Method and device for dynamically adjusting parking position, computer device and storage medium

Abstract

The application provides a method and device for dynamically adjusting a parking position, computer equipment and a storage medium. The method comprises: obtaining flight operation information of a target flight triggered by an exception at a current time, the flight operation information comprising initial parking position information of the target flight; obtaining a target optimization function for dynamically adjusting the parking position of the target flight according to an exception type of the target flight; adjusting the initial parking position information of the target flight based on the target optimization function to obtain parking position adjustment information of the target flight; and when the parking position adjustment information meets a preset adjustment stop condition, taking the parking position adjustment information as preferred parking position information of the target flight. The method can improve the adjustment and allocation efficiency of the parking position.

Description

[0001] Technology Neighborhood

[0002] This application relates to the field of aviation technology, specifically to a method, apparatus, computer equipment, and storage medium for dynamically adjusting parking positions. Background Technology

[0003] With the rapid development of the national economy, the demand for air transport is also constantly increasing. As the basic resource for the actual operation of airports, the rational allocation of parking spaces has a direct impact on the operational efficiency of airports. Therefore, optimizing the allocation of parking spaces has important practical application value.

[0004] Currently, the rational allocation of parking stands is a common problem in passenger aviation airports, primarily used to determine which stand each passenger aircraft will park at after landing. However, it's less frequently used in cargo aviation airports, as the target factors differ. For example, passenger aircraft primarily consider the aircraft and passengers, while cargo aircraft primarily consider the aircraft and pallets / containers. Existing parking stand allocation algorithms typically only run during the planning phase, such as 12 hours before flight departures to obtain the allocation plan for the entire day. However, after flights begin, various unforeseen circumstances may occur that deviate from the plan, such as flight delays or diversions. Therefore, parking stands may need to be adjusted in real time. Currently, most real-time adjustments for cargo airports are done manually, which can be triggered frequently and is time-consuming.

[0005] Therefore, the existing station allocation method suffers from the technical problem of low allocation efficiency. Summary of the Invention

[0006] Therefore, it is necessary to provide a method, device, computer equipment, and storage medium for dynamic adjustment of parking positions to address the aforementioned technical problems, so as to improve the efficiency of adjusting and allocating available parking positions for flights.

[0007] In a first aspect, this application provides a method for dynamically adjusting parking positions, including:

[0008] Obtain the flight operation information of the target flight that triggered the anomaly at the current moment. The flight operation information includes the initial gate information of the target flight.

[0009] Based on the anomaly type of the target flight, obtain the target optimization function for dynamically adjusting the parking position for the target flight;

[0010] Based on the objective optimization function, the initial gate information of the target flight is adjusted to obtain the gate adjustment information of the target flight;

[0011] When the gate adjustment information meets the preset adjustment stop conditions, the gate adjustment information will be used as the preferred gate information for the target flight.

[0012] In some embodiments of this application, a target optimization function for dynamically adjusting the parking positions of the target flight is obtained based on the anomaly type of the target flight. This includes: if the anomaly type of the target flight is a first anomaly, then a distance optimization function and / or a parking position change optimization function are obtained as the target optimization function; if the anomaly type of the target flight is a second anomaly, then a total distance optimization function and / or a runway change optimization function are obtained as the target optimization function; wherein, the first anomaly is a flight delay anomaly, and the second anomaly includes at least one of flight pushback anomaly, temporary diversion anomaly, duplicate flight anomaly, and route interchange anomaly.

[0013] In some embodiments of this application, the initial gate information of a target flight is adjusted based on a target optimization function to obtain gate adjustment information for the target flight. This includes: using the initial gate information as the target optimal solution for the target flight; updating the target optimal solution under preset constraints based on the target optimization function to adjust the initial gate information of the target flight and obtain gate adjustment information; wherein the constraints include at least one of unique allocation constraints, composite gate constraints, aircraft type matching constraints, gate locking constraints, safety interval constraints, and pushback interval constraints.

[0014] In some embodiments of this application, the flight operation information also includes flight parameter information, gate position parameter information, and auxiliary parameter information. Based on the objective optimization function, the target optimal solution is updated under preset constraints to adjust the initial gate position information of the target flight, thereby obtaining gate position adjustment information. This includes: using a tabu search algorithm to perform a neighborhood search on the target optimal solution to obtain neighborhood information; if the neighborhood information is not empty, obtaining the objective function value of each solution in the neighborhood information under the constraints based on the objective optimization function, flight parameter information, gate position parameter information, and auxiliary parameter information; determining the current optimal solution among the solutions, where the objective function value corresponding to the current optimal solution is the maximum value among the objective function values; and updating the target optimal solution according to the quality of the current optimal solution to adjust the initial gate position information of the target flight, thereby obtaining gate position adjustment information.

[0015] In some embodiments of this application, the target optimal solution is updated based on the quality of the current optimal solution to adjust the initial gate information of the target flight and obtain gate adjustment information. This includes: obtaining the objective function value of the target optimal solution under constraints based on the objective optimization function, as the first objective function value; using the objective function value of the current optimal solution as the second objective function value; if the second objective function value is greater than the first objective function value, then determining that the second quality of the current optimal solution is better than the first quality of the target optimal solution; when the second quality is better than the first quality, updating the target optimal solution to adjust the initial gate information and obtain gate adjustment information.

[0016] In some embodiments of this application, when the second quality is better than the first quality, the target optimal solution is updated to adjust the initial aircraft position information to obtain aircraft position adjustment information. This includes: when the second quality is better than the first quality, the preset continuous no-improvement parameter before obtaining the neighborhood information is zeroed out, and the initial preset value of the continuous no-improvement parameter is zero; the current optimal solution is used as the target optimal solution to update the target optimal solution; the current optimal solution is updated based on the descending order of the objective function values; and the update operation of the target optimal solution is repeated according to the quality of the updated current optimal solution to adjust the initial aircraft position information to obtain aircraft position adjustment information.

[0017] In some embodiments of this application, after obtaining the objective function value of the target optimal solution under the constraints based on the objective optimization function and using it as the first objective function value, the method further includes: if the second objective function value is less than or equal to the first objective function value, then determining that the first quality of the target optimal solution is better than the second quality of the current optimal solution; when the first quality is better than the second quality, incrementing the preset continuous non-improvement parameter before obtaining the neighborhood information by one, and keeping the target optimal solution unchanged.

[0018] In some embodiments of this application, after using the tabu search algorithm to perform a neighborhood search on the target optimal solution and obtain neighborhood information, the method further includes: if the neighborhood information is empty, then the initial position information is used as the target optimal solution.

[0019] In some embodiments of this application, when the gate adjustment information meets a preset adjustment stop condition, the gate adjustment information is used as the preferred gate information for the target flight. This includes: after determining the target optimal solution, incrementing the preset iteration parameter before obtaining the neighborhood information by one, where the initial preset value of the iteration parameter is zero; if the iteration parameter after the increment operation reaches a preset iteration threshold, the target optimal solution is used as the preferred gate information for the target flight; if the iteration parameter after the increment operation does not reach the preset iteration threshold, the neighborhood search operation for the target optimal solution is repeatedly executed based on the current continuous no-increase parameter until gate adjustment information that meets the adjustment stop condition is obtained.

[0020] In some embodiments of this application, if the iteration parameter after the increment operation does not reach a preset iteration threshold, then based on the current continuous non-increase parameter, the neighborhood search operation for the target optimal solution is repeatedly executed until the position adjustment information that meets the adjustment stopping condition is obtained. This includes: if the iteration parameter after the increment operation does not reach the preset iteration threshold, then the current continuous non-increase parameter is obtained; if the continuous non-increase parameter is greater than the preset continuous threshold, then the continuous non-increase parameter is zeroed out, and a first operator is used to perform a neighborhood search on the target optimal solution to update the neighborhood information of the target optimal solution; if the continuous non-increase parameter is less than or equal to the continuous threshold, a second operator is used to perform a neighborhood search on the target optimal solution to update the neighborhood information of the target optimal solution.

[0021] Secondly, this application provides a device for dynamically adjusting the parking position, comprising:

[0022] The information acquisition module is used to acquire the flight operation information of the target flight that triggered the anomaly at the current moment. The flight operation information includes the initial gate information of the target flight.

[0023] The function acquisition module is used to obtain the target optimization function for dynamically adjusting the parking position of the target flight based on the anomaly type of the target flight.

[0024] The gate adjustment module is used to adjust the initial gate information of the target flight based on the objective optimization function, so as to obtain the gate adjustment information of the target flight.

[0025] The gate selection module is used to select the gate adjustment information as the preferred gate information for the target flight when the gate adjustment information meets the preset adjustment stop conditions.

[0026] Thirdly, this application also provides a computer device, comprising:

[0027] One or more processors;

[0028] The memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by a processor to implement the stop position dynamic adjustment method in the above embodiments.

[0029] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the steps in the dynamic adjustment method for the stop position in the above embodiments.

[0030] Fifthly, embodiments of this application provide a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method provided in the first aspect described above.

[0031] The aforementioned method, apparatus, computer equipment, and storage medium for dynamic parking stand adjustment involve a server acquiring flight operation information of a target flight that has triggered an anomaly at the current moment. Based on the anomaly type of the target flight, a target optimization function is obtained to dynamically adjust the parking stand for that flight. Then, based on this optimization function, the initial parking stand information of the target flight is adjusted until the adjusted information meets a preset stopping condition. This adjusted information is then used as the preferred parking stand information for the target flight, thus achieving the goal of dynamic parking stand adjustment. This method can automatically solve for optimal parking stand adjustment schemes in different dynamic parking stand adjustment scenarios, improving the efficiency of parking stand allocation. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic diagram of a scenario illustrating the dynamic adjustment method for parking positions in an embodiment of this application;

[0034] Figure 2 This is a flowchart illustrating the dynamic adjustment method for the parking position in an embodiment of this application;

[0035] Figure 3 This is a schematic flowchart illustrating the dynamic adjustment method for parking positions in the embodiments of this application;

[0036] Figure 4 This is a schematic diagram of the structure of the dynamic adjustment device for the stopping position in the embodiments of this application;

[0037] Figure 5 This is a schematic diagram of the structure of the computer device in the embodiments of this application. Detailed Implementation

[0038] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0039] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0040] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0041] This application provides a method, apparatus, computer device, and storage medium for dynamically adjusting parking positions, which will be described in detail below.

[0042] See Figure 1 , Figure 1This is a schematic diagram illustrating a scenario for the dynamic adjustment method for parking positions provided in this application. This method can be applied to a dynamic adjustment system for parking positions. The dynamic adjustment system includes a terminal 100 and a server 200 connected via a network. The terminal 100 can be a device that includes both receiving and transmitting hardware, i.e., a device with receiving and transmitting hardware capable of performing bidirectional communication over a bidirectional communication link. Such a device can include cellular or other communication devices, having a single-line display, a multi-line display, or no multi-line display. Specifically, the terminal 100 can be a desktop terminal or a mobile terminal, and can also be a mobile phone, tablet computer, or laptop computer. The server 200 can be a standalone server or a server network or server cluster, including but not limited to computers, network hosts, a single network server, multiple network server sets, or a cloud server composed of multiple servers. The cloud server consists of a large number of computers or network servers based on cloud computing. Furthermore, the aforementioned network can specifically be a wide area network (WAN), a local area network (LAN), or a metropolitan area network (MAN).

[0043] Those skilled in the art in this field can understand. Figure 1 The application environment shown is merely one applicable scenario for the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include more than one. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one server, 200, is shown in the diagram. It is understood that this dynamic adjustment system for parking positions may also include one or more other servers; specific details are not specified here. Additionally, as... Figure 1 As shown, the dynamic adjustment system for parking positions may also include a memory for storing data, such as flight operation information.

[0044] It should be noted that, Figure 1 The schematic diagram of the dynamic parking space adjustment system shown is merely an example. The dynamic parking space adjustment system and scenario described in this embodiment of the invention are intended to more clearly illustrate the technical solutions of this invention and do not constitute a limitation on the technical solutions provided in this embodiment. Those skilled in the art will understand that, with the evolution of dynamic parking space adjustment systems and the emergence of new business scenarios, the technical solutions provided in this embodiment of the invention are also applicable to similar technical problems.

[0045] See Figure 2 This application provides a method for dynamically adjusting the parking position. This embodiment mainly applies this method to the above-mentioned... Figure 1 Taking server 200 as an example, the method includes steps S201 to S204, as follows:

[0046] S201, obtain the flight operation information of the target flight that triggered the anomaly at the current time. The flight operation information includes the initial gate information of the target flight.

[0047] The current time can refer to the time recorded by the computer device that loads the dynamic adjustment method for the stop position, such as 10:00:00 AM Beijing time on January 1, 2021.

[0048] The target flight can be a flight that has been detected triggering a preset abnormal situation at the current moment. The current operational status of this flight is not limited in this application; for example, the target flight may be in flight or waiting on the ground when the abnormality is triggered. The preset abnormal situations in this application include, but are not limited to, the following:

[0049] (1) Flight delays and landings: When the arrival time of flight A is delayed and later than the original arrival time, it may not be allocated to the originally scheduled gate (the gate was originally allocated to another flight B after the original departure time of flight A, and due to the delay, the actual departure time of flight A may be later than the scheduled landing time of flight B). In this case, it is necessary to reallocate the gates for flight A and flight B, and take into account other flights that may be affected, so the gates need to be dynamically adjusted.

[0050] (2) Flight pushback delay; When a flight A that is already parked at the target stand is delayed, its actual pushback time may be longer than the arrival time of flight B that was originally scheduled to park at the target stand after flight A pushback. In this case, it is necessary to consider reallocating the stand for flight B and taking into account other affected flights, so the stand needs to be dynamically adjusted.

[0051] (3) Temporary diversion of flights; the original static plan did not take into account the diverted flights, so it is necessary to temporarily allocate parking positions for them, and take into account other affected flights to make dynamic adjustments to the parking positions.

[0052] (4) Duplicate flights: The original plan was for aircraft A to fly route W: Shenzhen-Ezhou-Beijing, and aircraft B to fly other routes, but now aircraft B has also been changed to fly this route W. In this case, it is necessary to consider the parking position arrangement of aircraft B, and take into account other flights that may be affected, and make dynamic adjustments to the parking positions.

[0053] (5) Flight route swap; the destinations of aircraft A and aircraft B are swapped, and the pallets and containers carried by the two aircraft are also swapped. It should be noted that there are two situations where abnormal route swaps require dynamic gate adjustment: 1. Both aircraft A and B are still in flight; in this case, it is possible to directly swap the gates in the static gate plan. 2. One aircraft A is already parked at its designated gate, and then a route swap instruction is issued, while the other aircraft B is still in flight. In this case, it is necessary to consider reallocating the gate for aircraft B and comprehensively consider other potentially affected flights.

[0054] The flight operation information may include initial gate information, flight parameter information, gate parameter information, and auxiliary parameter information. The specific content of the flight operation information involved in this embodiment will be described in detail below.

[0055] Initial gate information, also known as static gate plan, refers to the static gate arrangement plan for the target flight, which can be used as an initial gate reference when dynamically adjusted.

[0056] In practice, when server 200 detects an anomaly in a flight, it can use that flight as the target flight and obtain its unique flight identifier. This unique identifier is then used to query the corresponding flight operation information in the database. The flight operation information stored in the database can be stored in a categorized table format or a summary table format. Regardless of the storage method, server 200 can use the unique flight identifier of the target flight to query and summarize the required flight operation information.

[0057] More specifically, server 200 may not retrieve flight operation information from a database, but rather from aviation systems such as the "Cooperative Scheduling System," "Air Traffic Control System," "Airline Operations Management System (FOC)," and "Passenger Information System (PIS)." These aviation systems can be loaded and run on other servers or terminals 100, allowing server 200 to access the information via a network. The data source for the flight operation information involved in this embodiment is not specifically limited in this application.

[0058] Furthermore, the detection methods for flight-triggered anomalies by server 200 may include: 1. Server 200 detects that a flight fails to arrive at the designated parking position at its preset arrival time; 2. Server 200 detects that a flight fails to take off at its preset departure time; 3. Server 200 detects that an aircraft not belonging to a certain time period will make a temporary diversion during that time period; 4. Server 200 detects that there is a change in the number of feasible aircraft on a certain route, i.e., an increase or even a decrease in the number; 5. Server 200 detects that ground staff issue a designation instructing two aircraft to switch routes.

[0059] S202, based on the anomaly type of the target flight, obtain the target optimization function for dynamically adjusting the parking positions of the target flight.

[0060] The target optimization function can be an optimization objective set to achieve the best effect in adjusting the stop position. The target optimization function used in this application embodiment is applicable to different types of anomalies, that is, different anomaly scenarios. The target optimization functions applicable to different scenarios will be illustrated in detail below.

[0061] In its specific implementation, the dynamic adjustment method for parking positions proposed in this application not only enables efficient dynamic adjustment of parking positions for target flights, but also allows users to select specific scenarios for dynamic adjustment. By employing a target optimization function corresponding to the selected scenario, it achieves precise dynamic adjustment of parking positions for target flights, thereby improving the efficiency and accuracy of parking position allocation. The steps for obtaining the target optimization function involved in this embodiment will be described in detail below.

[0062] In one embodiment, this step includes: if the anomaly type of the target flight is a first anomaly, then obtaining a distance optimization function and / or a gate change optimization function as the target optimization function; if the anomaly type of the target flight is a second anomaly, then obtaining a total distance optimization function and / or a runway change optimization function as the target optimization function; wherein, the first anomaly is a flight delay anomaly, and the second anomaly includes at least one of flight pushback anomaly, temporary diversion anomaly, duplicate flight anomaly, and route interchange anomaly.

[0063] The first anomaly can refer to flight delay anomaly, which is the anomaly situation 1 mentioned above; the second anomaly can refer to at least one of flight pushback anomaly, temporary diversion anomaly, duplicate flight anomaly, route interchange anomaly, which is any one or more of the anomaly situations 2-5 mentioned above.

[0064] The target optimization function corresponding to the first anomaly can be a distance optimization function, a gate position change optimization function, or a combination of both. The distance optimization function can be a preset optimization function related to "distance," and the gate position change optimization function can be a preset optimization function related to "gate position change." The distance optimization function can include functions 1-3 and 5-4 as shown below, and the gate position change optimization function can include function 4 as shown below. Details are as follows:

[0065] (1) Minimize the towing distance of palletized containers on delayed flights:

[0066]

[0067] (2) Minimize the loading and unloading distance of non-straight-turn pallet containers on the aircraft:

[0068]

[0069] (3) Minimize the landing taxi distance for delayed flights:

[0070]

[0071] (4) Minimize the changes between the results of dynamic adjustments and the original plan:

[0072]

[0073] (5) Minimize the total unloading and loading haulage distances of the non-direct-turn pallet containers.

[0074]

[0075] (6) Minimize the total straight-rotation distance of the rotating plate box:

[0076]

[0077] (7) Minimize the total takeoff and landing taxi distance of the aircraft:

[0078]

[0079] The objective optimization function corresponding to the second anomaly can be a total distance optimization function, a runway change optimization function, or a combination of both. The total distance optimization function can be a preset optimization function related to "total distance," and the runway change optimization function can be a preset optimization function related to "runway change." The total distance optimization function can include functions 2-4 as follows, and the gate change optimization function can include function 1 as follows, detailed below:

[0080] (1) For aircraft with takeoff and landing runways on the same side, the parking positions should be arranged on the same side of the runway as much as possible to reduce crossing:

[0081]

[0082] (2) Minimize the sum of the total unloading and loading haulage distances for non-direct-turn pallet containers:

[0083]

[0084] (3) Minimize the sum of the total straight-rotation distances of the rotating plate boxes:

[0085]

[0086] (4) Minimize the sum of the total takeoff and landing taxi distances of the aircraft:

[0087]

[0088] Among them, the objective optimization functions corresponding to the first anomaly and the objective optimization functions corresponding to the second anomaly, and the meanings of the parameters involved in all functions are as follows: I is the set of all aircraft, I... D Let A be the set of all delayed flights, and P be all pairs of flights, P = {(i,j)∈A} 2 ,i≠j}、T i For aircraft type i, A i For the arrival time of aircraft i, D i For the departure time of aircraft i, B i For the set of trays and boxes on aircraft i.

[0089] Where K is the set of all aircraft positions, N is the set of adjacent aircraft position pairs, and C is the set of adjacent aircraft position pairs. k Let θ be the set of camera positions in the same area as camera position k. k For the set of allocable aircraft types for position k, U k Let (B,E)∈U be the set of unavailable time periods for station k. k Let C be the start and end times of any unavailable period for station k. k Let C be the set of camera positions in the same area as camera position k, and let C be a composite camera position pair, where a large camera position and a small camera position form a composite camera position pair.

[0090] Among them, A ik Let D be the distance that aircraft i travels from landing taxi to parking position k. ik Let S be the distance that aircraft i taxis from gate k to takeoff, S be the pair of aircraft on the same side of the landing run and the gates on the same side, and G be the distance that aircraft i taxis from gate k to takeoff. D For straight box assembly, G F M represents the set of non-straight-sided containers, N represents the set of all unloading ports in the transfer center, and W represents the set of all loading ports in the transfer center. i The weight of the cargo loaded on aircraft i, W inThe weight of the cargo transported from the unloading port n of the transshipment center to aircraft i The distance from machine position k to unloading and towing. D is the transport distance from machine position k to loading port n. kk′ The linear rotation distance from camera position k to camera position k′, I S For safety interval, I D To introduce the interval, y ik If aircraft i has been assigned to gate k, set the value to 1 if yes, otherwise set it to 0. ik This indicates whether aircraft i is assigned to gate k; if yes, set it to 1, otherwise set it to 0.

[0091] In specific implementation, the aforementioned different types of objective optimization functions can be pre-classified and stored in the database of server 200. The purpose of classification is to provide optimization functions suitable for different dynamic adjustment scenarios for analysis, which can improve the accuracy of parking space adjustment and allocation. Furthermore, the dynamic adjustment scenarios mentioned in this embodiment include flight delay scenarios reflected by the first anomaly and non-flight delay scenarios reflected by the second anomaly. Server 200 responds to user requests, obtains the objective optimization function corresponding to the currently selected dynamic adjustment scenario for subsequent analysis, which can improve the efficiency and accuracy of parking space adjustment and allocation, and even enhance the robustness of the method proposed in this application.

[0092] S203, based on the objective optimization function, adjusts the initial gate information of the target flight to obtain the gate adjustment information of the target flight.

[0093] The camera position adjustment information can be the initial camera position information after one adjustment or the initial camera position information after multiple adjustments. The number of adjustments is the number of iterations mentioned in the embodiments of this application, which will be explained in detail below.

[0094] In the specific implementation, the server 200 selects a target optimization function suitable for the current scenario and adjusts the initial camera position information. This mainly uses the tabu search algorithm, which will be explained in detail below.

[0095] In one embodiment, this step includes: taking the initial gate information as the target optimal solution for the target flight; updating the target optimal solution based on the target optimization function under preset constraints to adjust the initial gate information of the target flight and obtain gate adjustment information; wherein the constraints include at least one of the following: unique allocation constraint, composite gate constraint, aircraft type matching constraint, gate locking constraint, safety interval constraint, and pushback interval constraint.

[0096] The unique allocation constraint, composite aircraft position constraint, aircraft type matching constraint, aircraft position locking constraint, safety interval constraint, and pushback interval constraint involved in the embodiments of this application are represented as follows:

[0097] (1) Unique allocation constraint; an aircraft can only be allocated to one parking position:

[0098]

[0099] (2) Composite camera position constraint; if one of the composite camera positions is used, the other cannot be used within the same time frame:

[0100]

[0101] Among them, P S This indicates the grouping of aircraft pairs whose arrival and departure times do not meet the safe interval requirement:

[0102] P S ={(i,j)∈P:max(A i -D j A j -D i ) s}

[0103] (3) Aircraft type matching constraints; aircraft positions cannot be assigned to mismatched aircraft types:

[0104]

[0105] Where θ represents an aircraft-gate pair where the aircraft type and gate do not match:

[0106]

[0107] (4) Stand locking constraint; aircraft cannot be allocated during stand unavailable periods:

[0108]

[0109] Where U represents an aircraft-gate pair with a time conflict:

[0110] U={(i,k)∈I×K:min(max(A i -E,BD i ):(B,E)∈U k )<0}

[0111] (5) Safety separation constraint: Two aircraft whose arrival or departure times do not meet the safety separation requirement cannot be assigned to the same gate.

[0112]

[0113] Among them, P S This indicates the grouping of aircraft pairs whose arrival and departure times do not meet the safe interval requirement:

[0114] P​s ={(i,j)∈P:max(A i -D j A j -D i ) s}

[0115] (6) Takeoff interval constraint; two aircraft whose departure times do not meet the takeoff interval requirement cannot be assigned to adjacent stands:

[0116]

[0117] Among them, P D This indicates the group of aircraft pairs whose arrival / departure times do not meet the pushback interval:

[0118] P D ={(i,j)∈P:|D i -D j | D}

[0119] In the specific implementation, the meaning of the parameters involved in this embodiment can be found in the parameter description section of the above embodiment, and will not be repeated here.

[0120] For more details, please refer to Figure 3 Before adjusting the initial gate information of the target flight, server 200 can first set this initial gate information as the target optimal solution. Then, in subsequent operations, the target optimization function applicable to the current scenario is adopted, and under all the above constraints, the target optimal solution is continuously iterated and updated. The iterative update process is also the process of adjusting the initial gate information of the target flight, and finally the required gate adjustment information can be obtained. The adjustment steps involved in this embodiment will be described in detail below.

[0121] In one embodiment, the flight operation information further includes flight parameter information, gate position parameter information, and auxiliary parameter information. Based on the objective optimization function, the target optimal solution is updated under preset constraints to adjust the initial gate position information of the target flight, resulting in gate position adjustment information. This includes: using a tabu search algorithm to perform a neighborhood search on the target optimal solution to obtain neighborhood information; if the neighborhood information is not empty, obtaining the objective function value of each solution in the neighborhood information under the constraints based on the objective optimization function, flight parameter information, gate position parameter information, and auxiliary parameter information; determining the current optimal solution among the solutions, where the objective function value corresponding to the current optimal solution is the maximum value among all objective function values; and updating the target optimal solution according to the quality of the current optimal solution to adjust the initial gate position information of the target flight, resulting in gate position adjustment information.

[0122] ​​Tabu search is a modern heuristic algorithm used to escape local optima. It first establishes an initial solution, then "moves" to another solution in its "neighborhood" based on this initial solution. Through multiple consecutive moves, it improves the quality of the solution. During the search, the algorithm maintains a "tabulist," preventing previously visited moves from being revisited in the next k (tabu tenure) iterations.

[0123] In this context, neighborhood information can refer to the neighborhood structure "N(S)", which is the combination of all feasible solutions reachable from a current solution S by performing a single "move" operation. It can contain one feasible solution, multiple feasible solutions, or even none. The neighborhood structure is the core of the heuristic algorithm, essentially defining how the entire search process is performed.

[0124] The flight parameter information, gate parameter information, and auxiliary parameter information have been illustrated in the above embodiments, referring to the various parameters in those embodiments. For example, the flight parameter information includes I, I... D P, T i A i D i B i For example, the station parameter information includes K, N, and C. k θ k U k C k C; The remaining information that does not belong to flight parameter information and gate parameter information belongs to auxiliary parameter information.

[0125] The objective function value refers to the optimization score obtained based on the objective optimization function analysis, and not necessarily the result value of the objective optimization function. In this application, a larger objective function value indicates a higher quality solution (aircraft position information), and a smaller result value indicates a higher quality solution (aircraft position information).

[0126] In practical implementation, the flight delay scenario in dynamic gate allocation is quite unique, requiring priority to ensure the timely delivery of pallets and containers for delayed flights. This involves direct transfer of pallets and containers, and point-to-point aircraft-to-aircraft towing issues. In this case, the variable size is O(|P|×|I′|×|K|). 2In this context, "I′" represents the set of delayed aircraft, "P" represents the set of pallets / cabins requiring straight turns, and "K" represents the set of all aircraft stands. In the worst-case scenario, if the number of delayed aircraft is large, the number of variables can exceed 10^6. For this scale, integer programming is relatively unsuitable, significantly slowing down the solution and causing unstable convergence. Heuristic algorithms, on the other hand, can quickly obtain feasible and high-quality solutions, making them suitable for large-scale problems. Therefore, this application proposes using tabu search techniques from heuristic algorithms to dynamically adjust the parking stands for the target flights, ensuring that the final parking stands are the preferred ones.

[0127] More specifically, regarding the parking space allocation problem, a single "move" operation can allocate an aircraft A from parking space 1 to parking space 2, while the goal of neighborhood search is to select the optimal solution (S0) from N(S). * For example, in "N(S)", the solution that minimizes the total hauling distance is iterated over and over. The score of the solution will continuously converge to a local optimum. Finding the local optimum solution yields the target optimal solution (S). * This means that the optimal parking position for the target flight in the current scenario has been found.

[0128] Further reading is available. Figure 3 Before server 200 uses the tabu search algorithm to analyze and solve for the optimal gate information of the target flight, it can first use the initial gate information (S) as the target optimal solution (S) for the target flight. * ), that is, defining "S" * =S", and then set the initial default value of the continuous no-boost parameter (Nolmp) to zero, that is, define "Nolmp=0", and set the initial default value of the iteration parameter (Gen) to zero, that is, define "Gen=0". Then, the server 200 can, according to the movement type set by the user, determine the optimal solution "S" for the target. * =S” to perform a neighborhood search and obtain the neighborhood information “N(S)” of the optimal solution for the target.

[0129] The preferred default move is "Insert Move". In the selection of the two exchange operators, "Exchange1 Move" and "Exchange2 Move", the default is to select "Exchange1 Move" every "m1" iterations and "Exchange2 Move" every "m2" iterations.

[0130] Furthermore, server 200 can analyze whether there are feasible solutions within the neighborhood information "N(S)" of the target optimal solution, i.e., determine whether the neighborhood information "N(S)" is empty. If "N(S)≠0" is not empty, it means that there are feasible solutions in the current neighborhood structure. Server 200 can obtain the objective function value of each feasible solution in "N(S)" based on the objective optimization function in the current scenario, combined with the flight parameter information, gate parameter information, and auxiliary parameter information of the target flight. Then, it can compare the objective function values ​​and select the maximum value. The feasible solution with the maximum objective function value can be used as the current optimal solution for subsequent analysis. Analyze the current optimal solution The steps will be explained in detail below.

[0131] Furthermore, if the neighborhood information is empty, i.e., "N(S) = 0", then the initial station information is taken as the optimal solution for the target, i.e., "S" is determined. * =S".

[0132] In one embodiment, updating the target optimal solution based on the quality of the current optimal solution to adjust the initial gate information of the target flight and obtain gate adjustment information includes: obtaining the objective function value of the target optimal solution under constraints based on the objective optimization function, as the first objective function value; using the objective function value of the current optimal solution as the second objective function value; if the second objective function value is greater than the first objective function value, determining that the second quality of the current optimal solution is better than the first quality of the target optimal solution; when the second quality is better than the first quality, updating the target optimal solution to adjust the initial gate information and obtain gate adjustment information.

[0133] For specific implementation details, please refer to [link / reference]. Figure 3 The first objective function value is the optimal solution to the objective (S). * The objective function value is the first objective function value, and the second objective function value is the current optimal solution. If the second objective function value is greater than the first objective function value, then the current optimal solution is considered. Better than the target optimal solution (S) * At this point, the optimal solution for the objective can be updated.

[0134] In one embodiment, when the second quality is better than the first quality, the target optimal solution is updated to adjust the initial aircraft position information to obtain aircraft position adjustment information. This includes: when the second quality is better than the first quality, resetting the preset continuous non-improvement parameter to zero before acquiring the neighborhood information, the initial preset value of the continuous non-improvement parameter being zero; using the current optimal solution as the target optimal solution to update the target optimal solution; updating the current optimal solution based on the descending order of the objective function values; and repeatedly performing the target optimal solution update operation according to the quality of the updated current optimal solution to adjust the initial aircraft position information to obtain aircraft position adjustment information.

[0135] Among them, the setting of continuous non-boosting parameter (Nolmp) adds an adaptive operator selection mechanism compared to the traditional tabu search algorithm, which makes the solution obtained by neighborhood search better.

[0136] The purpose of setting the iteration parameter (Gen) is to record the optimal solution of the objective (S). * The update frequency of ) is adjusted to prevent the server from getting stuck in an infinite loop when executing the stop position dynamic adjustment program.

[0137] For specific implementation details, please refer to [link / reference]. Figure 3 Current optimal solution Better than the target optimal solution (S) * When this happens, server 200 can perform a zeroing operation on parameters that have not been improved for a continuous period, i.e., "Nolmp=0", thereby updating the target optimal solution: It's important to note here that updating the target optimal solution at this point requires first determining the current optimal solution. Check if the move is taboo in the tabu list. If not, update the target optimal solution and add the move operator of this iteration to the tabu list. Set the tabu length "k" to prevent the move operator from being executed again in the next "k" iterations.

[0138] Furthermore, the tabu length "k" can be a fixed constant (T = c) or it can be dynamically changed, varying within an interval according to a certain rule or formula. If the tabu length is too short, it is easy to get stuck in a local optimum and be unable to escape the loop; if the tabu length is too long, all candidate solutions will be tabu, resulting in a large computation time and possibly causing the computation to stop. Therefore, this application embodiment proposes that the selection of the tabu length "k" should be based on actual business needs.

[0139] In one embodiment, after obtaining the objective function value of the target optimal solution under constraints based on the objective optimization function and using it as the first objective function value, the method further includes: if the second objective function value is less than or equal to the first objective function value, then determining that the first quality of the target optimal solution is better than the second quality of the current optimal solution; when the first quality is better than the second quality, incrementing the preset continuous non-improvement parameter before obtaining the neighborhood information by one, and keeping the target optimal solution unchanged.

[0140] For specific implementation details, please refer to [link / reference]. Figure 3 If the value of the second objective function is less than or equal to the value of the first objective function, it indicates that the objective is optimal (S). * (Better than the current optimal solution) At this point, because a solution better than the target (S) has not been found... * A better solution is found, therefore the objective optimal solution (S) cannot be updated. * The only executable operation is to zero out the continuously unimproved parameter: "Nolmp = Nolmp + 1", while maintaining the current target optimal solution (S). * )constant.

[0141] S204: When the gate adjustment information meets the preset adjustment stop conditions, the gate adjustment information is used as the preferred gate information for the target flight.

[0142] The adjustment of the stopping condition can be a condition set for the iteration parameter (Gen). The final optimized position information can be sent to the terminal 100 for display. See the description below for details.

[0143] In one embodiment, this step includes: after determining the target optimal solution, incrementing the preset iteration parameter before obtaining the neighborhood information by one, with the initial preset value of the iteration parameter being zero; if the iteration parameter after the increment operation reaches a preset iteration threshold, then the target optimal solution is used as the preferred gate information for the target flight; if the iteration parameter after the increment operation does not reach the preset iteration threshold, then based on the current continuous no-increase parameter, the neighborhood search operation for the target optimal solution is repeatedly executed until gate adjustment information that meets the adjustment stopping condition is obtained.

[0144] For specific implementation details, please refer to [link / reference]. Figure 3 Server 200 executes the steps provided in the above embodiments to determine the optimal solution to the objective (S). * After this, an iterative adjustment of the initial machine position information is completed. To determine whether to continue the next iterative adjustment, the iteration parameter (Gen) needs to be incremented by one: "Gen = Gen + 1". Then, it is determined whether the iteration parameter (Gen) after the increment operation has reached the iteration threshold. If so, the iteration operation ends, and the current target optimal solution (S) is set. *The corresponding gate information is used as the preferred gate information for the target flight. If not, the continuous no-boost parameters (Nolmp) are analyzed again, and the results of the continuous no-boost parameters (Nolmp) analysis are used to determine whether to continue iterating or stop iterating.

[0145] At this point, the iteration parameter (Gen) after the increment operation reaches the iteration threshold, which can be considered a stopping condition for adjustment. For example, if the initial iteration parameter "Gen = 0", after server 200 completes one iteration adjustment operation, it sets "Gen = 1". The iteration threshold at this time is "2", and server 200 can continue iterative adjustment. However, if the iteration threshold at this time is "1", server 200 needs to stop the iteration operation and output the preferred parking position information. The preferred parking position information includes, but is not limited to, the following: initial parking position, target parking position (i.e., the optimal parking position after adjustment), aircraft type, takeoff time, landing time, origin, destination, whether it is near a parking position, distance of the parking position from the unloading port, parking position orientation, takeoff runway, and landing runway.

[0146] Understandably, the initial gate information of a target flight differs from its preferred gate information in that: the target gate (i.e., the adjusted optimal parking gate), the landing runway, and the takeoff runway (takeoff and landing will be changed to this gate runway after the gate is adjusted).

[0147] In one embodiment, if the iteration parameter after the increment operation does not reach a preset iteration threshold, then based on the current continuous non-increase parameter, the neighborhood search operation for the target optimal solution is repeatedly executed until the position adjustment information that meets the adjustment stopping condition is obtained. This includes: if the iteration parameter after the increment operation does not reach the preset iteration threshold, then obtaining the current continuous non-increase parameter; if the continuous non-increase parameter is greater than the preset continuous threshold, then the continuous non-increase parameter is zeroed out, and a first operator is used to perform a neighborhood search on the target optimal solution to update the neighborhood information of the target optimal solution; if the continuous non-increase parameter is less than or equal to the continuous threshold, a second operator is used to perform a neighborhood search on the target optimal solution to update the neighborhood information of the target optimal solution.

[0148] In specific implementation, based on the above embodiments, please refer to... Figure 3 When the iteration parameter "Gen = 1" after the increment operation, and the iteration threshold is "2", it means that the iteration parameter after the increment operation has not reached the preset iteration threshold. The server 200 can further analyze whether the continuous non-promotion parameter (Nolmp) at the current moment has reached the continuous threshold. If so, the first operator (Insert Move) is selected to re-perform the neighborhood search and iterative adjustment; if not, the second operator (Exchange1 Move or Exchange2 Move) is selected to perform the neighborhood search and iterative adjustment until the preset threshold number of iterations is reached, and then the iteration can be stopped.

[0149] Furthermore, during the neighborhood search process, when selecting the second operator (Exchange1 Move or Exchange2 Move), Exchange1 Move is selected by default every m1 iterations, and Exchange2 Move is selected every m2 iterations. Therefore, when the continuous no-boost parameter (Nolmp) reaches the continuity threshold, NextMove is set to Exchange1 Move, and m1 consecutive Exchange1 Move iterations are performed; or NextMove is set to Exchange2 Move, and m2 consecutive Exchange2 Move iterations are performed.

[0150] The dynamic parking stand adjustment method in the above embodiments involves the server acquiring flight operation information of the target flight that triggered an anomaly at the current moment. Based on the anomaly type of the target flight, it obtains a target optimization function for dynamically adjusting the parking stand for the target flight. Then, based on the target optimization function, the initial parking stand information of the target flight is adjusted until the resulting adjustment information meets a preset adjustment stop condition. At this point, the adjusted parking stand information is used as the preferred parking stand information for the target flight, thus achieving the purpose of dynamic parking stand adjustment for the target flight. Using this method, for different dynamic parking stand adjustment scenarios, it can automatically solve for optimal parking stand adjustment schemes with multi-objective settings, improving the efficiency of parking stand adjustment and allocation, and increasing the accuracy of the preferred parking stand information required by the target flight.

[0151] To better implement the dynamic adjustment method for the parking position in the embodiments of this application, based on the dynamic adjustment method for the parking position, the embodiments of this application also provide a dynamic adjustment device for the parking position, such as... Figure 4 As shown, the dynamic adjustment device 400 for stopping position includes:

[0152] The information acquisition module 410 is used to acquire the flight operation information of the target flight that triggered the anomaly at the current time. The flight operation information includes the initial gate information of the target flight.

[0153] The function acquisition module 420 is used to acquire the target optimization function for dynamically adjusting the parking position of the target flight based on the anomaly type of the target flight.

[0154] The gate adjustment module 430 is used to adjust the initial gate information of the target flight based on the target optimization function to obtain the gate adjustment information of the target flight.

[0155] The gate selection module 440 is used to select the gate adjustment information as the preferred gate information for the target flight when the gate adjustment information meets the preset adjustment stop conditions.

[0156] In one embodiment, the function acquisition module 420 is further configured to acquire a distance optimization function and / or a gate change optimization function as the target optimization function if the anomaly type of the target flight is a first anomaly; and acquire a total distance optimization function and / or a runway change optimization function as the target optimization function if the anomaly type of the target flight is a second anomaly; wherein the first anomaly is a flight delay anomaly, and the second anomaly includes at least one of flight pushback anomaly, temporary diversion anomaly, duplicate flight anomaly, and route interchange anomaly.

[0157] In one embodiment, the gate adjustment module 430 is further configured to use the initial gate information as the target optimal solution for the target flight; based on the target optimization function, update the target optimal solution under preset constraints to adjust the initial gate information of the target flight and obtain gate adjustment information; wherein, the constraints include at least one of the following: unique allocation constraint, composite gate constraint, aircraft type matching constraint, gate locking constraint, safety interval constraint, and pushback interval constraint.

[0158] In one embodiment, the flight operation information also includes flight parameter information, gate position parameter information, and auxiliary parameter information. The gate position adjustment module 430 is further used to perform a tabu search algorithm to search the neighborhood of the target optimal solution to obtain neighborhood information. If the neighborhood information is not empty, the objective function value of each solution in the neighborhood information under the constraints is obtained based on the objective optimization function, flight parameter information, gate position parameter information, and auxiliary parameter information. The current optimal solution is determined, and the objective function value corresponding to the current optimal solution is the maximum value among the objective function values. The target optimal solution is updated according to the quality of the current optimal solution to adjust the initial gate position information of the target flight, thereby obtaining gate position adjustment information.

[0159] In one embodiment, the aircraft position adjustment module 430 is further configured to: obtain the objective function value of the target optimal solution under constraints based on the objective optimization function, and use it as the first objective function value; use the objective function value of the current optimal solution as the second objective function value; if the second objective function value is greater than the first objective function value, determine that the second quality of the current optimal solution is better than the first quality of the target optimal solution; when the second quality is better than the first quality, update the target optimal solution to adjust the initial aircraft position information and obtain aircraft position adjustment information.

[0160] In one embodiment, the aircraft position adjustment module 430 is further configured to: when the second quality is better than the first quality, perform a zeroing operation on the preset continuous non-improvement parameter before obtaining the neighborhood information, the initial preset value of the continuous non-improvement parameter being zero; use the current optimal solution as the target optimal solution to update the target optimal solution; update the current optimal solution based on the descending order of the objective function values; and repeatedly perform the target optimal solution update operation according to the quality of the updated current optimal solution to adjust the initial aircraft position information and obtain aircraft position adjustment information.

[0161] In one embodiment, the machine position adjustment module 430 is further configured to determine that if the second objective function value is less than or equal to the first objective function value, the first quality of the target optimal solution is better than the second quality of the current optimal solution; when the first quality is better than the second quality, the preset continuous non-improvement parameter before obtaining the neighborhood information is incremented by one, and the target optimal solution remains unchanged.

[0162] In one embodiment, the aircraft position adjustment module 430 is further configured to use the initial aircraft position information as the target optimal solution if the neighborhood information is empty.

[0163] In one embodiment, the gate selection module 440 is further configured to, after determining the target optimal solution, increment the preset iteration parameter before obtaining the neighborhood information by one, the initial preset value of the iteration parameter being zero; if the iteration parameter after the increment operation reaches a preset iteration threshold, the target optimal solution is used as the preferred gate information for the target flight; if the iteration parameter after the increment operation does not reach the preset iteration threshold, the neighborhood search operation for the target optimal solution is repeatedly executed based on the current continuous no-increase parameter until gate adjustment information that meets the adjustment stopping condition is obtained.

[0164] In one embodiment, the machine position selection module 440 is further configured to: if the iteration parameter after the increment operation does not reach a preset iteration threshold, obtain the current continuous non-incrementing parameter; if the continuous non-incrementing parameter is greater than the preset continuous threshold, perform a zeroing operation on the continuous non-incrementing parameter, and use a first operator to perform a neighborhood search on the target optimal solution to update the neighborhood information of the target optimal solution; if the continuous non-incrementing parameter is less than or equal to the continuous threshold, use a second operator to perform a neighborhood search on the target optimal solution to update the neighborhood information of the target optimal solution.

[0165] In the above embodiments, the dynamic parking stand adjustment device can automatically solve for optimal parking stand adjustment schemes in different dynamic parking stand adjustment scenarios, in conjunction with multi-objective settings. It can also optimize based on preset multi-objectives with different priorities, so as to prioritize cargo loading and unloading for target flights, such as delayed flights, while minimizing changes to parking stand plans for other flights. Ultimately, this improves the efficiency of parking stand adjustment and allocation, and enhances the accuracy of the optimal parking stand information required by target flights.

[0166] In some embodiments of this application, the dynamic adjustment device 400 for the stopping position can be implemented as a computer program, which can be implemented in, for example... Figure 5 The computer device shown operates on this device. The computer device's memory can store the various program modules that make up the dynamic adjustment device 400 for the stop position, for example, Figure 4The information acquisition module 410, function acquisition module 420, aircraft position adjustment module 430, and aircraft position optimization module 440 are shown. The computer program, composed of these modules, causes the processor to execute the steps in the dynamic aircraft position adjustment methods of the various embodiments of this application described in this specification.

[0167] For example, Figure 5 The computer device shown can be used as follows Figure 4 The information acquisition module 410 in the dynamic parking position adjustment device 400 shown executes step S201. The computer device can execute step S202 through the function acquisition module 420. The computer device can execute step S203 through the parking position adjustment module 430. The computer device can execute step S204 through the parking position selection module 440. The computer device includes a processor, memory, and network interface connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with external computer devices via a network connection. When the computer program is executed by the processor, it implements a dynamic parking position adjustment method.

[0168] Those skilled in the art in this field can understand. Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0169] In some embodiments of this application, a computer device is provided, including one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processors using the steps of the above-described dynamic stop position adjustment method. The steps of the dynamic stop position adjustment method here may be steps from the dynamic stop position adjustment methods of the various embodiments described above.

[0170] In some embodiments of this application, a computer-readable storage medium is provided, storing a computer program that is loaded by a processor, causing the processor to execute the steps of the above-described dynamic stop position adjustment method. The steps of the dynamic stop position adjustment method here can be the steps in the dynamic stop position adjustment methods of the various embodiments described above.

[0171] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0173] The above provides a detailed description of a method, apparatus, computer device, and storage medium for dynamically adjusting parking positions according to embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for dynamically adjusting the stopping position, characterized in that, include: Obtain the flight operation information of the target flight that triggered the anomaly at the current moment, the flight operation information including the initial gate information of the target flight; Based on the anomaly type of the target flight, obtain the target optimization function for dynamically adjusting the parking position of the target flight; Based on the target optimization function, the initial gate information of the target flight is adjusted to obtain the gate adjustment information of the target flight; When the gate adjustment information meets the preset adjustment stop condition, the gate adjustment information is used as the preferred gate information for the target flight; The step of obtaining a target optimization function for dynamically adjusting the parking positions for the target flight based on the anomaly type of the target flight includes: If the anomaly type of the target flight is the first anomaly, then the distance optimization function and / or the gate change optimization function are obtained as the target optimization function; the distance optimization function is used to minimize at least one of the following parameters: minimize the towing distance of the through-pass container on the delayed flight, minimize the loading and unloading towing distance of the non-through-pass container on the delayed flight, minimize the landing taxiing distance of the delayed flight, minimize the change between the dynamically adjusted result and the original plan, or minimize the total unloading towing distance and loading towing distance of the non-through-pass container; the gate change optimization function is used to minimize the change between the dynamically adjusted result and the original plan; If the anomaly type of the target flight is the second anomaly, then the total distance optimization function and / or the runway variation optimization function are obtained as the target optimization function; wherein, the first anomaly is a flight delay anomaly, and the second anomaly includes at least one of flight pushback anomaly, temporary diversion anomaly, duplicate flight anomaly, and route interchange anomaly; the total distance optimization function is used to minimize at least one of the following parameters: minimize the sum of the unloading and loading towing distances of the total non-straight-turn pallet containers, minimize the sum of the straight-turn distances of the total straight-turn pallet containers, or minimize the sum of the takeoff and landing taxiing distances of the total aircraft; the runway variation optimization function is used to arrange aircraft with takeoff and landing runways on the same side of the runway at the same side of the runway.

2. The method as described in claim 1, characterized in that, The step of adjusting the initial gate information of the target flight based on the target optimization function to obtain the gate adjustment information of the target flight includes: The initial gate information is used as the target optimal solution for the target flight; Based on the objective optimization function, the objective optimal solution is updated under preset constraints to adjust the initial gate information of the target flight, thereby obtaining the gate adjustment information; The constraints include at least one of the following: unique allocation constraint, composite aircraft position constraint, aircraft type matching constraint, aircraft position locking constraint, safety interval constraint, and pushback interval constraint.

3. The method as described in claim 2, characterized in that, The flight operation information also includes flight parameter information, gate parameter information, and auxiliary parameter information. Based on the objective optimization function, the optimal objective solution is updated under preset constraints to adjust the initial gate information of the target flight, resulting in the gate adjustment information, including: A tabu search algorithm is used to perform a neighborhood search on the optimal solution of the target to obtain neighborhood information. If the neighborhood information is not empty, then based on the objective optimization function, the flight parameter information, the gate parameter information, and the auxiliary parameter information, the objective function value of each solution in the neighborhood information under the constraints is obtained; Determine the current optimal solution among all the solutions, and the objective function value corresponding to the current optimal solution is the maximum value among all objective function values; Based on the quality of the current optimal solution, the target optimal solution is updated to adjust the initial gate information of the target flight, thereby obtaining the gate adjustment information.

4. The method as described in claim 3, characterized in that, The step of updating the target optimal solution based on the quality of the current optimal solution to adjust the initial gate information of the target flight, thereby obtaining the gate adjustment information, includes: Based on the objective optimization function, the objective function value of the optimal solution under the constraints is obtained and used as the first objective function value; The objective function value of the current optimal solution is used as the second objective function value; If the value of the second objective function is greater than the value of the first objective function, then the second quality of the current optimal solution is determined to be better than the first quality of the target optimal solution; When the second quality is better than the first quality, the target optimal solution is updated to adjust the initial aircraft position information, thereby obtaining the aircraft position adjustment information.

5. The method as described in claim 4, characterized in that, When the second quality is better than the first quality, the target optimal solution is updated to adjust the initial aircraft position information, resulting in the aircraft position adjustment information, including: When the second quality is better than the first quality, the preset continuous no-boost parameter before acquiring the neighborhood information is reset to zero, and the initial preset value of the continuous no-boost parameter is zero. The current optimal solution is used as the target optimal solution to update the target optimal solution; The current optimal solution is updated based on the descending order of the objective function values. Based on the quality of the updated current optimal solution, the update operation of the target optimal solution is repeatedly executed to adjust the initial aircraft position information, thereby obtaining the aircraft position adjustment information.

6. The method as described in claim 4, characterized in that, After obtaining the objective function value of the optimal solution under the constraints based on the objective optimization function, and using it as the first objective function value, the method further includes: If the value of the second objective function is less than or equal to the value of the first objective function, then the first quality of the target optimal solution is determined to be better than the second quality of the current optimal solution; When the first quality is better than the second quality, the preset continuous non-improvement parameter before obtaining the neighborhood information is incremented by one, and the target optimal solution is kept unchanged.

7. The method as described in claim 3, characterized in that, After employing the tabu search algorithm to perform a neighborhood search on the target optimal solution and obtain neighborhood information, the method further includes: If the neighborhood information is empty, then the initial position information is taken as the optimal solution for the target.

8. The method according to any one of claims 1-7, characterized in that, When the gate adjustment information meets the preset adjustment stop condition, the gate adjustment information is used as the preferred gate information for the target flight, including: After determining the optimal solution for the target, the preset iteration parameters that were obtained before acquiring the neighborhood information are incremented by one. The initial preset value of the iteration parameters is zero. If the iteration parameters after the increment operation reach a preset iteration threshold, then the target optimal solution is used as the preferred gate information for the target flight. If the iteration parameter after the increment operation does not reach the preset iteration threshold, then based on the current continuous non-increase parameter, the neighborhood search operation for the target optimal solution is repeatedly executed until the position adjustment information that meets the adjustment stop condition is obtained.

9. The method as described in claim 8, characterized in that, If the iteration parameter after the increment operation does not reach the preset iteration threshold, then based on the current continuous non-increase parameter, the neighborhood search operation for the target optimal solution is repeatedly executed until the position adjustment information that satisfies the adjustment stopping condition is obtained, including: If the iteration parameter after the increment operation does not reach the preset iteration threshold, then obtain the current continuous non-incrementing parameter; If the continuous non-improvement parameter is greater than the preset continuous threshold, then the continuous non-improvement parameter is reset to zero, and the first operator is used to perform a neighborhood search on the target optimal solution to update the neighborhood information of the target optimal solution. If the continuous non-improvement parameter is less than or equal to the continuous threshold, then the second operator is used to perform a neighborhood search on the target optimal solution and update the neighborhood information of the target optimal solution.

10. A dynamic adjustment device for the stopping position, characterized in that, include: The information acquisition module is used to acquire the flight operation information of the target flight that triggered the anomaly at the current time, including the initial gate information of the target flight. The function acquisition module is used to acquire a target optimization function for dynamically adjusting the parking position of the target flight based on the anomaly type of the target flight. The gate adjustment module is used to adjust the initial gate information of the target flight based on the target optimization function to obtain the gate adjustment information of the target flight. The gate selection module is used to select the gate adjustment information as the preferred gate information for the target flight when the gate adjustment information meets the preset adjustment stop conditions. Specifically, the function acquisition module is used to acquire a distance optimization function and / or a gate change optimization function as the target optimization function if the anomaly type of the target flight is the first anomaly. The distance optimization function is used to minimize at least one of the following parameters: minimize the towing distance of the through-pass container on the delayed flight, minimize the loading and unloading towing distance of the non-through-pass container on the delayed flight, minimize the landing taxiing distance of the delayed flight, minimize the change between the dynamically adjusted result and the original plan, or minimize the total unloading and loading towing distances of the non-through-pass containers. The gate change optimization function is used to minimize the change between the dynamically adjusted result and the original plan. If the anomaly type of the target flight is the second anomaly, then the total distance optimization function and / or the runway variation optimization function are obtained as the target optimization function; wherein, the first anomaly is a flight delay anomaly, and the second anomaly includes at least one of flight pushback anomaly, temporary diversion anomaly, duplicate flight anomaly, and route interchange anomaly; the total distance optimization function is used to minimize at least one of the following parameters: minimize the sum of the unloading and loading towing distances of the total non-straight-turn pallet containers, minimize the sum of the straight-turn distances of the total straight-turn pallet containers, or minimize the sum of the takeoff and landing taxiing distances of the total aircraft; the runway variation optimization function is used to arrange aircraft with takeoff and landing runways on the same side of the runway at the same side of the runway.

11. A computer device, characterized in that, The computer device includes: One or more processors; The memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the stop position dynamic adjustment method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to execute the steps in the dynamic adjustment method for the parking position as described in any one of claims 1 to 9.

Images