CN107808552A - Flight behavioral value method and apparatus - Google Patents
Flight behavioral value method and apparatus Download PDFInfo
- Publication number
- CN107808552A CN107808552A CN201711053273.2A CN201711053273A CN107808552A CN 107808552 A CN107808552 A CN 107808552A CN 201711053273 A CN201711053273 A CN 201711053273A CN 107808552 A CN107808552 A CN 107808552A
- Authority
- CN
- China
- Prior art keywords
- airport
- passengers
- flight
- real
- data
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0073—Surveillance aids
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0043—Traffic management of multiple aircrafts from the ground
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention provides a kind of flight behavioral value method and apparatus, wherein, this method includes：Obtain the real-time flight track data of airline carriers of passengers；According to the real-time flight track data, the special behavior of the airline carriers of passengers is detected.The present invention solves the existing technical problem that can not effectively learn that Consumer's Experience is relatively low caused by flight delay situation in advance, has reached the technique effect for improving Consumer's Experience.
Description
Technical field
The present invention relates to technical field of aerospace, more particularly to a kind of flight behavioral value method and apparatus.
Background technology
Aircraft is as the relatively conventional vehicles, because the free degree of airflight is significantly larger than land traffic, with the people
The boat passenger plane related time is often more discrete than the Annual distribution of land traffic and is difficult to predict.However, the guarantor for airport
Barrier personnel, for picking machine people, the prediction (arrival time of the flight especially to fly) of flight correlation time is that have very much
It is necessary.
In the correlative study of time prediction, the prediction for irregular flight (flight especially make preparation for dropping, to make a return voyage) is past
It is past relatively difficult.When flight is made preparation for dropping and is maked a return voyage, flight needs to drop to the airport different from former destination temporarily, and this was both
The destination airport to be looked for novelty adjusts the distribution of the resources such as aircraft gate, support personnel temporarily, can influence to seize the opportunity people again, the people that picks etc.
Plan, therefore, the confirmation to this special behavior is necessarily more early better.
In a practical situation, airport can be confirmed by blank pipe instruction, but blank pipe instruction occasional changes, then be examined
Consider the fault rate of human users, entirely accurate can not be ensured.However, for the people that picks for being in former destination, it is difficult to
It is notified in advance, the APP that in general has Scheduled Flight just understands triggering state generally when flight has fallen in alternate airport
Renewal.
For it is existing can not look-ahead irregular flight correlation time the problem of, not yet propose effective solve at present
Scheme.
The content of the invention
The embodiments of the invention provide a kind of flight behavioral value method, and flight abnormal behaviour is determined in real time to reach, right
To lift the purpose of Consumer's Experience, this method includes the abnormal timely processing that carries out：
Obtain the real-time flight track data of airline carriers of passengers；
According to the real-time flight track data, the special behavior of the airline carriers of passengers is detected.
In one embodiment, the special behavior includes at least one of：Go off course, make preparation for dropping, make a return voyage, spiral.
In one embodiment, the real-time flight track data includes at least one of：Time, longitude and latitude, height
Degree.
In one embodiment, the real-time flight track data of airline carriers of passengers is obtained, including：Obtain the airline carriers of passengers
Real-time flight track data, blank pipe message data, wherein, the blank pipe message data includes at least one of：Flight number,
Starting point airport code, airport of destination code, alternate airport information, information of making a return voyage.
In one embodiment, before the real-time flight track data of airline carriers of passengers is obtained, methods described also includes：
Obtain the historical trajectory data that the airline carriers of passengers corresponds to flight；
The historical trajectory data is excavated, determines the one or more conventional navigation road corresponding to the flight
Line.
In one embodiment, the historical trajectory data is excavated, determines one corresponding to the flight
Bar or a plurality of conventional navigation route, including：
To the historical trajectory data, these data carry out sliding-model control；
After sliding-model control, the adjacent data point for falling into same grid is subjected to deduplication operation, obtain one or
A plurality of conventional navigation route, the corresponding longitude and latitude position of data point of a grid.
In one embodiment, according to the real-time flight track data, the special behavior of the airline carriers of passengers is detected,
Including：
The real-time flight path and the conventional navigation route are contrasted, to determine that the airline carriers of passengers is
It is no to go off course.
In one embodiment, according to the real-time flight track data, the special behavior of the airline carriers of passengers is detected,
Including：
After it is determined that driftage situation occurs in the airline carriers of passengers, the position where airline carriers of passengers is determined；
It is determined that the predetermined number airport nearest with the airline carriers of passengers position, or, determine the airline carriers of passengers
History is made preparation for dropping the most predetermined number airport of number in the course line of place；
Alternate airport using the predetermined number airport determined as the airline carriers of passengers.
In one embodiment, according to the real-time flight track data, the special behavior of the airline carriers of passengers is detected,
Including：
According to the real-time flight track data, it is determined that in preset time window first point of flight path and last
Individual point；
Longitude and latitude distance between calculating first point and departure airport and arriving at the airport；
Longitude and latitude distance between calculating described last point and departure airport and arriving at the airport；
When in the preset time window, when flight reduces away from departure airport distance and increased away from destination airport distance, really
Determine airline carriers of passengers to spiral.
The embodiment of the present invention additionally provides a kind of flight behavioral value device, and flight abnormal behaviour is determined in real time to reach,
To the abnormal timely processing that carries out to lift the purpose of Consumer's Experience, the device includes：
First acquisition module, for obtaining the real-time flight track data of airline carriers of passengers；
Detection module, for according to the real-time flight track data, detecting the special behavior of the airline carriers of passengers.
In one embodiment, the special behavior includes at least one of：Go off course, make preparation for dropping, make a return voyage, spiral.
In one embodiment, the real-time flight track data includes at least one of：Time, longitude and latitude, height
Degree.
In one embodiment, first acquisition module is specifically used for the real-time flight rail for obtaining the airline carriers of passengers
Mark data, blank pipe message data, wherein, the blank pipe message data includes at least one of：Flight number, starting point airport generation
Code, airport of destination code, alternate airport information, information of making a return voyage.
In one embodiment, said apparatus also includes：Second acquisition module, for obtaining the real-time of airline carriers of passengers
Before flight path data, the historical trajectory data that the airline carriers of passengers corresponds to flight is obtained；
Determining module, for being excavated to the historical trajectory data, determine corresponding to one of the flight or
A plurality of conventional navigation route.
In one embodiment, the determining module includes：
Discretization unit, sliding-model control is carried out for these data to the historical trajectory data；
Duplicate removal unit, for after sliding-model control, the adjacent data point for falling into same grid to be carried out into duplicate removal behaviour
Make, obtain one or more conventional navigation route, the corresponding longitude and latitude position of data point of a grid.
In one embodiment, the detection module is specifically used for the real-time flight path and the routine
Navigation route is contrasted, to determine whether the airline carriers of passengers goes off course.
In one embodiment, the detection module includes：First determining unit, for it is determined that the airline carriers of passengers
After there is driftage situation, the position where airline carriers of passengers is determined；Second determining unit, for determining and the airline carriers of passengers institute
On the nearest predetermined number airport in position, or, history number of making preparation for dropping is most in course line where determining the airline carriers of passengers
Predetermined number airport；Generation unit, for using the predetermined number airport determined as the standby of the airline carriers of passengers
Airport drops.
In one embodiment, the detection module includes：3rd determining unit, for according to the real-time flight rail
Mark data, it is determined that first point of flight path and last point in preset time window；First computing unit, for calculating
First point and departure airport and the longitude and latitude distance between arriving at the airport；Second computing unit, for calculate it is described most
The latter point and departure airport and the longitude and latitude distance between arriving at the airport；4th determining unit, for when when described default
Between in window, when flight reduces away from departure airport distance and increased away from destination airport distance, determine that airline carriers of passengers spirals.
In embodiments of the present invention, the real-time flight track data of airline carriers of passengers is obtained；According to real-time flight track data,
The special behavior of the airline carriers of passengers is detected, the abnormal behaviour of flight can be found in time through the above way, so as to carry
Before determine the possible delay situation of flight, solve existing effectively can not learn in advance and use caused by flight delay situation
Relatively low technical problem is experienced at family, has reached the technique effect for improving Consumer's Experience.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, forms the part of the application, not
Form limitation of the invention.In the accompanying drawings：
Fig. 1 is the method flow diagram of flight behavioral value method according to embodiments of the present invention；
Fig. 2 is air lane schematic diagram according to embodiments of the present invention；
Fig. 3 is the structured flowchart of flight behavioral value device according to embodiments of the present invention.
Embodiment
It is right with reference to embodiment and accompanying drawing for the object, technical solutions and advantages of the present invention are more clearly understood
The present invention is described in further details.Here, the exemplary embodiment of the present invention and its illustrate to be used to explain the present invention, but simultaneously
It is not as a limitation of the invention.
The embodiments of the invention provide a kind of flight behavioral value method, as shown in figure 1, may include steps of：
S101：Obtain the real-time flight track data of airline carriers of passengers；
Wherein, real-time flight track data can include but is not limited at least one of：Time, longitude and latitude, height.
S102：According to the real-time flight track data, the special behavior of the airline carriers of passengers is detected.
Wherein, special behavior can include but is not limited at least one of：Go off course, make preparation for dropping, make a return voyage, spiral.
In order to realize the determination to flight abnormal behaviour, can not only be determined according to real-time flight track data, can be with
With reference to blank pipe message data etc., so that judging more fully.Wherein, blank pipe message data can include but is not limited to
It is at least one lower：Flight number, starting point airport code, airport of destination code, alternate airport information, information of making a return voyage.
In view of exception and it is normally a relative concept, it is abnormal in order to determine whether to exist, can first it determine just
Chang Hangban should corresponding to route, after being compared, it is possible to determine flight exception.Therefore, obtaining the reality of airline carriers of passengers
When flight path data before, the historical trajectory data that the airline carriers of passengers corresponds to flight can be obtained；To the historical track
Data are excavated, and determine the one or more conventional navigation route corresponding to the flight.
Specifically, being excavated to the historical trajectory data, determine that correspond to the flight one or more is normal
Navigation route is advised, can be included：To the historical trajectory data, these data carry out sliding-model control；Sliding-model control it
Afterwards, the adjacent data point for falling into same grid is subjected to deduplication operation, obtains one or more conventional navigation route, a net
The corresponding longitude and latitude position of the data point of lattice.
Accordingly, according to the real-time flight track data, the special behavior of the airline carriers of passengers is detected, can be included：
The real-time flight path and the conventional navigation route are contrasted, to determine whether the airline carriers of passengers occurs partially
Boat.
For situation that may be present of making preparation for dropping, after it is determined that there is driftage situation in the airline carriers of passengers, it may be determined that the people
Position where boat passenger plane；It is determined that the predetermined number airport nearest with the airline carriers of passengers position, or, it is determined that described
History is made preparation for dropping the most predetermined number airport of number in course line where airline carriers of passengers；The predetermined number that will can be determined
Alternate airport of the individual airport as the airline carriers of passengers.
For how to determine whether flight spirals, can determine in accordance with the following steps：
S1：According to the real-time flight track data, it is determined that first point of flight path and most in preset time window
The latter point；
S2：Longitude and latitude distance between calculating first point and departure airport and arriving at the airport；
S3：Longitude and latitude distance between calculating described last point and departure airport and arriving at the airport；
S4：When in the preset time window, when flight reduces away from departure airport distance and increased away from destination airport distance,
Determine that airline carriers of passengers spirals.
Above-mentioned flight behavioral value method is illustrated with reference to a specific embodiment, however it is noticeable
It is that the specific embodiment does not form the improper restriction to the application merely to the application is better described.
In this example, the driftage for airline carriers of passengers, the special behavior such as make preparation for dropping, make a return voyage, spiraling, propose that a kind of flight is special
The real-time detection method of behavior, based on a kind of data relatively more easily obtained：The positional information of airline carriers of passengers is (i.e., in real time
Flight path), to excavate civil aviaton's routine air route offline as starting point, by stream data calculate in the form of disposed, with reality
Now to holding the complete monitoring of winged flight in civil aviaton spatial domain.By the way that track digging technology is applied into Commercial Air Service, to divide
The flight path of flight is analysed, and using the real time position data of streaming computing processing flight, to ensure the real-time of detection.
Specifically, using the real-time track of airline carriers of passengers, the special behavior in flight course is detected.Wherein, it is special
Different behavior can include：Go off course, make preparation for dropping, make a return voyage, spiral.By the real-time detection to these special behaviors, and notify in time
External system, abundant flight status, the purpose of the accuracy of lifting time correlation forecasting system can be reached, and then improve airport
Production efficiency and average traveler, pick machine people trip experience.
Used data can include：Flight track data, blank pipe make preparation for dropping message, make a return voyage message.Wherein, flight track
Data can include：The aircraft real-time status such as time, longitude and latitude, height, blank pipe message can include：Flight number, plan set out/
Destination airport code, the contents such as target of making preparation for dropping/make a return voyage.
Based on above-mentioned data, following content can be performed：
1) the discretization expression in civil aviaton air route and conventional air route are excavated；
2) conventional air route is based on, the driftage behavior to flight is detected in real time；
3) by calculating the division of two-dimensional space and some geometry, to the making preparation for dropping of flight, behavior of making a return voyage is examined in real time
Survey, blank pipe is made preparation for dropping, the message that makes a return voyage carries out real-time verification；
4) behavior of being spiraled to flight is detected in real time, and when within a certain error range recovers navigation to the flight that spirals
Between be predicted.
Wherein, except it is above-mentioned be 1) that offline excavate is carried out to historical data in addition to, 2), 3), 4) above-mentioned is real-time calculating, can be with
Meet that the clients such as airline, airport, average traveler obtain the requirement of Flight Information in real time.
In this example, the processing to data can be carried out from Spark and python etc. at MapReduce distributions
Reason, real-time calculating platform are selected Spark Streaming frameworks, entered respectively by two kinds of message queues of Kafka and ActiveMQ
The transmitting-receiving of row real time data, necessary data buffer storage and system decoupling are realized using Redis.
Wherein, the computation schema of real time data can be：Collect the stream data based on time window, i.e. collection per minute
And in a few minutes of handling over all aerial flights position data.
Above-mentioned several schemes are specifically described below：
1) the discretization expression in civil aviaton air route and conventional air route are excavated
The navigation route of airline carriers of passengers can determine that the navigation circuit of flight is two between two airports by the navigation spots of static state
Dimension longitude and latitude determines substantially in space, and air route width is usually no more than 20 kilometers.Based on this, in the feelings that navigation point data is unknown
Under condition, conventional air route can be excavated using flight historical trajectory data, navigated flight historical trajectory data as measurement
Class whether the foundation of normal/cruise.
In view of the intrinsic width in conventional air route, the precision of longitude and latitude degrees of data can be reduced, 1 of latitude data of learning from else's experience or
2 effective digitals, so as to reach on the premise of air route expression is not influenceed, reduce data volume.This method is similar to longitude and latitude
Spatial gridding is spent, falls and is represented in the location point of a grid by the grid, by this gridding method, realize boat
The discretization expression on road.
Specifically, the track number of normal (non-to make preparation for dropping, the make a return voyage, cancelling) flight in each course line in history can be collected
According to these data progress sliding-model control, after sliding-model control, by the adjacent data point for falling into same grid progress
Deduplication operation, the history air route being simplified.Certainly, for same course line, there may be multiple conventional air routes.Such as Fig. 2
It is shown, illustrate the track of whole regular flight in Chongqing-Urumchi course line day, it can be clearly seen that same course line has more
Bar routine air route.Intuitively the coincidence point ratio in discrete air route can be determined as two different air routes less than a certain threshold value.Can
To portray the distance between different air routes using LCS (longest common subsequence) distances, by the LCS calculated between air route two-by-two away from
From applied to DB-SCAN clustering algorithms, a plurality of history air route on each course line is clustered, obtains any of any course line
Bar routine air route.
2) flight driftage detection in real time
Driftage is one of typical abnormal behaviour of flight, can be based on the above-mentioned static conventional air route excavated, inspection in real time
Survey the driftage behavior of flight.
For example, first, it can pass through Spark Streaming's with the position data per minute for collecting 3 minutes in the past
CombineByKey functions by each data point by flight frequency (such as：Date-flight number-departure place-arrival) returned
Collection, obtain using order of classes or grades at school as major key, using location point array of the flight in current time window as the map type data of value, then, will be every
The location data points of individual order of classes or grades at school are in chronological sequence ranked up, and carry out sampling processing.
After sampling processing, each sampled point and point nearest in different static air routes can be searched, calculates them
Distance in longitude and latitude space：Dist_nearest_grid, so as to navigate to which static state current flight is in
In air route, and it can judge whether current flight has gone off course by the magnitude relationship between default threshold value and distance.
Further, it is possible to the variation tendency according to the dist_nearest_grid of each sampled point in current time window, fixed
Justice goes out more complicated flight behavior：Distance has been at less level, then it is assumed that flight is normal, and Gao Shui is changed to from low-level
Flat then go off course, changing to low-level from high level is then returning to certain conventional air route, has been at high level then
It is in driftage state.
All carried out because the calculating based on time window is per minute, the calculating of follow-up time window is frequently necessary to use current class
State before secondary, to this end it is possible to use, Redis carries out the caching of state.Flight for state for driftage, compares normal/cruise
Flight the abnormal behaviour such as more likely make preparation for dropping, make a return voyage.
3) flight is made preparation for dropping/make a return voyage detection, blank pipe in real time are made preparation for dropping/, and make a return voyage message real-time verification
Making preparation for dropping, making a return voyage for flight is also the common improper behavior of flight.Real time position data based on flight, Ke Yili
Which airport is dropped to judge that current flight is actual with longitude and latitude when being highly just reduced to 0, however, this scheme produces
No matter the time of conclusion too late, is in alignment with the standby alternate airport ensured to aircraft of making preparation for dropping, or to preparing in former destination
The user to pick, this information delay are all difficult to receive.
In view of this problem, the real-time detection that a kind of flight is made preparation for dropping, maked a return voyage is proposed in this example, in schedule flight
During judge whether to make preparation for dropping as early as possible, make a return voyage.Further, since the factor such as human users and weather, airport changes at any time
Deng random factor, the making preparation for dropping of blank pipe, wrong report occurs in the message that makes a return voyage once in a while, and the positional information that flight is combined in this example is real-time
The mode of detection, realize blank pipe is made preparation for dropping, the real-time verification for the message that makes a return voyage.
For the driftage flight determined, a kind of candidate is proposed in this example and is made preparation for dropping the system of selection on ground, specifically, can
To be divided using kd tree algorithms to the longitude and latitude space of two dimension, this method can be realized --- any one in given space
Point, can constant time find the n airport nearest with current point as candidate make preparation for dropping ground, can also be based on current course line
History is made preparation for dropping statistics, is chosen n airport for making preparation for dropping most in current course line history and is made preparation for dropping ground as candidate.For have received
Blank pipe is made preparation for dropping, the flight for the message that makes a return voyage, candidate make preparation for dropping ground part consider message in give airport.
In this example, it can be collected, be sampled with the flight track data per minute for collecting past three minutes and by order of classes or grades at school,
Then, judge the making preparation for dropping of flight according to preset rules, make a return voyage：
1) receive the message that makes a return voyage of making preparation for dropping of blank pipe, and last first point in time window to last point formed to
Amount and first point point to the angle cos values on ground of being made preparation for dropping in message more than threshold value (such as：0.95) threshold value is；
2) message that makes a return voyage of making preparation for dropping of blank pipe is received, and is respectively less than relative to the difference in height and horizontal range on ground of being made preparation for dropping in message
Threshold value (for example, threshold value is 1000 meters of height, horizontal 100 kilometers of longitude and latitude), and difference in height and distance meet that certain condition is (horizontal
Distance (rice)/difference in height>9)；
3) blank pipe message is not received, but, by drop ground list, is deposited by the candidate that geographical position and historical data determine
Difference in height, horizontal range meet it is above-mentioned 2) in decision condition make preparation for dropping ground.
Wherein, the judgement time that significantly can in advance make preparation for dropping, make a return voyage with making preparation for dropping 1) is selected through the above way, and come into force ratio
Example is much larger than mode 2) and 3), mode 2) and it is 3) relatively later, belong to more careful strategy, calling together for whole scheme can be improved
The rate of returning.
Wherein, make preparation for dropping and flight transitory state caused by making a return voyage, can be cached using redis, furthermore, it is possible to will sentence
Determine result and external system is informed by message queue, trigger the calculating of external system.
4) flight spirals real-time detection
The behavior of spiraling of flight can have a strong impact on the accuracy of the prediction to flight arrival time, and can influence airport and trip
The experience of visitor, can be detected in real time to the behavior of spiraling as follows：
Pass through the observation to flight normal/cruise route, it is assumed that have a vector that destination is pointed to from departure place, remove
Set out, outside the fixation air route for the surrounding that arrives at the airport, whole way point in chronological order the subpoint on this vector forever by
Point to destination in departure place.So according to this characteristic, a kind of method that effective detection is spiraled is proposed in this example, specifically
, based on time window, 50 kilometers around departure place of going out, airport of destination, first point for track in time window and most
The latter point, the distance of longitude and latitude for calculating them respectively and setting out, arriving at the airport, when in certain time window flight away from departure airport
When distance reduces and increased away from destination airport distance, it can determine that current flight spirals.
Because the recovery time for behavior of spiraling will have a strong impact on the arrival time of flight, and hence it is also possible to recover to spiraling
Time is predicted.Consecutive number strong point can calculate direction change in passage time window, first direction can be more than into angle
The point of threshold value extracts spiral path accordingly as at the time of starting to spiral and position, and longitude and latitude is carried out using spiral path
The fitting of space inner circular, the center of circle and the radius of circle are obtained, the time of recovery can be predicted using present speed, if prediction
Obtain spiral result for one circle and it is approximately round in the case of, it is believed that prediction result is accurate.
The circle obtained for fitting, if radius is excessive, generally indicates that and prolongs backtracking, but unpredictable recovery
Time, there is certain probability that makes a return voyage, but cannot function as judgment rule.
In upper example, the tracing point in two dimensional surface is subjected to sliding-model control to represent aircraft using gridding technology
Navigation route, then, trajectory distance is portrayed by LCS distances, then, conventional air route is excavated using clustering algorithm.Further,
Stream data based on flight path, flight is gone off course in time window, made preparation for dropping, is maked a return voyage, behavior of spiraling is detected in real time；Root
According to information such as real time position, the horizontal range of heading and candidate ground of making preparation for dropping and differences in height, flight is made preparation for dropping, make a return voyage row for progress
For judgement, and based on geometry, fitting obtains spiraling time of recovery.
Which need not use the sensitive datas such as navigation spots latitude and longitude information, it is only necessary to utilize historical trajectory data
The conventional air route in any course line is excavated, only can be real using the positional information of flight without using airport, the core data of boat department
When detect the special behavior of flight, feed back to each system of civil aviaton, and average traveler in time.To a certain extent need not be according to
Rely in blank pipe is made preparation for dropping, make a return voyage message, it is possible to the making preparation for dropping of flight, trend of making a return voyage are inferred to as early as possible, for the blank pipe having been sent from
Message, it can be verified, so as to improve the accuracy of information.This method can provide for external system has high real-time
Information, multiple systems can be applied to, such as：Aerodrome Operations, flight arrival time forecasting system etc..
The framework that above-mentioned stream data calculates is not limited to Spark Streaming, can also use Storm etc., message
Queue is not limited to Kafka, ActiveMQ, can also use RabbitMQ etc., caching system is not limited to Redis, can also use
HBase, MemCached etc..Path discretization in upper example can directly take 1 and 2 effective digitals in latitude and longitude value, real
Latitude and longitude coordinates can be mapped to actual range in the operation of border, such as：Milimeter number etc., can equally realize to path point from
Dispersion.Distance between path, can be with the different metric form such as editing distance, Euclidean distance, in addition, road in addition to LCS
The similarity between distance and path between footpath antithesis each other, the practical significance portrayed is identical, other similarity degree on path
Amount and distance metric can be all contemplated.Clustering algorithm is not limited to DB-SCAN, K-means etc., and others possess algorithm
The purpose can be reached.The selection of above-mentioned involved various threshold values, it can choose and set according to actual conditions, not change
On the premise of index algorithm, it can choose at random as needed.It is any make preparation for dropping, information of making a return voyage, such as：Airline official website, the people
Navigate constituent parts operation data, the app that average traveler uses etc., substantially similar with blank pipe message property, can use.
Based on same inventive concept, a kind of flight behavioral value device is additionally provided in the embodiment of the present invention, as following
Described in embodiment.It is similar to flight behavioral value method to solve the principle of problem due to flight behavioral value device, therefore flight
The implementation of behavioral value device may refer to the implementation of flight behavioral value method, repeats part and repeats no more.It is following to be used
, term " unit " or " module " can realize the combination of the software and/or hardware of predetermined function.Although following examples institute
The device of description is preferably realized with software, but hardware, or the combination of software and hardware realization be also may and quilt
Conception.Fig. 3 is a kind of structured flowchart of the flight behavioral value device of the embodiment of the present invention, as shown in figure 3, can include：
First acquisition module 301 and detection module 302, are illustrated to the structure below.
First acquisition module 301, for obtaining the real-time flight track data of airline carriers of passengers；
Detection module 302, for according to the real-time flight track data, detecting the special behavior of the airline carriers of passengers.
In one embodiment, above-mentioned special behavior can include but is not limited at least one of：Go off course, make preparation for dropping,
Make a return voyage, spiral.
In one embodiment, above-mentioned real-time flight track data can include but is not limited at least one of：When
Between, longitude and latitude, height.
In one embodiment, the first acquisition module 301 specifically can be used for obtaining in real time flying for the airline carriers of passengers
Row track data, blank pipe message data, wherein, the blank pipe message data can include but is not limited at least one of：Boat
Class number, starting point airport code, airport of destination code, alternate airport information, information of making a return voyage.
In one embodiment, said apparatus can also include：Second acquisition module, for obtaining airline carriers of passengers
Before real-time flight track data, the historical trajectory data that the airline carriers of passengers corresponds to flight is obtained；Determining module, for institute
State historical trajectory data to be excavated, determine the one or more conventional navigation route corresponding to the flight.
In one embodiment, determining module can include：Discretization unit, for the historical trajectory data this
A little data carry out sliding-model control；Duplicate removal unit, for after sliding-model control, by the adjacent data for falling into same grid
Point carries out deduplication operation, obtains one or more conventional navigation route, the corresponding longitude and latitude position of data point of a grid.
In one embodiment, detection module 302 it is specific can be used for by the real-time flight path with it is described
Conventional navigation route is contrasted, to determine whether the airline carriers of passengers goes off course.
In one embodiment, detection module 302 can include：First determining unit, for it is determined that the civil aviaton
After driftage situation occurs in passenger plane, the position where airline carriers of passengers is determined；Second determining unit, for determining and civil aviaton visitor
The nearest predetermined number airport in machine position, or, history makes preparation for dropping number most in course line where determining the airline carriers of passengers
More predetermined number airports；Generation unit, for using the predetermined number airport determined as the airline carriers of passengers
Alternate airport.
In one embodiment, detection module 302 can include：3rd determining unit, for being flown in real time according to described
Row track data, it is determined that first point of flight path and last point in preset time window；First computing unit, is used for
Longitude and latitude distance between calculating first point and departure airport and arriving at the airport；Second computing unit, for calculating
Longitude and latitude distance between stating last point and departure airport and arriving at the airport；4th determining unit, for when described pre-
If in time window, when flight reduces away from departure airport distance and increased away from destination airport distance, determine that airline carriers of passengers spirals.
In another embodiment, a kind of software is additionally provided, the software is used to perform above-described embodiment and preferred reality
Apply the technical scheme described in mode.
In another embodiment, a kind of storage medium is additionally provided, above-mentioned software is stored with the storage medium, should
Storage medium includes but is not limited to：CD, floppy disk, hard disk, scratch pad memory etc..
As can be seen from the above description, the embodiment of the present invention realizes following technique effect：Obtain airline carriers of passengers
Real-time flight track data；According to real-time flight track data, the special behavior of the airline carriers of passengers is detected, through the above way
The abnormal behaviour of flight can be found in time, so as to determine the possible delay situation of flight in advance, solved existing
The technical problem that Consumer's Experience is relatively low caused by flight delay situation can not be effectively learnt in advance, reached raising Consumer's Experience
Technique effect.
Obviously, those skilled in the art should be understood that each module of the above-mentioned embodiment of the present invention or each step can be with
Realized with general computing device, they can be concentrated on single computing device, or are distributed in multiple computing devices
On the network formed, alternatively, they can be realized with the program code that computing device can perform, it is thus possible to by it
Store and performed in the storage device by computing device, and in some cases, can be to be held different from order herein
They, are either fabricated to each integrated circuit modules or will be multiple in them by the shown or described step of row respectively
Module or step are fabricated to single integrated circuit module to realize.So, the embodiment of the present invention is not restricted to any specific hard
Part and software combine.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the embodiment of the present invention can have various modifications and variations.Within the spirit and principles of the invention, made
Any modification, equivalent substitution and improvements etc., should be included in the scope of the protection.
Claims (18)
- A kind of 1. flight behavioral value method, it is characterised in that including：Obtain the real-time flight track data of airline carriers of passengers；According to the real-time flight track data, the special behavior of the airline carriers of passengers is detected.
- 2. the method as described in claim 1, it is characterised in that the special behavior includes at least one of：Go off course, be standby Drop, make a return voyage, spiral.
- 3. the method as described in claim 1, it is characterised in that the real-time flight track data includes at least one of： Time, longitude and latitude, height.
- 4. the method as described in claim 1, it is characterised in that the real-time flight track data of airline carriers of passengers is obtained, including：Real-time flight track data, the blank pipe message data of the airline carriers of passengers are obtained, wherein, the blank pipe message data includes At least one of：Flight number, starting point airport code, airport of destination code, alternate airport information, information of making a return voyage.
- 5. the method as described in claim 1, it is characterised in that before the real-time flight track data of airline carriers of passengers is obtained, Methods described also includes：Obtain the historical trajectory data that the airline carriers of passengers corresponds to flight；The historical trajectory data is excavated, determines the one or more conventional navigation route corresponding to the flight.
- 6. method as claimed in claim 5, it is characterised in that excavate, determined correspondingly to the historical trajectory data In one or more conventional navigation route of the flight, including：To the historical trajectory data, these data carry out sliding-model control；After sliding-model control, the adjacent data point for falling into same grid is subjected to deduplication operation, obtains one or more Conventional navigation route, the corresponding longitude and latitude position of data point of a grid.
- 7. method as claimed in claim 5, it is characterised in that according to the real-time flight track data, detect the civil aviaton The special behavior of passenger plane, including：The real-time flight path and the conventional navigation route are contrasted, to determine whether the airline carriers of passengers is sent out Raw driftage.
- 8. the method as described in claim 1, it is characterised in that according to the real-time flight track data, detect the civil aviaton The special behavior of passenger plane, including：After it is determined that driftage situation occurs in the airline carriers of passengers, the position where airline carriers of passengers is determined；It is determined that the predetermined number airport nearest with the airline carriers of passengers position, or, determine the airline carriers of passengers place History is made preparation for dropping the most predetermined number airport of number in course line；Alternate airport using the predetermined number airport determined as the airline carriers of passengers.
- 9. the method as described in claim 1, it is characterised in that according to the real-time flight track data, detect the civil aviaton The special behavior of passenger plane, including：According to the real-time flight track data, it is determined that in preset time window first point of flight path and last Point；Longitude and latitude distance between calculating first point and departure airport and arriving at the airport；Longitude and latitude distance between calculating described last point and departure airport and arriving at the airport；When in the preset time window, when flight reduces away from departure airport distance and increased away from destination airport distance, the people are determined Boat passenger plane spirals.
- A kind of 10. flight behavioral value device, it is characterised in that including：First acquisition module, for obtaining the real-time flight track data of airline carriers of passengers；Detection module, for according to the real-time flight track data, detecting the special behavior of the airline carriers of passengers.
- 11. device as claimed in claim 10, it is characterised in that the special behavior includes at least one of：Go off course, be standby Drop, make a return voyage, spiral.
- 12. device as claimed in claim 10, it is characterised in that the real-time flight track data include it is following at least it One：Time, longitude and latitude, height.
- 13. device as claimed in claim 10, it is characterised in that first acquisition module is specifically used for obtaining the civil aviaton Real-time flight track data, the blank pipe message data of passenger plane, wherein, the blank pipe message data includes at least one of：Boat Class number, starting point airport code, airport of destination code, alternate airport information, information of making a return voyage.
- 14. device as claimed in claim 10, it is characterised in that also include：Second acquisition module, for before the real-time flight track data of airline carriers of passengers is obtained, obtaining the airline carriers of passengers pair Answer the historical trajectory data of flight；Determining module, for being excavated to the historical trajectory data, determine one or more corresponding to the flight Conventional navigation route.
- 15. device as claimed in claim 14, it is characterised in that the determining module includes：Discretization unit, sliding-model control is carried out for these data to the historical trajectory data；Duplicate removal unit, for after sliding-model control, the adjacent data point for falling into same grid being carried out into deduplication operation, obtained To one or more conventional navigation route, the corresponding longitude and latitude position of data point of a grid.
- 16. device as claimed in claim 14, it is characterised in that the detection module is specifically used for the real-time flight rail Mark route is contrasted with the conventional navigation route, to determine whether the airline carriers of passengers goes off course.
- 17. device as claimed in claim 10, it is characterised in that the detection module includes：First determining unit, for after it is determined that driftage situation occurs in the airline carriers of passengers, determining the position where airline carriers of passengers Put；Second determining unit, for determination and the nearest predetermined number airport in the airline carriers of passengers position, or, it is determined that History is made preparation for dropping the most predetermined number airport of number in course line where the airline carriers of passengers；Generation unit, for the alternate airport using the predetermined number airport determined as the airline carriers of passengers.
- 18. device as claimed in claim 10, it is characterised in that the detection module includes：3rd determining unit, for according to the real-time flight track data, it is determined that in preset time window flight path One point and last point；First computing unit, for the longitude and latitude distance between calculating first point and departure airport and arriving at the airport；Second computing unit, for the longitude and latitude distance between calculating described last point and departure airport and arriving at the airport；4th determining unit, for when in the preset time window, flight reduces and away from destination airport away from departure airport distance During distance increase, determine that airline carriers of passengers spirals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053273.2A CN107808552B (en) | 2017-10-27 | 2017-10-27 | Flight behavior detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053273.2A CN107808552B (en) | 2017-10-27 | 2017-10-27 | Flight behavior detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107808552A true CN107808552A (en) | 2018-03-16 |
| CN107808552B CN107808552B (en) | 2020-04-21 |
Family
ID=61591554
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711053273.2A Active CN107808552B (en) | 2017-10-27 | 2017-10-27 | Flight behavior detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107808552B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108648511A (en) * | 2018-06-29 | 2018-10-12 | 飞友科技有限公司 | A method of judging that Aircraft Air spirals based on ADS-B data |
| CN109903554A (en) * | 2019-02-21 | 2019-06-18 | 长安大学 | A kind of road grid traffic operating analysis method based on Spark |
| CN110009545A (en) * | 2019-03-19 | 2019-07-12 | 中国民航大学 | A kind of flight location information parallelization fusion method based on multi-data source |
| CN110379210A (en) * | 2019-07-30 | 2019-10-25 | 四川九洲空管科技有限责任公司 | A kind of civil aircraft exception flight monitoring method and device |
| CN110712765A (en) * | 2019-10-30 | 2020-01-21 | 北京航空航天大学 | Aircraft abnormal operation positioning method based on operation spectrum |
| CN110751859A (en) * | 2019-10-17 | 2020-02-04 | 深圳市瑞达飞行科技有限公司 | Data processing method and device, computer system and readable storage medium |
| CN110827582A (en) * | 2019-10-25 | 2020-02-21 | 海南太美航空股份有限公司 | System and method for automatically acquiring flight landing point in emergency |
| CN111695050A (en) * | 2020-05-29 | 2020-09-22 | 飞友科技有限公司 | Airport position navigation method and flight service system based on user behaviors |
| CN112182133A (en) * | 2020-09-29 | 2021-01-05 | 南京北斗创新应用科技研究院有限公司 | AIS data-based ship loitering detection method |
| CN112348960A (en) * | 2020-11-27 | 2021-02-09 | 中国人民解放军空军工程大学 | Airspace conflict detection method suitable for global space range |
| CN113112876A (en) * | 2021-04-09 | 2021-07-13 | 河北师范大学 | Flight behavior detection method |
| CN113177097A (en) * | 2021-04-16 | 2021-07-27 | 江西航天鄱湖云科技有限公司 | Track initial discrimination method based on attribute clustering and space-time constraint |
| CN116052482A (en) * | 2023-04-03 | 2023-05-02 | 中航信移动科技有限公司 | Method for early warning of aircraft track yaw, electronic equipment and storage medium |
| CN116363908A (en) * | 2023-06-02 | 2023-06-30 | 中航信移动科技有限公司 | Flight track yaw detection method, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101572019A (en) * | 2009-06-01 | 2009-11-04 | 民航数据通信有限责任公司 | Radar track fitting and statistical analysis device |
| CN102819966A (en) * | 2012-09-10 | 2012-12-12 | 南京航空航天大学 | Off-course flight passing time forecasting method based on radar tracks |
| CN104484717A (en) * | 2014-12-09 | 2015-04-01 | 中国航空工业集团公司第六三一研究所 | Onboard flight path prediction method based on current air route |
| 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 |
| US9569959B1 (en) * | 2012-10-02 | 2017-02-14 | Rockwell Collins, Inc. | Predictive analysis for threat detection |
| CN106651108A (en) * | 2016-10-25 | 2017-05-10 | 合肥飞友网络科技有限公司 | Method for scheduling airport vehicles according to flight information |
-
2017
- 2017-10-27 CN CN201711053273.2A patent/CN107808552B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101572019A (en) * | 2009-06-01 | 2009-11-04 | 民航数据通信有限责任公司 | Radar track fitting and statistical analysis device |
| CN102819966A (en) * | 2012-09-10 | 2012-12-12 | 南京航空航天大学 | Off-course flight passing time forecasting method based on radar tracks |
| US9569959B1 (en) * | 2012-10-02 | 2017-02-14 | Rockwell Collins, Inc. | Predictive analysis for threat detection |
| CN104484717A (en) * | 2014-12-09 | 2015-04-01 | 中国航空工业集团公司第六三一研究所 | Onboard flight path prediction method based on current air route |
| 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 |
| CN106651108A (en) * | 2016-10-25 | 2017-05-10 | 合肥飞友网络科技有限公司 | Method for scheduling airport vehicles according to flight information |
Non-Patent Citations (2)
| Title |
|---|
| LISHUAI LI ET AL.: "Anomaly detection via a Gaussian Mixture Model for flight operation and safety monitoring", 《TRANSPORTATION RESEARCH PART C: EMERGING TECHNOLOGIES》 * |
| 殷允楠: "空中交通流量统计预测技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108648511A (en) * | 2018-06-29 | 2018-10-12 | 飞友科技有限公司 | A method of judging that Aircraft Air spirals based on ADS-B data |
| CN109903554A (en) * | 2019-02-21 | 2019-06-18 | 长安大学 | A kind of road grid traffic operating analysis method based on Spark |
| CN110009545B (en) * | 2019-03-19 | 2023-01-24 | 中国民航大学 | Flight position information parallelization fusion method based on multiple data sources |
| CN110009545A (en) * | 2019-03-19 | 2019-07-12 | 中国民航大学 | A kind of flight location information parallelization fusion method based on multi-data source |
| CN110379210A (en) * | 2019-07-30 | 2019-10-25 | 四川九洲空管科技有限责任公司 | A kind of civil aircraft exception flight monitoring method and device |
| CN110379210B (en) * | 2019-07-30 | 2020-11-03 | 四川九洲空管科技有限责任公司 | Method and device for monitoring abnormal flight of civil aircraft |
| CN110751859A (en) * | 2019-10-17 | 2020-02-04 | 深圳市瑞达飞行科技有限公司 | Data processing method and device, computer system and readable storage medium |
| CN110827582A (en) * | 2019-10-25 | 2020-02-21 | 海南太美航空股份有限公司 | System and method for automatically acquiring flight landing point in emergency |
| CN110712765A (en) * | 2019-10-30 | 2020-01-21 | 北京航空航天大学 | Aircraft abnormal operation positioning method based on operation spectrum |
| CN110712765B (en) * | 2019-10-30 | 2021-06-18 | 北京航空航天大学 | Aircraft abnormal operation positioning method based on operation sequence |
| CN111695050A (en) * | 2020-05-29 | 2020-09-22 | 飞友科技有限公司 | Airport position navigation method and flight service system based on user behaviors |
| CN112182133A (en) * | 2020-09-29 | 2021-01-05 | 南京北斗创新应用科技研究院有限公司 | AIS data-based ship loitering detection method |
| CN112348960A (en) * | 2020-11-27 | 2021-02-09 | 中国人民解放军空军工程大学 | Airspace conflict detection method suitable for global space range |
| CN112348960B (en) * | 2020-11-27 | 2024-05-07 | 中国人民解放军空军工程大学 | Airspace conflict detection method suitable for global space range |
| CN113112876A (en) * | 2021-04-09 | 2021-07-13 | 河北师范大学 | Flight behavior detection method |
| CN113177097A (en) * | 2021-04-16 | 2021-07-27 | 江西航天鄱湖云科技有限公司 | Track initial discrimination method based on attribute clustering and space-time constraint |
| CN113177097B (en) * | 2021-04-16 | 2023-07-25 | 江西航天鄱湖云科技有限公司 | Track start judging method based on attribute clustering and space-time constraint |
| CN116052482A (en) * | 2023-04-03 | 2023-05-02 | 中航信移动科技有限公司 | Method for early warning of aircraft track yaw, electronic equipment and storage medium |
| CN116363908A (en) * | 2023-06-02 | 2023-06-30 | 中航信移动科技有限公司 | Flight track yaw detection method, electronic equipment and storage medium |
| CN116363908B (en) * | 2023-06-02 | 2023-08-04 | 中航信移动科技有限公司 | Flight track yaw detection method, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107808552B (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808552A (en) | Flight behavioral value method and apparatus | |
| CN104615849B (en) | A kind of flight plan assessment system and implementation method suitable for General Aviation | |
| CN105206057B (en) | Detection method and system based on Floating Car resident trip hot spot region | |
| US9310211B1 (en) | Extracting patterns from location history | |
| CN102859569B (en) | Determine the emergency condition landing point of aircraft | |
| CN103262141B (en) | Aircraft path conformance monitors | |
| US20150379408A1 (en) | Using Sensor Information for Inferring and Forecasting Large-Scale Phenomena | |
| CN103903101B (en) | A kind of General Aviation multi-source information supervising platform and method thereof | |
| Veloso et al. | Sensing urban mobility with taxi flow | |
| CN110555544B (en) | Traffic demand estimation method based on GPS navigation data | |
| CN105225541A (en) | Based on the method for Trajectory Prediction in short-term that blank pipe historical data is excavated | |
| CN110196962A (en) | A kind of air speed abnormality recognition method based on Density Estimator | |
| CN109191883A (en) | A kind of intelligent transportation system based on intelligent perception | |
| CN103164617B (en) | A kind of aircraft behavior prediction system and Forecasting Methodology | |
| Kapoor et al. | Airplanes aloft as a sensor network for wind forecasting | |
| Evans et al. | Using machine-learning to dynamically generate operationally acceptable strategic reroute options | |
| Rubnich et al. | An algorithm to identify robust convective weather avoidance polygons in en route airspace | |
| CN105241464B (en) | A kind of crane rail slash figure fast matching method | |
| US20230417372A1 (en) | Methods and internet of things (iot) systems for managing smart gas safety hazard items based on geographic information systems | |
| Hamdi et al. | Drone-as-a-service composition under uncertainty | |
| Lei et al. | A distance-based trajectory outlier detection method on maritime traffic data | |
| KR102422300B1 (en) | Method and system for providing climate information for port selection of urban air mobility | |
| Ryerson | Diversion ahead: Modeling the factors driving diversion airport choice | |
| Yang et al. | What-why analysis of expert interviews: Analysing geographically-embedded flow data | |
| CN106530838B (en) | A kind of method of aircraft flight profiles jump removal |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |