithm of an embodiment is shown, a method for allocating boarding gates based on historical data and transfer passenger information, which includes:

[0044] Obtain historical data of flights and boarding gates, as well as transfer passenger information and corresponding transfer flights;

[0045] Analyze the acquired historical data of flights and boarding gates to obtain boarding gates that are periodically assigned to flights;

[0046] and predicting flight delays based on historical flight data;

[0047] The pre-assigned boarding gate is calculated based on the periodically assigned boarding gate of the flight, the predicted flight delays, the transfer passenger information and the corresponding transfer flight;

[0048] The pre-assigned check-in gates are evaluated using indicators including transfer efficiency and fit with historically assigned gates;

[0049] If the evaluation indicators are met, the aircraft stand allocation plan will be output; if the evaluation indicators are not met, the boarding gates of the connecting flights will be adjusted.

[0050] The evaluation index of the above embodiment can use KPI evaluation index to evaluate the pre-allocated check-in gates. That is, design and construct a personalized KPI evaluation index as an abstract business model index for transfer passenger services, and improve this index in the mathematical model, so as to evaluate the boarding gate allocation results in a targeted manner.

[0051] The acquired historical data of the flight and boarding gate, the transfer passenger information and the corresponding transfer flight information can be preprocessed by data cleaning and normalization. The MSE can be used as the loss function in the process of calculating the pre-allocated boarding gate.

[0052] In one embodiment, LSTM can also be used to train and learn from historical data of flights and boarding gates. That is, self-learning and prediction are carried out based on historical flight data, and a better solution is given in combination with the implementation of the allocation plan; the target time period allocation plan is predicted from the rules learned from historical data from an intelligent perspective, and the difference between the predicted data and the algorithm results is used as the basis for modifying the algorithm parameters to improve the accuracy of the results given by the algorithm next time.

[0053] In the above embodiment, for normal flights, a genetic algorithm is used to obtain a pre-assigned boarding gate; for delayed flights, a recommendation algorithm is used to obtain a pre-assigned boarding gate.

[0054] Corresponding to the method of the above embodiment, the present invention may be a system for allocating boarding gates based on historical data and transfer passenger information, specifically comprising:

[0055] The data acquisition module is used to obtain historical data of flights and boarding gates, as well as transfer passenger information and corresponding transfer flights;

[0056] A data analysis module, configured to obtain boarding gates periodically allocated to flights based on the acquired historical data of flights and boarding gates;

[0057] The rolling prediction module is used to predict flight delays based on historical flight data;

[0058] The boarding gate calculation output module is used to calculate the pre-assigned boarding gate according to the boarding gates periodically assigned by the flight, the predicted flight delays, the transfer passenger information and the corresponding transfer flights;

[0059] The evaluation module is used to evaluate the pre-allocated check-in gates using indicators including transfer efficiency and the degree of fit with historically allocated boarding gates; if the evaluation indicators are met, the aircraft stand allocation plan is output; if the evaluation indicators are not met, the boarding gates of the transfer flights are adjusted.

[0060] The above embodiments include the following innovative features:

[0061] (1) Transfer passenger optimization model

[0062] Transfer passengers are passengers who transfer from an arriving flight to a departing flight operated by the same or different aircraft. The transfer process time is the time it takes for transfer passengers to go through the process from the arrival of the previous flight to the departure of the next flight. Shortening the transfer process time can increase the transfer opportunities for passengers at hub airports and improve the transfer success rate; the transfer process time is mainly determined by the nature of the flight and the location of the boarding gate; the boarding time is mainly determined by the boarding method, and the time used for boarding through the jet bridge (i.e., successfully arranging a flight close to the boarding gate) is shorter, so improving the utilization rate of the close boarding gate and allocating close boarding gates to more flights are key factors in boarding time. Therefore, this patent maximizes the utilization rate of the close boarding gate, which is converted into the problem of allocating boarding gates to more flights. Assume that within a time period T, there are m boarding gates at an airport, and the gate set is G = {G(j)|j = 1, 2, L, m}, j ∈ [1, m] represents the number of the boarding gate; within a fixed time period, there are n flights, and the flight set is J = {J(i)|i = 1, 2, L, n}, i ∈ [1, n] represents the flight number, m < n; the gate allocation model that minimizes the total transfer process time of transfer passengers is as follows:

[0063]

[0064]

[0065]

[0066]

[0067] L ij +ΔT≤A ij (4)

[0068] A ij >L ij (5)

[0069]

[0070] x ij ∈{0,1} (7)

[0071] The objective function represents the total transfer process time of transfer passengers, where there are n flights and m boarding gates; f ik represents the passenger flow from inbound flight i to outbound flight m; x ij is a 0-1 variable, which takes 1 if flight i is assigned to gate j, and 0 otherwise; x kl is a 0-1 variable, which takes 1 if flight k is assigned to gate l, and 0 otherwise; D jl is the transfer process time for passengers from arrival gate j to departure gate l. The total transfer process time required for passengers from arrival flight i to departure flight l is x ijD jl , G j Indicates the gate size type; Q i F is the flight size type; j To represent the gate attribute with a numerical value, F j =1,2 represent domestic flight boarding gate and international flight boarding gate respectively; E i is the flight attribute, E i =1,2 respectively indicates that the flight is a domestic flight or an international flight; A ij is the time for flight i to arrive at gate j; L ij is the time when flight i leaves gate j; ΔT is the minimum time interval for two consecutive take-off and landing flights to use the same boarding gate; Formula (1) is the uniqueness of the boarding gate used by the flight, and any flight can only be assigned to one boarding gate; Formula (2) is in line with the principle of matching flight type with boarding gate; Formula (3) is in line with the principle of matching flight nature with boarding gate; Formula (4) is the minimum time interval constraint for consecutive take-off and landing flights to use the same boarding gate; Formula (5) is that when two consecutive take-off and landing flights stop at the same boarding gate, the landing time of the latter flight should be greater than the take-off time of the former flight; Formula (6) U j is a 0-1 variable, which takes the value 1 if gate j is used and 0 otherwise. Formula (7) is a 0-1 decision variable, which takes the value 1 if flight i is assigned to gate j and 0 otherwise.

[0072] (2) Rolling Forecast Based on Historical Data

[0073] Reasonable use of historical data on boarding gate allocation can make the algorithm more intelligent and the resulting allocation plan more suitable for actual scenarios. LSTM is used to predict flight delays, passenger numbers, and flight traffic. The implementation steps are as follows:

[0074] STEP 1: First, the data needs to be preprocessed, including data cleaning, normalization, etc.

[0075] STEP2: Define the input data size according to the number of features, output the prediction target, and use MSE (mean square error) as the loss function;

[0076] STEP 3: Divide the data and use LSTM to train the training set. Then use the test set for verification.

[0077] The effect evaluation and analysis in the above-mentioned embodiment judges each boarding gate allocation plan based on at least the following indicators: 1) Transfer efficiency (transfer tension). Transfer efficiency refers to the tension of transfers for passengers on transfer flights. It is reflected in the boarding gate allocation as transfer flights need to be arranged as close as possible to reduce the difficulty of passengers' transfers. The higher the transfer efficiency, the lower the passenger transfer tension. 2) The degree of fit of historical boarding gate allocation. The degree of fit of historical boarding gate allocation refers to the degree of repetition between the boarding gate allocation plan recommended by the algorithm and the historical plan. The higher the degree of fit of historical boarding gate allocation, the fewer boarding gate allocations for flights that need to be adjusted, and the fewer adjustments to the corresponding flight guarantees and personnel schedules, which can reduce scheduling costs and have certain economic benefits.

[0078] Combination Figure 1 In another embodiment, for implementing the boarding gate allocation method of the present invention, one preferred specific step may be:

[0079] Step 1: Based on the historical data of flights, boarding gates, etc., the flight delays are predicted and the boarding gates assigned to the flights are counted periodically.

[0080] Step 2: Calculate the quantitative relationship matrix between flights and boarding gates based on the business rules and the results of step 1. The larger the value of the element, the higher the probability that the corresponding flight will select the corresponding boarding gate, and vice versa. In particular, when the value is 0, it means that the flight cannot select the boarding gate.

[0081] Step 3: Determine the solution space of the boarding gates that each flight can stop at. For normal flights, a genetic algorithm is used to obtain the pre-allocation solution; for delayed flights, a recommendation algorithm is used to obtain the recommended boarding gates.

[0082] Step 4: Evaluate the KPI indicators for the obtained solution. If the target requirements are not met, make partial adjustments to the connecting flights and go to step 3; otherwise, output the solution.

[0083] The effect of the present invention can be further illustrated by the following experimental data, specifically:

[0084] Simulation conditions: The simulation was performed using MATLAB software on an Intel(R) Core i3-2130 3.4GHZ CPU, 16G memory, and WINDOWS 8 operating system.

[0085] Cooperate with the algorithm model to complete the code combing, code development and interface debugging of each part.

[0086] For this innovative optimization model of boarding gate allocation, we selected actual business data of an airport for experiments, and established a mathematical model based on the historical allocation data of the database, the airport's resource data information, constraint rules, and target requirements. This model can output intelligent boarding gate allocation strategy recommendations and make real-time adjustments to the allocation strategy based on abnormal situations. This algorithm is encapsulated and its stability is guaranteed, and the interface call can be completed in the JAVA environment.

[0087] After classifying and statistically analyzing the experimental data, it was found that the experimental effect had a significant improvement in the walking distance of transit passengers, reducing the walking distance of passengers.

[0088] Walking distance: The daily passenger throughput of a certain airport is about 80,000, of which the proportion of transfer passengers is about one-thirtieth, or about 2,600 people. After using the transfer passenger optimization model, the improvement is also about 5%-6%, saving 130-160 transfer passengers from taking shuttle buses, and also saving more than 130-160 people walking distance. If the average distance from each boarding gate to the boarding gate ranges from 0.7 to 1.5 km, the walking distance saved for passengers is about 165 km (calculated according to the average 1.1*150 (average number of people)), as shown in Table 1.

[0089] Table 1 Comparative data of walking distance of transfer passengers

[0090]

[0091] Historical allocation of boarding gates: Using the patent application method, through the delay prediction model, refine the adjustment strategy indicators, learn the historical allocation data, and strive to achieve a 60% fit between the personnel habitual allocation data and the system allocation data. The comparison data is shown in Table 2.

[0092] Table 2 Comparison of historical boarding gate allocation fit data

[0093] month Adjustment times - before using patented method Adjustment times - after using patented method March 5317 times (total for all commanders) 3293 times (total of all commanders) April 5755 times (total for all commanders) 3568 times (total of all commanders) May 5211 times (total for all commanders) 3178 times (total for all commanders) …………… November 5425 times (total for all commanders) 3092 times (total for all commanders)

[0094] In summary, the above invention design process includes the following two key points: (1) Intelligent boarding gate allocation. By using historical data of flights and boarding gates, on the one hand, the boarding gates periodically allocated to flights are analyzed, which can improve the fit between the algorithm's calculation results and the actual situation, conform to the flight's stop habits, and alleviate the large-scale adjustment of flights and boarding gates; on the other hand, through the rolling prediction model, the data information of flight delays is obtained, and a reasonable recommendation algorithm is designed to achieve real-time dynamic adjustment of flights. (2) Perfect KPI indicators. In the existing boarding gate allocation algorithm, the impact of transfer passengers on boarding gate allocation is not considered. In the above process, by adding evaluation indicators for transfer passengers, the resulting boarding gate allocation plan can better improve passenger satisfaction.

[0095] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0096] References to "one embodiment", "another embodiment", "embodiment", etc. in this specification refer to specific features, structures or characteristics described in conjunction with the embodiment as included in at least one embodiment generally described in this application. The appearance of the same expression in multiple places in the specification does not necessarily refer to the same embodiment. Further, when a specific feature, structure or characteristic is described in conjunction with any embodiment, it is claimed that the realization of such feature, structure or characteristic in conjunction with other embodiments also falls within the scope of the present invention.

[0097] Although the present invention is described herein with reference to a number of illustrative embodiments of the present invention, it will be appreciated that those skilled in the art may devise many other modifications and implementations that fall within the scope and spirit of the principles disclosed herein. More specifically, within the scope of the present disclosure, drawings, and claims, a variety of variations and improvements may be made to the components and / or layout of the subject combination layout. In addition to variations and improvements made to the components and / or layout, other uses will also be apparent to those skilled in the art.

Claims

1. A method for allocating boarding gates based on historical data and transfer passenger information, Features include: Obtain historical data of flights and boarding gates, as well as transfer passenger information and corresponding transfer flights; Analyze the acquired historical data of flights and boarding gates to obtain boarding gates that are periodically assigned to flights; and predicting flight delays based on historical flight data; The pre-assigned boarding gate is calculated based on the periodically assigned boarding gate of the flight, the predicted flight delays, the transfer passenger information and the corresponding transfer flight; The pre-assigned check-in gates are evaluated using indicators including transfer efficiency and fit with historically assigned gates; If the evaluation indicators are met, the aircraft slot allocation plan will be output; if the evaluation indicators are not met, the boarding gate of the connecting flight will be adjusted; It also includes a boarding gate calculation output module, which includes a transfer passenger optimization model. The transfer passenger optimization model includes: Assume that within a time period T, there are m boarding gates at an airport, and the boarding gate set is G = {G(j)|j = 1, 2, ..., m}, j∈[1, m] represents the number of the boarding gate; within a fixed time period, there are n flights, and the flight set is J = {J(i)|i = 1, 2, ..., n}, i∈[1, n] represents the flight number, m < n; the boarding gate allocation model that minimizes the total transfer process time of transfer passengers is as follows: L ij +ΔT≤A ij (4) A ij >L ij (5) x ij ∈{0,1} (7) The objective function represents the total transfer process time of transfer passengers, where there are n flights and m boarding gates; f ik represents the passenger flow from inbound flight i to outbound flight m; x ij is a 0-1 variable, which takes 1 if flight i is assigned to gate j, and 0 otherwise; x kl is a 0-1 variable, which takes 1 if flight k is assigned to the boarding gate, and takes 0 otherwise; D jl is the transfer process time for passengers from arrival gate j to departure gate l. The total transfer process time required for passengers from arrival flight i to departure flight is x ij D jl , G j Indicates the gate size type; Q i F is the flight size type; j To represent the gate attribute with a numerical value, F j =1, 2 represent domestic flight boarding gate, international flight boarding gate respectively; E i is the flight attribute, E i =1, 2 means the flight is domestic flight, international flight respectively; A ij is the time for flight i to arrive at gate j; L ij is the time when flight i leaves gate j; ΔT is the minimum time interval for two consecutive take-off and landing flights to use the same boarding gate; Formula (1) is the uniqueness of the boarding gate used by the flight, and any flight can only be assigned to one boarding gate; Formula (2) is in line with the principle of matching flight type with boarding gate; Formula (3) is in line with the principle of matching flight nature with boarding gate; Formula (4) is the minimum time interval constraint for consecutive take-off and landing flights to use the same boarding gate; Formula (5) is that when two consecutive take-off and landing flights stop at the same boarding gate, the landing time of the latter flight should be greater than the take-off time of the former flight; Formula (6) U j is a 0-1 variable, which takes the value 1 if gate j is used and 0 otherwise. Formula (7) is a 0-1 decision variable, which takes the value 1 if flight i is assigned to gate j and 0 otherwise.

2. The method for allocating boarding gates based on historical data and transfer passenger information according to claim 1, Features KPI evaluation indicators are used to evaluate the pre-allocated registration points.

3. The method for allocating boarding gates based on historical data and transfer passenger information according to claim 1, Features The acquired historical data of the flight and boarding gate, the transfer passenger information and the corresponding transfer flight information are pre-processed by data cleaning and normalization.

4. The method for allocating boarding gates based on historical data and transfer passenger information according to claim 1, Features MSE is used as the loss function in the process of calculating the pre-assigned boarding gate.

5. The method for allocating boarding gates based on historical data and transfer passenger information according to claim 1, Features It also includes the use of LSTM to obtain historical data on flights and boarding gates for training and learning.

6. The method for allocating boarding gates based on historical data and transfer passenger information according to claim 1, Features For normal flights, a genetic algorithm is used to obtain the pre-assigned boarding gates.

7. The method for allocating boarding gates based on historical data and transfer passenger information according to claim 1, Features For delayed flights, a recommendation algorithm is used to obtain the pre-assigned boarding gate.

8. A system for assigning boarding gates based on historical data and transfer passenger information, Features include: The data acquisition module is used to obtain historical data of flights and boarding gates, as well as transfer passenger information and corresponding transfer flights; A data analysis module, configured to obtain boarding gates periodically allocated to flights based on the acquired historical data of flights and boarding gates; The rolling prediction module is used to predict flight delays based on historical flight data; The boarding gate calculation output module is used to calculate the pre-assigned boarding gate according to the boarding gates periodically assigned by the flight, the predicted flight delays, the transfer passenger information and the corresponding transfer flights; An evaluation module for evaluating the pre-assigned gates using indicators including transfer efficiency and fit of historically assigned gates; If the evaluation indicators are met, the aircraft slot allocation plan will be output; if the evaluation indicators are not met, the boarding gate of the connecting flight will be adjusted; The boarding gate calculation output module includes a transfer passenger optimization model, which includes: Assume that within a time period T, there are m boarding gates at an airport, and the boarding gate set is G = {G(j)|j = 1, 2, ..., m}, j∈[1, m] represents the number of the boarding gate; within a fixed time period, there are n flights, and the flight set is J = {J(i)|i = 1, 2, ..., n}, i∈[1, n] represents the flight number, m < n; the boarding gate allocation model that minimizes the total transfer process time of transfer passengers is as follows: L ij +ΔT≤A ij (4) A ij >L ij (5) x ij ∈{0,1} (7) The objective function represents the total transfer process time of transfer passengers, where there are n flights and m boarding gates; f ik represents the passenger flow from inbound flight i to outbound flight m; x ij is a 0-1 variable, which takes 1 if flight i is assigned to gate j, and 0 otherwise; x kl is a 0-1 variable, which takes 1 if flight k is assigned to gate l, and 0 otherwise; D jl is the transfer process time for passengers from arrival gate j to departure gate l. The total transfer process time required for passengers from arrival flight i to departure flight l is x ij D jl , G j Indicates the gate size type; Q i F is the flight size type; j To represent the gate attribute with a numerical value, F j =1, 2 represent domestic flight boarding gate, international flight boarding gate respectively; E i is the flight attribute, E i =1, 2 means the flight is domestic flight, international flight respectively; A ij is the time for flight i to arrive at gate j; L ij is the time when flight i leaves boarding gate j; ΔT is the minimum time interval for two consecutive take-off and landing flights to use the same boarding gate; Formula (1) is the uniqueness of the boarding gate used by the flight, and any flight can only be assigned to one boarding gate; Formula (2) is in line with the principle of matching flight type with boarding gate; Formula (3) is in line with the principle of matching flight nature with boarding gate; Formula (4) is the minimum time interval constraint for consecutive take-off and landing flights to use the same boarding gate; Formula (5) is that when two consecutive take-off and landing flights stop at the same boarding gate, the landing time of the latter flight should be greater than the take-off time of the former flight; Formula (6) U j is a 0-1 variable, which takes the value 1 if gate j is used and 0 otherwise. Formula (7) is a 0-1 decision variable, which takes the value 1 if flight i is assigned to gate j and 0 otherwise.