Methods and related equipment for predicting flight arrival and / or departure times.

Abstract

This application provides a method and related equipment for predicting flight arrival and / or departure times. The method includes: receiving airport information of the flight to be predicted, wherein the airport information is the information of the airport where the flight will arrive and / or depart; determining the taxiing time of the flight to be predicted based on the airport information; if the flight to be predicted is an inbound flight, determining the arrival time of the flight to be predicted based on the taxiing time; and / or, if the flight to be predicted is a outbound flight, determining the departure time of the flight to be predicted based on the taxiing time. Using this application embodiment can promote the scientific management of flight taxiing, save taxiing time, and improve taxiing efficiency.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and related equipment for predicting flight arrival and / or departure times. Background Technology

[0002] With the development of science and technology, air transport has gradually become one of the main modes of transportation. More and more passengers are choosing airplanes for business activities and travel. Therefore, the number of flights that airlines need to schedule daily is also increasing. Accurately predicting flight arrival and departure times can improve the operational efficiency of airlines and reduce expenses.

[0003] Existing airfield surveillance radar systems can capture the real-time position of aircraft, but they cannot accurately predict taxiing times by considering various complex airfield factors. Therefore, they cannot accurately predict and determine the arrival time of flights, cannot reduce taxiing conflicts, and have low operational efficiency. While existing technologies can predict pushback times, they still rely on a traditional first-come, first-served model. Therefore, they fail to consider the influence of various complex airfield factors to determine the optimal pushback time, resulting in low taxiing efficiency for flights. Summary of the Invention

[0004] This application provides a method and related equipment for predicting flight arrival and / or flight departure times, which can promote scientific management of flight taxiing, save taxiing time, and improve taxiing efficiency.

[0005] In a first aspect, embodiments of this application provide a method for predicting flight arrival and / or departure times, including:

[0006] Receive airport information for the flight to be predicted, wherein the airport information is the information of the airport where the flight to be predicted was located when it entered and / or departed;

[0007] Based on the airport information of the flight to be predicted, determine the taxiing time of the flight to be predicted;

[0008] If the flight to be predicted is an inbound flight, then the arrival time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted; and / or,

[0009] If the flight to be predicted is an outbound flight, the launch time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted.

[0010] The above method can be applied to servers and executed by the server or its internal components (such as chips, software modules, or integrated circuits).

[0011] In this embodiment, the taxiing time of the flight to be predicted is obtained by analyzing the information of the airport where the flight is located during its approach and / or pushback. Since airport information is related to the factors faced by the flight during approach or pushback, the taxiing time determined by fully considering the current airport conditions has high accuracy. Therefore, the pushback and / or approach times obtained based on the taxiing time also have high accuracy. Improving the prediction accuracy of the pushback and / or approach times can enhance the safety and efficiency of flight taxiing, and also improve flight taxiing efficiency.

[0012] In one possible implementation of the first aspect, the airport information includes arriving airport information and / or departing airport information. Determining the taxiing time of the flight to be predicted based on the airport information includes:

[0013] Based on the arrival airport information of the flight to be predicted, determine the arrival taxiing time of the flight to be predicted; and / or,

[0014] Based on the departure airport information of the flight to be predicted, the departure taxiing time of the flight to be predicted is determined.

[0015] As can be seen, the embodiments of this application predict taxiing time based on different scenarios, such as inbound or outbound flights, by combining information from each scenario. Therefore, the accuracy of predicting inbound and / or outbound taxiing times can be improved.

[0016] In one possible implementation of the first aspect, determining the arrival taxiing time of the flight to be predicted based on the arrival airport information of the flight to be predicted includes:

[0017] The arrival airport information is input into the first prediction model to obtain the arrival taxiing time of the flight to be predicted; wherein, the first prediction model is trained based on the historical scene information of the airport.

[0018] As can be seen, the embodiments of this application integrate big data and artificial intelligence technologies, and use the trained prediction model to predict the arrival taxiing time, thereby improving the prediction accuracy.

[0019] In one possible implementation of the first aspect, the arrival airport information includes surface information of the airport to which the predicted flight will arrive, and the airport surface information includes one or more of the following: arrival flight information that has landed but not yet entered its designated position, departure flight information waiting at the runway head, flight information waiting to cross, departure flight information taxiing on the taxiway, flight information that has already been launched, and flight information that is expected to be launched.

[0020] As can be seen, the embodiments of this application introduce a ground flight traffic distribution factor, which fully considers various factors affecting flight taxiing, and can improve the accuracy of taxiing time prediction.

[0021] In one possible implementation of the first aspect, if the flight to be predicted is an inbound flight, the arrival time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted, including:

[0022] If the flight to be predicted has already landed, then obtain the current time of the flight to be predicted;

[0023] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0024] The entry time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted, the current time, and the first taxiing path.

[0025] As can be seen, the embodiments of this application take into account the influence of taxiing time and taxiing path when determining the arrival time of the flight to be predicted, thus improving the accuracy of the arrival time prediction.

[0026] In one possible implementation of the first aspect, determining the departure taxiing time of the flight to be predicted based on the departure airport information of the flight to be predicted includes:

[0027] The departure airport information is input into the second prediction model to obtain the departure taxiing time of the flight to be predicted; the second prediction model is trained based on the historical departure taxiing data of the airport.

[0028] As can be seen, the embodiments of this application integrate big data and artificial intelligence technologies, and use the trained prediction model to predict departure taxiing time, thereby improving the prediction accuracy of departure taxiing time.

[0029] In one possible implementation of the first aspect, the departure airport information includes taxiing data of the airport from which the flight to be predicted will depart, the taxiing data including one or more of the following: gate number, runway number, aircraft type, airline, and the time period in which the flight to be predicted is located.

[0030] In one possible implementation of the first aspect, after determining the taxiing time of the flight to be predicted based on the airport information of the flight to be predicted, before determining the arrival time of the flight to be predicted based on the taxiing time of the flight to be predicted if the flight to be predicted is an inbound flight; and / or, before determining the departure time of the flight to be predicted based on the taxiing time of the flight to be predicted if the flight to be predicted is an outbound flight, the method further includes:

[0031] Obtain the location information of inbound flights at the airport where the flight to be predicted is located;

[0032] The arrival flight location information is input into the third prediction model to obtain the arrival flight landing time; wherein, the third prediction model is trained based on the historical arrival flight location information of the airport.

[0033] As can be seen, the embodiments of this application integrate big data and artificial intelligence technologies, and use the trained prediction model to predict the landing time of inbound flights, thereby improving the accuracy of landing time prediction.

[0034] In one possible implementation of the first aspect, the inbound flight location information includes one or more of the following: longitude, latitude, speed, altitude, flight direction, and aircraft type of the inbound flight.

[0035] As can be seen, the embodiments of this application can extract control scenario data for modeling, and use the current flight location information before the flight lands to predict the flight landing time, thereby improving the accuracy of landing time prediction.

[0036] In one possible implementation of the first aspect, if the flight to be predicted is an inbound flight, then the inbound flight location information is the location information of the flight to be predicted, and the inbound flight landing time is the landing time of the flight to be predicted.

[0037] If the flight to be predicted is an outbound flight, then the inbound flight location information includes the location information of one or more inbound flights in the airport where the flight to be predicted is located, and the inbound flight landing time includes the landing time of one or more inbound flights in the airport where the flight to be predicted is located.

[0038] It can be seen that, regardless of whether the flight to be predicted is an inbound or outbound flight, the predicted landing time is related to the predicted arrival time and / or departure time.

[0039] In one possible implementation of the first aspect, the step of determining the arrival time of the flight to be predicted based on the taxiing time of the flight to be predicted if the flight to be predicted is an inbound flight includes:

[0040] If the flight to be predicted is an inbound flight, obtain the arrival time of the flight to be predicted;

[0041] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0042] The landing time of the flight to be predicted is determined based on the landing time of the flight to be predicted, the first taxiing path, and the taxiing time of the flight to be predicted.

[0043] It can be seen that for inbound flights that have not yet landed, in order to improve the accuracy of the predicted arrival time, the arrival time can be determined by combining the arrival time, taxiing path and taxiing time.

[0044] In one possible implementation of the first aspect, determining the first taxiway path of the flight to be predicted includes:

[0045] Obtain the first location information of the flight to be predicted at the airport;

[0046] The first location information is input into the fourth prediction model to obtain the first taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the historical taxiing data of the airport.

[0047] As can be seen, the taxiing path is determined based on the location information of the flight to be predicted. By using the taxiing path, the potential conflicts that the flight may encounter during taxiing can be predicted in advance, thereby reducing taxiing conflicts and improving flight operation efficiency.

[0048] In one possible implementation of the first aspect, determining the departure time of the flight to be predicted based on its taxiing time if the flight to be predicted is a departure flight includes:

[0049] If the flight to be predicted is an outbound flight, then obtain the landing time of one or more inbound flights in the airport where the flight to be predicted is located, and information on other flights in the airport where the flight to be predicted is located.

[0050] Determine a second taxiing path for the flight to be predicted, wherein the second taxiing path is the path the flight to be predicted will take on the airport;

[0051] The runway availability of the airport is determined based on the landing time of one or more inbound flights at the airport where the flight to be predicted is located, the second taxiway, and information on other flights at the airport where the flight to be predicted is located.

[0052] The launch time of the flight to be predicted is determined based on the idle time and the taxiing time of the flight to be predicted.

[0053] As can be seen, the embodiments of this application combine the spatial distribution of inbound and outbound flights, taxiing time, and information from other flights, and integrate big data and artificial intelligence technologies to determine the predicted departure pushback time, thereby avoiding flights pushing back from their parking positions too early or waiting on the ground for a long time to take off.

[0054] In one possible implementation of the first aspect, determining the second taxiway path of the flight to be predicted includes:

[0055] Obtain the second location information of the flight to be predicted at the airport;

[0056] The second location information is input into the fourth prediction model to obtain the second taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

[0057] As can be seen, the taxiing path is determined based on the location information of the flight to be predicted. By using the taxiing path, the potential conflicts that the flight may encounter during taxiing can be predicted in advance, thereby reducing taxiing conflicts and improving flight operation efficiency.

[0058] In one possible implementation of the first aspect, the information on other flights at the airport where the flight to be predicted is located includes one or more of the following: the number of flights waiting to take off at the runway head, the number of flights waiting to cross, the remaining taxi time of flights that have already been pushed back, and the runway takeoff interval.

[0059] In one possible implementation of the first aspect, the first location information includes one or more of the following: the runway number, the gate number, the time period, and the aircraft type of the flight to be predicted after arrival.

[0060] The second location information includes one or more of the following: the gate number where the flight to be predicted was located before departure, the runway number of the departure flight, the time period, and the aircraft type.

[0061] Secondly, embodiments of this application provide a prediction device, which includes a processing unit and a communication unit, for implementing the method described in the first aspect or any possible implementation of the first aspect.

[0062] In one possible implementation of the second aspect, a communication unit is configured to receive airport information of the flight to be predicted, wherein the airport information is the information of the airport where the flight to be predicted is located when it enters and / or departs.

[0063] The processing unit is used to determine the taxiing time of the flight to be predicted based on the airport information of the flight to be predicted.

[0064] The processing unit is further configured to, if the flight to be predicted is an inbound flight, determine the arrival time of the flight to be predicted based on the taxiing time of the flight to be predicted; and / or,

[0065] If the flight to be predicted is an outbound flight, the launch time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted.

[0066] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0067] Based on the arrival airport information of the flight to be predicted, determine the arrival taxiing time of the flight to be predicted; and / or,

[0068] Based on the departure airport information of the flight to be predicted, the departure taxiing time of the flight to be predicted is determined.

[0069] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0070] The arrival airport information is input into the first prediction model to obtain the arrival taxiing time of the flight to be predicted; wherein, the first prediction model is trained based on the historical scene information of the airport.

[0071] In one possible implementation of the second aspect, the arrival airport information includes surface information of the airport to which the predicted flight will arrive, and the airport surface information includes one or more of the following: arrival flight information that has landed but not yet entered its designated position, departure flight information waiting at the runway head, flight information waiting to cross, departure flight information taxiing on the taxiway, flight information that has already been pushed back, and flight information that is expected to be pushed back.

[0072] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0073] If the flight to be predicted has already landed, then obtain the current time of the flight to be predicted;

[0074] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0075] The entry time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted, the current time, and the first taxiing path.

[0076] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0077] The departure airport information is input into the second prediction model to obtain the departure taxiing time of the flight to be predicted; the second prediction model is trained based on the historical departure taxiing data of the airport.

[0078] In one possible implementation of the second aspect, the departure airport information includes taxiing data of the airport from which the flight to be predicted will depart, and the taxiing data includes one or more of the following: gate number, runway number, aircraft type, airline, and the time period in which the flight to be predicted is located.

[0079] In one possible implementation of the second aspect, the processing unit is further configured to:

[0080] The location information of inbound flights at the airport where the flight to be predicted is located is obtained through the communication unit;

[0081] The arrival flight location information is input into the third prediction model to obtain the arrival flight landing time; wherein, the third prediction model is trained based on the historical arrival flight location information of the airport.

[0082] In one possible implementation of the second aspect, the inbound flight location information includes one or more of the following: longitude, latitude, speed, altitude, flight direction, and aircraft type.

[0083] In one possible implementation of the second aspect, if the flight to be predicted is an inbound flight, then the inbound flight location information is the location information of the flight to be predicted, and the inbound flight landing time is the landing time of the flight to be predicted.

[0084] If the flight to be predicted is an outbound flight, then the inbound flight location information includes the location information of one or more inbound flights in the airport where the flight to be predicted is located, and the inbound flight landing time includes the landing time of one or more inbound flights in the airport where the flight to be predicted is located.

[0085] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0086] If the flight to be predicted is an inbound flight, obtain the arrival time of the flight to be predicted;

[0087] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0088] The landing time of the flight to be predicted is determined based on the landing time of the flight to be predicted, the first taxiing path, and the taxiing time of the flight to be predicted.

[0089] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0090] The first location information of the flight to be predicted at the airport is obtained through the communication unit.

[0091] The first location information is input into the fourth prediction model to obtain the first taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the historical taxiing data of the airport.

[0092] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0093] If the flight to be predicted is an outbound flight, then obtain the landing time of one or more inbound flights in the airport where the flight to be predicted is located, and information on other flights in the airport where the flight to be predicted is located.

[0094] Determine a second taxiing path for the flight to be predicted, wherein the second taxiing path is the path the flight to be predicted will take on the airport;

[0095] The runway availability of the airport is determined based on the landing time of one or more inbound flights at the airport where the flight to be predicted is located, the second taxiway, and information on other flights at the airport where the flight to be predicted is located.

[0096] The launch time of the flight to be predicted is determined based on the idle time and the taxiing time of the flight to be predicted.

[0097] In one possible implementation of the second aspect, the processing unit is specifically used for:

[0098] The second location information of the flight to be predicted at the airport is obtained through the communication unit.

[0099] The second location information is input into the fourth prediction model to obtain the second taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

[0100] In one possible implementation of the second aspect, the information on other flights in the airport where the flight to be predicted is located includes one or more of the following: the number of flights waiting to take off at the runway head, the number of flights waiting to cross, the remaining taxi time of flights that have already been pushed back, and the runway takeoff interval.

[0101] In one possible implementation of the second aspect, the first location information includes one or more of the following: the runway number, the gate number, the time period, and the aircraft type of the flight to be predicted after arrival.

[0102] The second location information includes one or more of the following: the gate number where the flight to be predicted was located before departure, the runway number of the departure flight, the time period, and the aircraft type.

[0103] Thirdly, embodiments of this application provide a computing device, which includes a processor and a memory; the memory stores a computer program; when the processor executes the computer program, the computing device performs the method described in the first aspect above.

[0104] It should be noted that the processor included in the computing device described in the third aspect above can be a processor specifically designed to execute these methods (referred to as a dedicated processor for distinction), or a processor that executes these methods by calling a computer program, such as a general-purpose processor. Optionally, at least one processor may include both dedicated and general-purpose processors.

[0105] Optionally, the computer program described above can be stored in memory. For example, the memory can be a non-transitory memory, such as read-only memory (ROM), which can be integrated with the processor on the same device or disposed on different devices. This application does not limit the type of memory or the arrangement of the memory and the processor.

[0106] In one possible implementation, the at least one memory is located outside the computing device.

[0107] In yet another possible implementation, the at least one memory is located within the computing device.

[0108] In another possible implementation, a portion of the memory of the at least one memory is located within the computing device, while another portion of the memory is located outside the computing device.

[0109] In this application, the processor and memory may also be integrated into a single device, that is, the processor and memory can be integrated together.

[0110] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on at least one processor, implement the method described in the first aspect above.

[0111] Fifthly, this application provides a computer program product comprising computer instructions that, when executed on at least one processor, implement the method described in any of the first aspects. The computer program product can be a software installation package, which can be downloaded and executed on a computing device when the aforementioned method is required.

[0112] The beneficial effects of the technical methods provided in the second to fifth aspects of this application can be referred to the beneficial effects of the technical solution in the first aspect, and will not be repeated here. Attached Figure Description

[0113] The accompanying drawings used in the embodiments of this application are described below.

[0114] Figure 1A This is a schematic diagram of a flight time prediction system architecture provided in an embodiment of this application;

[0115] Figure 1B This is a schematic diagram of another flight time prediction system architecture provided in an embodiment of this application;

[0116] Figure 2 This is a schematic diagram of the prediction method for flight arrival time and / or departure time provided in the embodiments of this application;

[0117] Figure 3 This is a schematic diagram illustrating a method for predicting the landing time of an inbound flight, provided in an embodiment of this application.

[0118] Figure 4 This is a schematic diagram of a flight taxiing path prediction scenario provided in an embodiment of this application;

[0119] Figure 5 This is a schematic diagram illustrating a scenario for predicting the arrival time of an inbound flight, provided in an embodiment of this application.

[0120] Figure 6 This is a schematic diagram illustrating a scenario for predicting the pushback time of departing flights, provided in an embodiment of this application.

[0121] Figure 7 This is a schematic diagram of a launch time prediction process provided in an embodiment of this application;

[0122] Figure 8 This is a schematic diagram of the structure of a prediction device provided in an embodiment of this application;

[0123] Figure 9 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0124] The embodiments of this application are described below with reference to the accompanying drawings.

[0125] For ease of understanding, the following examples illustrate some probabilities relevant to embodiments of this application for reference. As follows:

[0126] 1. Aircraft

[0127] An aircraft is a flying machine capable of controlled flight within the atmosphere. It is a broad category of aircraft, referring to any machine that gains aerodynamic lift and flight through the relative motion of its fuselage and the air. This includes airplanes, helicopters, and so on.

[0128] 2. Flights

[0129] A flight is any scheduled public transport of passengers, mail, or cargo by aircraft. It is generally composed of a two-letter airline code followed by four digits, and airline codes are stipulated and published by the Civil Aviation Administration of China. Typically, a flight refers to a transport flight where an aircraft departs from its originating station along a prescribed route, making stopovers to its final destination, or directly to its final destination without stopovers. Flights operating on international routes are called international flights, and flights operating on domestic routes are called domestic flights. For example, CA1202, which flew from Beijing to Shanghai on May 25, 2007, is an example of a flight.

[0130] 3. Inbound flights, outbound flights

[0131] "Port" refers to the local airport. Arrival flights are aircraft that land and enter the airport, while departure flights are aircraft that take off and leave the airport.

[0132] 4. Gliding time

[0133] For departing flights, taxiing time refers to the time required from the time the aircraft receives the pushback instruction from the apron control and the wheel chocks are removed until the actual takeoff.

[0134] For inbound flights, taxiing time refers to the time required for a flight to taxi on the taxiway and come to a stop at its parking position after landing.

[0135] To better understand the method and related apparatus for predicting flight arrival and / or departure times provided in this application, the system architecture used in this application embodiment is described below.

[0136] Please see Figure 1A , Figure 1A This is a schematic diagram of a flight time prediction system architecture provided in an embodiment of this application. Figure 1A As shown, the system architecture includes at least one user device 101 and at least one server 102.

[0137] User equipment 101 is an electronic device with data processing and data transmission / reception capabilities. For example, it can be a standalone device, including a handheld terminal, wearable device, or robot, or a component (such as a chip or integrated circuit) included within a standalone device. For instance, when the terminal device is a handheld terminal, it can be a mobile phone, tablet computer, or computer (such as a laptop computer or PDA).

[0138] User equipment 101 is a device with data processing and data transmission / reception capabilities. It should be understood that, for convenience, it is referred to as a server here, and its specific form can be a physical device such as a server or host, or a virtual device such as a virtual machine or container. Optionally, user equipment 101 can be deployed independently in a single device, or it can be distributed across multiple devices.

[0139] User equipment 101 can deploy various systems to provide multiple data sources, such as airport information for the flight to be predicted. This airport information refers to the airport at which the flight to be predicted arrives and / or departs. When user equipment 101 (or the user using user equipment 101) needs to know the taxiing time of the flight to be predicted, user equipment 101 can send the airport information of the flight to be predicted to server 102, which will then calculate and determine the taxiing time.

[0140] Therefore, server 102 can receive airport information for the flight to be predicted and determine the taxiing time based on this information. It is understandable that airports handle many arriving and departing flights daily, and accurately predicting the arrival time of arriving flights or the departure time of departing flights can improve airport operational efficiency. Therefore, if the flight to be predicted is an arriving flight, server 102 can determine its arrival time based on its taxiing time. If the flight to be predicted is a departing flight, server 102 can determine its departure time based on its taxiing time. Thus, server 102 can adjust the schedule of other flights within the airport based on the arrival time of the arriving flight to reduce taxiing conflicts and improve airport operational efficiency. And / or, server 102 can shorten the taxiing time of departing flights based on their departure time, thereby improving taxiing efficiency.

[0141] It should be understood that the communication link between the user equipment 101 and the server 102 can be a wired link, a wireless link, or a combination of wired and wireless links. Further, alternatively, communication can also be achieved through one or more network technologies. This application does not limit the communication method between the user equipment 101 and the server 102.

[0142] In one possible implementation, please refer to Figure 1B , Figure 1B This is a schematic diagram of another flight time prediction system architecture provided in an embodiment of this application. From Figure 1BAs can be seen, user equipment 101 can include the following systems: airside operations management system 1011, integration system 1012, ground service system 1013, multipoint positioning system 1014, en-route surveillance system 1015, and progress record system 1016. Each system can provide different data sources. For example, airside operations management system 1011 can provide airport airworthiness information (such as arrival airport information, departure airport information, etc.), integration system 1012 can provide dynamic information on flights / gates, multipoint positioning system 1014 can provide flight position information (such as longitude, latitude, altitude, speed, direction, etc.), en-route surveillance system 1015 can provide flight en-route information, and progress record system 1016 can provide flight status information, etc. Among them, arrival airport information can include the airport surface information when the flight arrives; departure flight information can include taxiing data of the airport from which the flight departs.

[0143] For example, the airport's surface information includes one or more of the following: first taxiway, information on arriving flights that have landed but not yet entered their positions, information on departing flights waiting at the runway head, information on flights waiting to cross, information on departing flights taxiing on the taxiway, information on flights that have already been pushed back, and information on flights expected to be pushed back.

[0144] For example, taxiing data may include one or more of the following: second taxiing path, gate number, runway number, aircraft type, airline, and time period in which the flight to be predicted is located.

[0145] When a forecast is needed, user equipment 101 can send information collected from each system (such as airport information of the flight to be predicted) to server 102 in real time. The airport information of the flight to be predicted may include airport surface information and taxiing data. Optionally, user equipment 101 can send the collected taxiing data to message queue 1022 in server 102 in real time, and user equipment 101 can send the collected airport surface information to database 1021 in server in real time. After receiving the airport information of the flight to be predicted, server 102 can determine the taxiing time of the flight to be predicted. Optionally, if the airport information is arrival airport information, server 102 can determine the arrival taxiing time of the flight to be predicted based on the arrival airport information (such as surface information of the airport the flight to be predicted will enter), and then determine the arrival time of the flight to be predicted based on the arrival taxiing time. If the airport information is for a departing airport, the server can determine the departure taxiing time of the flight to be predicted based on the departure airport information (such as taxiing data of the airport from which the flight will depart), and then determine the pushback time of the flight to be predicted based on the departure taxiing time. Therefore, server 102 can provide predictions of arrival and / or pushback times for one or more of the airside operation management system 1011, integrated system 1012, and ground service system 1013 of user equipment 101.

[0146] For example, user equipment 101 can send historical data from each system to server 102. Therefore, server 102 can train models based on different historical data from the airport to obtain multiple prediction models. For instance, server 102 can train a first prediction model based on historical airport information, which is used to predict the arrival taxiing time of flights based on real-time data. Alternatively, server 102 can train a second prediction model based on historical departure taxiing data from the airport, which is used to predict the departure taxiing time of flights based on real-time data. Or, server 102 can train a third prediction model based on the location information of historical arriving flights from the airport, which is used to predict the landing time of arriving flights based on real-time data. Alternatively, the server can train a fourth prediction model based on historical taxiing data of flights at the airport, which is used to predict the taxiing path of flights based on real-time data, such as a first taxiing path and a second taxiing path, where the first taxiing path is the taxiing path of arriving flights and the second taxiing path is the taxiing path of departing flights.

[0147] In one possible implementation scenario, if the flight to be predicted is an inbound flight, server 102 can determine the arrival time of the flight based on its landing time and taxiing time. Optionally, server 102 can determine the arrival time of the flight based on the landing time, taxiing time, and a first taxiing path. The first taxiing path (i.e., the taxiing path when the flight is an inbound flight) can be used to predict intersection conflict points, which can then be used to determine the arrival time of the inbound flight.

[0148] In one possible implementation scenario, if the flight to be predicted is a departing flight, server 102 can determine the runway availability time based on the landing times of one or more arriving flights at the airport where the flight to be predicted is located and information on other flights at the airport where the flight to be predicted is located. Then, it can determine the pushback time of the flight to be predicted based on the availability time and the taxiing time of the flight to be predicted. Optionally, server 102 can determine the runway availability time based on the landing times of one or more arriving flights at the airport where the flight to be predicted is located, information on other flights at the airport where the flight to be predicted is located, and a second taxiway path. The second taxiway path (i.e., the taxiway path when the flight to be predicted is a departing flight) can be used to predict runway conflict points, and these conflict points can be used to determine the pushback time of departing flights.

[0149] In one possible design, such as Figure 1A or Figure 1B The server 102 shown can be a cloud platform. This platform includes a cloud service provider that abstracts flight arrival and / or departure times for users. For example, after a user purchases a flight arrival and / or departure time service, the cloud platform, in response to the user's action, creates a predictive model on the resources provided by the cloud service provider, determines the arrival and / or departure times based on the predictive model, and then provides the arrival and / or departure times to the user. Correspondingly, the user's device can present an interface to use the flight arrival and / or departure time service.

[0150] It should be noted that, in the embodiments of this application, the cloud platform can be a central cloud platform, an edge cloud platform, or a cloud platform including both a central cloud and an edge cloud platform; this embodiment of the application does not specifically limit it. Furthermore, when the cloud platform includes both a central cloud and an edge cloud platform, the flight schedule prediction system can be partially deployed in the edge cloud platform and partially deployed in the central cloud platform.

[0151] The methods of the embodiments of this application will be described in detail below.

[0152] Please see Figure 2 , Figure 2This is a schematic flowchart illustrating the method for predicting flight arrival and / or departure times provided in an embodiment of this application. Optionally, this method can be applied to... Figure 1A or Figure 1B The flight schedule prediction system shown.

[0153] like Figure 2 The method shown includes at least steps S201 to S204.

[0154] Step S201: The server receives the airport information for the flight to be predicted.

[0155] The server receives airport information for the flight to be predicted from the user device. Accordingly, when a user device (the user using user device 101) has a prediction requirement, the user device can send the airport information for the flight to be predicted to the server. This airport information can be the airport where the flight is about to enter and / or exit. For example, if the airport the flight is about to enter is Shenzhen Airport, then the airport is Shenzhen Airport, and the airport information is the current information for Shenzhen Airport; if the airport the flight is exiting is Shanghai Airport, then the airport is Shanghai Airport, and the airport information is the current information for Shanghai Airport.

[0156] Understandably, if inbound and outbound flights depart from different airports, their airport information will be different. Even if they depart from the same airport, because inbound and outbound flights are separate events, the airport environments they encounter may differ, thus affecting them differently. Therefore, for inbound flights, the airport information is the information from the arriving airport; for outbound flights, the airport information is the information from the departing airport.

[0157] For example, the aforementioned arrival airport information includes surface information of the airport to which the predicted flight will arrive. This surface information includes one or more of the following: a first taxiway, information on arriving flights that have landed but not yet entered their parking positions, information on departing flights waiting at the runway threshold, information on flights waiting to cross, information on departing flights taxiing on the taxiway, information on flights that have already been pushed back, and information on flights expected to be pushed back. Here, "entering a parking position" refers to the predicted flight taxiing into its parking position; "waiting at the runway threshold" means that there are currently departing or arriving flights on the runway, thus requiring a wait; and "waiting to cross" refers to crossing the runway.

[0158] For example, the aforementioned departure airport information includes taxiing data of the airport from which the flight to be predicted will depart. The taxiing data includes one or more of the following: second taxiing path, gate number, runway number, aircraft type, airline, and the time period in which the flight to be predicted is located.

[0159] Understandably, an airport's functional areas include runways, taxiways, and parking stands, among others. A runway is generally a long, narrow area in an airport used for aircraft (such as airplanes) to take off or land. A taxiway is a passageway within the airport for aircraft (such as airplanes) to taxi. Its main function is to provide a route from the runway to the terminal area, allowing landed aircraft to quickly leave the runway without interfering with aircraft on the takeoff runway, and minimizing delays to arriving aircraft.

[0160] In step S202, the server determines the taxiing time of the flight to be predicted based on the airport information of the flight to be predicted.

[0161] Specifically, the taxiing of a flight to be predicted may be affected by a variety of factors on the airport surface. Therefore, the server needs to combine information on the airport surface where the flight to be predicted is located when it enters and / or pushes out to determine the taxiing time of the flight to be predicted.

[0162] For example, airport information includes arrival airport information and / or departure airport information.

[0163] In one possible scenario, when the flight to be predicted is an inbound flight, the server can determine the arrival taxiing time of the flight based on the arrival airport information. Further, the server can input the arrival airport information into a first prediction model, and the output of the first prediction model is the arrival taxiing time of the flight to be predicted. Therefore, the server can obtain the arrival taxiing time of the flight to be predicted. It is understood that the first prediction model is trained based on historical airport situation information. For example, when training the first prediction model, historical airport situation information, including information on inbound flights that have landed but not yet entered their designated positions, information on outbound flights waiting at the runway threshold, information on outbound flights waiting to cross, information on outbound flights taxiing on the taxiway, information on outbound flights that have already launched, information on outbound flights expected to launch, and the historical position of flights, can be input into the machine learning model. This model is then trained and validated using machine learning algorithms, such as extreme gradient boosting (XGBoost), ultimately yielding a first prediction model that meets validation criteria. Therefore, by inputting the airport surface information of the flight to be predicted at the time of arrival into the first prediction model and using the XGBoost algorithm, the arrival taxiing time of the flight to be predicted can be obtained.

[0164] In another possible scenario, when the flight to be predicted is an departing flight, the server can determine the departure taxiing time of the flight based on the departure airport information. Further, the server can input the departure airport information into a second prediction model, and the output of the second prediction model is the departure taxiing time of the flight to be predicted. Therefore, the server can obtain the departure taxiing time of the flight to be predicted. It is understood that the second prediction model is trained based on the airport's historical departure taxiing data. For example, the departure taxiing time can be a relatively smooth taxiing time, that is, the time taken to take off from the runway tip of the taxiway assuming that there are basically no other flights obstructing the airport surface. Therefore, when training the second prediction model, historical departure taxiing data of the airport, including factors such as gate number, runway number, aircraft type, airline, and different times of day, after removing data with obstructed taxiing on the surface, can be input into a machine learning model. This data can then be trained and validated using machine learning algorithms, such as K-means clustering, to finally obtain a second prediction model that meets the validation criteria. Therefore, by inputting the airport taxiing data of the flight to be predicted at the time of departure into the second prediction model and using the K-means algorithm, the departure taxiing time of the flight to be predicted can be obtained.

[0165] Step S203: If the flight to be predicted is an inbound flight, then the arrival time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted.

[0166] When the flight to be predicted is an inbound flight, the taxiing time of the flight to be predicted is the inbound taxiing time.

[0167] In one possible scenario, the flight to be predicted may encounter potential conflicts during its taxiing process upon arrival, i.e., it may encounter other flights taxiing at the same time. Therefore, during the taxiing process, it is necessary to predict the flight's taxiing path to identify potential conflicts in advance and prepare for avoidance. Specifically, the server can obtain the first location information of the flight's arrival taxiing at the airport, input this information into a fourth prediction model, and the output of the fourth prediction model is the first taxiing path of the flight to be predicted. It is understood that the fourth prediction model for predicting taxiing paths is trained based on historical taxiing data from the airport. For example, when training the fourth prediction model, factors such as runway number, gate number, corresponding time of day, aircraft type, and arrival / departure identification can be extracted from historical taxiing data, and then trained and validated using a classification algorithm to finally obtain the fourth prediction model. Therefore, when the first position information of the flight to be predicted during its taxiing at the airport is input into the fourth prediction model, information such as the runway number, gate number, time period, and aircraft type of the flight to be predicted is extracted from the first position information. After classifying the above information and performing probability statistics, multiple taxiing paths can be obtained. The taxiing path with the highest probability among the multiple taxiing paths is determined as the first taxiing path.

[0168] Therefore, when the flight to be predicted is an inbound flight, after the server obtains the arrival taxiing time and the first taxiing path of the flight, if the flight has already landed, it can obtain the current time of the flight and determine the arrival time of the flight based on the taxiing time, the current time, and the first taxiing path. That is, arrival time = current time + taxiing time + avoidance time caused by the first taxiing path. It is understandable that if the server can determine from the first taxiing path that it may cause a collision, i.e., the first taxiing path may overlap with the taxiing paths of other flights, the flight to be predicted may need to avoid collisions during its arrival taxiing. Therefore, the server can estimate the avoidance time caused by the collision of the first taxiing path. If the server determines from the first taxiing path that it will not cause a collision, there will be no avoidance time, and therefore the avoidance time is zero.

[0169] In another possible scenario, if the flight to be predicted has not yet landed, its landing time needs to be predicted in order to accurately predict its arrival time. For example, please refer to... Figure 3 , Figure 3 This is a schematic diagram illustrating a method for predicting the landing time of an arriving flight, as provided in an embodiment of this application. Figure 3 As shown, with the airport where the predicted flight will land as the center, every k kilometers forms a ring (e.g., in the middle). Figure 3The flight volume (within five rings) and the location information of arriving flights (including one or more factors such as longitude, latitude, altitude, flight direction, and aircraft type) are input into a third prediction model. A machine learning algorithm (such as a decision tree algorithm) is then used to predict the arrival time of the arriving flights. It should be noted that an air traffic flow distribution factor is introduced during the training of the third prediction model. This factor includes the flight volume within a ring of k kilometers centered on the destination airport, as well as flight location information, which includes one or more factors such as longitude, latitude, altitude, flight direction, and aircraft type. A machine learning algorithm (such as a decision tree algorithm) is then used to build the model, resulting in the third prediction model. It can be understood that the flight to be predicted is an arriving flight that has not yet landed; therefore, the location information of the flight to be predicted can be obtained from the arrival time of the arriving flights output by the third prediction model.

[0170] Therefore, if the flight to be predicted is an inbound flight that has not yet landed, the server can obtain the landing time and first taxiway path of the flight to be predicted. Based on the taxiing time, landing time, and first taxiway path, the server determines the arrival time of the flight to be predicted. That is, arrival time = landing time + taxiing time + avoidance time caused by the first taxiway path. The avoidance time caused by the first taxiway path can be referred to the above description and will not be repeated here.

[0171] Step S204: If the flight to be predicted is a departing flight, the launch time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted.

[0172] When the flight to be predicted is an outbound flight, the taxiing time of the flight to be predicted is the outbound taxiing time.

[0173] In one possible scenario, the flight to be predicted may encounter potential conflicts during its departure taxiing, i.e., encountering other flights taxiing on the way. Therefore, during departure taxiing, it's necessary to predict the flight's taxiing path to identify potential conflicts in advance and prepare for avoidance. Specifically, the server can obtain the second location information of the departing flight within the airport, input this information into a fourth prediction model, and the output of the fourth prediction model is the second taxiing path of the flight to be predicted. It's understood that the fourth prediction model for predicting taxiing paths is trained based on historical taxiing data from the airport. For example, when training the fourth prediction model, factors such as runway number, gate number, corresponding time of day, aircraft type, and arrival / departure identifiers can be extracted from historical taxiing data. These factors are then trained and validated using a classification algorithm to finally obtain the fourth prediction model. Therefore, when the second location information of the flight to be predicted as it departs from the airport is input into the fourth prediction model, information such as the runway number, gate number, time period, and aircraft type of the flight to be predicted is extracted from the second location information. After classifying the above information and performing probability statistics, multiple taxiing paths can be obtained. The taxiing path with the highest probability among the multiple taxiing paths is determined as the second taxiing path.

[0174] In another possible scenario, the pushback time of a departing flight is influenced by the status of other arriving and departing flights. Therefore, to accurately predict the pushback time, the server needs to predict the landing times of one or more arriving flights at the airport from which the departing flight will depart. Understandably, since the flight to be predicted is a departing flight, the landing times of one or more arriving flights at the airport from the landing times output by the third prediction model can be used to obtain the landing times of one or more arriving flights at the airport where the flight to be predicted is located. Furthermore, to improve the accuracy of the pushback time prediction, information about other flights at the airport also needs to be considered, including one or more of the following: the number of flights waiting to take off at the runway head, the number of flights waiting to cross, the remaining taxi time of already pushed-out flights, runway takeoff intervals, etc.

[0175] Therefore, with the goal of minimizing taxiing time, the server can determine the runway's availability time at the airport based on the landing times of one or more arriving flights at the airport where the predicted flight is located, the second taxiway path, and information on other flights at the airport. Runway availability time can be understood as the absence of factors that could affect the taxiing of the predicted flight at that moment, but it does not mean that other flights cannot be on that runway. Finally, the server can determine the pushback time of the predicted flight based on the availability time and the taxiing time of the predicted flight.

[0176] It should be noted that the implementation of this application does not limit the execution order of steps S203 and S204. That is, step S203 can be executed first and then step S204 can be executed; step S204 can be executed first and then step S203 can be executed; or step S203 and step S204 can be executed simultaneously.

[0177] When the server predicts the arrival and / or departure times of a flight using one or more prediction models, it can send the corresponding arrival and / or departure times to the user equipment. The user equipment (or the user using the user equipment) can then use the arrival and / or departure times to ensure the operation of flights at the airport, thereby improving operational efficiency.

[0178] For prediction scenario one, please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic diagram illustrating a flight taxiing path prediction scenario provided in an embodiment of this application. From Figure 4 It can be seen that due to the planar structure of runways, taxiways, and parking stands, arriving flights may conflict with other flights during their taxiing and parking maneuvers. Similarly, departing flights may conflict with other flights during their taxiing and takeoff maneuvers. If the aircraft could predict the taxiing paths of arriving flights during their parking maneuvers, or the taxiing paths of departing flights during their departure maneuvers, it would be possible to provide early warnings for flights with potential conflict risks, thus shortening their taxiing time.

[0179] For example, such as Figure 4 As shown, the server can use the real-time location information of arriving flights, such as the runway number after landing, the gate number to be used, the landing time, and the aircraft type, to classify and statistically analyze the above information using a fourth prediction model to determine the taxiing path with the highest probability. From Figure 4 It can be seen that there is a crossing conflict on the approach taxiway. That is, during the process of taxiing to the parking position according to the approach taxiway, there may be a crossing conflict with other flights waiting to cross. Therefore, the approaching flight needs to give way and wait for the crossing flight to pass before taxiing into the parking position.

[0180] For example, such as Figure 4 As shown, the server can use the real-time location information of departing flights, such as the gate number the departing flight was in before taxiing, the runway number to be taken off, the current time period, and the aircraft type, to classify and statistically analyze the above information using the fourth prediction model, and determine the departure taxiing path with the highest probability. From Figure 4It can be seen that there are overlapping and conflicting taxiing paths on the departure routes. That is, during the process of entering the runway according to the departure taxiing path, there may be a path overlap with the taxiing paths of other flights. Therefore, departing flights need to give way and wait until the flight causing the path overlap is no longer taxiing on that path before taxiing into the runway for takeoff.

[0181] For prediction scenario two, please refer to [link / reference]. Figure 5 , Figure 5 This is a schematic diagram illustrating a scenario for predicting the arrival time of an inbound flight, as provided in an embodiment of this application. It is understood that the arrival time of an inbound flight is related to its taxiing time; improving the accuracy of taxiing time prediction can improve the accuracy of the arrival time. Figure 5 It can be seen that predicting the taxiing time of inbound flights requires incorporating factors related to ground flight traffic distribution. Please refer to Table 1, which shows the importance of various factors in predicting taxiing time as analyzed by the applicant. Table 1 indicates that the top three factors are the runway, the aircraft stand, and the small area where the aircraft stand is located. The taxiing time prediction model considers the impact of all factors in Table 1 on taxiing time, but the degree of importance of each factor in the model varies.

[0182] Table 1

[0183] factor Importance score Runway 272 Craftsite 204 Small area (craftsite_area) 195 Flight volume launched in small areas (before_landin_fit_cnt) 136 Number of flights crossing the runway (wait_in_cross_fit_cnt) 91 Airlines (airline_no) 61 Recently, the large region has released flight schedules (wait_off_cnt2). 37 Total number of flights arriving in Hong Kong on that day (fit_cnt) 28 Total number of departing flights on that day (fit_cnt_off) 26 Large region (area_ex) 26 The latest data on total departing flights (wait_off_fit_cnt) has been released. 19 Aircraft category 17 Number of flights that have recently landed in the large region (wait_in_fit_cnt) 6

[0184] Therefore, factors affecting flight traffic distribution can include arriving flights that have landed but not yet entered their designated positions, departing flights waiting at the runway threshold, flights waiting to cross, flights taxiing on the taxiway, flights that have already pushed back, and flights expected to push back. Machine learning algorithms (such as the XGboost algorithm) are then used to predict the taxiing time of arriving flights. For arriving flights that have not yet landed, the landing time is predicted based on a landing time prediction model, combined with the arriving flight's location information such as longitude, latitude, direction, and speed. Therefore, the arrival time of an arriving flight = landing time + taxiing time. For arriving flights that have already landed, the arrival time of an arriving flight = current time + taxiing time. From... Figure 4 It can be understood that if there is a crossing conflict on the taxiway to the port, it may cause a time for avoidance. Therefore, the arrival time of arriving flights also needs to take into account the time for avoidance caused by crossing conflicts.

[0185] For prediction scenario three, please refer to [link / reference]. Figure 6 , Figure 6 This is a schematic diagram illustrating a scenario for predicting the departure time of a departing flight, as provided in an embodiment of this application. From... Figure 6It can be seen that by introducing ground flight traffic distribution factors, combining flight location information, and using big data and artificial intelligence technologies, the optimal departure time can be predicted. This avoids flights pushing back from their gates too early and waiting for takeoff for extended periods on the ground, thereby shortening taxiing time and improving taxiing efficiency. Figure 6 As shown, the prediction of the optimal pushback time for departing flights considers the impact of various inbound and outbound flights in different regions on the pushback time prediction. It is understandable that the factors in Table 1 affect the prediction of departure taxiing time, but the degree of influence of each factor varies. Therefore, the prediction of pushback time can mainly consider one or more of the following factors: arriving flights about to land, departing flights waiting at the runway threshold, arriving flights waiting to cross the runway, departing flights taxiing, the smooth taxiing time of departing flights, runway takeoff / landing intervals, etc., and combined with the location information of other arriving flights such as longitude, latitude, direction, and speed, the K-means algorithm is used to model the taxiing time of departing flights, thereby obtaining the predicted pushback time.

[0186] For example, please see Figure 7 , Figure 7 This is a schematic diagram illustrating a process for predicting the launch time provided in an embodiment of this application. From Figure 7 It can be seen that predicting the optimal pushback time requires considering both the impact of various factors on the prediction of the pushback time of departing flights and historical taxiing data, and making predictions through data modeling.

[0187] Runway idle time, calculated by combining the takeoff and landing data of arriving and departing flights on the same runway, predicts the time gap when no flights are taking off or landing. The predicted runway idle time Tr is determined by factors such as the landing times of other arriving flights, the number of flights waiting to take off at the runway threshold, the number of flights waiting to cross, the remaining taxiing time of currently taxiing flights, and the runway takeoff / takeoff interval. The taxiing time of departing flights includes the remaining taxiing time from the gate to the runway threshold or after taxiing out of the gate. A taxiing time model can be trained using historical departing taxiing data. By inputting the current taxiing data of departing flights into the taxiing time model, the current taxiing time Tln of arriving flights can be predicted. Therefore, the pushback time can be determined using runway idle time Tr and taxiing time Tln. For example, if the current time now() = 10:00 and the taxiing time Tln = 5 minutes, then Tln + now() = 10:05. In this case, as long as the runway is available at or before Tr = 10:05, departing flights with proper support can push back at 10:00 for takeoff. If the runway is only available at Tr = 10:10, then to save taxiing time, departing flights, with proper support, will push back at or after 10:05.

[0188] The methods of the embodiments of this application have been described in detail above, and the apparatus of the embodiments of this application is provided below.

[0189] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a prediction device 80 provided in an embodiment of this application. The prediction device 80 can be a server or a component within the server, such as a chip, software model, or integrated circuit. The prediction device 80 is used to implement the aforementioned method for predicting flight arrival and / or departure times, for example... Figure 2 The method in the illustrated embodiment.

[0190] In one possible implementation, the prediction device 80 may include a communication unit 801 and a processing unit 802.

[0191] In one possible implementation, the communication unit 801 is configured to receive airport information of the flight to be predicted, wherein the airport information is the information of the airport where the flight to be predicted is located when it enters and / or exits.

[0192] Processing unit 802 is used to determine the taxiing time of the flight to be predicted based on the airport information of the flight to be predicted;

[0193] The processing unit 802 is further configured to, if the flight to be predicted is an inbound flight, determine the arrival time of the flight to be predicted based on the taxiing time of the flight to be predicted; and / or,

[0194] If the flight to be predicted is an outbound flight, the launch time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted.

[0195] In yet another possible implementation, the processing unit 802 is specifically used for:

[0196] Based on the arrival airport information of the flight to be predicted, determine the arrival taxiing time of the flight to be predicted; and / or,

[0197] Based on the departure airport information of the flight to be predicted, the departure taxiing time of the flight to be predicted is determined.

[0198] In another possible implementation, the processing unit 802 is specifically used to: input the arrival airport information into a first prediction model to obtain the arrival taxiing time of the flight to be predicted; wherein, the first prediction model is trained based on the historical scene information of the airport.

[0199] In another possible implementation, the arrival airport information includes surface information of the airport to which the predicted flight will arrive, and the airport surface information includes one or more of the following: arrival flight information that has landed but not yet entered its designated position, departure flight information waiting at the runway head, flight information waiting to cross, departure flight information taxiing on the taxiway, flight information that has already been pushed back, and flight information that is expected to be pushed back.

[0200] In yet another possible implementation, the processing unit 802 is specifically used for:

[0201] If the flight to be predicted has already landed, then obtain the current time of the flight to be predicted;

[0202] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0203] The entry time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted, the current time, and the first taxiing path.

[0204] In yet another possible implementation, the processing unit 802 is specifically used for:

[0205] The departure airport information is input into the second prediction model to obtain the departure taxiing time of the flight to be predicted; the second prediction model is trained based on the historical departure taxiing data of the airport.

[0206] In another possible implementation, the departure airport information includes taxiing data of the airport from which the flight to be predicted will depart, and the taxiing data includes one or more of the following: gate number, runway number, aircraft type, airline, and the time period in which the flight to be predicted is located.

[0207] In yet another possible implementation, the processing unit 802 is further configured to:

[0208] The communication unit 801 obtains the location information of the inbound flights at the airport where the flight to be predicted is located;

[0209] The arrival flight location information is input into the third prediction model to obtain the arrival flight landing time; wherein, the third prediction model is trained based on the historical arrival flight location information of the airport.

[0210] In another possible implementation, the inbound flight location information includes one or more of the following: longitude, latitude, speed, altitude, flight direction, and aircraft type.

[0211] In another possible implementation, if the flight to be predicted is an inbound flight, then the inbound flight location information is the location information of the flight to be predicted, and the inbound flight landing time is the landing time of the flight to be predicted.

[0212] If the flight to be predicted is an outbound flight, then the inbound flight location information includes the location information of one or more inbound flights in the airport where the flight to be predicted is located, and the inbound flight landing time includes the landing time of one or more inbound flights in the airport where the flight to be predicted is located.

[0213] In yet another possible implementation, the processing unit 802 is specifically used for:

[0214] If the flight to be predicted is an inbound flight, obtain the arrival time of the flight to be predicted;

[0215] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0216] The landing time of the flight to be predicted is determined based on the landing time of the flight to be predicted, the first taxiing path, and the taxiing time of the flight to be predicted.

[0217] In yet another possible implementation, the processing unit 802 is specifically used for:

[0218] The first location information of the flight to be predicted at the airport is obtained through the communication unit 801.

[0219] The first location information is input into the fourth prediction model to obtain the first taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the historical taxiing data of the airport.

[0220] In yet another possible implementation, the processing unit 802 is specifically used for:

[0221] If the flight to be predicted is an outbound flight, then obtain the landing time of one or more inbound flights in the airport where the flight to be predicted is located, and information on other flights in the airport where the flight to be predicted is located.

[0222] Determine a second taxiing path for the flight to be predicted, wherein the second taxiing path is the path the flight to be predicted will take on the airport;

[0223] The runway availability of the airport is determined based on the landing time of one or more inbound flights at the airport where the flight to be predicted is located, the second taxiway, and information on other flights at the airport where the flight to be predicted is located.

[0224] The launch time of the flight to be predicted is determined based on the idle time and the taxiing time of the flight to be predicted.

[0225] In yet another possible implementation, the processing unit 802 is specifically used for:

[0226] The second location information of the flight to be predicted at the airport is obtained through the communication unit 801.

[0227] The second location information is input into the fourth prediction model to obtain the second taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

[0228] In another possible implementation, the information on other flights in the airport where the flight to be predicted is located includes one or more of the following: the number of flights waiting to take off at the runway head, the number of flights waiting to cross, the remaining taxi time of flights that have already been pushed back, and the runway takeoff interval.

[0229] In another possible implementation, the first location information includes one or more of the following: the runway number, the gate number, the time period, and the aircraft type of the flight to be predicted after arrival.

[0230] The second location information includes one or more of the following: the gate number where the flight to be predicted was located before departure, the runway number of the departure flight, the time period, and the aircraft type.

[0231] It should be understood that related descriptions can also be found in [the relevant documentation / reference]. Figure 2 The descriptions in the illustrated embodiments will not be repeated here.

[0232] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of a computing device 90 provided in an embodiment of this application. The computing device 90 can be an independent device (such as one or more servers, etc.) or a component inside an independent device (such as a chip, software module, or hardware module, etc.). The computing device 90 may include at least one processor 901. Optionally, it may also include at least one memory 903. Further optionally, the computing device 90 may also include a communication interface 902. Even more optionally, it may also include a bus 904, wherein the processor 901, the communication interface 902, and the memory 903 are connected through the bus 904.

[0233] The processor 901 is a module that performs arithmetic and / or logical operations. Specifically, it can be one or a combination of processing modules such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor unit (MPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a complex programmable logic device (CPLD), a coprocessor (to assist the central processing unit in completing corresponding processing and applications), and a microcontroller unit (MCU).

[0234] The communication interface 902 can be used to provide information input or output to the at least one processor. And / or, the communication interface 902 can be used to receive data transmitted externally and / or transmit data externally, and can be a wired link interface including an Ethernet cable, or a wireless link interface (Wi-Fi, Bluetooth, general wireless transmission, vehicular short-range communication technology, and other short-range wireless communication technologies, etc.). Optionally, the communication interface 902 may also include a transmitter (such as a radio frequency transmitter, antenna, etc.) or a receiver coupled to the interface.

[0235] The memory 903 provides storage space, in which data such as the operating system and computer programs can be stored. The memory 903 can be one or a combination of several of the following: random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0236] At least one processor 901 in the computing device 90 is used to execute the aforementioned method for predicting flight arrival and / or departure times, for example... Figure 2 The embodiment shown describes a method for predicting flight arrival and / or departure times.

[0237] Optionally, processor 901 can be a processor specifically designed to execute these methods (for clarity, referred to as a dedicated processor), or a processor that executes these methods by invoking a computer program, such as a general-purpose processor. Optionally, at least one processor may include both dedicated and general-purpose processors. Optionally, when the computing device includes at least one processor 901, the aforementioned computer program may be stored in memory 903.

[0238] In one possible implementation, at least one processor 901 in the computing device 90 is configured to execute computer-invoking instructions to perform the following operations:

[0239] The airport information of the flight to be predicted is received through the communication interface 902. The airport information is the information of the airport where the flight to be predicted is located when it enters and / or exits.

[0240] Based on the airport information of the flight to be predicted, determine the taxiing time of the flight to be predicted;

[0241] If the flight to be predicted is an inbound flight, then the arrival time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted; and / or,

[0242] If the flight to be predicted is an outbound flight, the launch time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted.

[0243] In yet another possible implementation, the processor 901 is specifically used for:

[0244] Based on the arrival airport information of the flight to be predicted, determine the arrival taxiing time of the flight to be predicted; and / or,

[0245] Based on the departure airport information of the flight to be predicted, the departure taxiing time of the flight to be predicted is determined.

[0246] In another possible implementation, the processor 901 is specifically used to: input the arrival airport information into a first prediction model to obtain the arrival taxiing time of the flight to be predicted; wherein the first prediction model is trained based on the historical scene information of the airport.

[0247] In another possible implementation, the arrival airport information includes surface information of the airport to which the predicted flight will arrive, and the airport surface information includes one or more of the following: arrival flight information that has landed but not yet entered its designated position, departure flight information waiting at the runway head, flight information waiting to cross, departure flight information taxiing on the taxiway, flight information that has already been pushed back, and flight information that is expected to be pushed back.

[0248] In yet another possible implementation, the processor 901 is specifically used for:

[0249] If the flight to be predicted has already landed, then obtain the current time of the flight to be predicted;

[0250] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0251] The entry time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted, the current time, and the first taxiing path.

[0252] In yet another possible implementation, the processor 901 is specifically used for:

[0253] The departure airport information is input into the second prediction model to obtain the departure taxiing time of the flight to be predicted; the second prediction model is trained based on the historical departure taxiing data of the airport.

[0254] In another possible implementation, the departure airport information includes taxiing data of the airport from which the flight to be predicted will depart, and the taxiing data includes one or more of the following: gate number, runway number, aircraft type, airline, and the time period in which the flight to be predicted is located.

[0255] In yet another possible implementation, the processor 901 is further configured to:

[0256] The location information of inbound flights at the airport where the flight to be predicted is located is obtained through the communication interface 902;

[0257] The arrival flight location information is input into the third prediction model to obtain the arrival flight landing time; wherein, the third prediction model is trained based on the historical arrival flight location information of the airport.

[0258] In another possible implementation, the inbound flight location information includes one or more of the following: longitude, latitude, speed, altitude, flight direction, and aircraft type.

[0259] In another possible implementation, if the flight to be predicted is an inbound flight, then the inbound flight location information is the location information of the flight to be predicted, and the inbound flight landing time is the landing time of the flight to be predicted.

[0260] If the flight to be predicted is an outbound flight, then the inbound flight location information includes the location information of one or more inbound flights in the airport where the flight to be predicted is located, and the inbound flight landing time includes the landing time of one or more inbound flights in the airport where the flight to be predicted is located.

[0261] In yet another possible implementation, the processor 901 is specifically used for:

[0262] If the flight to be predicted is an inbound flight, obtain the arrival time of the flight to be predicted;

[0263] Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport;

[0264] The landing time of the flight to be predicted is determined based on the landing time of the flight to be predicted, the first taxiing path, and the taxiing time of the flight to be predicted.

[0265] In yet another possible implementation, the processor 901 is specifically used for:

[0266] The first location information of the flight to be predicted at the airport is obtained through the communication interface 902.

[0267] The first location information is input into the fourth prediction model to obtain the first taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the historical taxiing data of the airport.

[0268] In yet another possible implementation, the processor 901 is specifically used for:

[0269] If the flight to be predicted is an outbound flight, then obtain the landing time of one or more inbound flights in the airport where the flight to be predicted is located, and information on other flights in the airport where the flight to be predicted is located.

[0270] Determine a second taxiing path for the flight to be predicted, wherein the second taxiing path is the path the flight to be predicted will take on the airport;

[0271] The runway availability of the airport is determined based on the landing time of one or more inbound flights at the airport where the flight to be predicted is located, the second taxiway, and information on other flights at the airport where the flight to be predicted is located.

[0272] The launch time of the flight to be predicted is determined based on the idle time and the taxiing time of the flight to be predicted.

[0273] In yet another possible implementation, the processor 901 is specifically used for:

[0274] The second location information of the flight to be predicted at the airport is obtained through the communication interface 902.

[0275] The second location information is input into the fourth prediction model to obtain the second taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

[0276] In another possible implementation, the information on other flights in the airport where the flight to be predicted is located includes one or more of the following: the number of flights waiting to take off at the runway head, the number of flights waiting to cross, the remaining taxi time of flights that have already been pushed back, and the runway takeoff interval.

[0277] In another possible implementation, the first location information includes one or more of the following: the runway number, the gate number, the time period, and the aircraft type of the flight to be predicted after arrival.

[0278] The second location information includes one or more of the following: the gate number where the flight to be predicted was located before departure, the runway number of the departure flight, the time period, and the aircraft type.

[0279] It should be understood that related descriptions can also be found in [the relevant documentation / reference]. Figure 2 The descriptions in the illustrated embodiments will not be repeated here.

[0280] This application also provides a computer-readable storage medium storing instructions that, when executed on at least one processor, implement the aforementioned method for predicting flight arrival and / or departure times, for example... Figure 2 The method for predicting flight arrival and / or departure times is shown.

[0281] This application also provides a computer program product comprising computer instructions that, when executed by a computing device, implement the aforementioned method for predicting flight arrival and / or departure times, for example... Figure 2 The method for predicting flight arrival and / or departure times is shown.

[0282] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0283] In this application, "at least one" in the embodiments refers to one or more items, and "more than one" refers to two or more items. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, (a and b), (a and c), (b and c), or (a and b and c), where a, b, and c can be single or multiple. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0284] Furthermore, unless otherwise stated, the use of ordinal numbers such as "first" and "second" in the embodiments of this application is for distinguishing multiple objects and is not for limiting the order, sequence, priority, or importance of multiple objects. For example, "first user equipment" and "second user equipment" are only for ease of description and do not indicate differences in the structure, importance, etc. of the first user equipment and the second user equipment. In some embodiments, the first user equipment and the second user equipment may also be the same device.

[0285] In the above embodiments, the term "when..." can be interpreted, depending on the context, as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". The above descriptions are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the concept and principles of this application should be included within the protection scope of this application.

[0286] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

Claims

1. A method for predicting flight arrival and / or departure times, characterized in that, include: Receive airport information for the flight to be predicted, wherein the airport information is the information of the airport where the flight to be predicted was located when it entered and / or departed; Based on the airport information of the flight to be predicted, determine the taxiing time of the flight to be predicted; Obtain the location information of inbound flights at the airport where the flight to be predicted is located; The arrival flight location information is input into the third prediction model to obtain the arrival time of the arrival flight; wherein, the third prediction model is trained based on the historical arrival flight location information of the airport; If the flight to be predicted is an inbound flight, then the arrival time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted; and / or, If the flight to be predicted is an outbound flight, the launch time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted. If the flight to be predicted is an inbound flight, then the location information of the inbound flight is the location information of the flight to be predicted, and the landing time of the inbound flight is the landing time of the flight to be predicted. If the flight to be predicted is an outbound flight, then the inbound flight location information includes the location information of one or more inbound flights in the airport where the flight to be predicted is located, and the inbound flight landing time includes the landing time of one or more inbound flights in the airport where the flight to be predicted is located. If the flight to be predicted is an inbound flight, then determining the arrival time of the flight to be predicted based on the taxiing time of the flight to be predicted includes: If the flight to be predicted is an inbound flight, obtain the arrival time of the flight to be predicted; Determine a first taxiing path for the flight to be predicted, wherein the first taxiing path is the path the flight to be predicted will take on the airport; The landing time of the flight to be predicted is determined based on the landing time of the flight to be predicted, the first taxiing path, and the taxiing time of the flight to be predicted. If the flight to be predicted is a departure flight, then determining the departure time of the flight to be predicted based on its taxiing time includes: If the flight to be predicted is an outbound flight, then obtain the landing time of one or more inbound flights in the airport where the flight to be predicted is located, and information on other flights in the airport where the flight to be predicted is located. Determine a second taxiing path for the flight to be predicted, wherein the second taxiing path is the path the flight to be predicted will take on the airport; The runway availability of the airport is determined based on the landing time of one or more inbound flights at the airport where the flight to be predicted is located, the second taxiway, and information on other flights at the airport where the flight to be predicted is located. The launch time of the flight to be predicted is determined based on the idle time and the taxiing time of the flight to be predicted.

2. The method according to claim 1, characterized in that, The airport information includes arriving airport information and / or departing airport information. Determining the taxiing time of the flight to be predicted based on the airport information includes: Based on the arrival airport information of the flight to be predicted, determine the arrival taxiing time of the flight to be predicted; and / or, Based on the departure airport information of the flight to be predicted, the departure taxiing time of the flight to be predicted is determined.

3. The method according to claim 2, characterized in that, The step of determining the arrival taxiing time of the flight to be predicted based on the arrival airport information of the flight to be predicted includes: The arrival airport information is input into the first prediction model to obtain the arrival taxiing time of the flight to be predicted; wherein, the first prediction model is trained based on the historical scene information of the airport.

4. The method according to claim 2 or 3, characterized in that, The arrival airport information includes the surface information of the airport to which the predicted flight will arrive. The airport surface information includes one or more of the following: arrival flight information that has landed but not yet entered its designated position, departure flight information waiting at the runway head, flight information waiting to cross, departure flight information taxiing on the taxiway, flight information that has already been pushed back, and flight information that is expected to be pushed back.

5. The method according to claim 2, characterized in that, The step of determining the departure taxiing time of the flight to be predicted based on the departure airport information of the flight to be predicted includes: The departure airport information is input into the second prediction model to obtain the departure taxiing time of the flight to be predicted; the second prediction model is trained based on the historical departure taxiing data of the airport.

6. The method according to claim 2 or 5, characterized in that, The departure airport information includes taxiing data of the airport from which the flight to be predicted will depart. The taxiing data includes one or more of the following: gate number, runway number, aircraft type, airline, and the time period in which the flight to be predicted is located.

7. The method according to any one of claims 1-3, characterized in that, The location information of the arriving flight includes one or more of the following: longitude, latitude, speed, altitude, flight direction, and aircraft type.

8. The method according to any one of claims 1-3, characterized in that, Determining the first taxiing path of the flight to be predicted includes: Obtain the first location information of the flight to be predicted at the airport; The first location information is input into the fourth prediction model to obtain the first taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

9. The method according to any one of claims 1-3, characterized in that, Determining the second taxiing path of the flight to be predicted includes: Obtain the second location information of the flight to be predicted at the airport; The second location information is input into the fourth prediction model to obtain the second taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

10. The method according to any one of claims 1-3, characterized in that, The information on other flights at the airport where the flight to be predicted is located includes one or more of the following: the number of flights waiting to take off at the runway head, the number of flights waiting to cross, the remaining taxi time of flights that have already been pushed back, and the runway takeoff interval.

11. The method according to claim 8, characterized in that, The first location information includes one or more of the following: the runway number, the gate number, the time period, and the aircraft type where the predicted flight will be located after arrival.

12. The method according to claim 9, characterized in that, The second location information includes one or more of the following: the gate number where the flight to be predicted was located before departure, the runway number of the departure flight, the time period, and the aircraft type.

13. A prediction device, characterized in that, include: A communication unit is used to receive airport information of the flight to be predicted, wherein the airport information is the information of the airport where the flight to be predicted is located when it enters and / or exits; The processing unit is used to determine the taxiing time of the flight to be predicted based on the airport information of the flight to be predicted. The processing unit is also used to obtain the arrival flight location information of the airport where the flight to be predicted is located through the communication unit; The processing unit is further configured to input the arrival flight location information into a third prediction model to obtain the arrival flight landing time; wherein, the third prediction model is trained based on the historical arrival flight location information of the airport. The processing unit is further configured to determine the arrival time of the flight to be predicted based on the taxiing time of the flight to be predicted if the flight to be predicted is an inbound flight; and / or, If the flight to be predicted is an outbound flight, the launch time of the flight to be predicted is determined based on the taxiing time of the flight to be predicted. If the flight to be predicted is an inbound flight, then the location information of the inbound flight is the location information of the flight to be predicted, and the landing time of the inbound flight is the landing time of the flight to be predicted. If the flight to be predicted is an outbound flight, then the inbound flight location information includes the location information of one or more inbound flights in the airport where the flight to be predicted is located, and the inbound flight landing time includes the landing time of one or more inbound flights in the airport where the flight to be predicted is located. If the flight to be predicted is an inbound flight, then determining the arrival time of the flight to be predicted based on the taxiing time of the flight to be predicted includes: If the flight to be predicted is an inbound flight, obtain the arrival time of the flight to be predicted; A first taxiing path is determined for the flight to be predicted, which is the path the flight to be predicted will take on the airport; the arrival time of the flight to be predicted is determined based on the landing time of the flight to be predicted, the first taxiing path, and the taxiing time of the flight to be predicted. If the flight to be predicted is a departure flight, then determining the departure time of the flight to be predicted based on its taxiing time includes: If the flight to be predicted is an outbound flight, then obtain the landing time of one or more inbound flights in the airport where the flight to be predicted is located, and information on other flights in the airport where the flight to be predicted is located. Determine a second taxiing path for the flight to be predicted, wherein the second taxiing path is the path the flight to be predicted will take on the airport; The runway availability of the airport is determined based on the landing time of one or more inbound flights at the airport where the flight to be predicted is located, the second taxiway, and information on other flights at the airport where the flight to be predicted is located. The launch time of the flight to be predicted is determined based on the idle time and the taxiing time of the flight to be predicted.

14. The apparatus according to claim 13, characterized in that, The processing unit is specifically used for: Based on the arrival airport information of the flight to be predicted, determine the arrival taxiing time of the flight to be predicted; and / or, Based on the departure airport information of the flight to be predicted, the departure taxiing time of the flight to be predicted is determined.

15. The apparatus according to claim 14, characterized in that, The processing unit is specifically used for: The arrival airport information is input into the first prediction model to obtain the arrival taxiing time of the flight to be predicted; wherein, the first prediction model is trained based on the historical scene information of the airport.

16. The apparatus according to claim 14 or 15, characterized in that, The arrival airport information includes the surface information of the airport to which the predicted flight will arrive. The airport surface information includes one or more of the following: arrival flight information that has landed but not yet entered its designated position, departure flight information waiting at the runway head, flight information waiting to cross, departure flight information taxiing on the taxiway, flight information that has already been pushed back, and flight information that is expected to be pushed back.

17. The apparatus according to any one of claims 13-15, characterized in that, The processing unit is specifically used for: The departure airport information is input into the second prediction model to obtain the departure taxiing time of the flight to be predicted; the second prediction model is trained based on the historical departure taxiing data of the airport.

18. The apparatus according to claim 14, characterized in that, The departure airport information includes taxiing data of the airport from which the flight to be predicted will depart. The taxiing data includes one or more of the following: gate number, runway number, aircraft type, airline, and the time period in which the flight to be predicted is located.

19. The apparatus according to any one of claims 13-15, characterized in that, The location information of the arriving flight includes one or more of the following: longitude, latitude, speed, altitude, flight direction, and aircraft type.

20. The apparatus according to any one of claims 13-15, characterized in that, The processing unit is specifically used for: The first location information of the flight to be predicted at the airport is obtained through the communication unit. The first location information is input into the fourth prediction model to obtain the first taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

21. The apparatus according to any one of claims 13-15, characterized in that, The processing unit is specifically used for: The second location information of the flight to be predicted at the airport is obtained through the communication unit. The second location information is input into the fourth prediction model to obtain the second taxiing path of the flight to be predicted; wherein the fourth prediction model is trained based on the airport's historical taxiing data.

22. The apparatus according to any one of claims 13-15, characterized in that, The information on other flights at the airport where the flight to be predicted is located includes one or more of the following: the number of flights waiting to take off at the runway head, the number of flights waiting to cross, the remaining taxi time of flights that have already been pushed back, and the runway takeoff interval.

23. The apparatus according to claim 20, characterized in that, The first location information includes one or more of the following: the runway number, the gate number, the time period, and the aircraft type where the predicted flight will be located after arrival.

24. The apparatus according to claim 21, characterized in that, The second location information includes one or more of the following: the gate number where the flight to be predicted was located before departure, the runway number of the departure flight, the time period, and the aircraft type.

25. A computing device, characterized in that, The computing device includes a processor and memory; The memory stores computer programs; When the processor executes the computer program, the computing device performs the method according to any one of claims 1 to 12.

26. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on at least one processor, implement the method as described in any one of claims 1 to 12.

27. A computer program product, characterized in that, The computer program product includes computer instructions that, when executed on at least one processor, implement the method as described in any one of claims 1 to 12.

Images