CN116263888A

CN116263888A - Method for predicting flight entering time and/or pushing time and related equipment

Info

Publication number: CN116263888A
Application number: CN202111524700.7A
Authority: CN
Inventors: 潘培根; 姚华传; 蔡良达
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2021-12-14
Filing date: 2021-12-14
Publication date: 2023-06-16

Abstract

The embodiment of the application provides a method for predicting flight arrival time and/or departure time and related equipment, wherein the method comprises the following steps: receiving airport information of flights to be predicted, wherein the airport information is information of an airport where the flights to be predicted are located when the flights to be predicted are located and/or pushed out; determining the taxi time of the flight to be predicted according to airport information of the flight to be predicted; if the flight to be predicted is the inbound flight, determining the inbound time of the flight to be predicted according to the taxi time of the flight to be predicted; and/or if the flight to be predicted is the departure flight, determining the push time of the flight to be predicted according to the taxi time of the flight to be predicted. By adopting the embodiment of the application, the scientific management and control in the flight sliding process can be promoted, the sliding time is saved, and the sliding efficiency is improved.

Description

Method for predicting flight entering time and/or pushing time and related equipment

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a method and related device for predicting a flight entry time and/or a flight push time.

Background

With the development of science and technology, air transportation is becoming one of the main transportation modes. More and more passengers choose a quick means of transportation for the aircraft during business and travel. Accordingly, the number of flights that airlines need to schedule daily is also increasing. And accurately predicts the arrival time and the departure time of the flight, so that the operation efficiency of the flight company can be improved, and the expenditure is reduced.

The existing field monitoring radar system can capture the real-time position of the aircraft in real time, but cannot combine multiple complex factors of scenes to accurately predict the sliding time in advance. Therefore, the arrival time of the flight cannot be accurately predicted and determined, the flight sliding conflict cannot be reduced, and the operation efficiency is low. While the prior art predicts the moment of push, it still comes in a traditional mode of first-come first-serve. Therefore, the optimal push-out moment cannot be determined by combining the influences of various complex factors of the scene, and the taxi efficiency of the flight is not high.

Disclosure of Invention

The embodiment of the application provides a prediction method and related equipment for flight arrival time and/or flight push-out time, which can be used for scientifically controlling the flight sliding process, saving the sliding time and improving the sliding efficiency.

In a first aspect, an embodiment of the present application provides a method for predicting a flight arrival time and/or a departure time, including:

receiving airport information of flights to be predicted, wherein the airport information is information of an airport where the flights to be predicted are located when the flights to be predicted are located and/or pushed out;

determining the taxi time of the flight to be predicted according to the airport information of the flight to be predicted;

If the flight to be predicted is the inbound flight, determining the inbound time of the flight to be predicted according to the taxi time of the flight to be predicted; and/or the number of the groups of groups,

and if the flight to be predicted is the departure flight, determining the push-out time of the flight to be predicted according to the taxi time of the flight to be predicted.

The above method may be applied to a server, and executed by the server or a component (e.g., a chip, a software module, or an integrated circuit) inside the server.

In the embodiment of the application, the taxi time of the flight to be predicted is obtained by analyzing the information of the airport where the flight to be predicted is located when the flight to be predicted is located and/or pushed out, and because the information of the airport is related to the factors faced when the flight to be predicted is located or pushed out, the taxi time determined by fully combining the situation of the current airport has higher accuracy. Therefore, the pushing-out time and/or the positioning time obtained according to the sliding time also has higher accuracy. After the prediction precision of the pushing-out time and/or the entering time is improved, the safety and the high efficiency in the flight sliding process can be improved, and the flight sliding efficiency can also be improved.

In a possible implementation manner of the first aspect, the airport information comprises incoming airport information and/or outgoing airport information. The determining the taxi time of the flight to be predicted according to the airport information of the flight to be predicted comprises the following steps:

Determining the arrival taxi time of the flight to be predicted according to the arrival airport information of the flight to be predicted; and/or the number of the groups of groups,

and determining the departure taxi time of the flight to be predicted according to the departure airport information of the flight to be predicted.

It can be seen that different situations, such as an inbound flight or an outbound flight, earned by the embodiments of the present application can be combined with the situation information of the different situations to predict the taxi time. Therefore, the accuracy of predicting the departure taxi time and/or the arrival taxi time can be improved.

In a possible implementation manner of the first aspect, the determining, according to the airport entering information of the to-be-predicted flight, an airport entering taxi time of the to-be-predicted flight includes:

inputting the airport entering information into a first prediction model to obtain the airport entering taxi time of the flight to be predicted; the first prediction model is trained according to historical scene information of the airport.

It can be seen that the embodiment of the application is to integrate big data and artificial intelligence technology, and predict the arrival taxi time through the prediction model obtained by training, so that the prediction accuracy can be improved.

In a possible implementation manner of the first aspect, the airport entering information includes airport scene information of the airport to be entered by the flight to be predicted, and the airport scene information includes one or more of the following: the method comprises the steps of entering port landing but not entering port flight information, exiting port flight information waiting for a runway head, flight information waiting to pass through, exiting port flight information sliding on a taxiway, already-deduced flight information and expected deduced flight information.

It can be seen that the embodiment of the application introduces the ground flight flow distribution factor, fully considers each factor affecting the flight taxiing, and can improve the prediction accuracy of the taxiing time.

In a possible implementation manner of the first aspect, if the flight to be predicted is an inbound flight, determining the inbound time of the flight to be predicted according to the taxi time of the flight to be predicted includes:

if the flight to be predicted is landed, acquiring the current time of the flight to be predicted;

determining a first taxi path of the flight to be predicted, wherein the first taxi path is a path of the flight to be predicted to taxi on the airport;

and determining the in-place time of the flight to be predicted according to the taxi time of the flight to be predicted, the current time and the first taxi path.

It can be seen that, in the embodiment of the present application, when determining the arrival time of the flight to be predicted, the influence of the taxi time and the taxi path is considered, so that the accuracy of predicting the arrival time can be improved.

In a possible implementation manner of the first aspect, the determining, according to the departure airport information of the flight to be predicted, a departure taxi time of the flight to be predicted includes:

Inputting the departure airport information into a second prediction model to obtain the departure taxi time of the flight to be predicted; the second prediction model is trained according to historical departure taxi data of the airport.

It can be seen that the embodiment of the application fuses big data and artificial intelligence technology, predicts the departure slide time through the prediction model obtained by training, and accordingly the prediction accuracy of the departure slide time can be improved.

In a possible implementation manner of the first aspect, the departure airport information includes taxi data of the airport to which the flight to be predicted is about to depart, the taxi data including one or more of the following: the number of the aircraft, the number of the runway, the type of the aircraft, the airline and the period of time in which the flight to be predicted is located.

In a possible implementation manner of the first aspect, after the determining, according to airport information of the flight to be predicted, a taxi time of the flight to be predicted, if the flight to be predicted is an inbound flight, determining, according to the taxi time of the flight to be predicted, a taxi-in time of the flight to be predicted is before; and/or if the flight to be predicted is an outgoing flight, determining the push time of the flight to be predicted according to the taxi time of the flight to be predicted further includes:

Acquiring the position information of the incoming flights of the airport where the flights to be predicted are located;

inputting the arrival flight position information into a third prediction model to obtain the arrival flight landing time; the third prediction model is trained according to the position information of the historical incoming flights of the airport.

It can be seen that the embodiment of the application fuses big data and artificial intelligence technology, predicts the landing time of the inbound flight through the prediction model obtained through training, and accordingly the prediction accuracy of the landing time can be improved.

In a possible implementation manner of the first aspect, the inbound flight location information includes one or more of longitude, latitude, speed, altitude, flight direction, and model of the inbound flight.

It can be seen that the embodiment of the application can extract the control scene condition data for modeling, and predict the landing time of the flight by the position information of the current flight before the flight lands, so that the prediction accuracy of the landing time can be improved.

In a possible implementation manner of the first aspect, if the flight to be predicted is an inbound flight, the inbound flight location information is location information of the flight to be predicted, and the inbound flight landing time is a landing time of the flight to be predicted;

And if the flight to be predicted is an outbound flight, the inbound flight position information comprises position information of one or more inbound flights in an airport where the flight to be predicted is located, and the inbound flight landing time comprises landing time of one or more inbound flights in the airport where the flight to be predicted is located.

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

if the flight to be predicted is the inbound flight, acquiring the landing time of the flight to be predicted;

and determining the arrival time of the flight to be predicted according to the landing time of the flight to be predicted, the first sliding path and the sliding time of the flight to be predicted.

It can be seen that, for a landing-free flight, the landing time, the taxi path and the taxi time can be combined to determine the landing time in order to improve the accuracy of prediction of the landing time.

In a possible implementation manner of the first aspect, the determining the first taxi path of the flight to be predicted includes:

acquiring first position information of the flight to be predicted at the airport;

inputting the first position information into a fourth prediction model to obtain a first taxi path of the flight to be predicted; the fourth prediction model is trained according to historical taxi data of the airport.

It can be seen that the taxi path is determined based on the position information of the flight to be predicted, and the conflict possibly encountered by the flight in the taxi process can be predicted in advance through the taxi path, so that the taxi conflict of the flight can be reduced, and the flight operation efficiency is improved.

In a possible implementation manner of the first aspect, if the flight to be predicted is a pull-out flight, determining the pull-out time of the flight to be predicted according to the taxi time of the flight to be predicted includes:

if the flight to be predicted is the departure flight, acquiring landing time of one or more departure flights in the airport where the flight to be predicted is located and information of other flights in the airport where the flight to be predicted is located;

Determining a second taxi path of the flight to be predicted, wherein the second taxi path is a path of the flight to be predicted to taxi on the airport;

determining idle time of a runway of the airport according to the landing time of one or more inbound flights in the airport where the flight to be predicted is located, the second taxi path and information of other flights in the airport where the flight to be predicted is located;

and determining the push-out time of the flight to be predicted according to the idle time and the sliding time of the flight to be predicted.

It can be seen that the embodiment of the application combines the spatial distribution condition of the incoming and outgoing flights, the taxiing time and the information of other flights, integrates big data and artificial intelligence technology, determines the forecast of the outgoing and outgoing pushing moment, and avoids the premature pushing of the flights or the waiting for take-off on the ground for a long time.

In a possible implementation manner of the first aspect, the determining the second taxi path of the flight to be predicted includes:

acquiring second position information of the flight to be predicted at the airport;

inputting the second position information into a fourth prediction model to obtain a second taxi path of the flight to be predicted; the fourth prediction model is trained according to historical taxi data of the airport.

In a possible implementation manner of the first aspect, the information of 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 for departure by the runway head, the number of flights waiting for traversal, the remaining taxi time of the flights already launched, the runway departure interval.

In a possible implementation manner of the first aspect, the first location information includes one or more of the following: the runway number, the airplane position number of the entering position, the period of the position and the airplane type of the scheduled flight after entering the port;

the second location information includes one or more of: the number of the machine at which the flight to be predicted is located before departure, the running number of the departure flight, the period of time at which the flight to be predicted is located and the model.

In a second aspect, embodiments of the present application provide a prediction apparatus, which includes a processing unit and a communication unit, where the prediction apparatus is configured to implement the method described in the first aspect or any one of the possible implementation methods of the first aspect.

In a possible implementation manner of the second aspect, the communication unit is configured to receive airport information of a flight to be predicted, where the airport information is information of an airport where the flight to be predicted is located when the flight to be predicted is located and/or pushed out;

the processing unit is used for determining the sliding time of the flight to be predicted according to the airport information of the flight to be predicted;

the processing unit is further configured to determine an arrival time of the flight to be predicted according to a taxi time of the flight to be predicted if the flight to be predicted is an inbound flight; and/or the number of the groups of groups,

In a possible implementation manner of the second aspect, the processing unit is specifically configured to:

In a possible implementation manner of the second aspect, the airport entering information includes airport scene information of the airport to be entered by the flight to be predicted, and the airport scene information includes one or more of the following: the method comprises the steps of entering port landing but not entering port flight information, exiting port flight information waiting for a runway head, flight information waiting to pass through, exiting port flight information sliding on a taxiway, already-deduced flight information and expected deduced flight information.

In a possible implementation manner of the second aspect, the departure airport information includes taxi data of the airport to which the flight to be predicted is about to depart, the taxi data including one or more of the following: the number of the aircraft, the number of the runway, the type of the aircraft, the airline and the period of time in which the flight to be predicted is located.

In a possible implementation manner of the second aspect, the processing unit is further configured to:

acquiring the position information of the incoming flight of the airport where the flight to be predicted is located through the communication unit;

In a possible implementation manner of the second aspect, the inbound flight location information includes one or more of longitude, latitude, speed, altitude, flight direction, and model of the inbound flight.

In one possible implementation manner of the second aspect, if the flight to be predicted is an inbound flight, the inbound flight location information is location information of the flight to be predicted, and the inbound flight landing time is a landing time of the flight to be predicted;

acquiring first position information of the flight to be predicted at the airport through the communication unit;

acquiring second position information of the flight to be predicted at the airport through the communication unit;

In a possible implementation manner of the second aspect, the information of 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 for departure by the runway head, the number of flights waiting for traversal, the remaining taxi time of the flights already launched, the runway departure interval.

In a possible implementation manner of the second aspect, the first location information includes one or more of the following: the runway number, the airplane position number of the entering position, the period of the position and the airplane type of the scheduled flight after entering the port;

In a third aspect, embodiments of the present application provide a computing device comprising a processor and a memory; a memory having a computer program stored therein; the computer program is executed by a processor, which performs the method described in the first aspect.

The processor included in the computing device described in the third aspect may be a processor dedicated to performing the methods (referred to as a special purpose processor for convenience), or may be a processor that performs the methods by calling a computer program, such as a general purpose processor. In the alternative, the at least one processor may also include both special purpose and general purpose processors.

Alternatively, the above-mentioned computer program may be stored in a memory. For example, the Memory may be a non-transitory (non-transitory) Memory, such as a Read Only Memory (ROM), which may be integrated on the same device as the processor, or may be separately disposed on different devices, and the type of the Memory and the manner in which the Memory and the processor are disposed in the embodiments of the present application are not limited.

In one possible implementation, the at least one memory is located outside of the computing device.

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

In yet another possible implementation, a portion of the at least one memory is located within the computing device and another portion of the at least one memory is located outside of the computing device.

In this application, the processor and the memory may also be integrated in one device, i.e. the processor and the memory may also be integrated together.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having instructions stored therein that, when executed on at least one processor, implement the method described in the first aspect.

In a fifth aspect, the present application provides a computer program product comprising computer instructions which, when run on at least one processor, implement a method as described in any one of the preceding aspects. The computer program product may be a software installation package, which may be downloaded and executed on a computing device in case the aforementioned method is required.

The technical methods provided in the second to fifth aspects of the present application may refer to the beneficial effects of the technical solutions of the first aspect, and are not described herein again.

Drawings

The drawings used in the embodiments of the present application are described below.

FIG. 1A is a schematic diagram of a prediction system architecture for a flight time according to an embodiment of the present application;

FIG. 1B is a schematic diagram of another embodiment of a predictive system architecture for a flight time;

fig. 2 is a schematic flow chart of a method for predicting flight arrival time and/or departure time according to an embodiment of the present application;

FIG. 3 is a schematic diagram of predicting landing time of an inbound flight according to an embodiment of the present disclosure;

fig. 4 is a schematic view of a scenario of a flight taxi path prediction provided in an embodiment of the present application;

Fig. 5 is a schematic view of a scenario of arrival time prediction of an inbound flight according to an embodiment of the present application;

fig. 6 is a schematic view of a scenario of departure flight push-out time prediction provided in an embodiment of the present application;

fig. 7 is a schematic flow chart of a push-out time prediction according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a prediction apparatus according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a computing device according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described below with reference to the accompanying drawings in the embodiments of the present application.

For ease of understanding, the following description of probabilities relevant to embodiments of the present application are given by way of example in part for reference. The following is described:

1. aircraft (aircyraft)

An aircraft capable of controlled flight within the atmosphere is a broad class of aircraft, meaning any machine that achieves aerodynamic lift-off flight by relative movement of the fuselage and air. Including aircraft, helicopters, and the like.

2. Flight

A flight refers to any regular flight that engages in public transport of passengers, mail, or cargo with an aircraft. The code is generally composed of two-word codes of each airline company plus 4 as numbers, and the codes of the airlines are published by civil aviation administration regulations. Generally, a flight refers to a transport flight in which an aircraft takes off from a start station according to a specified route, passes through a stop to a destination station or passes through no stop to the destination station. Flights flying on international airlines are referred to as international flights, and flights flying on domestic airlines are referred to as domestic flights. CA1202, for example, from beijing to the ocean at 5 months and 25 days 2007 is an example of a flight.

3. Inlet and outlet flights

"harbor" refers to a local airport, and inbound flights refer to aircraft landing into the airport, and outbound flights refer to aircraft taking off from the airport.

4. Coasting time

For outbound flights, taxi time refers to the time required for the flight to pull back the gear from the apron administration to the actual take off.

For an incoming flight, the taxi time refers to the time required for the flight to taxi on the taxiway after landing until stopping on the stand.

In order to better understand the method and related device for predicting the flight arrival time and/or the departure time provided in the embodiments of the present application, a system architecture used in the embodiments of the present application is described below.

Referring to fig. 1A, fig. 1A is a schematic diagram of a prediction system architecture of a flight time according to an embodiment of the present application. As shown in fig. 1A, the system architecture includes at least one user device 101 and at least one server 102.

The user equipment 101 is an electronic device with data processing and data transceiving capabilities. For example, the device may be a stand-alone device including a handheld terminal, a wearable device, a robot, or may be a component (e.g., a chip or an integrated circuit) included in the stand-alone device. For example, when the terminal device is a handheld terminal, it may be a mobile phone (mobile phone), a tablet (pad), a computer (such as a notebook, a palm computer, etc.), or the like.

The user equipment 101 is a device having data processing and data transceiving capabilities. It should be understood that the description herein is referred to as a server, and the specific form may be a physical device such as a server, or a host, or a virtual device such as a virtual machine, or a container, or the like. Alternatively, the user device 101 may be independently deployed in one device, or may be distributed and deployed on multiple devices.

A variety of systems may be deployed in the user device 101 for providing a variety of data sources, such as airport information for flights to be predicted. The airport information is information of an airport where the flight to be predicted is located when the flight is located and/or pushed out. When the user device 101 (or a user using the user device 101) needs to know the taxi time of the flight to be predicted, the user device 101 may send airport information of the flight to be predicted to the server 102, and the server 102 performs calculation to determine the taxi time of the flight to be predicted.

Accordingly, the server 102 may receive airport information for the flight to be predicted, and determine a taxi time for the flight to be predicted based on the airport information for the flight to be predicted. It can be understood that the airport has a plurality of inbound flights or outbound flights each day, and the airport operation efficiency can be improved by accurately predicting the inbound time of the inbound flights or accurately predicting the outbound time of the outbound flights. Therefore, if the flight to be predicted is an inbound flight, the server 102 may determine the inbound time of the flight to be predicted according to the taxi time of the flight to be predicted. If the flight to be predicted is an outbound flight, the server 102 may determine a departure time of the flight to be predicted according to the taxi time of the flight to be predicted. Therefore, the server 102 can regulate other flights in the airport according to the arrival time of the to-be-predicted flights to be entered, and reduce the flight taxi conflict, thereby improving the operation efficiency of the airport. And/or the server 102 may shorten the taxi time of the flight according to the departure time of the flight to be predicted to be discharged, thereby improving the taxi efficiency of the flight.

It should be understood that the link between the user equipment 101 and the server 102 may be a wired link, a wireless link, or a combination of a wired link and a wireless link. Further alternatively, the communication may be implemented by one or more network technologies. The communication manner between the user equipment 101 and the server 102 is not limited in this application.

In one possible implementation, please refer to fig. 1B, fig. 1B is a schematic diagram of another system architecture for predicting a flight time according to an embodiment of the present application. As can be seen from fig. 1B, the user equipment 101 may comprise a number of systems: an air side operation management system 1011, an integration system 1012, a ground service system 1013, a multi-point positioning system 1014, a route monitoring system 1015 and a process list system 1016. Each system may provide a different data source, for example, the air side operations management system 1011 may provide airport airworthiness information (e.g., inbound airport information, outbound airport information, etc.), the integrated system 1012 may provide dynamic information of flights/positions, the multi-point positioning system 1014 may provide location information (e.g., longitude, latitude, altitude, speed, direction, etc.) of flights, the route monitoring system 1015 may provide route information of flight flights, the process list system 1016 may provide flight status information, etc. The airport entering information may include airport scene information when the flight enters the port; the outbound flight information may include taxi data for an airport where the flight was outbound.

Illustratively, the airport scene information includes one or more of the following: the first taxi-path, the inbound flight information of the inbound landing but not inbound, the outbound flight information of the waiting of the runway head, the flight information of waiting to pass through, the outbound flight information of taxiing on the taxi-path, the flight information already proposed and the flight information expected to be proposed.

Illustratively, the taxi data comprises one or more of the following: the second taxi path, the aircraft location number, the track number, the model, the airline, and the period in which the flight to be predicted is located.

When there is a predicted need, the user equipment 101 may send information collected in each system (for example, airport information of a flight to be predicted) to the server 102 in real time. The airport information of the flight to be predicted may include airport scene information and taxi data. Alternatively, the user device 101 may send the collected taxi data to the message queue 1022 in the server 102 in real time, and the user device 101 may send the collected airport scene information to the database 1021 in the server in real time. After receiving airport information for the flight to be predicted, the server 102 may determine the taxi time for the flight to be predicted. Alternatively, if the airport information is airport information, the server 102 may determine the departure taxi time of the to-be-predicted flight according to airport information of the to-be-predicted flight (for example, airport scene information of the to-be-predicted airport, etc.), and further may determine the arrival time of the to-be-predicted flight according to the departure taxi time. If the airport information is departure airport information, the server may determine departure taxi time of the flight to be predicted according to departure airport information of the flight to be predicted (for example, taxi data of the airport to be departure of the flight to be predicted), and further may determine a departure time of the flight to be predicted according to the departure taxi time. Thus, the server 102 may provide predictions of the on-site times and/or the off-site times for one or more of the air side operations management system 1011, the integration system 1012, and the ground system 1013 of the user device 101.

Illustratively, the user device 101 may send historical data in each system to the server 102, and thus, the server 102 may perform model training based on different historical data of the airport, resulting in multiple predictive models. For example, the server 102 may train to obtain a first prediction model based on historical airport scenario information, where the first prediction model is used to predict the departure taxi time of a flight based on real-time data. Alternatively, the server 102 may be trained from historical departure taxi data of the airport to obtain a second predictive model for predicting departure taxi times of flights based on real-time data. Still alternatively, the server 102 may be trained to obtain a third prediction model according to location information of historical inbound flights of the airport, where the third prediction model is used to predict the inbound flight landing time based on real-time data. Or, the server may train to obtain a fourth prediction model according to historical taxi data of the flight at the airport, where the fourth prediction model is used to predict taxi paths of the flight based on the real-time data, for example, a first taxi path and a second taxi path, where the first taxi path is a taxi path of an incoming flight and the second taxi path is a taxi path of an outgoing flight.

In one possible implementation scenario, if the flight to be predicted is an inbound flight, the server 102 may determine the inbound time of the flight to be predicted according to the landing time of the flight to be predicted and the taxi time of the flight to be predicted. Alternatively, the server 102 may determine the arrival time of the flight to be predicted according to the arrival time of the flight to be predicted and the first taxi path of the taxi time of the flight to be predicted. The first taxi path (i.e., the taxi path when the flight to be predicted is an inbound flight) may be used to predict a cross-conflict point, which may be used to determine the inbound time of the inbound flight.

In one possible implementation scenario, if the flight to be predicted is an outbound flight, the server 102 may determine an idle time of a runway of the airport according to a landing time of one or more inbound flights in the airport where the flight to be predicted is located and information of other flights in the airport where the flight to be predicted is located, and then determine a departure time of the flight to be predicted according to the idle time and a taxi time of the flight to be predicted. Alternatively, the server 102 may determine the free time of the runway of the airport based on the arrival time of one or more inbound flights in the airport where the flight to be predicted is located, information of other flights in the airport where the flight to be predicted is located, and the second taxi path. The second taxi path (i.e., the taxi path when the flight to be predicted is an outgoing flight) may be used to predict a crossing runway conflict point, which may be used to determine the departure time of the outgoing flight.

In one possible design, server 102 as shown in FIG. 1A or FIG. 1B may be a cloud platform. The platform comprises a cloud service provider which is provided for a user at the time of flight arrival and/or the time of release when the cloud platform is abstracted into a flight. For example, after a user purchases a flight arrival time and/or departure time service, the cloud platform creates a predictive model on a resource provided by a cloud service provider in response to an operation of the user, determines the arrival time and/or departure time according to the predictive model, and then provides the arrival time and/or departure time to the user. Accordingly, user devices used by the user may present an interface using flight entry time and/or pull-out time services.

It should be noted that, in the embodiment of the present application, the cloud platform may be a cloud platform of a center cloud, a cloud platform of an edge cloud, or a cloud platform including a center cloud and an edge cloud, which is not specifically limited in the embodiment of the present application. And when the cloud platform is a cloud platform comprising a center cloud and an edge cloud, the flight time prediction system can be partially deployed in the cloud platform of the edge cloud and partially deployed in the cloud platform of the center cloud.

The method of the embodiment of the present application is described in detail below.

Referring to fig. 2, fig. 2 is a flowchart of a method for predicting a flight arrival time and/or a flight departure time according to an embodiment of the present application. Alternatively, the method may be applied to the flight time prediction system shown in fig. 1A or 1B.

The method shown in fig. 2 at least includes steps S201 to S204.

In step S201, the server receives airport information of a flight to be predicted.

Wherein the server receives airport information for flights to be predicted from the user device. Accordingly, when the user device (user using the user device 101) has a predicted demand, the user device may send airport information of the flight to be predicted to the server. The airport information may be information of an airport where the flight to be predicted is located and/or pushed out, for example, the airport where the flight to be predicted is located is a Shenzhen airport, the airport is a Shenzhen airport, and the airport information is information of a current Shenzhen airport; if the airport to be predicted is an Shanghai airport, the airport is the Shanghai airport, and the airport information is the current information of the Shanghai airport.

It will be appreciated that if the airports of the inbound and outbound flights are different airports, then the airport information must be different. If the airport of the incoming flight and the outgoing flight is the same airport, the airport environments facing the incoming flight and the outgoing flight may be different, and the influence on the incoming flight and the outgoing flight may be different, because the incoming flight and the outgoing flight belong to different matters. In summary, for inbound flights, airport information is inbound airport information; for outbound flights, the airport information is outbound airport information.

Illustratively, the airport entering information comprises airport scene information of the airport to be predicted to be entered by the flight, and the airport scene information comprises one or more of the following: the first taxi-path, the inbound flight information of the inbound landing but not inbound, the outbound flight information of the waiting of the runway head, the flight information of waiting to pass through, the outbound flight information of taxiing on the taxi-path, the flight information already proposed and the flight information expected to be proposed. Wherein, entering refers to the flight to be predicted sliding into the stand; the waiting of the runway head means that the current runway has a flight in departure or a flight in departure, so that waiting is needed; waiting to traverse refers to traversing the runway.

Illustratively, the departure airport information comprises taxi data of the airport from which the flight is to be predicted to depart, the taxi data comprising one or more of: the second taxi path, the airplane position number, the runway number, the airplane type, the airline company and the period in which the flight to be predicted is located.

It will be appreciated that the functional areas of the airport include runways, taxiways and stands, and the like. Runways are generally elongated areas on airports for aircraft (such as airplanes) to take off or land. Taxiways are tunnels in airports for aircraft (such as airplanes) to taxi, and the main function is to provide a tunnel from the runway to the waiting area, so that the landed aircraft quickly leaves the runway, does not interfere with the aircraft taking off the runway, and avoids delaying the landing of the aircraft coming randomly as much as possible.

Step S202, the server determines the taxi time of the flight to be predicted according to the airport information of the flight to be predicted.

Specifically, the taxiing of a flight to be predicted on a taxiway may be affected by a variety of factors on the airport scene, and therefore, the server needs to determine the taxiing time of the flight to be predicted in combination with information on the airport scene where the flight to be predicted was located when the flight to be predicted was in place and/or was out.

Illustratively, the airport information includes incoming airport information and/or outgoing airport information.

In one possible scenario, when the flight to be predicted is an inbound flight, the server may determine an inbound taxi time of the flight to be predicted according to inbound airport information of the flight to be predicted. Further, the server may input airport information into the first prediction model, where the result output by the first prediction model is the taxi time of the incoming flight to be predicted. Thus, the server can obtain the departure taxi time of the flight to be predicted. It will be appreciated that the first predictive model is trained from historical airport scene information. For example, when the first prediction model is trained, information including the historical departure flight information of the departure landing but not the departure, the historical departure flight information waiting for the departure head, the historical flight information waiting for the crossing, the historical departure flight information sliding on the taxiway, the historical flight information already pushed out, the historical flight information expected to be pushed out, the historical position of the flight and the like can be input into the machine learning model assembly, and training and verification can be performed through a machine learning algorithm, such as an extreme gradient lifting (eXtreme Gradient Boosting, XGBoost) algorithm, and finally the first prediction model meeting the verification standard is obtained. Therefore, when the airport scene information of the to-be-predicted flight entering is input into the first prediction model, the entering taxi time of the to-be-predicted flight can be obtained by using the XGBoost algorithm.

In another possible scenario, when the flight to be predicted is an outgoing flight, the server may determine an outgoing taxi time of the flight to be predicted according to the outgoing airport information of the flight to be predicted. Further, the server may input departure airport information into a second prediction model, where the result output by the second prediction model is the departure taxi time of the flight to be predicted. Thus, the server can obtain the departure taxi time of the flight to be predicted. It will be appreciated that the second predictive model is trained from historical departure taxi data for the airport. For example, the departure taxi time may be a relatively smooth taxi time, i.e. the time taken to take off from the head of a taxiway at a airport assuming that there is substantially no other flight blocking effect on the airport scene. Therefore, when the second prediction model is trained, the historical departure taxi data of the airport can be input into the machine learning model, and the second prediction model meeting the verification standard is finally obtained through training and verification by a machine learning algorithm, such as a K-means clustering (K-means) algorithm, wherein the historical departure taxi data of the airport comprises factors such as machine position number, runway number, machine type, airline, different time of day and the like, and the data after the data which block the taxi on the scene are removed. Thus, when taxi data of an airport at the departure of a flight to be predicted is input to the second prediction model, the departure taxi time of the flight to be predicted can be obtained using the K-means algorithm.

Step S203, if the flight to be predicted is the inbound flight, determining the inbound time of the flight to be predicted according to the taxi time of the flight to be predicted.

When the flight to be predicted is the inbound flight, the taxi time of the flight to be predicted is the inbound taxi time.

In one possible scenario, the flight to be predicted may be subject to collision hazards during taxiing in the port, i.e., other taxiing flights are encountered during taxiing. Therefore, in the taxi process of entering the port, it is necessary to predict the taxi path of the flight, so as to identify the potential collision hazard in advance, and prepare for avoidance in advance. That is, the server may obtain the first position information of the taxi in the airport of the flight to be predicted, input the first position information into the fourth prediction model, and the result output by the fourth prediction model is the first taxi path of the flight to be predicted. It will be appreciated that the fourth predictive model for predicting taxi paths is trained from historical taxi data for the airport. Illustratively, when the fourth prediction model is trained, factors such as a track number, a machine position number, a period of time corresponding to one day, a machine type, an entrance and exit identifier and the like can be extracted according to historical sliding data, and then training and verification are performed through a classification algorithm, so that the fourth prediction model is finally obtained. Therefore, when the first position information of the to-be-predicted flight sliding in the airport is input into the fourth prediction model, the information of the runway number, the airplane position number, the positioned time period, the airplane type and the like of the to-be-predicted flight is extracted from the first position information, and then the information is classified and probability statistics is carried out, so that a plurality of sliding paths can be obtained. And determining the sliding path with the highest probability of certainty among the plurality of sliding paths as a first sliding path.

Therefore, when the to-be-predicted flight is the inbound flight, after the server obtains the inbound taxi time and the first taxi path of the to-be-predicted flight, if the to-be-predicted flight is landed, the current time of the to-be-predicted flight can be obtained, and the inbound time of the to-be-predicted flight can be determined according to the taxi time, the current time and the first taxi path of the to-be-predicted flight. That is, the in-position time=the current time+the coasting time+the avoidance time caused by the first coasting path. It will be appreciated that if the server determines that the first taxi path may cause cross collision according to the first taxi path, that is, the first taxi path may have a cross repeated area with taxi paths of other flights, the to-be-predicted flight may need to avoid during the taxi in the taxi. Therefore, the server can estimate the avoidance time caused by the cross conflict caused by the first sliding path. If the server determines that the first sliding path does not cause cross conflict according to the first sliding path, no avoidance time exists, so that the avoidance time is zero.

In another possible scenario, if the flight to be predicted is not landed, in order to accurately predict the arrival time of the flight, it is necessary to predict the landing time of the flight. For example, referring to fig. 3, fig. 3 is a schematic diagram of predicting landing time of an inbound flight according to an embodiment of the present application. As shown in fig. 3, taking an airport where a flight to be predicted is about to land as a center, inputting the number of flights with each k being known as one ring (for example, five rings exist in fig. 3) and the position information (including one or more factors of longitude, latitude, altitude, flight direction and machine type) of the incoming flight into a third prediction model, and predicting by using a machine learning algorithm (for example, a decision tree algorithm), wherein the result output by the third prediction model is the landing time of the incoming flight. In the training of the third prediction process, an air flight flow distribution factor is introduced. The air flight distribution factor includes the number of flights in a circle per k km at the destination airport center, and flight location information including one or more factors including longitude, latitude, altitude, direction of flight, model type, and then model building using a machine learning algorithm (e.g., decision tree algorithm) to obtain a third predictive model. It can be understood that the flight to be predicted is an inbound flight that has not landed, and therefore, the location information of the flight to be predicted can be obtained from the landing time of the inbound flight output from the third prediction model.

Therefore, if the flight to be predicted is an inbound non-landing flight, the server may acquire the landing time and the first taxi path of the flight to be predicted. And determining the arrival time of the flight to be predicted according to the taxi time, the landing time and the first taxi path of the flight to be predicted. That is, the landing time=the landing time+the coasting time+the avoidance time caused by the first coasting path. Reference may be made to the above description for the avoidance time caused by the first taxi path, and no further description is given here.

Step S204, if the flight to be predicted is the departure flight, determining the push time of the flight to be predicted according to the taxi time of the flight to be predicted.

When the flight to be predicted is the departure flight, the taxi time of the flight to be predicted is the departure taxi time.

In one possible scenario, the flight to be predicted may be subject to collision hazards during taxiing at the departure, i.e., other taxiing flights are encountered during taxiing. Therefore, in the departure taxiing process, it is necessary to predict the taxiing route of the flight, so as to identify the potential collision hazards in advance, and make preparation for avoidance in advance. That is, the server may obtain second position information of the departure taxi in the airport of the flight to be predicted, input the second position information into the fourth prediction model, and the result output by the fourth prediction model is the second taxi path of the flight to be predicted. It will be appreciated that the fourth predictive model for predicting taxi paths is trained from historical taxi data for the airport. Illustratively, when the fourth prediction model is trained, factors such as a track number, a machine position number, a period of time corresponding to one day, a machine type, an entrance and exit identifier and the like can be extracted according to historical sliding data, and then training and verification are performed through a classification algorithm, so that the fourth prediction model is finally obtained. Therefore, when the second position information of the flight to be predicted sliding out of the airport is input into the fourth prediction model, the information of the runway number, the airplane position number, the positioned time period, the airplane type and the like of the flight to be predicted is extracted from the second position information, and then the information is classified and probability statistics is carried out, so that a plurality of sliding paths can be obtained. And determining the sliding path with the highest probability of certainty among the plurality of sliding paths as a second sliding path.

In another possible scenario, since the departure time of an outbound flight is affected by other inbound flights and other outbound flights. Therefore, in order to accurately predict the departure time of the flight, the server needs to predict the arrival time of one or more inbound flights at the airport where the outbound flight is about to be outbound. It will be appreciated that the flight to be predicted is an outbound flight, and thus the arrival time of one or more inbound flights in the airport where the flight to be predicted is located may be obtained from the arrival flight arrival time output from the third prediction model. Further, in order to improve the prediction accuracy of the time of departure, information about other flights in the airport needs to be considered, including one or more of the following: the number of flights waiting for departure by the head of the runway, the number of flights waiting to be traversed, the remaining taxi time of flights already launched, the runway departure interval, etc.

Therefore, the server can aim to shorten the taxi time, and determine the idle time of the runway of the airport according to the landing time of one or more incoming flights in the airport where the flights to be predicted are located, the second taxi path and the information of other flights in the airport where the flights to be predicted are located. The idle time of the runway is understood to be that the runway has no factors affecting the sliding of the flights to be predicted at the idle time, and does not represent that no other flights can exist on the runway. Finally, the server can determine the push-out time of the flight to be predicted according to the idle time and the taxi time of the flight to be predicted.

It should be noted that, the execution sequence of step S203 and step S204 is not limited in the embodiment of the present application, that is, step S203 may be executed first, and then step S204 may be executed; step S204 may be performed first, and then step S203 may be performed; step S203 and step S204 may also be performed simultaneously.

When the server predicts the arrival time and/or the departure time of the flight to be predicted through one or more prediction models, the arrival time and/or the departure time of the corresponding flight can be sent to the user equipment. The user equipment (or a user using the user equipment) can ensure the operation of flights on the airport according to the in-place time and/or the out-of-arrival time, so that the operation efficiency can be provided.

Referring to fig. 4, fig. 4 is a schematic view of a scenario of flight taxiing path prediction according to an embodiment of the present application. As can be seen from fig. 4, due to the planar structure of the runway, taxiway and stand, an inbound flight may collide with other flights during the inbound taxiing. And the departure flight may collide with other flights during the departure taxi-out process. If the machine can predict and obtain the taxi path of the inbound flight in the inbound process in advance, or the taxi path of the outbound flight in the outbound flight process, the flight with potential conflict risks can be early warned in advance, and the taxi time of the flight is shortened.

For example, as shown in fig. 4, the server may determine the taxi-in path with the maximum recommended probability according to real-time location information of the taxi-in flight, for example, the runway number of the taxi-in flight after landing, the airplane number to be landed, the landing period, the airplane type, and the like, by classifying the information and performing probability statistics through the fourth prediction model. As can be seen from fig. 4, there is a collision between the flights waiting for the crossing during the taxiing to the stand according to the taxi path. Therefore, the inbound flight needs to avoid, wait for the crossing of the crossing flight, and then slide into place.

For example, as shown in fig. 4, the server may determine the departure taxi path with the maximum recommended probability according to real-time location information of the departure flight, such as the number of the departure flight located at the machine position before the departure taxi, the number of the runway to be taken off, the current time period, the model, and the like, by classifying and performing probability statistics on the information through the fourth prediction model. As can be seen from fig. 4, there is a cross collision on the departure taxi path, that is, during the course of entering the runway according to the departure taxi path, there may be a cross collision of the taxi paths of other flights. Therefore, the departure flight needs to avoid, and after waiting for the flight with the crossed path to not taxi on the path, the flight slides into the runway to take off.

Referring to fig. 5, fig. 5 is a schematic view of a scenario for predicting arrival time of an inbound flight according to an embodiment of the present application. It can be understood that the arrival time of the inbound flight is related to the taxi time of the flight, so that the prediction accuracy of the taxi time is improved, and the accuracy of the arrival time can be improved. As can be seen from fig. 5, for the prediction of the ground taxi time of the inbound flight, it is necessary to introduce a ground flight flow distribution factor. Referring to Table I, the importance of various factors analyzed by the applicant to the predicted taxi time is shown. As can be seen from Table one, the factor row is the small area in which the runway, airplane and airplane are located, respectively, in the first three digits. The influence of all factors in the table one on the coasting time is considered in the coasting time prediction model, and the importance degree of each factor in the model is different.

List one

Factors of	Importance score
		Runway (runway)	272
Machine position (craft tsite)	204
		Small area (craft tsite_area)	195
The small area pushes out the flight volume (before_land_fit_cnt)	136
		The amount of flights crossing the runway (wait_in_cross_fit_cnt)	91
Air span (airline_no)	61
		The most recent large area has already deduced the flight volume (wait_off_cnt 2)	37
Total amount of inbound flights on the same day (fit_cnt)	28
		Total number of flights out of the day (fit_cnt_off)	26
Large area (area_ex)	26
		Total number of recently deduced departure flights (wait_off_fit_cnt)	19
Model (air_category)	17
		Large area recently landed flight volume (wait_in_fit_cnt)	6

Thus, the flight traffic distribution factors may include factors such as inbound flights that are inbound to the ground but not inbound, outbound flights waiting for the head of the runway, flights waiting to traverse, flights taxiing on the taxiway, flights already launched, flights expected to be launched, and the like, and the taxiing time prediction of inbound flights is performed by a machine learning algorithm (e.g., XGboost algorithm). For the incoming flights which do not land, the landing time is predicted based on a landing time prediction model by combining information of the positions of the incoming flights, such as longitude, latitude, direction, speed and the like. Thus, the arrival time of an inbound flight=landing time+taxi time. For an inbound flight that has landed, inbound flight inbound time = current time + taxi time. As can be seen from fig. 4, if there is a crossing collision on the taxi path, the collision avoidance time may be caused. Therefore, the arrival time of the inbound flight also needs to consider the avoidance time caused by the crossing collision.

Referring to fig. 6, fig. 6 is a schematic view of a scenario for predicting departure flight pushing-out time according to an embodiment of the present application. As can be seen from fig. 6, the ground flight flow distribution factor is introduced, and the departure optimal time is deduced and predicted by using big data and artificial intelligence technology in combination with the flight position information. The method can avoid the premature push-out of the flight to take off on the ground for a long time, thereby achieving the purposes of shortening the flight taxi time and improving the taxi efficiency. As shown in fig. 6, the prediction of the optimal departure time of the outbound flight takes into account the influence of each inbound flight in each region on the prediction of the departure time. It will be appreciated that the factors in Table I have an effect on the prediction of departure taxi times, except for the degree of importance of each factor effect. Thus, for the prediction of the moment of push-out, one can mainly consider one or more of the following factors: the method comprises the steps of going-in flights to land, going-out flights waiting at the runway heads, going-in flights waiting to traverse the runway, going-out flights in taxiing, smooth taxiing time of the going-out flights, runway rising/falling intervals and the like, modeling the taxiing time of the coming-out flights through a K-means algorithm by combining position information such as longitude, latitude, direction and speed information of other coming-in flights, and accordingly predicting the deduced moment.

For example, referring to fig. 7, fig. 7 is a schematic flow chart of prediction of a push-out time according to an embodiment of the present application. As can be seen from fig. 7, for the prediction of the optimal departure time, both the influence of factors on the prediction of the departure flight time and the historical taxi data are considered, and the prediction is performed by data modeling.

And the idle moment of the runway is combined with the take-off and landing conditions of the inbound and outbound flights of the same runway, and the time gap of no flight take-off and landing is predicted. The prediction of the runway idle time Tr can be determined by predicting the landing time of other inbound flights, the quantity of flights waiting for take-off by the runway head, the quantity of flights waiting for crossing, the remaining taxi time of the current taxi flight, the runway start/flight interval and other factors. The taxi time of an outgoing flight includes the remaining taxi time from the airport taxi to the slideway head or already out of the airport. The taxi time model can be obtained through training of historical departure taxi data, current taxi data of the departure flight is input into the taxi time model, and current taxi time Tln of the departure flight can be predicted. Thus, the push-out timing can be determined by the runway idle timing Tr and the coasting time Tln. For example, if the current time now () =10:00 and the taxi time Tln =5 minutes, tln +now () =10:05, so long as the runway is free and available at tr=10:05 and before, the guaranteed departure flight can be launched at 10:00. If the runway is available only when tr=10:10, the departure flight is launched at 10:05 and later if guaranteed in order to save taxi time.

The foregoing details the method of embodiments of the present application, and the apparatus of embodiments of the present application is provided below.

Referring to fig. 8, fig. 8 is a schematic structural diagram of a prediction apparatus 80 according to an embodiment of the present application, where the prediction apparatus 80 may be a server, or may be a device in the server, such as a chip, a software model, an integrated circuit, etc. The prediction device 80 is configured to implement the aforementioned method for predicting the flight entry time and/or the departure time, for example, the method in the embodiment shown in fig. 2.

In a possible embodiment, the prediction means 80 may comprise a communication unit 801 and a processing unit 802.

In a possible implementation method, a communication unit 801 is configured to receive airport information of a flight to be predicted, where the airport information is information of an airport where the flight to be predicted is located when the flight to be predicted is located and/or pushed out;

a processing unit 802, configured to determine a taxi time of the flight to be predicted according to airport information of the flight to be predicted;

the processing unit 802 is further configured to determine, if the flight to be predicted is an inbound flight, an inbound time of the flight to be predicted according to a taxi time of the flight to be predicted; and/or the number of the groups of groups,

In yet another possible implementation, the processing unit 802 is specifically configured to:

In yet another possible implementation, the processing unit 802 is specifically configured to: inputting the airport entering information into a first prediction model to obtain the airport entering taxi time of the flight to be predicted; the first prediction model is trained according to historical scene information of the airport.

In yet another possible embodiment, the airport entering information comprises airport scenario information of the airport to be entered for the flight to be predicted, the airport scenario information comprising one or more of the following: the method comprises the steps of entering port landing but not entering port flight information, exiting port flight information waiting for a runway head, flight information waiting to pass through, exiting port flight information sliding on a taxiway, already-deduced flight information and expected deduced flight information.

In yet another possible embodiment, the departure airport information comprises taxi data of the airport from which the flight is to be predicted to depart, the taxi data comprising one or more of: the number of the aircraft, the number of the runway, the type of the aircraft, the airline and the period of time in which the flight to be predicted is located.

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

Acquiring the arrival flight position information of the airport where the flight to be predicted is located through the communication unit 801;

In yet another possible embodiment, the inbound flight location information includes one or more of longitude, latitude, speed, altitude, direction of flight, and model of the inbound flight.

In yet another possible implementation manner, if the flight to be predicted is an inbound flight, the inbound flight location information is location information of the flight to be predicted, and the inbound flight landing time is a landing time of the flight to be predicted;

acquiring first location information of the flight to be predicted at the airport through the communication unit 801;

acquiring second location information of the flight to be predicted at the airport through the communication unit 801;

In yet another possible implementation manner, the information of 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 for departure by the runway head, the number of flights waiting for traversal, the remaining taxi time of the flights already launched, the runway departure interval.

In yet another possible embodiment, the first location information comprises one or more of: the runway number, the airplane position number of the entering position, the period of the position and the airplane type of the scheduled flight after entering the port;

It should be understood that the description may also refer to the description in the embodiment shown in fig. 2, and will not be repeated here.

Referring to fig. 9, fig. 9 is a schematic structural diagram of a computing device 90 according to an embodiment of the present application, where the computing device 90 may be a stand-alone device (e.g. one or more of servers, etc.), or may be a component (e.g. a chip, a software module, a hardware module, etc.) inside the stand-alone device. The computing device 90 may include at least one processor 901. Optionally, at least one memory 903 may also be included. Further optionally, the computing device 90 may also include a communication interface 902. Still further optionally, a bus 904 may be included, wherein the processor 901, the communication interface 902, and the memory 903 are coupled by the bus 904.

The processor 901 is a module for performing arithmetic operation and/or logic operation, and may specifically be one or more of a central processing unit (central processing unit, CPU), a picture processor (graphics processing unit, GPU), a microprocessor (microprocessor unit, MPU), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA), a complex programmable logic device (Complex programmable logic device, CPLD), a coprocessor (assisting the central processing unit to perform corresponding processing and application), a micro control unit (Microcontroller Unit, MCU), and other processing modules.

The communication interface 902 may be used to provide information input or output to the at least one processor. And/or the communication interface 902 may be configured to receive data sent from and/or send data to the outside, which may be a wired link interface including, for example, an ethernet cable, or may be a wireless link (Wi-Fi, bluetooth, universal wireless transmission, vehicle-mounted short-range communication technology, and other short-range wireless communication technologies, etc.) interface. Optionally, the communication interface 902 may also include a transmitter (e.g., radio frequency transmitter, antenna, etc.) or a receiver, etc. coupled to the interface.

The memory 903 is used to provide storage space in which data such as an operating system and computer programs can be stored. The memory 903 may be one or more of a random access memory (random access memory, RAM), a read-only memory (ROM), an erasable programmable read-only memory (erasable programmable read only memory, EPROM), or a portable read-only memory (compact disc read-only memory, CD-ROM), etc.

The at least one processor 901 in the computing device 90 is configured to perform the aforementioned method for predicting the flight entry time and/or the pull-out time, for example, the method for predicting the flight entry time and/or the pull-out time described in the embodiment shown in fig. 2.

Alternatively, the processor 901 may be a processor (for convenience of distinction, referred to as a dedicated processor) dedicated to performing the methods, or may be a processor that performs the methods by calling a computer program, for example, a general-purpose processor. In the alternative, the at least one processor may also include both special purpose and general purpose processors. Alternatively, in the case of a computing device comprising at least one processor 901, the above-described computer program may be present in the memory 903.

In one possible implementation, at least one processor 901 in the computing device 90 is configured to execute call computer instructions to:

receiving airport information of flights to be predicted through a communication interface 902, wherein the airport information is information of an airport where the flights to be predicted are located when the flights to be predicted are located and/or pushed out;

In yet another possible implementation manner, the processor 901 is specifically configured to:

In yet another possible implementation manner, the processor 901 is specifically configured to: inputting the airport entering information into a first prediction model to obtain the airport entering taxi time of the flight to be predicted; the first prediction model is trained according to historical scene information of the airport.

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

acquiring the arrival flight position information of the airport where the flight to be predicted is located through the communication interface 902;

acquiring first location information of the flight to be predicted at the airport through the communication interface 902;

acquiring second location information of the flight to be predicted at the airport through the communication interface 902;

The present application also provides a computer readable storage medium having instructions stored therein that, when executed on at least one processor, implement the foregoing method for predicting a flight entry time and/or a departure time, for example, the method for predicting a flight entry time and/or a departure time shown in fig. 2.

The present application also provides a computer program product comprising computer instructions that, when executed by a computing device, implement the aforementioned method of predicting a flight entry time and/or a departure time, for example, the method of predicting a flight entry time and/or a departure time shown in fig. 2.

In the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

Reference to "at least one" in embodiments herein means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a. b, c, (a and b), (a and c), (b and c), or (a and b and c), wherein a, b, c may be single or plural. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: three cases of a alone, a and B together, and B alone, wherein A, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship.

And, unless otherwise indicated, the use of ordinal numbers such as "first," "second," etc., in the embodiments herein are used for distinguishing between multiple objects and not for defining a sequence, timing, priority, or importance of the multiple objects. For example, the first user device and the second user device are merely for convenience of description, and are not meant to represent differences in structure, importance, etc. of the first user device and the second user device, and in some embodiments, the first user device and the second user device may also be the same device.

As used in the above embodiments, the term "when … …" may be interpreted to mean "if … …" or "after … …" or "in response to determination … …" or "in response to detection … …" depending on the context. The foregoing description of the preferred embodiments is merely exemplary in nature and is in no way intended to limit the invention, its application, to the form and details of construction and the arrangement of the preferred embodiments, and thus, any and all modifications, equivalents, and alternatives falling within the spirit and principles of the present application.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

Claims

1. A method for predicting a flight entry time and/or a departure time, comprising:

2. The method according to claim 1, wherein the airport information comprises incoming airport information and/or outgoing airport information, and wherein the determining the taxi time of the flight to be predicted based on the airport information of the flight to be predicted comprises:

3. The method of claim 2, wherein the determining the departure taxi time of the flight to be predicted based on the departure airport information of the flight to be predicted comprises:

4. A method according to claim 2 or 3, wherein the airport entering information comprises airport scenario information of the airport to which the flight to be predicted is to enter, the airport scenario information comprising one or more of: the method comprises the steps of entering port landing but not entering port flight information, exiting port flight information waiting for a runway head, flight information waiting to pass through, exiting port flight information sliding on a taxiway, already-deduced flight information and expected deduced flight information.

5. The method according to any one of claims 2 to 4, wherein if the flight to be predicted is an inbound flight, determining the inbound time of the flight to be predicted according to the taxi time of the flight to be predicted comprises:

6. The method of claim 2, wherein the determining the departure taxi time of the flight to be predicted based on the departure airport information of the flight to be predicted comprises:

7. The method of claim 2 or 6, wherein the departure airport information comprises taxi data for the airport from which the flight to be predicted is to depart, the taxi data comprising one or more of: the number of the aircraft, the number of the runway, the type of the aircraft, the airline and the period of time in which the flight to be predicted is located.

8. The method according to any one of claims 1 to 7, wherein after determining the taxi time of the flight to be predicted according to airport information of the flight to be predicted, if the flight to be predicted is an inbound flight, determining a departure time of the flight to be predicted according to the taxi time of the flight to be predicted; and/or if the flight to be predicted is an outgoing flight, determining the push time of the flight to be predicted according to the taxi time of the flight to be predicted further includes:

9. The method of claim 8, wherein the inbound flight location information comprises one or more of longitude, latitude, speed, altitude, direction of flight, model of the inbound flight.

10. The method according to claim 8 or 9, wherein,

if the flight to be predicted is an incoming flight, the incoming flight position information is the position information of the flight to be predicted, and the landing time of the incoming flight is the landing time of the flight to be predicted;

11. The method of claim 10, wherein if the flight to be predicted is an inbound flight, determining the inbound time of the flight to be predicted according to the taxi time of the flight to be predicted comprises:

12. The method of claim 5 or 11, wherein the determining the first taxi path of the flight to be predicted comprises:

13. The method of claim 10, wherein determining the departure time of the flight to be predicted according to the taxi time of the flight to be predicted if the flight to be predicted is a departure flight comprises:

14. The method of claim 13, wherein the determining the second taxi path of the flight to be predicted comprises:

15. The method of claim 13 or 14, wherein the information of other flights in the airport where the flight to be predicted is located comprises one or more of: the number of flights waiting for departure by the runway head, the number of flights waiting for traversal, the remaining taxi time of the flights already launched, the runway departure interval.

16. The method of claim 12 or 14, wherein the first location information comprises one or more of: the runway number, the airplane position number of the entering position, the period of the position and the airplane type of the scheduled flight after entering the port;

17. A prediction apparatus, comprising:

the communication unit is used for receiving airport information of flights to be predicted, wherein the airport information is information of an airport where the flights to be predicted are located when the flights to be predicted are located and/or pushed out;

18. The apparatus according to claim 17, wherein the processing unit is specifically configured to:

19. The apparatus according to claim 18, wherein the processing unit is specifically configured to:

20. The apparatus of claim 18 or 19, wherein the airport entry information comprises airport scenario information for the airport to which the flight is to be predicted to enter, the airport scenario information comprising one or more of: the method comprises the steps of entering port landing but not entering port flight information, exiting port flight information waiting for a runway head, flight information waiting to pass through, exiting port flight information sliding on a taxiway, already-deduced flight information and expected deduced flight information.

21. The device according to any one of claims 18 to 20, wherein the processing unit is specifically configured to:

22. The apparatus according to claim 21, wherein the processing unit is specifically configured to:

23. The apparatus of claim 18 or 22, wherein the departure airport information comprises taxi data for the airport at which the flight to be predicted is to be departed, the taxi data comprising one or more of: the number of the aircraft, the number of the runway, the type of the aircraft, the airline and the period of time in which the flight to be predicted is located.

24. The apparatus according to any one of claims 17 to 23, wherein the processing unit is further configured to:

25. The apparatus of claim 24, wherein the inbound flight location information comprises one or more of longitude, latitude, speed, altitude, direction of flight, model of the inbound flight.

26. The apparatus of claim 24 or 25, wherein the device comprises a plurality of sensors,

27. The apparatus according to claim 26, wherein the processing unit is specifically configured to:

28. The apparatus according to claim 21 or 27, wherein the processing unit is specifically configured to:

29. The apparatus according to claim 26, wherein the processing unit is specifically configured to:

30. The apparatus according to claim 29, wherein the processing unit is configured to:

31. The apparatus of claim 29 or 30, wherein the information of other flights in the airport where the flight is to be predicted comprises one or more of: the number of flights waiting for departure by the runway head, the number of flights waiting for traversal, the remaining taxi time of the flights already launched, the runway departure interval.

32. The apparatus of claim 28 or 30, wherein the first location information comprises one or more of: the runway number, the airplane position number of the entering position, the period of the position and the airplane type of the scheduled flight after entering the port;

33. A computing device, the computing device comprising a processor and a memory;

the memory stores a computer program;

the computing device performs the method of any of the preceding claims 1 to 16 when the processor executes the computer program.

34. A computer readable storage medium having instructions stored therein which, when executed on at least one processor, implement the method of any one of claims 1 to 16.

35. A computer program product comprising computer instructions which, when run on at least one processor, implement the method of any one of claims 1 to 16.