CN111626519A - Flight arrival time prediction method and device and electronic equipment - Google Patents
Flight arrival time prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN111626519A CN111626519A CN202010484433.4A CN202010484433A CN111626519A CN 111626519 A CN111626519 A CN 111626519A CN 202010484433 A CN202010484433 A CN 202010484433A CN 111626519 A CN111626519 A CN 111626519A
- Authority
- CN
- China
- Prior art keywords
- flight
- runway
- arrival
- inbound
- delayed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000003111 delayed effect Effects 0.000 claims abstract description 98
- 238000012706 support-vector machine Methods 0.000 claims abstract description 71
- 230000010006 flight Effects 0.000 claims abstract description 65
- 238000012360 testing method Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 description 6
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a flight arrival time prediction method, a flight arrival time prediction device and electronic equipment, wherein the method comprises the following steps: when the distance between the flight and the flight destination is determined to be smaller than a distance threshold value, acquiring flight information of the flight to be predicted, a flight departure place and a flight destination; determining an arrival direction when the flight arrives based on the flight departure place and the flight destination; processing flight information of the flights by using a support vector machine regression model for identifying delayed flights in the arrival direction to obtain a processing result; wherein when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival predicted time of the flight. The flight arrival time prediction method, the flight arrival time prediction device and the electronic equipment provided by the embodiment of the invention can greatly improve the accuracy of flight arrival time prediction.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a flight arrival time prediction method, a flight arrival time prediction device, electronic equipment and a computer readable storage medium.
Background
Currently, in airport operation support operation, flight arrival time needs to be predicted in order to prepare flight ground support services (such as refueling, tractor positioning and the like) in advance.
When predicting the arrival time of a flight, the arrival time of the flight is generally estimated using data such as the current distance from the airport of the flight and the historical arrival time of the flight.
The predicted flight arrival time is inaccurate.
Disclosure of Invention
To solve the above problems, embodiments of the present invention provide a flight arrival time prediction method, device, electronic device, and computer-readable storage medium.
In a first aspect, an embodiment of the present invention provides a flight arrival time prediction method, including:
when the distance between the flight and the flight destination is determined to be smaller than a distance threshold value, acquiring flight information of the flight to be predicted, a flight departure place and a flight destination;
determining an arrival direction of the flight when the flight arrives based on the flight departure place and the flight destination;
processing the flight information of the flight by using a support vector machine regression model for identifying delayed flights in the arrival direction to obtain a processing result; when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival predicted time of the flight.
In a second aspect, an embodiment of the present invention further provides a flight arrival time prediction apparatus, including:
the acquisition module is used for acquiring flight information, a flight departure place and a flight destination of a flight to be predicted when the distance between the flight and the flight destination is determined to be smaller than a distance threshold;
the determining module is used for determining the arrival direction of the flight when the flight arrives on the basis of the flight departure place and the flight destination;
and the processing module is used for processing the flight information of the flight by using a support vector machine regression model for identifying delayed flights in the inbound direction to obtain a processing result, wherein the processing result carries the first arrival prediction time of the flight when the processing result indicates that the flight is the delayed flight.
In a third aspect, the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the method in the first aspect.
In a fourth aspect, embodiments of the present invention also provide an electronic device, which includes a memory, a processor, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor to perform the steps of the method according to the first aspect.
In the solutions provided in the foregoing first to fourth aspects of the embodiments of the present invention, an inbound direction of a flight is determined, and flight information of the flight is processed by using a support vector machine regression model for identifying a delayed flight in the inbound direction to obtain a processing result, and when the processing result indicates that the flight is a delayed flight, the processing result carries a first arrival prediction time of the flight, and compared with a manner in which arrival time of the flight can be roughly predicted only by using data such as a current distance between the flight and an airport and a historical arrival time of the flight in the related art, the arrival time of the flight can be predicted by using a trained support vector machine regression model for identifying the delayed flight in the inbound direction, so that accuracy of predicting the arrival time of the flight can be greatly improved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating a flight arrival time prediction method provided in embodiment 1 of the present invention;
fig. 2 is a schematic structural diagram illustrating a flight arrival time prediction apparatus provided in embodiment 2 of the present invention;
fig. 3 shows a schematic structural diagram of an electronic device provided in embodiment 3 of the present invention.
Detailed Description
Currently, in airport operation support operation, flight arrival time needs to be predicted in order to prepare flight ground support services (such as refueling, tractor positioning and the like) in advance. When predicting the arrival time of a flight, the arrival time of the flight is generally estimated using data such as the current distance from the airport of the flight and the historical arrival time of the flight. Fewer factors are considered, resulting in inaccurate predicted flight arrival times.
In order to solve the above technical problems, embodiments of the present application provide a flight arrival time prediction method, apparatus, electronic device, and computer-readable storage medium, where flight arrival time is predicted by using a supervised learning classification algorithm based on a theory and an algorithm of machine learning and rich historical flight arrival information, so as to improve accuracy of predicting flight arrival time; and moreover, on the basis of the existing statistical data of the flight sliding history, the prediction of the arrival time and the moving path of the flight from the runway to the target stand-off position is realized, and further calculation is made for the advance preparation of ground guarantee work, so that the prediction result is relatively accurate and reliable.
Based on this, according to the flight arrival time prediction method, the flight arrival time prediction device, the electronic device, and the computer-readable storage medium provided in this embodiment, the arrival direction of a flight is determined, flight information of the flight is processed by using a support vector machine regression model for identifying a delayed flight in the arrival direction, so as to obtain a processing result, and when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival prediction time of the flight, so that the arrival time of the flight can be predicted by using the trained support vector machine regression model for identifying the delayed flight in the arrival direction, and the accuracy of predicting the arrival time of the flight can be greatly improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
Example 1
The main execution body of the flight arrival time prediction method proposed by the present embodiment is a server.
The server may use any computing device capable of predicting the flight arrival time in the prior art, and details are not repeated here.
Since the flight arrival time prediction method proposed in this embodiment needs to use a trained support vector machine regression model for identifying delayed flights, before describing the flight arrival time prediction method described in the following steps 100 to 104, the flight arrival time prediction method proposed in this embodiment describes how to train a support vector machine regression model for identifying delayed flights first:
(1) acquiring flight track data of delayed flights in the same inbound direction;
(2) dividing the acquired flight trajectory data into a first part of flight trajectories which serve as a training data set of a regression model of a support vector machine and a second part of flight trajectories which serve as a test data set of the regression model of the support vector machine;
(3) when the test result indicates that the trained support vector machine regression model cannot identify all second part flight tracks as flight tracks of delayed flights, inputting the first part flight tracks into the support vector machine regression model, and training the support vector machine regression model;
(4) testing the second part of flight trajectories by using the trained support vector machine regression model to obtain a test result;
(5) and when the test result indicates that the trained support vector machine regression model can identify all the second part flight trajectories as the air flight trajectories of delayed flights, determining that the trained support vector machine regression model is the support vector machine regression model for identifying the delayed flights in the inbound direction.
In the step (1), since flight path data of delayed flights in different inbound directions are different and flight path data in the same inbound direction are similar, a support vector machine regression model for identifying delayed flights in different inbound directions needs to be obtained.
In order to train the regression model of the support vector machine for identifying delayed flights in different inbound directions, the flight trajectory data of the delayed flight in each inbound direction in different inbound directions can be obtained from the historical delayed flight data table stored in the server.
The flight trajectory data comprises: flight identification, flight origin, flight destination, longitude data, latitude data, altitude data, actual landing time, flight landing duration, and inbound runway identification.
The server can determine the inbound direction of the delayed flight according to the flight departure place and the flight destination recorded in the flight path data, and classify the flight path data of the delayed flight with the same inbound direction.
When the inbound direction of the delayed flight is determined, the inbound direction of the delayed flight can be determined according to the position relationship between the departure place and the destination of the flight.
In one embodiment, when the origin of the delayed flight is northwest of the destination of the delayed flight, then the server may determine that the inbound direction of the delayed flight is northwest.
The longitude data, the latitude data and the altitude data refer to the longitude data, the latitude data and the altitude data of the position of the delayed flight, which are acquired by the server when the server determines that the distance from the delayed flight to the destination of the flight is less than the distance threshold according to the position information sent by the delayed flight.
The distance threshold may be any distance between 300 km and 500 km, which is not described in detail herein.
The flight landing time length is used for representing the time length from the time point when the distance between the flight and the flight destination is less than the distance threshold value to the time point when the flight falls to the runway.
The actual landing time is used for representing the time point of the flight landing on the runway.
After the classification of the flight path data of the delayed flights with the same arrival direction is completed, the flight path data of the delayed flights with each arrival direction can be obtained, so that the flight path data of the delayed flights with each arrival direction is respectively input into the support vector machine regression model for processing, and the support vector machine regression model for identifying the delayed flights with each arrival direction can be respectively obtained.
After the flight path data of the delayed flights in each inbound direction is obtained through the step (1), the following steps (2) to (4) can be continuously executed, and the flight path data of the delayed flights in each same inbound direction in each inbound direction is processed by using a support vector machine regression model to respectively obtain the support vector machine regression model for identifying the delayed flights in each inbound direction.
In the step (2), in one embodiment, the first part of the flight path of the training data set of the regression model of the support vector machine may include 80% of the flight path data of the delayed flights in the same inbound direction; the second part of the flight path of the test data set, which is a regression model of the support vector machine, may include 20% of the flight path data of the delayed flights in the same inbound direction.
In the step (3), the first part of flight trajectory is input into a support vector machine regression model, and a specific process of training the support vector machine regression model is the prior art, and is not described herein again.
The regression model of the support vector machine obtained after training can identify whether the flight with the same arrival direction as the input flight trajectory data is a delayed flight.
In the step (4), the trained support vector machine regression model is used to test the second part of flight trajectory, and the process of obtaining the test result is the prior art and is not described herein again.
After the support vector machine regression models for identifying delayed flights in each inbound direction are obtained through the training of the contents described in the above steps (1) to (5), the following steps 100 to 104 may be continuously performed to obtain the support vector machine regression models for identifying delayed flights in each inbound direction through the training to predict the arrival time of the flights.
Referring to a flowchart of a flight arrival time prediction method shown in fig. 1, the flight arrival time prediction method provided in this embodiment includes the following specific steps:
and step 100, when the distance between the flight and the flight destination is determined to be smaller than a distance threshold, acquiring flight information, a flight departure place and a flight destination of the flight to be predicted.
In the step 100, the flight information includes: flight identification, longitude data, latitude data, and altitude data of the flight, a second runway identification of the flight inbound runway, and a destination flight identification of the flight.
And the second runway identification of the flight arrival runway is used for indicating the runway identification of the runway which the flight should enter when landing.
And the destination station identifier of the flight is used for representing the station identifier of the station allocated to the flight by the airport.
The server can determine the distance between the flight and the flight destination according to the longitude data, the latitude data and the altitude data of the flight, and when the distance between the flight and the flight destination is smaller than a distance threshold value, the flight information, the flight departure place and the flight destination of the flight to be predicted are obtained.
The flight information of the flight is acquired in real time by the interaction of the server and the flight; and the flight origin and flight destination are obtained by the server from flight data stored by the server.
And 102, determining an arrival direction of the flight when the flight arrives according to the flight departure place and the flight destination.
In the step 102, the process of determining the inbound direction when the flight arrives at the port by the server is similar to the process of determining the inbound direction of the delayed flight by the server according to the flight departure place and the flight destination of the delayed flight described in the steps (1) to (5), and is not described again here.
104, processing flight information of the flights by using a support vector machine regression model for identifying delayed flights in the arrival direction to obtain a processing result; when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival predicted time of the flight.
In the step 104, a specific process of processing the flight information of the flight by using the support vector machine regression model for identifying delayed flights in the inbound direction is the prior art, and is not described herein again.
And the first arrival prediction time is used for representing the time length from the time point when the distance between the predicted flight and the flight destination is less than the distance threshold value to the time point when the flight falls to the runway when the flight is a delayed flight.
The above steps 100 to 104 only describe the process of predicting the arrival time of the flight when the flight is a delayed flight, and the following steps (1) to (3) are continued to describe the process of predicting the arrival time of the flight when the flight is a normal flight that is not a delayed flight:
(1) when the processing result indicates that the flight is a non-delayed flight, obtaining a longitude query range based on the longitude data and a longitude threshold, obtaining a latitude query range based on the latitude data and a latitude threshold, and obtaining an altitude query range based on the altitude data and an altitude threshold;
(2) inquiring the historical flight entering information meeting the longitude inquiry range, the latitude inquiry range and the altitude inquiry range; wherein the flight historical inbound information comprises: the first runway identification of the flight inbound runway and the flight landing time length of the inbound flight on the corresponding runway of the first runway identification are obtained; the flight landing time length is used for representing the time length from the time point when the distance between the flight and the flight destination is less than the distance threshold value to the time point when the flight lands on the runway;
(3) and calculating the median of the flight landing time length of the inbound flight on the runway corresponding to different first runway identifications, and obtaining the second arrival prediction time of the flight based on the median of the flight landing time length of the inbound flight on the runway corresponding to different first runway identifications.
In the step (1), the longitude threshold, the latitude threshold, and the altitude threshold are cached in the server.
The longitude query range is a longitude range from longitude data minus a longitude threshold to longitude data plus a longitude threshold.
The latitude query range is a range of longitude from latitude data minus a latitude threshold to latitude data plus a latitude threshold.
The altitude query range is the longitude range from the altitude data minus the altitude threshold to the altitude data plus the altitude threshold.
In one embodiment, the longitude threshold may be set to 0.25565 degrees; the latitude threshold may be set at 0.11225 degrees; the height threshold may be set to 209.3 meters.
In the step (2), the flight historical inbound information is cached in the database set by the server, and is used for storing the historical inbound information of the non-delayed flights.
The flight historical inbound information includes but is not limited to: the method comprises the steps of obtaining longitude data, latitude data and altitude data of flights, identifying a first runway of a flight arrival runway, identifying flight landing time of the arrival flights on the corresponding runway of the first runway, and moving paths and moving time of the flights from the arrival runway to a stand.
The longitude data, the latitude data and the altitude data of the flight are obtained by the server when the server determines that the distance between the flight and the destination of the flight is less than the distance threshold according to the position information sent by the flight.
The longitude data, latitude data and altitude data of the position of the flight are sent to the server by the flight.
The moving time length of the flights from the arrival runway to the stand is used for representing the time length between the landing time point of all landed flights on the arrival runway and the entering time point of the flights to the stand.
The moving path of the flight from the inbound runway to the stand refers to a moving track which is passed by all landed flights after the inbound runway lands to the flight entering the stand.
In order to query the flight history inbound information satisfying the longitude query range, the latitude query range, and the altitude query range, the flight history inbound information may be processed according to longitude data, latitude data, and altitude data of flights recorded in the flight history inbound information in the database, and the flight history inbound information in which the longitude data falls in the longitude query range, the latitude data falls in the longitude query range, and the altitude data falls in the longitude query range is used as the flight history inbound information satisfying the longitude query range, the latitude query range, and the altitude query range.
The first runway identification of the flight inbound runway is used for including runway identifications of all runways of the airport that the flight can land in the inbound.
In the step (3), after the flight history inbound information meeting the longitude query range, the latitude query range and the altitude query range is obtained through query, the flight landing durations in the flight history inbound information respectively having the same first runway identifier in the queried flight history inbound information are summed up to obtain a summed up calculation result, and then the median of the summed up calculation result is taken, so that the median of the flight landing durations of inbound flights on the runway corresponding to different first runway identifiers is calculated.
And performing accumulation calculation on the medians of the flight landing time lengths of the inbound flights on the runway corresponding to the different first runway identifications, so as to obtain median accumulation calculation results of the flight landing time lengths in all the runways, and then taking the average value of the median accumulation calculation results, so as to obtain the second arrival prediction time of the flights.
And the second arrival predicted time is used for indicating the time length from the time point when the distance between the predicted flight and the flight destination is less than the distance threshold value to the time point when the flight falls to the runway when the flight is a non-delayed flight.
Through the contents of the steps (1) to (3), the longitude query range, the latitude query range and the altitude query range are combined together to provide an airspace taking the position of the flight as the center, and the second arrival prediction time of the flight is obtained by using the flight landing time of the non-delayed flight passing through the airspace, so that the accuracy of the prediction of the landing time of the non-delayed flight can be improved.
In the related art, only the flight landing time length can be predicted, but the moving path and the moving time length from the landing runway to the set target position after the flight landing cannot be predicted. In order to predict a moving path and a moving duration from the landing runway to a set target position after the flight lands, the flight arrival time prediction method provided by this embodiment may further perform the following steps (1) to (5):
(1) inquiring the historical inbound information of the flights, wherein the inbound runway is a runway corresponding to the second runway identifier, and the stop of the flight is a stop corresponding to the target stop identifier;
(2) taking the most frequently used moving path in the searched moving paths in the flight historical inbound information as the moving path of the flight;
(3) calculating the average value of the moving time of the inquired flight historical arrival information record, and taking the calculated average value as the third arrival prediction time of the flight;
(4) when the flight is a delayed flight, obtaining a first predicted arrival time of the flight based on the first predicted arrival time and a third predicted arrival time;
(5) and when the flight is a non-delayed flight, obtaining a second predicted time of the flight based on the second arrival predicted time and a third arrival predicted time.
In the step (1), using the second runway identifier and the target airport identifier, querying the historical flight arrival information containing the arrival runway as the runway corresponding to the second runway identifier and the airport stop of the flight as the airport stop corresponding to the target airport identifier from the database.
In the step (2), the inquired flight historical inbound information refers to flight historical inbound information that includes that the inbound runway is a runway corresponding to the second runway identifier and that the stand of the flight is a stand corresponding to the target stand identifier.
In the step (3), the third arrival predicted time is used to indicate a time length for the predicted flight to move from the inbound runway to the target stand.
As can be seen from the description in the steps (1) to (3), the historical flight arrival information including that the arrival runway is a runway corresponding to the second runway identifier and that the flight stop of the flight is a stop corresponding to the target stop identifier is inquired from the historical flight arrival information in the database, the moving path with the most use times in the inquired historical flight arrival information is determined as the moving path of the predicted flight, and the average value of the moving time recorded by the inquired historical flight arrival information is used as the third arrival prediction time of the flight, so that the moving path and the moving time from the landing runway to the set target stop after the flight lands are predicted.
In the step (4), the first predicted time of the flight is obtained by the following formula:
the first predicted arrival time + the third predicted arrival time of the flight
In the step (5), the second predicted time of the flight is obtained by the following formula:
the second predicted arrival time + the third predicted arrival time of the flight
In summary, according to the flight arrival time prediction method provided in this embodiment, the inbound direction of a flight is determined, and the flight information of the flight is processed by using the support vector machine regression model for identifying a delayed flight in the inbound direction, so as to obtain a processing result, when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival prediction time of the flight, and compared with a manner that the arrival time of the flight can be roughly predicted only by using data such as the current distance from the airport and the historical arrival time of the flight in the related art, the arrival time of the flight can be predicted by using the trained support vector machine regression model for identifying the delayed flight in the inbound direction, so that the accuracy of predicting the arrival time of the flight can be greatly improved.
Example 2
The present embodiment proposes a flight arrival time prediction apparatus for executing the flight arrival time prediction method proposed in embodiment 1 above.
The flight arrival time prediction apparatus proposed in this embodiment includes:
an obtaining module 200, configured to obtain flight information of a flight to be predicted, a flight departure place and a flight destination when it is determined that a distance between the flight and the flight destination is smaller than a distance threshold;
a determining module 202, configured to determine an arrival direction of the flight when the flight arrives based on the flight departure place and the flight destination;
the processing module 204 is configured to process flight information of the flight by using a support vector machine regression model for identifying a delayed flight in the inbound direction to obtain a processing result, where the processing result carries a first arrival prediction time of the flight when the processing result indicates that the flight is the delayed flight.
The flight information includes: longitude data, latitude data, and altitude data for the flight.
The device, still include:
the first control module is used for obtaining a longitude query range based on the longitude data and a longitude threshold value, obtaining a latitude query range based on the latitude data and a latitude threshold value and obtaining an altitude query range based on the altitude data and an altitude threshold value when the processing result indicates that the flight is a non-delayed flight;
the second control module is used for inquiring the flight history inbound information meeting the longitude inquiry range, the latitude inquiry range and the altitude inquiry range; wherein the flight historical inbound information comprises: the first runway identification of the flight inbound runway and the flight landing time length of the inbound flight on the corresponding runway of the first runway identification are obtained; the flight landing time length is used for representing the time length from the time point when the distance between the flight and the flight destination is less than the distance threshold value to the time point when the flight lands on the runway;
and the third control module is used for calculating the median of the flight landing time length of the inbound flights on the runway corresponding to different first runway identifications, and obtaining the second arrival predicted time of the flights based on the median of the flight landing time length of the inbound flights on the runway corresponding to different first runway identifications.
The flight information further includes: a second runway identification of an inbound runway for the flight and an identification of a target flight seat for the flight; the flight historical inbound information further comprises: the moving path and the moving time length of the flight from the arrival runway to the stand.
The device, still include:
the fourth control module is used for inquiring the historical inbound information of the flights, wherein the inbound runway is a runway corresponding to the second runway identifier, and the stop of the flight is a stop corresponding to the target stop identifier;
the fifth control module is used for taking the moving path which is used for the most times in the moving paths in the inquired flight historical inbound information as the moving path of the flight;
the sixth control module is used for calculating the average value of the moving time length in the inquired flight historical arrival information and taking the calculated average value as the third arrival prediction time of the flight;
a seventh control module, configured to, when the flight is a delayed flight, obtain an arrival time of the flight based on the first arrival predicted time and the third arrival predicted time;
and the eighth control module is used for obtaining the predicted time of the flight based on the second arrival predicted time and the third arrival predicted time when the flight is a non-delayed flight.
The flight arrival time prediction apparatus according to this embodiment further includes:
the second processing module is used for acquiring flight track data of delayed flights in the same inbound direction;
the third processing module is used for dividing the acquired flight trajectory data into a first part of flight trajectories which are used as a training data set of a regression model of the support vector machine and a second part of flight trajectories which are used as a test data set of the regression model of the support vector machine;
the fourth processing module is used for inputting the first part of flight trajectories into the regression model of the support vector machine and training the regression model of the support vector machine when the test result indicates that the trained regression model of the support vector machine cannot identify all the second part of flight trajectories as flight trajectories of delayed flights;
the fifth processing module is used for testing the second part of flight trajectories by using the trained regression model of the support vector machine to obtain a test result;
and the sixth processing module is used for determining that the trained support vector machine regression model is the support vector machine regression model for identifying delayed flights in the inbound direction when the test result indicates that the trained support vector machine regression model can identify all the second part flight trajectories as the air flight trajectories of the delayed flights.
In summary, according to the flight arrival time prediction apparatus provided in this embodiment, the inbound direction of a flight is determined, and the flight information of the flight is processed by using the support vector machine regression model for identifying a delayed flight in the inbound direction, so as to obtain a processing result, when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival prediction time of the flight, and compared with a manner in which the arrival time of the flight can be roughly predicted only by using data such as a current distance from an airport and a historical arrival time of the flight in the related art, the arrival time of the flight can be predicted by using the trained support vector machine regression model for identifying the delayed flight in the inbound direction, so that the accuracy of predicting the arrival time of the flight can be greatly improved.
Example 3
The present embodiment proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the data processing method described in embodiment 1 above. For specific implementation, refer to method embodiment 1, which is not described herein again.
In addition, referring to the schematic structural diagram of an electronic device shown in fig. 3, the present embodiment further provides an electronic device, where the electronic device includes a bus 51, a processor 52, a transceiver 53, a bus interface 54, a memory 55, and a user interface 56. The electronic device comprises a memory 55.
In this embodiment, the electronic device further includes: one or more programs stored on the memory 55 and executable on the processor 52, configured to be executed by the processor for performing the following steps (1) to (3):
(1) when the distance between the flight and the flight destination is determined to be smaller than a distance threshold value, acquiring flight information of the flight to be predicted, a flight departure place and a flight destination;
(2) determining an arrival direction of the flight when the flight arrives based on the flight departure place and the flight destination;
(3) processing the flight information of the flight by using a support vector machine regression model for identifying delayed flights in the arrival direction to obtain a processing result; when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival predicted time of the flight.
A transceiver 53 for receiving and transmitting data under the control of the processor 52.
In fig. 3, a bus architecture (represented by bus 51), bus 51 may include any number of interconnected buses and bridges, with bus 51 linking together various circuits including one or more processors, represented by general purpose processor 52, and memory, represented by memory 55. The bus 51 may also link various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further in this embodiment. A bus interface 54 provides an interface between the bus 51 and the transceiver 53. The transceiver 53 may be one element or may be multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. For example: the transceiver 53 receives external data from other devices. The transceiver 53 is used for transmitting data processed by the processor 52 to other devices. Depending on the nature of the computing system, a user interface 56, such as a keypad, display, speaker, microphone, joystick, may also be provided.
The processor 52 is responsible for managing the bus 51 and the usual processing, running a general-purpose operating system as described above. And memory 55 may be used to store data used by processor 52 in performing operations.
Alternatively, processor 52 may be, but is not limited to: a central processing unit, a singlechip, a microprocessor or a programmable logic device.
It will be appreciated that the memory 55 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data rate Synchronous Dynamic random access memory (ddr SDRAM ), Enhanced Synchronous SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct memory bus RAM (DRRAM). The memory 55 of the systems and methods described in this embodiment is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 55 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof: an operating system 551 and application programs 552.
The operating system 551 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application 552 includes various applications, such as a Media Player (Media Player), a Browser (Browser), and the like, for implementing various application services. A program implementing the method of an embodiment of the present invention may be included in the application 552.
In summary, in the electronic device and the computer-readable storage medium provided in this embodiment, the inbound direction of a flight is determined, and flight information of the flight is processed by using a support vector machine regression model for identifying a delayed flight in the inbound direction, so as to obtain a processing result, when the processing result indicates that the flight is the delayed flight, the processing result carries the first arrival predicted time of the flight, and compared with a manner in which the arrival time of the flight can be roughly estimated only by using data such as a current distance between the flight and an airport and a historical arrival time of the flight in the related art, the arrival time of the flight can be predicted by using a trained support vector machine regression model for identifying the delayed flight in the inbound direction, so that accuracy of predicting the arrival time of the flight can be greatly improved.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A flight arrival time prediction method, comprising:
when the distance between the flight and the flight destination is determined to be smaller than a distance threshold value, acquiring flight information of the flight to be predicted, a flight departure place and a flight destination;
determining an arrival direction of the flight when the flight arrives based on the flight departure place and the flight destination;
processing the flight information of the flight by using a support vector machine regression model for identifying delayed flights in the arrival direction to obtain a processing result; when the processing result indicates that the flight is a delayed flight, the processing result carries the first arrival predicted time of the flight.
2. The method of claim 1, wherein the flight information comprises: longitude data, latitude data, and altitude data of the flight;
the method further comprises the following steps:
when the processing result indicates that the flight is a non-delayed flight, obtaining a longitude query range based on the longitude data and a longitude threshold, obtaining a latitude query range based on the latitude data and a latitude threshold, and obtaining an altitude query range based on the altitude data and an altitude threshold;
inquiring the historical flight entering information meeting the longitude inquiry range, the latitude inquiry range and the altitude inquiry range; wherein the flight historical inbound information comprises: the first runway identification of the flight inbound runway and the flight landing time length of the inbound flight on the corresponding runway of the first runway identification are obtained; the flight landing time length is used for representing the time length from the time point when the distance between the flight and the flight destination is less than the distance threshold value to the time point when the flight lands on the runway;
and calculating the median of the flight landing time length of the inbound flight on the runway corresponding to different first runway identifications, and obtaining the second arrival prediction time of the flight based on the median of the flight landing time length of the inbound flight on the runway corresponding to different first runway identifications.
3. The method of claim 2, wherein the flight information further comprises: a second runway identification of an inbound runway for the flight and an identification of a target flight seat for the flight; the flight historical inbound information further comprises: the flight identifies a moving path and moving duration from an inbound runway corresponding to the second runway to the target airport terminal;
the method further comprises the following steps:
inquiring the historical inbound information of the flights, wherein the inbound runway is a runway corresponding to the second runway identifier, and the stop of the flight is a stop corresponding to the target stop identifier;
taking the most frequently used moving path in the searched moving paths in the flight historical inbound information as the moving path of the flight;
calculating the average value of the moving time length in the inquired flight historical arrival information, and taking the calculated average value as the third arrival prediction time of the flight;
when the flight is a delayed flight, obtaining a first predicted arrival time of the flight based on the first predicted arrival time and a third predicted arrival time;
and when the flight is a non-delayed flight, obtaining a second predicted time of the flight based on the second arrival predicted time and a third arrival predicted time.
4. The method of claim 1, further comprising:
acquiring flight track data of delayed flights in the same inbound direction;
dividing the acquired flight trajectory data into a first part of flight trajectories which serve as a training data set of a regression model of a support vector machine and a second part of flight trajectories which serve as a test data set of the regression model of the support vector machine;
when the test result indicates that the trained support vector machine regression model cannot identify all second part flight tracks as flight tracks of delayed flights, inputting the first part flight tracks into the support vector machine regression model, and training the support vector machine regression model;
testing the second part of flight trajectories by using the trained support vector machine regression model to obtain a test result;
and when the test result indicates that the trained support vector machine regression model can identify all the second part flight trajectories as the air flight trajectories of delayed flights, determining that the trained support vector machine regression model is the support vector machine regression model for identifying the delayed flights in the inbound direction.
5. A flight arrival time prediction apparatus, comprising:
the acquisition module is used for acquiring flight information, a flight departure place and a flight destination of a flight to be predicted when the distance between the flight and the flight destination is determined to be smaller than a distance threshold;
the determining module is used for determining the arrival direction of the flight when the flight arrives on the basis of the flight departure place and the flight destination;
and the processing module is used for processing the flight information of the flight by using a support vector machine regression model for identifying delayed flights in the inbound direction to obtain a processing result, wherein the processing result carries the first arrival prediction time of the flight when the processing result indicates that the flight is the delayed flight.
6. The apparatus of claim 5, wherein the flight information comprises: longitude data, latitude data, and altitude data of the flight;
the device, still include:
the first control module is used for obtaining a longitude query range based on the longitude data and a longitude threshold value, obtaining a latitude query range based on the latitude data and a latitude threshold value and obtaining an altitude query range based on the altitude data and an altitude threshold value when the processing result indicates that the flight is a non-delayed flight;
the second control module is used for inquiring the flight history inbound information meeting the longitude inquiry range, the latitude inquiry range and the altitude inquiry range; wherein the flight historical inbound information comprises: the first runway identification of the flight inbound runway and the flight landing time length of the inbound flight on the corresponding runway of the first runway identification are obtained; the flight landing time length is used for representing the time length from the time point when the distance between the flight and the flight destination is less than the distance threshold value to the time point when the flight lands on the runway;
and the third control module is used for calculating the median of the flight landing time length of the inbound flights on the runway corresponding to different first runway identifications, and obtaining the second arrival predicted time of the flights based on the median of the flight landing time length of the inbound flights on the runway corresponding to different first runway identifications.
7. The apparatus of claim 6, wherein the flight information further comprises: a second runway identification of an inbound runway for the flight and an identification of a target flight seat for the flight; the flight historical inbound information further comprises: the moving path and the moving time length of the flight from the arrival runway to the stand;
the device, still include:
the fourth control module is used for inquiring the historical inbound information of the flights, wherein the inbound runway is a runway corresponding to the second runway identifier, and the stop of the flight is a stop corresponding to the target stop identifier;
the fifth control module is used for taking the moving path which is used for the most times in the moving paths in the inquired flight historical inbound information as the moving path of the flight;
the sixth control module is used for calculating the average value of the moving time length in the inquired flight historical arrival information and taking the calculated average value as the third arrival prediction time of the flight;
a seventh control module, configured to, when the flight is a delayed flight, obtain an arrival time of the flight based on the first arrival predicted time and the third arrival predicted time;
and the eighth control module is used for obtaining the predicted time of the flight based on the second arrival predicted time and the third arrival predicted time when the flight is a non-delayed flight.
8. The apparatus of claim 5, further comprising:
the second processing module is used for acquiring flight track data of delayed flights in the same inbound direction;
the third processing module is used for dividing the acquired flight trajectory data into a first part of flight trajectories which are used as a training data set of a regression model of the support vector machine and a second part of flight trajectories which are used as a test data set of the regression model of the support vector machine;
the fourth processing module is used for inputting the first part of flight trajectories into the regression model of the support vector machine and training the regression model of the support vector machine when the test result indicates that the trained regression model of the support vector machine cannot identify all the second part of flight trajectories as flight trajectories of delayed flights;
the fifth processing module is used for testing the second part of flight trajectories by using the trained regression model of the support vector machine to obtain a test result;
and the sixth processing module is used for determining that the trained support vector machine regression model is the support vector machine regression model for identifying delayed flights in the inbound direction when the test result indicates that the trained support vector machine regression model can identify all the second part flight trajectories as the air flight trajectories of the delayed flights.
9. 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 the claims 1 to 4.
10. An electronic device comprising a memory, a processor, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor to perform the steps of the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010484433.4A CN111626519A (en) | 2020-06-01 | 2020-06-01 | Flight arrival time prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010484433.4A CN111626519A (en) | 2020-06-01 | 2020-06-01 | Flight arrival time prediction method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111626519A true CN111626519A (en) | 2020-09-04 |
Family
ID=72272686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010484433.4A Pending CN111626519A (en) | 2020-06-01 | 2020-06-01 | Flight arrival time prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111626519A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580204A (en) * | 2020-12-16 | 2021-03-30 | 同济大学 | Train delay time prediction method under abnormal events in railway section |
| CN112687128A (en) * | 2020-11-27 | 2021-04-20 | 民航成都信息技术有限公司 | Prediction method and device for estimated arrival time of flight path and automatic prediction system |
| CN112801376A (en) * | 2021-01-31 | 2021-05-14 | 华为技术有限公司 | Method, apparatus and storage medium for determining estimated time of arrival of a vessel |
| CN115392886A (en) * | 2022-10-28 | 2022-11-25 | 中国民用航空总局第二研究所 | Time reporting method, time reporting device, storage medium and processor of arrival airplane |
| CN116681413A (en) * | 2023-08-03 | 2023-09-01 | 中航信移动科技有限公司 | Flight arrival time determining method, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303896A (en) * | 2015-09-07 | 2016-02-03 | 合肥飞友网络科技有限公司 | Method for precisely pre-estimating estimated arrival time of flight |
| US20180012499A1 (en) * | 2016-07-07 | 2018-01-11 | Passur Aerospace, Inc. | System and Method for Predicting Aircraft Taxi Time |
| CN110675007A (en) * | 2019-12-06 | 2020-01-10 | 南京萨利智能科技有限公司 | Flight delay prediction method and device and computer storage medium |
-
2020
- 2020-06-01 CN CN202010484433.4A patent/CN111626519A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303896A (en) * | 2015-09-07 | 2016-02-03 | 合肥飞友网络科技有限公司 | Method for precisely pre-estimating estimated arrival time of flight |
| US20180012499A1 (en) * | 2016-07-07 | 2018-01-11 | Passur Aerospace, Inc. | System and Method for Predicting Aircraft Taxi Time |
| CN110675007A (en) * | 2019-12-06 | 2020-01-10 | 南京萨利智能科技有限公司 | Flight delay prediction method and device and computer storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112687128A (en) * | 2020-11-27 | 2021-04-20 | 民航成都信息技术有限公司 | Prediction method and device for estimated arrival time of flight path and automatic prediction system |
| CN112687128B (en) * | 2020-11-27 | 2022-06-03 | 民航成都信息技术有限公司 | Prediction method and device for estimated arrival time of flight path and automatic prediction system |
| CN112580204A (en) * | 2020-12-16 | 2021-03-30 | 同济大学 | Train delay time prediction method under abnormal events in railway section |
| CN112801376A (en) * | 2021-01-31 | 2021-05-14 | 华为技术有限公司 | Method, apparatus and storage medium for determining estimated time of arrival of a vessel |
| CN115392886A (en) * | 2022-10-28 | 2022-11-25 | 中国民用航空总局第二研究所 | Time reporting method, time reporting device, storage medium and processor of arrival airplane |
| CN116681413A (en) * | 2023-08-03 | 2023-09-01 | 中航信移动科技有限公司 | Flight arrival time determining method, electronic equipment and storage medium |
| CN116681413B (en) * | 2023-08-03 | 2023-10-27 | 中航信移动科技有限公司 | Flight arrival time determining method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111626519A (en) | Flight arrival time prediction method and device and electronic equipment | |
| US11783590B2 (en) | Method, apparatus, device and medium for classifying driving scenario data | |
| CN110210604B (en) | Method and device for predicting movement track of terminal equipment | |
| CN104599002B (en) | Method and equipment for predicting order value | |
| CN114120650B (en) | Method and device for generating test results | |
| CN110647675B (en) | Method and device for recognition of stop point and training of prediction model and storage medium | |
| CN110471055B (en) | Method and device for predicting flight path, readable storage medium and terminal equipment | |
| CN112815948B (en) | Method, device, computer equipment and storage medium for identifying yaw mode | |
| Weng et al. | Real-time bus travel speed estimation model based on bus GPS data | |
| CN111667689B (en) | Method, device and computer device for predicting vehicle travel time | |
| CN114802303A (en) | Obstacle trajectory prediction method, obstacle trajectory prediction device, electronic device, and storage medium | |
| CN113066302A (en) | Vehicle information prediction method and device and electronic equipment | |
| CN114819135A (en) | Training method of detection model, target detection method, device and storage medium | |
| CN108171605A (en) | A kind of vehicle secondary mortgage alarm method, device, server and storage medium | |
| CN113837268B (en) | Method, device, equipment and medium for determining track point state | |
| CN111160594B (en) | Method and device for estimating arrival time and storage medium | |
| CN111240361A (en) | Flight control method, device and equipment based on four-dimensional data and storage medium | |
| Yang et al. | Terminal-area aircraft intent inference approach based on online trajectory clustering | |
| US20220084228A1 (en) | Estimating ground truth object keypoint labels for sensor readings | |
| US20210101614A1 (en) | Spatio-temporal pose/object database | |
| US20170184488A1 (en) | Facility state analysis device, analysis method for facility state, storage medium, and facility management system | |
| Antoniades et al. | Fare and duration prediction: A study of New York city taxi rides | |
| US20200312171A1 (en) | Systems and methods for dynamically detecting moving object trajectory conflict using estimated times of arrival | |
| JP7232727B2 (en) | Map data management device and map data management method | |
| CN112767732B (en) | Parking position determining method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |