CN115293562A

CN115293562A - Flight plan generation method and device for flight, computer equipment and storage medium

Info

Publication number: CN115293562A
Application number: CN202210922153.6A
Authority: CN
Inventors: 吴子轩; 胡旗松; 吕玮; 胡志江; 刘志凌; 梁辰旭; 殷文; 余胜; 袁洁
Original assignee: Xiamen Airlines Co Ltd
Current assignee: Xiamen Airlines Co Ltd
Priority date: 2022-08-02
Filing date: 2022-08-02
Publication date: 2022-11-04

Abstract

The application relates to a flight plan generation method, a flight plan generation device, a computer device, a storage medium and a computer program product. The method comprises the following steps: acquiring a historical track of a first flight and a candidate runway of a second flight; selecting a takeoff runway of the second flight from the candidate runways according to the historical track of the first flight; selecting a target departure program from the candidate departure programs according to the matching degree of the planned trajectory of the candidate departure programs and the historical trajectory of the first flight; and generating a flight plan of the second flight based on the take-off runway of the second flight and the target departure program. By adopting the method, the specific rule of each airport on the use runway can be found, the flight plan of the second flight is selected, and the target departure program is selected from the candidate departure programs, so that the flight plan is more accurate, the risk of overweight landing is avoided to a certain extent, and the extra filling waste of fuel oil is avoided.

Description

Flight plan generation method and device for flight, computer equipment and storage medium

Technical Field

The present application relates to the field of aviation technologies, and in particular, to a flight plan generation method and apparatus for a flight, a computer device, a storage medium, and a computer program product.

Background

In the traditional technology, in order to ensure flight safety, except for a part of routes subjected to risk assessment, the release of all flights of an airline company mainly adopts a procedure of entering and leaving the flight with the largest distance of the routes, and the release is carried out according to the conservative take-off and landing runway.

However, according to actual operation conditions for many years, due to the influence of operation modes, meteorological conditions and other factors, a certain specific rule exists on the use of runways for each airport, and only the fixed runways are adopted, so that not only is extra fuel filling waste caused, but also the flight has the risk of overweight landing in some cases, namely the current takeoff runway and departure procedure selection modes based on the maximized distance are not optimal for operation safety or fuel saving benefits.

In order to ensure the flight safety, most flights of an airline company are released by adopting an departure procedure with the largest distance of the flight line in the departure direction. However, according to practical operation conditions for many years, it is rare that the departure procedure must be operated with the maximum distance, and the flight is not provided with the departure procedure with sufficient accuracy, and in some cases, the flight is at risk of an overweight landing.

Disclosure of Invention

In view of the above, it is necessary to provide a flight plan generating method, device, computer readable storage medium and computer program product for flight with improved accuracy.

In a first aspect, the present application provides a flight plan generating method for a flight. The method comprises the following steps:

acquiring a historical track of a first flight and a candidate runway of a second flight;

selecting a takeoff runway of the second flight from the candidate runways according to the historical track of the first flight;

selecting a target departure program from the candidate departure programs according to the matching degree of the planned trajectory of the candidate departure program and the historical trajectory of the first flight;

and generating a flight plan of the second flight based on the takeoff runway of the second flight and the target departure program.

In one embodiment, the historical trajectory of the first flight includes a first coordinate point and a second coordinate point that are different in height and are obtained in chronological order; selecting a takeoff runway of the second flight from the candidate runways according to the historical track of the first flight, wherein the selecting comprises the following steps:

when the height of the first coordinate point is a preset height value, inquiring the difference value of the runway threshold azimuth angle between the first coordinate point and the candidate runway according to the difference value of the azimuth angle between the first coordinate point and the second coordinate point to obtain a runway azimuth angle inquiry result;

searching a candidate runway corresponding to the runway azimuth angle query result from the candidate runways;

and selecting the runway on the opposite side as a take-off runway of the second flight according to the candidate runway corresponding to the runway azimuth angle query result.

In one embodiment, the selecting a takeoff runway for the second flight from the candidate runways according to the historical trajectory of the first flight further comprises:

when the height of the first coordinate point and the height of the runway are larger than the preset height value, comparing the distance between the first coordinate point and the runway opening of each candidate runway to obtain a distance comparison result;

screening the candidate runways based on the distance comparison result;

and selecting the runway on the opposite side of the screened candidate runway as a take-off runway of the second flight.

In one embodiment, the obtaining the historical track of the first flight and the candidate runway of the second flight includes:

acquiring a historical track of a first flight, and acquiring a second coordinate point from the historical track;

screening the preset runways on the same side of the track of the first flight on the basis of the distance between the second coordinate point and the runway openings of the preset runways;

and taking a preset runway on the same side of the historical track of the first flight as a candidate runway of the second flight.

In one embodiment, the obtaining the historical track of the first flight and the candidate runway of the second flight comprises:

sequentially selecting route points from the original historical track of the first flight;

verifying the waypoints based on the height data of the waypoints;

generating a verified historical track according to the verified waypoints;

and obtaining a candidate runway of the second flight according to the verified historical track.

In one embodiment, the selecting a target departure procedure from the candidate departure procedures according to the matching degree of the planned trajectory of the candidate departure procedure and the historical trajectory of the first flight includes:

judging whether each point in the planned track of the candidate departure program is a matching point according to whether each point in the planned track is matched with the historical waypoint of the first flight;

calculating the matching degree of the planned track and the historical track based on the number of matching points in the planned track of the candidate off-site program;

and selecting a target departure program from the candidate departure programs according to the matching degree of the planned trajectory and the historical trajectory.

In one embodiment, the determining whether each point in the planned trajectory of the candidate departure procedure matches the historical waypoints of the first flight comprises:

if the historical number of waypoints of the first flight in the first matching range is greater than a first preset number of waypoints, the target point in the planned trajectory of the candidate departure program is the matching point;

if the historical waypoint number of the first flight in the first matching range is less than or equal to the preset waypoint number, judging whether the target point is the matching point according to whether the historical waypoint of the first flight exists in a second matching range of each point in the planned track of the candidate departure program; the second matching range is larger than the first matching range;

if the historical waypoint number of the first flight in the first matching range is greater than the first preset waypoint number and is less than or equal to the second preset waypoint number, and the departure point of the planned track of the candidate departure program is different from the historical departure point of the first flight, judging whether the target point is the matching point according to whether the historical waypoint of the first flight exists in a third matching range of each point in the planned track of the candidate departure program; the third matching range is greater than the second matching range.

In one embodiment, the degree of matching is determined based on the number of points of matching of the planned trajectory with the historical trajectory of the first flight and departure points; selecting a target departure procedure from the candidate departure procedures according to the matching degree of the planned trajectory and the historical trajectory, wherein the selecting step comprises the following steps:

when a plurality of candidate departure programs with the maximum number of the matching points exist, acquiring historical departure points of the first flight and departure points of a planned track of the candidate departure program with the maximum number of the matching points;

judging whether the departure point of the planned trajectory is consistent with the historical departure point of the first flight;

if yes, selecting a target departure program according to the candidate departure programs with the consistent historical departure points of the first flight;

and if not, selecting the target departure program from the candidate departure programs according to the flight departure distance between the historical departure point of the first flight and the departure airport and the planned departure distance between the planned departure point of each candidate departure program and the departure airport.

In one embodiment, the method further comprises:

when the departure airport of the second flight is the target airport and the candidate departure program with the maximum number of the matching points is smaller than or equal to the threshold value of the number of the candidate departure programs, determining that the candidate departure program deviates from the target departure program of the second flight;

when the departure airport of the second flight is the target airport, the number of matching points of the candidate departure program with the maximum number of matching points is less than or equal to the threshold value of the number of matching points, and the departure point of the corresponding planned trajectory is inconsistent with the historical departure point of the first flight, determining that the candidate departure program deviates from the target departure program of the second flight;

and when the departure airport of the second flight is not the target airport, judging whether the candidate departure program deviates from the target departure program of the second flight according to whether the ratio of the number of the matching points occupying the historical departure points of the first flight exceeds the corresponding threshold value of the number of the matching points.

In one embodiment, the method further comprises a training step of the predictive model, the training step comprising:

resampling and randomly splitting the acquired historical data of the first flight according to the characteristic items;

optimizing at least one of a prediction model of the takeoff runway and a prediction model of the target departure procedure according to data of the resampled and randomly split feature items;

the optimized prediction model of the takeoff runway is used for predicting the takeoff runway;

and the optimized prediction model of the target field departure program is used for predicting the target field departure program.

In a second aspect, the present application further provides a flight plan generating device for flights. The device comprises:

the data acquisition module is used for acquiring the historical track of the first flight and the candidate runway of the second flight;

a runway selection module, configured to select a takeoff runway of the second flight from the candidate runways according to the historical trajectory of the first flight;

the departure program selection module is used for selecting a target departure program from the candidate departure programs according to the matching degree of the planned track of the candidate departure program and the historical track of the first flight;

and the plan generating module is used for generating a flight plan of the second flight based on the take-off runway of the second flight and the target departure program.

In a third aspect, the application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of flight plan generation for a flight in any of the embodiments described above when the computer program is executed.

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of flight plan generation for a flight in any of the embodiments described above.

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, performs the steps of generating a flight plan for a flight according to any of the embodiments described above.

According to the flight plan generation method, the flight plan generation device, the computer equipment, the storage medium and the computer program product of the flight, the takeoff runway of the second flight is selected from the candidate runways according to the historical track of the first flight, and a certain specific rule of each airport on the use runway is found out; selecting a target departure program from the candidate departure programs according to the matching degree of the planned track of the candidate departure program and the historical track of the first flight, so that the second flight is released without adopting the departure program with the maximum distance in the departure direction of the flight line; therefore, based on the takeoff runway of the second flight and the target departure program, the flight plan can be more accurate, the risk of overweight landing is avoided to a certain extent, and the extra filling waste of fuel is avoided.

Drawings

FIG. 1 is a diagram of an application environment of a flight plan generating method for flights in one embodiment;

FIG. 2 is a flow chart illustrating a method for generating a flight plan for a flight in one embodiment;

FIG. 3 is a flowchart illustrating a flight plan generating method for flights according to another embodiment;

FIG. 4 is a schematic flow diagram illustrating flight runway selection in one embodiment;

FIG. 5 is a flow diagram illustrating target departure procedure selection in one embodiment;

FIG. 6 is a flow diagram of predictive model training in one embodiment;

FIG. 7 is a block diagram showing a configuration of a flight plan generating apparatus for flights in one embodiment;

FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The flight plan generating method for flights provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server.

The terminal 102 may be one of various airborne devices, airport devices and other internet of things devices, and may also be various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers. The present scheme may be performed by at least one of the terminal 102 or the server 104.

In one embodiment, as shown in fig. 2, a flight plan generating method for flights is provided, which is described from an angle by taking the method as an example applied to the terminal 102 in fig. 1, and includes the following steps:

step 202, obtaining a historical track of the first flight and a candidate runway of the second flight.

The first flight and the second flight are in a corresponding relationship determined according to the construction and application of the neural network model, and the corresponding relationship is represented as follows: a neural network model is built or invoked from data of a first flight to predict data of a second flight. The specific correspondence may be shown by three aspects: the first flight may correspond to a flight number for which a flight plan has been executed or is being executed within a certain time period of the current time, and correspondingly, the second flight may correspond to a flight number for which a flight plan is being generated; the first flight can be used for determining various characteristic items of the neural network model, and correspondingly, the second flight is used for acquiring relevant data of flight numbers of the various characteristic items of the neural network model; the first flight may also be used to obtain historical data to train, test or validate some neural network model, and correspondingly, the second flight is a flight that predicts a flight path or departure procedure through the neural network model.

When the first flight and the second flight are in any corresponding relation, the first flight and the second flight are determined. It will be appreciated that the first flight and the second flight may be the same flight number on different dates. For example: when the flight plan of the flight number MF8555 on 1 month and 1 day is executed and the flight plan of the flight number MF8555 on 1 month and 4 days is generated, the data corresponding to the flight number MF8555 on 1 month and 1 day belongs to the data of the first flight, and the data of the second flight can be predicted by training the neural network through the data corresponding to the flight number MF8555 on 1 month and 1 day, wherein the data of the second flight is the flight number MF8555 on 1 month and 4 days.

The historical trajectory of the first flight is a flight trajectory obtained based on flight records in the historical data. The data source of the historical track can be any one of airborne QAR data of the airline department, civil aviation information sharing data and ADS-B data of FA purchased through GMP, and a plurality of data sources can be mutually verified to obtain more accurate data.

The flight trajectory may be the GNSS coordinate data obtained during the time period from the departure to the stop of the vehicle according to the flight date and the departure airport of the flight. The GNSS coordinate data is coordinate data in a Global Navigation Satellite System (Global Navigation Satellite System). When the GNSS coordinate data has the problem of inconsistent flight data, correction can be carried out through FA data (flight tracking data). The historical trajectory of the first flight includes at least a first coordinate point and a second coordinate point which are different in height and acquired in time sequence.

In one embodiment, focus is on the discussion of candidate runways. Obtaining a historical track of a first flight and a candidate runway of a second flight, comprising: acquiring a historical track of a first flight, and acquiring a second coordinate point from the historical track; screening the preset runways on the same side of the track of the first flight on the basis of the distance between the second coordinate point and the runway opening of each preset runway; and taking a preset runway on the same side of the historical track of the first flight as a candidate runway of the second flight.

The candidate runway for the second flight is a runway that needs to be considered in making a flight plan for the second flight; the candidate runway may be a preset runway in an airport where the second flight is located, data of the preset runway is obtained from an interface according to airport four-character codes, and the candidate runway may also be an ipsilateral runway screened from the preset runway based on a historical track of the first flight.

When the distance between the second coordinate point and the runway opening of a certain preset runway is smaller than the distance between the second coordinate point and half of the runway openings of the preset runways, the preset runway is the same-side runway screened from the preset runways.

And step 204, selecting a takeoff runway of the second flight from the candidate runways according to the historical track of the first flight.

The takeoff runway of the second flight may be a prediction result of a prediction model constructed according to a machine learning algorithm, and the machine learning algorithm used may be various regression models for classification, including but not limited to: a decision tree model, a random forest model and a limit tree model. The extreme tree model (ET) is very suitable for processing discrete variable data, overfitting can be effectively avoided by introducing a resampling technology and a random splitting strategy, excellent performance is shown when large-scale data volume and high-dimensional characteristics are processed, and the method has good generalization performance and high precision. The training step of the prediction model according to the limit tree model comprises the following steps: resampling and randomly splitting the acquired historical data of the first flight according to the characteristic items; optimizing a prediction model of a takeoff runway according to data of the characteristic items of resampling and random splitting; and the optimized prediction model of the takeoff runway is used for predicting the takeoff runway.

In one embodiment, the historical trajectory of the first flight includes a first coordinate point and a second coordinate point which are obtained in time sequence and have different heights, wherein the height can be an altitude, a coordinate height or a relative height of a horizontal plane corresponding to the runway; correspondingly, the preset height values are respectively set according to the altitude, can be set according to the coordinate height, and can also be determined according to the horizontal height of the coordinate points corresponding to the runway. For example: when the height is set based on the relative height of the horizontal plane corresponding to the coordinates and the runway, the preset height value is about 0.

Correspondingly, according to the historical track of the first flight, selecting a takeoff runway of the second flight from the candidate runways, and the method comprises the following steps: when the height of the first coordinate point is a preset height value, inquiring the runway threshold azimuth angle difference value of the first coordinate point and the candidate runway according to the azimuth angle difference value between the first coordinate point and the second coordinate point to obtain a runway azimuth angle inquiry result; searching a candidate runway corresponding to the runway azimuth angle query result from the candidate runways; and selecting the runway on the opposite side as a take-off runway of the second flight according to the candidate runway corresponding to the runway azimuth angle query result.

The azimuth angle difference value between the first coordinate point and the second coordinate point is obtained by performing difference operation on the first coordinate point and the second coordinate point. The difference operation may be performed as follows: calculating a first coordinate point azimuth angle relative to a preset direction, and then calculating a second coordinate point azimuth angle relative to the preset direction; and calculating the difference value of the azimuth angle of the first coordinate point and the azimuth angle of the second coordinate point to obtain an azimuth angle difference value. It is understood that the difference operation may also be a way of calculating variance, standard deviation, data gradient, etc.

The runway azimuth query result is a runway threshold azimuth difference value closest to the azimuth difference value between the first coordinate point and the second coordinate point. The runway opening azimuth difference value is obtained by performing difference calculation on the basis of the azimuth of the first coordinate point and the azimuth of the coordinates of the runway opening, and has a calculation process similar to that of the azimuth difference value between the first coordinate point and the second coordinate point.

The candidate runway corresponding to the runway azimuth angle query result is the closest runway opening when a certain plane indicated by the second flight leaves the runway; correspondingly, according to the candidate runway corresponding to the runway azimuth angle query result, selecting the runway on the opposite side as the takeoff runway of the second flight, and the method comprises the following steps: and calculating the runway identification and the transposition mode of the opposite side according to the identification of the candidate runway corresponding to the runway azimuth angle query result, and selecting the takeoff runway of the second flight according to the runway identification and the transposition mode of the opposite side.

For example: selecting a coordinate point with a first height different from zero and an adjacent coordinate point of the coordinate point in the historical track of the first flight; the adjacent coordinate points of the coordinate point are chronologically labeled as a first coordinate point P1 and a second coordinate point P2. If the height of the first coordinate point P1 is zero, that is, the first coordinate point P1 is a point on the runway, the azimuth Angle difference value Angle _0 between the first coordinate point P1 and the second coordinate point P2 is calculated, the runway threshold azimuth Angle difference values Angle _ X between the first coordinate point P1 and the X candidate runways are calculated, and the runway threshold N with the Angle closest to Angle _0 is obtained. The runway opening N is the closest runway opening when the aircraft leaves the runway, while the actual flight entry is the runway opening on the opposite side N' of the runway opening N, which is obtained by identifying the runway opening N with +18 and left-hand steering.

Further, when the height of the first coordinate point is larger than the preset height value, comparing the distance between the first coordinate point and the runway opening of each candidate runway to obtain a distance comparison result; screening the candidate runways based on the distance comparison result; and selecting the runway on the opposite side of the screened candidate runway as a takeoff runway of the second flight. And the distance comparison result is used for determining a runway opening closest to the first coordinate point P1, and determining the screened candidate runway by the runway opening. And selecting the runway on the opposite side of the screened candidate runway as a take-off runway of a second flight.

In one embodiment, the second flight's correction process is discussed from the perspective of invoking the neural network model. When the terminal sends an instruction for calling the neural network model, checking whether the feature item data of the first flight in the previous and subsequent time periods are consistent or not according to the previous and subsequent time periods of the takeoff time and the instruction sending time; and/or checking whether the characteristic item data of the second flight in the previous and later time periods are consistent.

The characteristic item data is data set for modeling a certain airport and comprises the types of flight historical data, flight number related data, airline data, airplane data, meteorological data and the like; the time period corresponds to a plurality of time lengths, the first flight and the second flight are determined according to the first time length, and if the first time length does not determine the first flight and the second flight at the same time, the missing flight can be determined according to the second time length which is longer than the first time length.

For example: taking 2 flights at the latest takeoff time within 15min before the instruction sending time, judging as error data if the feature item data are inconsistent, and correcting according to the feature item data which are consistent front and back; if the time exceeds 15min, no enough flight taking-off flight exists, respectively taking 2 flights at the latest take-off/landing moment within 15min forwards and 15min backwards, if the flight taking-off flight and the landing flight are inconsistent, judging that the flight taking-off flight and the landing flight are wrong, and correcting according to the characteristic item data which is consistent; if the number of flights is not enough in more than 15min, respectively taking 2 flights at the latest take-off/landing moment within 30min forwards and 30min backwards, if the flights are inconsistent, judging the flights to be error data, and correcting the flights according to the characteristic item data which is consistent; if not, the FA data (flight tracking data) is taken and corrected.

And step 206, selecting a target departure program from the candidate departure programs according to the matching degree of the planned track of the candidate departure program and the historical track of the first flight.

The candidate departure procedure is an optional departure procedure. The Departure procedure, i.e., standard Instrument Departure (SID), is a publicly issued flight procedure for use after an aircraft performing Instrument flight takes off from an airport, and is classified into two types: a standard instrument departure procedure for pilot navigation and a radar-guided standard instrument departure procedure. There are many different standard departure procedures for an airport, and the same runway will guide the aircraft to different departure points for different departure procedures to guide the aircraft out of the terminal geofence.

And the planned track of the candidate departure program comprises a plurality of route points and navigation points of each departure program, each route point respectively represents a coordinate point which the corresponding flight passes through, the matching degree of the planned track and the historical track of the first flight is calculated through the route points, and the target departure program with high matching degree is screened out.

In one embodiment, the process of calculating the degree of match is discussed. Selecting a target departure program from the candidate departure programs according to the matching degree of the planned trajectory of the candidate departure program and the historical trajectory of the first flight, wherein the target departure program comprises the following steps: judging whether each point in the planned track of the candidate departure program is a matching point according to whether each point in the planned track is matched with the historical waypoint of the first flight; calculating the matching degree of the planned track and the historical track based on the number of matching points in the planned track of the candidate departure program; and selecting a target departure program from the candidate departure programs according to the matching degree of the planned trajectory and the historical trajectory.

And step 208, generating a flight plan of the second flight based on the takeoff runway and the target departure procedure of the second flight.

Because the takeoff runway and the target departure program of the second flight can be calculated based on the neural network model, the calculation process is carried out by designing and constructing a prediction model for the flight takeoff runway and the departure program by using an artificial intelligence algorithm based on the historical track of the flight, and prediction reference of the takeoff runway and the departure program is provided for assisting the signatory to make a flight plan, so that the fixed selection of the departure program of the current terminal area is broken, and the accuracy and the flexibility of the flight plan can be effectively improved.

Flight planning refers to providing information to an air traffic service unit that a flight completes a flight. The flight plan may specifically be a parameter of any phase of taxiing, takeoff, climbing, cruising, approaching, descending, landing, taxiing, which may be speed, altitude, horizontal distance, etc. In the present embodiment, the flight plan is mainly a flight plan for the takeoff, climb and partial cruise phases.

In the flight plan generating method of the flight, according to the historical track of the first flight, a takeoff runway of a second flight is selected from candidate runways, and a certain specific rule of each airport on the use runway is found out; selecting a target departure program from the candidate departure programs according to the matching degree of the planned track of the candidate departure program and the historical track of the first flight, so that the second flight is released without adopting the departure program with the maximum distance in the departure direction of the airline; therefore, based on the takeoff runway and the target departure procedure of the second flight, the flight plan can be more accurate, the risk of overweight landing is avoided to a certain extent, and the extra filling waste of fuel is avoided.

In one embodiment, as shown in fig. 3, a flight plan generating method for flights is provided, which is illustrated from another perspective by taking the method as an example applied to the terminal 102 in fig. 1, and includes the following steps:

step 302, obtaining a historical track of the first flight and a candidate runway of the second flight.

In one embodiment, obtaining the historical track of the first flight and the candidate runway of the second flight comprises: sequentially selecting route points from the original historical track of the first flight; verifying the waypoints based on the height data of the waypoints; generating a verified historical track according to the verified waypoints; and acquiring a candidate runway of the second flight according to the verified historical track.

The original historical track can be historical track data verified according to a plurality of data sources, or historical track data of a specific source. When the number of the second flights is multiple, sequencing each flight according to the time sequence, and selecting the waypoints in sequence. And with the assistance of the protective verification of the height data, the data reliability of the second flight can be ensured by acquiring the candidate runway of the second flight according to the verified historical track. After the verified historical track is obtained, the candidate runway of the second flight can be obtained more accurately.

And step 304, selecting a takeoff runway of the second flight from the candidate runways according to the historical track of the first flight.

Step 302-step 304, refer to the embodiment of step 202-step 204.

And step 306, judging whether each point in the planned track of the candidate departure procedure is a matching point according to whether each point in the planned track is matched with the historical waypoint of the first flight.

In one embodiment, determining whether each point in the planned trajectory of the candidate departure procedure is a matching point according to whether each point in the planned trajectory matches a historical waypoint of the first flight comprises:

if the historical number of waypoints of the first flight in the first matching range is greater than the first preset number of waypoints, the target point in the planned trajectory of the candidate departure program is a matching point;

if the historical waypoint number of the first flight in the first matching range is less than or equal to the preset waypoint number, judging whether the target point is a matching point according to whether the historical waypoint of the first flight exists in the second matching range of each point in the planned track of the candidate departure program; the second matching range is larger than the first matching range;

if the historical waypoint number of the first flight in the first matching range is larger than the first preset waypoint number and smaller than or equal to the second preset waypoint number and the departure point of the planned track of the candidate departure program is different from the historical departure point of the first flight, judging whether the target point is a matching point according to whether the historical waypoint of the first flight exists in the third matching range of each point in the planned track of the candidate departure program; the third matching range is greater than the second matching range.

The radiuses of the first matching range, the second matching range and the third matching range are increased in sequence, and the use conditions of the matching ranges are different, so that whether each point is matched or not can be determined more accurately, and the matching degree can be calculated more accurately. Wherein the first matching range is 0.5 nautical miles, the second matching range is 3 nautical miles, the third matching range is 5.5 nautical miles, and the error range of the third matching range is 0.5 nautical miles.

And 308, calculating the matching degree of the planned track and the historical track based on the number of the matching points in the planned track of the candidate departure program.

And 310, selecting a target departure procedure from the candidate departure procedures according to the matching degree of the planned trajectory and the historical trajectory.

In one embodiment, the degree of match is determined based on the number of points of match of the planned trajectory with the historical trajectory of the first flight and the departure point; correspondingly, selecting a target departure program from the candidate departure programs according to the matching degree of the plan track and the historical track, wherein the target departure program comprises the following steps:

when a plurality of candidate departure programs with the maximum number of matching points exist, acquiring historical departure points of the first flight and departure points of planned tracks of the candidate departure programs with the maximum number of matching points; judging whether the departure point of the planned track is consistent with the historical departure point of the first flight;

if yes, selecting a target departure program according to the candidate departure programs with the consistent historical departure points of the first flight; when the candidate departure programs with the consistent historical departure points of the first flight are consistent, preferentially selecting the candidate departure programs as target departure programs; in addition, the candidate departure program with the PBN identification can also be preferentially selected as the target departure program.

If not, selecting a target departure program from the candidate departure programs according to the flight departure distance between the historical departure point of the first flight and the departure airport and the planned departure distance between the planned departure point of each candidate departure program and the departure airport.

When the number of matching points of the planned track and the historical track of the first flight is the maximum value, and the departure point of the planned track is consistent with the historical departure point, obtaining a target departure program with the highest matching degree with the second flight; and when the number of the matching points of the planned track and the historical track of the first flight is the maximum value and the departure point of the planned track is inconsistent with the historical departure point, calculating the actual departure distance and judging whether the actual departure point is consistent with the planned departure point.

Specifically, according to the flight departure distance between the historical departure point and the departure airport of the first flight and the planned departure distance between the planned departure point and the departure airport of each candidate departure program, a selected target departure program is selected from the candidate departure programs, and the method comprises the following steps:

calculating a first planned departure distance based on the first candidate departure procedure, and calculating a second planned departure distance based on the second candidate departure procedure;

when the flight departure distance is smaller than the first planned departure distance and the flight departure distance is smaller than the second planned departure distance, selecting a second candidate departure program as a target departure program;

when the flight departure distance is greater than the first planned departure distance and the flight departure distance is greater than the second planned departure distance, selecting a first candidate departure program as a target departure program;

when the difference value of the first planned departure distance and the second planned departure distance exceeds the planned departure distance range and the flight departure distance is between the first planned departure distance and the second planned departure distance, comparing the second planned departure distance with the planned departure distance range based on the flight departure distance; if the current value is less than the preset threshold value, selecting a second candidate field departure program as a target field departure program; if so, selecting a first candidate field departure program as a target field departure program;

when the difference value between the first planned departure distance and the second planned departure distance is smaller than the planned departure distance range and the flight departure distance is positioned between the first planned departure distance and the second planned departure distance, comparing the first difference value between the flight departure distance and the first planned departure distance with the second difference value between the flight departure distance and the second planned departure distance; and selecting a corresponding candidate off-field program according to the smaller difference value of the first difference value and the second difference value.

Wherein, according to the smaller one of the first difference and the second difference, selecting the corresponding candidate departure procedure refers to: when the first difference is smaller than the second difference, selecting a first candidate departure program as a target departure program; and when the first difference is larger than the second difference, selecting a second candidate field departure program as the target field departure program.

In order to more clearly describe the process of selecting a selected target departure program from the candidate departure programs, the flight departure distance is used as the L distance, the first candidate departure program is determined as the A program, the first planned departure distance is the A distance, the second candidate departure program is determined as the B program, and the first planned departure distance is the B distance.

Correspondingly, when the distance L is smaller than the distance A and the distance L is smaller than the distance B, selecting the program B as a target off-field program;

when the distance L is greater than the distance A and the distance L is greater than the distance B, selecting the program A as a target field departure program;

when the difference value of the distance A and the distance B is larger than the planned distance range (20 nautical miles) from the field and the distance L is located between the distance A and the distance B, comparing the sum of the distance B and the planned distance range (20 nautical miles) from the field based on the distance L; if the value is less than the preset value, the program B is a target off-field program; if the value is larger than the threshold value, the program A is a target field leaving program;

and when the difference value of the distance A and the distance B is smaller than the planned distance range (20 nautical miles), the distance L is positioned between the distance A and the distance B, and the actual distance L is closer to the distance A and the distance B, taking the distance program corresponding to the closer distance as the target distance program code.

Further, in order to guarantee the safety of the second flight, whether the candidate departure program is suitable to be used as the target departure program of the second flight is judged by judging whether the candidate departure program deviates from the target departure program of the second flight; based on this, the method further comprises:

when the departure airport of the second flight is the target airport and the candidate departure program with the maximum number of the matching points is less than or equal to the threshold value of the number of the candidate departure programs, determining that the candidate departure program deviates from the target departure program of the second flight;

when the departure airport of the second flight is the target airport, the number of the matching points of the candidate departure program with the maximum number of the matching points is less than or equal to the threshold value of the number of the matching points, and the departure point of the corresponding planned trajectory is inconsistent with the historical departure point of the first flight, determining that the candidate departure program deviates from the target departure program of the second flight;

and when the departure airport of the second flight is not the target airport, judging whether the candidate departure program deviates from the target departure program of the second flight according to whether the proportion of the number of the matching points occupying the historical departure points of the first flight exceeds the corresponding threshold value of the number of the matching points.

Specifically, the departure airport is an airport where the second flight takes off, and when the departure airport constructs the neural network model according to the flight, the target airport is obtained. The target airport can collect the data of the characteristic items according to the neural network model, and then forecast according to the collected data so as to accurately judge whether each candidate departure program can be used as a target departure program of the second flight. And when the departure airport is not the target airport, judging whether the candidate departure program deviates from the target departure program of the second flight according to the matching degree of the number of the matching points.

In one embodiment, the target airport is taken as the airport of a building, the number of matching points of each airport is i, and i is an integer; the maximum value of the number of the matching points is imax, the threshold value of the number of the candidate off-field programs is 1, and the threshold value of the number of the matching points is 2; correspondingly, it includes:

when the departure airport of the second flight is the airport of the building door, and the candidate departure program of imax is less than or equal to 1, determining that the candidate departure program deviates from the target departure program of the second flight, and marking the candidate departure program as 'ATC DIRECT';

when the departure airport of the second flight is an airport of a building door, the candidate departure programs of imax are less than or equal to 2 and departure points are inconsistent, the second flight is determined as a target departure program of the second flight, and each candidate departure program is marked as 'ATC DIRECT';

and when the departure airport of the second flight is not the airport of the building door, judging according to the proportion that i occupies the historical departure point of the first flight, if the proportion of the matching point to the planning point is less than 0.7, determining that the second flight deviates from the target departure program, and recording each candidate departure program as 'ATC DIRECT'. And if the ratio of the matching points to the planning points is more than 0.7, determining that the candidate departure program does not deviate from the target departure program of the second flight, and selecting the target departure program of the second flight from the candidate departure programs according to the matching degree of the number of the matching points. The target departure procedure deviating from the second flight means that the target departure procedure of the second flight does not exist in the candidate departure procedures.

In step 312, a flight plan for the second flight is generated based on the takeoff runway and the target departure procedure for the second flight.

Step 312 may refer to an embodiment of step 208.

The method further comprises the following steps: according to the characteristic items, resampling and randomly splitting the acquired historical data of the first flight; optimizing a prediction model of the target off-field program according to the data of the re-sampled and randomly split feature items; and the optimized prediction model of the target departure program is used for predicting the target departure program.

In one embodiment, the significance of the predictive model is more clearly understood from the application scenario.

The balance of operation safety and oil-saving benefit is always a difficult point for civil aviation development. According to statistics, in 2020, the fuel oil is consumed by 2500 million tons in the whole civil aviation in an accumulated mode, so that the carbon emission is 8000 million tons, and how to realize the overall development of the aviation transportation safety and the green low-carbon integration is a major challenge faced by aviation departments. However, documents indicate that the technology of the civil aviation is deeply integrated with new technologies such as artificial intelligence, big data, internet of things and the like, and the technology innovation of the civil aviation industry is realized by using a digital technology. After years of information operation, the navigation department has mass operation data, realizes data driving to carry out intelligent decision, excavates potential fuel-saving space on the premise of ensuring flight safety, obtains an optimal solution of safety margin and fuel-saving benefit balance, and is an action direction explored by people.

The main defects of the current analysis of flight take-off runway and departure programs are low accuracy, which is reflected in low data integration efficiency, poor reliability of an analysis mode, and the release system only can adopt a single curing route. In order to ensure flight safety, except for part of routes subjected to risk assessment, the departure procedure with the largest distance in the departure direction of the route is adopted for the release of all flights of the airline company. However, according to actual operation conditions for many years, the situation that the train has to operate by adopting the departure program with the largest distance is rare, a more effective and accurate departure program cannot be provided for a unit, additional fuel filling waste is caused, and in some cases, flights have the risk of overweight landing, namely, the current departure selection mode is not optimal for operation safety or fuel saving benefit.

According to research, the selection of the departure procedure mainly has high relevance with the conditions of a takeoff/landing airport and airway meteorological conditions, a first departure point, the current use condition of a takeoff runway, a control command condition, third-party activities, airway congestion conditions and the like, and belongs to a complex combined decision problem.

Therefore, the scheme needs to be independently modeled aiming at the prediction of the take-off runway and the departure procedure, firstly, the take-off runway and the departure procedure of a first flight are respectively determined, then, the take-off runway and the departure procedure are spliced with the flight plan, the navigation information, the weather and weather information and other information of a second flight to form two data sets, the data sets are brought into a machine learning algorithm to train a prediction model, and finally, the model is released to service. Therefore, through the calculation process related to the artificial intelligence algorithm and the historical operation big data of the first flight, a prediction model is designed and constructed for a flight take-off runway and an departure program, prediction reference of the take-off runway and the departure program is provided for the dispatching personnel to make a flight plan, and therefore the fixed selection of the departure program in the current terminal area is broken through, the accuracy and the flexibility of the flight plan can be effectively improved, and various problems in the application scene are solved. The research result can also be timely popularized to civil aviation control units, auxiliary reference is provided for control scheme making and decision making, the reasonable utilization rate of terminal area airspace resources can be effectively improved, and the refined operation level is improved.

Further, as shown in fig. 4, steps of the prediction model of the takeoff runway are introduced, which include the following steps:

step 401, acquiring historical track GNSS coordinate data in a time period from driving to closing according to the flying-in date and a take-off airport of each flight;

step 402, screening the historical tracks according to a takeoff place, sorting the screened historical tracks according to time, and sequentially processing the historical tracks sorted according to the time according to the following steps 3-13, wherein the historical tracks in the processing are the historical tracks of the first flight;

step 403, finding out a coordinate point with a height different from zero and adjacent coordinate points of the coordinate point from the historical track of the first flight, and marking the coordinate points as a first coordinate point P1 and a second coordinate point P2 in time sequence; wherein, the adjacent coordinate point of the coordinate point is preferably the coordinate point of the previous time point of the coordinate point.

Step 404, obtaining runway data from an interface according to airport four-character codes (assuming that 2X runway exits are obtained);

step 405, calculating the distance between the second coordinate point P2 and the longitude and latitude coordinates of the runway threshold, and leaving X runway thresholds (screening out the same side runway) with the closer distance;

step 406, if the height of the first coordinate point P1 is zero, the first coordinate point P1 is a point on the runway, an azimuth difference value Angle _0 between P1 and P2 is calculated, an azimuth difference value Angle _ X between P1 and the runway opening of each runway opening is calculated, and a runway opening N with an Angle closest to Angle _0 is obtained;

and 407, if the height of the P1 is greater than zero, calculating to obtain the runway threshold N closest to the P1. And N is the closest runway opening when the airplane leaves the runway.

In step 408, the second flight actually flies into the opposite side of the runway port N, and N' is obtained by +18 and L/R transposition.

Further, the method also includes a scheme for correcting the feature item data of the first flight and the feature item data of the second flight, including:

409, taking 2 flights at the latest takeoff moment within 15min before the instruction sending moment, determining as error data if the feature item data are inconsistent, and correcting according to the characteristic item data which are consistent front and back;

step 410, if the number of enough flights to take off exceeds 15min, respectively taking 2 flights at the latest take-off/landing time within 15min forward and 15min backward, if the flight numbers are inconsistent, determining error data, and correcting according to the characteristic item data which is consistent front and back;

step 411, if no enough flights exist in more than 15min, respectively taking 2 flights at the latest takeoff/landing time within 30min forwards and 30min backwards, if the flights are not consistent, determining error data, and correcting according to consistent characteristic item data before and after; if not, the FA data (flight tracking data) is taken for correction;

step 412, if not, selecting FA data;

and step 413, outputting a takeoff runway of the second flight.

Further, as shown in fig. 5, steps of the prediction model of the departure procedure are introduced, which include:

and step 501, collecting data of each point in flight trajectories of the flights. Each point data source comprises one or more of airborne QAR data owned by the airline company, civil aviation information sharing data and ADS-B data of FA purchased through GMP;

502, carrying out historical track on airborne QAR data, civil aviation information sharing data and FA data, wherein the historical track comprises longitude and latitude data of all coordinate points sequenced by time data and height data of the coordinate points used for verifying the longitude and latitude data;

step 503, sequencing the original historical track of each flight according to time, sequentially selecting waypoints from the historical tracks sequenced according to time, and simultaneously assisting with protective verification of the height data to ensure the reliability of the time data and the historical tracks to obtain verified historical tracks;

step 504, the verified historical tracks of the multiple data sources are mutually verified, unreliable data sources are eliminated, and available data are calculated through an off-field program matching algorithm;

4.1 according to all the candidate departure programs, taking the waypoints of the corresponding planned trajectories one by one, and if the historical waypoint of the first flight exists in the first matching range (such as 0.5 nautical miles) of the target point in each waypoint, determining that the target point is the matching point.

4.2, 4.1, the detailed flow of matching point confirmation includes:

4.2.1. if the historical number of waypoints of the first flight, which exist in the first matching range, of the target point is less than or equal to the preset number of waypoints (such as 1), changing the coverage circle from the first matching range to a second matching range (3 NM);

4.2.2. if the historical waypoint number of the first flight in the first matching range is larger than a first preset waypoint number (such as 1) and smaller than or equal to a second preset waypoint number (such as 3), and the departure point of the planned trajectory of the candidate departure program is different from the historical departure point of the first flight, the coverage circle is changed from the first matching range to a third matching range (5.5 NM); wherein 0.5NM is the error range; consulted regulatory bodies, 5NM is the more commonly used bias data.

4.3 counting all the candidate departure programs, selecting the departure point with the most matching points as the target departure program, and taking the departure point corresponding to the candidate departure program as the actual departure point of the second flight. And recording the distance from the candidate distance from the field program as the planned distance from the field corresponding to the target distance from the field program. The distance between the actual departure point of the second flight and the historical departure point of the first flight (often the last QAR point) is calculated and is reported as the departure point difference.

4.4, in 4.3, the detailed judgment flow of the program with the largest number of matching points includes:

4.4.1. if the candidate departure program with the maximum number of the matching points is less than or equal to the threshold value (1) of the number of the candidate departure programs, the matching is not carried out, the candidate departure program is determined to deviate from the target departure program of the second flight, and the candidate departure program is marked as 'ATC DIRECT';

4.4.2. if the candidate departure program with the maximum number of the matching points is larger than the threshold value (1) of the number of the candidate departure programs, calculating an actual departure distance, and judging whether the departure point of the planned trajectory is consistent with the historical departure point of the first flight; if the departure programs are consistent, the target departure program is determined, and if the departure programs are not consistent, the candidate departure program is determined to deviate from the target departure program of the second flight;

4.4.3. when the number of the matching points of the candidate departure program with the maximum number of the matching points is less than or equal to the threshold (2) of the number of the matching points, and the departure point of the planned track is inconsistent with the historical departure point of the first flight, determining that the candidate departure program deviates from the target departure program of the second flight, and marking the candidate departure program as 'ATC DIRECT';

4.4.4. and when the departure airport is not the target airport (such as an airport of a building door), judging whether the ratio of the number of the matching points occupying the historical departure point of the first flight exceeds the corresponding threshold value of the number of the matching points, and if the ratio of the number of the matching points to the planning points is less than 0.7, determining that the candidate departure program deviates from the target departure program of the second flight.

4.5 and 4.3, when the candidate departure programs with the maximum number of the matching points are multiple, preferentially selecting the programs consistent with the departure points of the planning program; programs with PBN identification are preferably selected. And if the conditions cannot be met, judging according to distance calculation.

In 4.6 and 4.5, the specific step of judging according to the flight departure distance is that the flight departure distance is taken as an L distance, the first candidate departure program is determined as a program a, the first planned departure distance is an a distance, the second candidate departure program is determined as a program B, and the first planned departure distance is a distance B:

4.6.1. when the L distance is smaller than the A distance and the L distance is smaller than the B distance, selecting a code of the program B as a code of a target off-field program;

4.6.2. when the distance L is greater than the distance A and the distance L is greater than the distance B, selecting the code of the program A as the code of the target field departure program;

4.6.3. when the difference value of the distance A and the distance B is larger than the planned distance range (20 nautical miles) from the field and the distance L is located between the distance A and the distance B, comparing the sum of the distance B and the planned distance range (20 nautical miles) from the field based on the distance L; if the current value is less than the preset value, the code of the program B is the code of the target off-field program; if the number of the target departure program is larger than the number of the target departure program, the code of the program A is the code of the target departure program;

4.6.4. and when the difference value of the distance A and the distance B is smaller than the planned distance range (20 nautical miles), the distance L is positioned between the distance A and the distance B, and the distance L is closer to the distance A and the distance B, taking the distance program corresponding to the closer distance as the target distance program code.

And 505, predicting a target departure procedure as an actual departure procedure of the second flight.

In one embodiment, a plurality of feature items of a predictive model are described, and data is collected according to the data of the feature items for realizing modeling. The target item predicted by the prediction model is at least one of a takeoff runway and a target departure procedure of the second flight;

wherein, the data of the characteristic item is related to the schedule information related to the flight, and comprises the following steps: flight date, airline, departure/arrival airport, estimated departure time, airplane-on-hold, etc.; the data acquisition of the characteristic items relates to navigation information, and comprises the following steps: total airport flow and port entry and exit flow; the data of the characteristic items relate to weather and meteorological information, including in METAR and TAF messages: wind speed, wind direction, visibility, cloud base height, cloud cover, special meteorological phenomena and the like. The model feature items and their preset formats are shown in table 1.

TABLE 1

Further, as shown in fig. 6, a training method of the prediction model is explained.

Considering that most of the influence variables in the take-off runway and departure program prediction are discrete numerical values or category variables, an Extreme Tree (ET) algorithm in the field of machine learning is very suitable for processing discrete variable data, and by introducing a resampling technology and a random splitting strategy, overfitting can be effectively avoided, excellent performance is shown when large-scale data volume and high-dimensional characteristics are processed, and the method has good generalization performance and high precision. Therefore, an ET algorithm is adopted as a base model, data calculated by the base model relate to vectors which comprise information such as flight plans, navigation information, weather meteorology and the like and are represented in a numerical characterization mode, and data and corresponding processes which are combined with the vectors and calculated by a take-off runway and a target departure program of a second flight are obtained to respectively obtain prediction models of the take-off runway and the departure program, and the specific steps are as follows:

step 601: acquiring first flight take-off track related data (ACTRWY) and departure program related data (ACTPGM) of a specified airport according to the steps corresponding to the prediction models of the take-off track and the departure program respectively, and generating data sets A1 and A2 serving as target columns of the prediction models;

step 602: collecting flight plan, navigation information, weather and weather information and other information of a first flight, integrating according to a preset format of the characteristic items, and creating data sets D1 and D2 as characteristic items of the model;

step 603: respectively merging the A1 and the A2 with the D1 and the D2 according to flight IDs, updating the data sets D1 and D2, performing data preprocessing including data integration, data cleaning and feature construction, and unique hot coding, and eliminating problem data to obtain an updated data set;

step 604: respectively training a take-off runway prediction model and an departure program prediction model by utilizing an ET algorithm based on the updated data sets D1 and D2, and performing five-fold cross inspection and hyper-parameter optimization;

step 605: respectively outputting a prediction model with the optimal comprehensive score as a take-off runway prediction model and an departure program prediction model;

step 606: issuing the takeoff runway prediction model and the departure program prediction model output in the step 605 to serve, providing API (application programming interface) for calling of an application system, and inputting data corresponding to the second flight into the called model according to the preset format of the feature item data during calling.

The data corresponding to the second flight may be updated feature item data obtained based on the first flight, or may be updated feature item data obtained based on the second flight.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application further provides a flight plan generating device for implementing the flight plan generating method for flights. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the method, so the specific limitations in the embodiment of the flight plan generating device for one or more flights provided below can be referred to the limitations on the flight plan generating method for flights, and are not described herein again.

In one embodiment, as shown in fig. 8, there is provided a flight plan generating apparatus for an airline flight, including: a data acquisition module 702, a runway selection module 704, an departure procedure selection module 706, and a plan generation module 708, wherein:

a data obtaining module 702, configured to obtain a historical track of a first flight and a candidate runway of a second flight;

a runway selection module 704, configured to select a takeoff runway of the second flight from the candidate runways according to the historical trajectory of the first flight;

an departure program selecting module 706, configured to select a target departure program from the candidate departure programs according to a matching degree between a planned trajectory of the candidate departure program and a historical trajectory of the first flight;

a plan generating module 708, configured to generate a flight plan of the second flight based on the takeoff runway of the second flight and the target departure program.

In one embodiment, the historical trajectory of the first flight includes a first coordinate point and a second coordinate point that are different in height and are obtained in chronological order; the runway selection module 704 includes:

the angle query unit is used for querying the runway threshold azimuth angle difference value of the first coordinate point and the candidate runway according to the azimuth angle difference value between the first coordinate point and the second coordinate point when the height of the first coordinate point is a preset height value, so as to obtain a runway azimuth query result;

the runway calculating unit is used for searching a candidate runway corresponding to the runway azimuth angle query result from the candidate runway;

and the runway selecting unit is used for selecting the runway on the opposite side as the take-off runway of the second flight according to the candidate runway corresponding to the runway azimuth angle query result.

In one embodiment, the runway selection module 704 further comprises:

the distance comparison unit is used for comparing the distance between the first coordinate point and the runway opening of each candidate runway to obtain a distance comparison result when the height of the first coordinate point and the height of the runway are greater than the preset height value;

a runway screening unit for screening the candidate runways based on the distance comparison result;

and the take-off runway selecting unit is used for selecting the runways on the opposite sides of the screened candidate runways as take-off runways of the second flight.

In one embodiment, the data acquisition module 702 is configured to:

screening the preset runways on the same side of the track of the first flight on the basis of the distance between the second coordinate point and the runway opening of each preset runway;

In one embodiment, the data acquisition module 702 is configured to:

verifying the waypoints based on the height data of the waypoints;

generating a verified historical track according to the verified waypoints;

and acquiring a candidate runway of the second flight according to the verified historical track.

In one embodiment, the off-site program selection module 706 includes:

the matching point judging unit is used for judging whether each point in the planned track of the candidate departure program is a matching point according to whether each point in the planned track is matched with the historical waypoint of the first flight;

the matching degree calculation unit is used for calculating the matching degree of the planned track and the historical track based on the number of matching points in the planned track of the candidate departure program;

and the target departure program selecting unit is used for selecting a target departure program from the candidate departure programs according to the matching degree of the plan track and the historical track.

In an embodiment, the matching point determining unit is specifically configured to:

In one embodiment, the degree of matching is determined based on the number of points of matching of the planned trajectory with the historical trajectory of the first flight and departure points; the target departure program selecting unit is specifically configured to:

when a plurality of candidate departure programs with the maximum number of the matching points exist, acquiring historical departure points of the first flight and departure points of planned trajectories of the candidate departure programs with the maximum number of the matching points;

In one embodiment, the target departure procedure selecting unit is further configured to:

In one embodiment, the apparatus further comprises a training module of the predictive model, the training module to:

and the optimized prediction model of the target departure program is used for predicting the target departure program.

The modules in the flight plan generating device for the flight can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer apparatus includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the running of computer programs in the non-volatile storage medium. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a flight plan generating method for flights. The display unit of the computer equipment is used for forming a visual and visible picture, and can be a display screen, a projection device or a virtual reality imaging device, the display screen can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant country and region.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, databases, or other media used in the embodiments provided herein can include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the various embodiments provided herein may be, without limitation, general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, or the like.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method of generating a flight plan for a flight, the method comprising:

selecting a take-off runway of the second flight from the candidate runways according to the historical track of the first flight;

and generating a flight plan of the second flight based on the take-off runway of the second flight and the target departure program.

2. The method of claim 1, wherein the historical trajectory of the first flight comprises a first coordinate point and a second coordinate point that are different in height and are obtained chronologically; selecting a takeoff runway of the second flight from the candidate runways according to the historical track of the first flight, wherein the selecting comprises the following steps:

3. The method of claim 2, wherein selecting a take-off runway for the second flight from the candidate runways based on the historical trajectory of the first flight, further comprises:

screening the candidate runways based on the distance comparison result;

4. The method of claim 1, wherein obtaining the historical track of the first flight and the candidate runway of the second flight comprises:

5. The method of claim 1, wherein obtaining the historical trajectory for the first flight and the candidate runway for the second flight comprises:

verifying the waypoints based on the height data of the waypoints;

generating a verified historical track according to the verified waypoints;

6. The method of claim 1, wherein selecting a target departure procedure from the candidate departure procedures according to a degree of matching between a planned trajectory of the candidate departure procedure and a historical trajectory of the first flight comprises:

7. The method of claim 6, wherein determining whether each point in the planned trajectory of the candidate departure procedure matches a historical waypoint of the first flight comprises:

8. The method of claim 6, wherein the degree of match is determined based on a number of points of match of the planned trajectory with a historical trajectory of the first flight and a departure point; selecting a target departure procedure from the candidate departure procedures according to the matching degree of the planned trajectory and the historical trajectory, wherein the selecting step comprises the following steps:

judging whether the departure point of the planned track is consistent with the historical departure point of the first flight;

9. The method of claim 1, further comprising:

when the departure airport of the second flight is a target airport and the candidate departure program with the maximum number of matching points is less than or equal to the threshold value of the number of candidate departure programs, determining that the candidate departure program deviates from the target departure program of the second flight;

10. The method of claim 1, further comprising a training step of the predictive model, the training step comprising:

11. An apparatus for generating a flight plan for a flight, the apparatus comprising:

12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 10 when executing the computer program.

13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 10.