CN106779245A - Civil aviaton's needing forecasting method and device based on event - Google Patents
Civil aviaton's needing forecasting method and device based on event Download PDFInfo
- Publication number
- CN106779245A CN106779245A CN201710004030.3A CN201710004030A CN106779245A CN 106779245 A CN106779245 A CN 106779245A CN 201710004030 A CN201710004030 A CN 201710004030A CN 106779245 A CN106779245 A CN 106779245A
- Authority
- CN
- China
- Prior art keywords
- date
- current flight
- civil aviaton
- curve
- demand
- 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
- 238000013277 forecasting method Methods 0.000 title claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000002159 abnormal effect Effects 0.000 claims description 69
- 230000005856 abnormality Effects 0.000 claims description 13
- 238000012935 Averaging Methods 0.000 claims description 9
- 238000007726 management method Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000000714 time series forecasting Methods 0.000 description 1
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a kind of civil aviaton's needing forecasting method and device based on event.Wherein, the method includes：Date according to current flight has without exception, and the outer source event that will occur of same day date determines type of prediction of the current flight in the date to the factor of influence of civil aviaton's demand in course line where current flight；Type of prediction according to current flight in the date, Tian Ji civil aviaton requirement forecasting index of the prediction current flight in the date.By the present invention, solve the problems, such as that civil aviaton's requirement forecasting is inaccurate, add influence of the outer source event to civil aviaton's demand, improve the accuracy of civil aviaton's requirement forecasting.
Description
Technical field
The present invention relates to civil aviaton's data processing field, in particular to a kind of requirement forecasting side of civil aviaton based on event
Method and device.
Background technology
In civil aviaton field, the problem of airline yield management person is perplexed always is：How maximum revenue is being kept
Under the premise of, there is provided rational position in storehouse arrangement is meeting the trip requirements of the variation of air passenger, disordering.With Civil Aviation Industry
Fast development, the change of the Accurate Prediction market demand is the core demand of yield management department of airline, wherein, based on O＆D
The passenger flight requirement forecasting of (departure place ＆ reaches ground, also abbreviation OD) is most important for airline yield management person.Though
Right airline can easily obtain each course line historical passenger amount data at present, but a not analysis for maturation and pre-
Surveying model can reflect passenger's changes in demand following to flight, to provide decision support for yield management person.Therefore, how
The future trends of passenger flight demand can timely and effectively be predicted, for airline's yield management provides decision-making foundation,
It is the requirement to the new stage of information system.
Current technology can mainly realize the query function of each flight historical passenger amount based on O＆D, by history number
According to current passenger demand is reflected, can only accomplish to react the trend of current demand in real time, it is impossible to provide and change tomorrow requirement
Effective prediction of trend, thus it is little that such statistical model gives response time of yield management person.Even if having certain
Forecast function, also only considered the influence of historical data, have ignored influence of the objective event to changes in demand.From present situation,
In the long-term sales management in of domestic operator (referring generally to two weeks later flights), traditional market demand is mainly used
Measuring method, short-term sales management (within general two weeks) also depends on the experience of people, lacks to passenger flight demand
The prediction of variation tendency is measured, is supported for yield management person provides effective data.
The content of the invention
The invention provides a kind of civil aviaton's needing forecasting method and device based on event, with least solving correlation technique
The problem inaccurate to civil aviaton's requirement forecasting.
According to an aspect of the invention, there is provided a kind of civil aviaton's needing forecasting method based on event, including：According to work as
The date of preceding flight has without exception, and the outer source event that same day date will occur is to the current flight institute
In the factor of influence of civil aviaton's demand in course line, type of prediction of the current flight in the date is determined；According to described
Type of prediction of the current flight in the date, predicts Tian Ji civil aviaton demand of the current flight in the date
Predictive index.
Alternatively, having without exception according to the date of current flight, and same day date whether there is influence
The event of civil aviaton's demand, determined the current flight before the type of prediction of the date, and methods described also includes：Root
According to course line where the current flight week civil aviaton's demanding criteria curve and the course line civil aviaton's demand abnormal curve, really
The date of the fixed current flight has without exception；Obtain same day date will occur outer source event, and
The factor of influence of the outer source event to civil aviaton's demand in course line where the current flight is calculated according to preset strategy.
Alternatively, in the week civil aviaton's demanding criteria curve and course line according to where current flight course line
Civil aviaton's demand abnormal curve, determine the current flight the date have it is without exception before, methods described also includes：Solution
Analyse the journal file of Civil aviation information system and calculate Tian Ji civil aviatons demand data；By the identical week of course line where the current flight
The Tian Ji civil aviatons demand data of attribute, is averaging after rejecting abnormalities point, obtains the week civil aviaton demanding criteria curve；Will with institute
State the history in course line where current flight Query Dates civil aviaton demand curve week civil aviaton demand corresponding with its date
Standard curve is compared, and to paramorph history, Query Dates civil aviaton demand curve carries out K-means clusters, retains every
The center curve of class, as civil aviaton's demand abnormal curve in the course line.
Alternatively, the type of prediction according to the current flight in the date, predicts the current flight in institute
The Tian Ji civil aviatons requirement forecasting index for stating the date includes：It is to be taken off day described in the current flight in the type of prediction
The outer source event that phase is without exception and same day date of the current flight will occur where the current flight to navigating
In the case that the factor of influence of civil aviaton's demand of line is zero, according to the history Query Dates civil aviaton demand curve and the star
Phase civil aviaton's demanding criteria curve, predicts the Tian Ji civil aviaton requirement forecasting index of the current flight in the date.
Alternatively, the type of prediction according to the current flight in the date, predicts the current flight in institute
The Tian Ji civil aviatons requirement forecasting index for stating the date includes：It is to be taken off day described in the current flight in the type of prediction
The outer source event that same day date that there is abnormal and described current flight phase will occur where the current flight to navigating
In the case that the factor of influence of civil aviaton's demand of line is zero, according to the history Query Dates civil aviaton demand curve, the star
Phase civil aviaton's demanding criteria curve and civil aviaton's demand abnormal curve, predict the current flight described in the date
Tian Ji civil aviatons requirement forecasting index.
Alternatively, the type of prediction according to the current flight in the date, predicts the current flight in institute
The Tian Ji civil aviatons requirement forecasting index for stating the date includes：It is to be taken off day described in the current flight in the type of prediction
The outer source event that phase is without exception and same day date of the current flight will occur where the current flight to navigating
In the case that the factor of influence of civil aviaton's demand of line is not zero, the factor of influence is added to week civil aviaton demanding criteria
On curve, and history Query Dates civil aviaton demand curve is combined, predict the current flight in the date
The Tian Ji civil aviatons requirement forecasting index.
Alternatively, the type of prediction according to the current flight in the date, predicts the current flight in institute
The Tian Ji civil aviatons requirement forecasting index for stating the date includes：It is to be taken off day described in the current flight in the type of prediction
The outer source event that same day date that there is abnormal and described current flight phase will occur where the current flight to navigating
In the case that the factor of influence of civil aviaton's demand of line is not zero, according to history Query Dates civil aviaton demand curve, described
Week civil aviaton's demanding criteria curve and civil aviaton's demand abnormal curve, predict the current flight the of the date
One Tian Ji civil aviatons requirement forecasting index；The factor of influence is added on the week civil aviaton demanding criteria curve, and is combined
History Query Dates civil aviaton demand curve, predicts that second Tian Ji civil aviaton of the current flight in the date needs
Seek predictive index；According to the first Tian Ji civil aviatons requirement forecasting index and the second Tian Ji civil aviatons requirement forecasting index, really
The Tian Ji civil aviaton requirement forecasting index of the fixed current flight in the date.
According to another aspect of the present invention, a kind of civil aviaton's demand-prediction device based on event is additionally provided, including：The
One determining module, for having without exception according to the date of current flight, and same day date is outer by what is occurred
Source event determines that the current flight takes off day described to the factor of influence of civil aviaton's demand in course line where the current flight
The type of prediction of phase；Prediction module, for the type of prediction according to the current flight in the date, prediction is described to work as
Tian Ji civil aviaton requirement forecasting index of the preceding flight in the date.
Alternatively, described device also includes：Second determining module, for the week in the course line according to where the current flight
Civil aviaton's demanding criteria curve and civil aviaton's demand abnormal curve in the course line, determine the date of the current flight
Have without exception；First computing module, for obtaining the outer source event that same day date will occur, and according to preset strategy
Calculate the factor of influence of the outer source event to civil aviaton's demand in course line where the current flight.
Alternatively, described device also includes：Second computing module, by parse Civil aviation information system journal file and based on
Suan Tianji civil aviatons demand data；3rd computing module, for by the day level of the identical week attribute in course line where the current flight
Civil aviaton's demand data, is averaging after rejecting abnormalities point, obtains the week civil aviaton demanding criteria curve；4th computing module, uses
In by the history Query Dates civil aviaton demand curve week corresponding with its date with course line where the current flight
Civil aviaton's demanding criteria curve is compared, to paramorph history Query Dates civil aviaton demand curve carry out K-means gather
Class, retains the center curve per class, as civil aviaton's demand abnormal curve in the course line.
By the present invention, have without exception using according to the date of current flight, and same day date will occur
Outer source event to the factor of influence of civil aviaton's demand in course line where current flight, determine prediction of the current flight in the date
Type；Type of prediction according to current flight in the date, prediction current flight is pre- in the Tian Ji civil aviatons demand of date
The mode of index is surveyed, solves the problems, such as that civil aviaton's requirement forecasting is inaccurate, add influence of the outer source event to civil aviaton's demand, carried
The accuracy of Gao Liao civil aviatons requirement forecasting.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description does not constitute inappropriate limitation of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of civil aviaton's needing forecasting method according to embodiments of the present invention；
Fig. 2 is the structured flowchart of the civil aviaton's demand-prediction device based on event according to embodiments of the present invention；
Fig. 3 is the structural representation of civil aviaton's demand index forecast model according to the preferred embodiment of the invention；
Fig. 4 is the functional structure chart of civil aviaton's demand index forecast model according to the preferred embodiment of the invention；
Fig. 5 is the Organization Chart of civil aviaton's demand index forecast model according to the preferred embodiment of the invention；
Fig. 6 is the flow chart of anomaly according to the preferred embodiment of the invention；
Fig. 7 is the flow chart according to the treatment of type of prediction logical division according to the preferred embodiment of the invention.
Specific embodiment
Describe the present invention in detail below with reference to accompanying drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the feature in embodiment and embodiment in the application can be mutually combined.
It should be noted that term " first ", " in description and claims of this specification and above-mentioned accompanying drawing
Two " it is etc. for distinguishing similar object, without for describing specific order or precedence.
Embodiment 1
A kind of civil aviaton's needing forecasting method is provided in the present embodiment, and Fig. 1 is that civil aviaton according to embodiments of the present invention needs
The flow chart of Forecasting Methodology is sought, as shown in figure 1, the flow comprises the following steps：
Step S101, the date according to current flight has without exception, and the external source that same day date will occur
Event determines type of prediction of the current flight in the date to the factor of influence of civil aviaton's demand in course line where current flight；
Step S102, the type of prediction according to current flight in the date, prediction current flight is in the day of date
Level civil aviaton requirement forecasting index.
By above-mentioned steps, when the prediction of Tian Ji civil aviatons requirement forecasting index is carried out, it is considered to which outer source event is needed to civil aviaton
The factor of influence asked so that civil aviaton's requirement forecasting index can sense the influence of outer source event, improve civil aviaton's requirement forecasting
Accuracy.Following continuous many days Tian Ji civil aviatons requirement forecasting index is counted, can obtain following many days civil aviaton needs
Ask predictive index curve, the variation tendency of display civil aviaton requirement forecasting index.
Alternatively, having without exception according to the date of current flight, and same day date whether there is influence civil aviaton
The event of demand, determined current flight before the type of prediction of date, and method also includes：Navigated according to where current flight
Line week civil aviaton's demanding criteria curve and course line civil aviaton's demand abnormal curve, determine the date of current flight whether there is
It is abnormal；The outer source event that acquisition same day date will occur, and outer source event is calculated to current flight institute according to preset strategy
In the factor of influence of civil aviaton's demand in course line.
Alternatively, week civil aviaton's demanding criteria curve is generated in the following manner：Parse the day of Civil aviation information system
Will file simultaneously calculates Tian Ji civil aviatons demand data；By the Tian Ji civil aviatons demand number of the identical week attribute in course line where current flight
According to, it is averaging after rejecting abnormalities point, obtain week civil aviaton's demanding criteria curve.
Alternatively, civil aviaton's demand abnormal curve is obtained in the following manner：To be gone through with course line where current flight
Shi Yi Query Dates civil aviaton's demand curve week civil aviaton demanding criteria curve corresponding with its date is compared, to form
Query Dates civil aviaton demand curve carries out K-means clusters to abnormal history, retains the center curve per class, as course line
Civil aviaton's demand abnormal curve.
Alternatively, the type of prediction according to current flight in the date, the type of prediction includes four classes, i.e.,：It is without exception
Without event, have it is abnormal without event, it is without exception have an event, and have and abnormal have event.In pre- observation level civil aviaton requirement forecasting index
When, it is predicted using different prediction logic or forecast model according to different type of prediction.
For example, in type of prediction for the date of current flight is without exception and same day date of current flight will be sent out
In the case that raw outer source event is zero (thinking without event) to the factor of influence of civil aviaton's demand in course line where current flight,
According to history Query Dates civil aviaton demand curve and week civil aviaton's demanding criteria curve, prediction current flight is in the date
Tian Ji civil aviatons requirement forecasting index.
For example, in type of prediction for same day date that there are exception and current flight the date of current flight will be sent out
In the case that raw outer source event is zero (thinking without event) to the factor of influence of civil aviaton's demand in course line where current flight,
According to history Query Dates civil aviaton demand curve, week civil aviaton's demanding criteria curve and civil aviaton's demand abnormal curve, prediction is worked as
Tian Ji civil aviaton requirement forecasting index of the preceding flight in the date.
For example, in type of prediction for the date of current flight is without exception and same day date of current flight will be sent out
In the case that raw outer source event is not zero to the factor of influence of civil aviaton's demand in course line where current flight, factor of influence is folded
It is added on week civil aviaton's demanding criteria curve, and combines history Query Dates civil aviaton demand curve, prediction current flight is rising
Fly the Tian Ji civil aviatons requirement forecasting index on date.
For example, in type of prediction for same day date that there are exception and current flight the date of current flight will be sent out
In the case that raw outer source event is not zero to the factor of influence of civil aviaton's demand in course line where current flight, looked into according to history
Date civil aviaton's demand curve, week civil aviaton's demanding criteria curve and civil aviaton's demand abnormal curve are ask, prediction current flight is taking off
The first Tian Ji civil aviatons requirement forecasting index on date；Factor of influence is added on week civil aviaton's demanding criteria curve, and is combined
History Query Dates civil aviaton demand curve, second Tian Ji civil aviaton requirement forecasting index of the prediction current flight in the date；
According to the first Tian Ji civil aviatons requirement forecasting index and the second Tian Ji civil aviatons requirement forecasting index, determine current flight in the date
Tian Ji civil aviatons requirement forecasting index.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but a lot
In the case of the former be more preferably implementation method.Based on such understanding, technical scheme is substantially in other words to existing
The part that technology contributes can be embodied in the form of software product, and computer software product storage is in a storage
In medium (such as ROM/RAM, magnetic disc, CD), including some instructions are used to so that a station terminal equipment (can be mobile phone, calculate
Machine, server, or network equipment etc.) perform method described in each embodiment of the invention.
Embodiment 2
A kind of civil aviaton's demand-prediction device based on event is additionally provided in the present embodiment, and the device is above-mentioned for realizing
Embodiment and preferred embodiment, had carried out repeating no more for explanation.As used below, term " module " can be real
The combination of the software and/or hardware of existing predetermined function.Although the device described by following examples is preferably realized with software,
But hardware, or the realization of the combination of software and hardware is also that may and be contemplated.
Fig. 2 is the structured flowchart of the civil aviaton's demand-prediction device based on event according to embodiments of the present invention, such as Fig. 2 institutes
Show, the device includes：First determining module 21 and prediction module 22, wherein,
First determining module 21, for having without exception according to the date of current flight, and same day date will
The outer source event for occurring determines current flight in the date factor of influence of civil aviaton's demand in course line where current flight
Type of prediction；Prediction module 22, coupled to the first determining module 21, for according to current flight the date prediction class
Type, Tian Ji civil aviaton requirement forecasting index of the prediction current flight in the date.
Alternatively, device also includes：Second determining module, coupled to the first determining module 21, for according to current flight
Place course line week civil aviaton's demanding criteria curve and course line civil aviaton's demand abnormal curve, determine taking off day for current flight
Phase has without exception；First computing module, coupled to the first determining module 21, for obtaining the external source that same day date will occur
Event, and factor of influence of the outer source event to civil aviaton's demand in course line where current flight is calculated according to preset strategy.
Alternatively, device also includes：Second computing module, for parsing the journal file of Civil aviation information system and calculating day
Level civil aviaton demand data；3rd computing module, coupled to the second computing module and the second determining module, for by current flight institute
In course line, the Tian Ji civil aviatons demand data of identical week attribute, is averaging after rejecting abnormalities point, obtains week civil aviaton's demanding criteria
Curve；4th computing module, coupled to the 3rd computing module and the second determining module, for by with course line where current flight
Query Dates civil aviaton demand curve week civil aviaton demanding criteria curve corresponding with its date is compared history, to shape
Query Dates civil aviaton demand curve carries out K-means clusters to the abnormal history of state, retains the center curve per class, as course line
Civil aviaton's demand abnormal curve.
Alternatively, prediction module 22 is used in type of prediction as the date of current flight is without exception and current flight
Same day date is by the outer source event for occurring to situation that the factor of influence of civil aviaton's demand in course line where current flight is zero
Under, according to history Query Dates civil aviaton demand curve and week civil aviaton's demanding criteria curve, prediction current flight is in day of taking off
The Tian Ji civil aviatons requirement forecasting index of phase.
Alternatively, prediction module 22 is used in type of prediction as there are exception and current flight the date of current flight
Same day date is by the outer source event for occurring to situation that the factor of influence of civil aviaton's demand in course line where current flight is zero
Under, according to history Query Dates civil aviaton demand curve, week civil aviaton's demanding criteria curve and civil aviaton's demand abnormal curve, prediction
Tian Ji civil aviaton requirement forecasting index of the current flight in the date.
Alternatively, prediction module 22 is used in type of prediction as the date of current flight is without exception and current flight
The feelings that to the factor of influence of civil aviaton's demand in course line where current flight be not zero the outer source event for occurring by same day date
Under condition, factor of influence is added on week civil aviaton's demanding criteria curve, and combines history Query Dates civil aviaton demand curve,
Tian Ji civil aviaton requirement forecasting index of the prediction current flight in the date.
Alternatively, prediction module 22 is used in type of prediction as there are exception and current flight the date of current flight
The feelings that to the factor of influence of civil aviaton's demand in course line where current flight be not zero the outer source event for occurring by same day date
Under condition, according to history Query Dates civil aviaton demand curve, week civil aviaton's demanding criteria curve and civil aviaton's demand abnormal curve, in advance
Survey first Tian Ji civil aviaton requirement forecasting index of the current flight in the date；Factor of influence is added to week civil aviaton's demand mark
On directrix curve, and history Query Dates civil aviaton demand curve is combined, the second day level people of the prediction current flight in the date
Boat requirement forecasting index；According to the first Tian Ji civil aviatons requirement forecasting index and the second Tian Ji civil aviatons requirement forecasting index, it is determined that working as
Tian Ji civil aviaton requirement forecasting index of the preceding flight in the date.
It should be noted that above-mentioned modules can be by software or hardware to realize, for the latter, Ke Yitong
Cross in the following manner realization, but not limited to this：Above-mentioned module is respectively positioned in same processor；Or, above-mentioned module is located at many respectively
In individual processor.
Embodiment 3
Embodiments of the invention additionally provide a kind of software, and the software is used to perform above-described embodiment and preferred embodiment
Described in technical scheme.
Embodiment 4
Embodiments of the invention additionally provide a kind of storage medium.In the present embodiment, above-mentioned storage medium can be set
Storage is set to for performing the program code of following steps：
Step S101, the date according to current flight has without exception, and the external source that same day date will occur
Event determines type of prediction of the current flight in the date to the factor of influence of civil aviaton's demand in course line where current flight；
Step S102, the type of prediction according to current flight in the date, prediction current flight is in the day of date
Level civil aviaton requirement forecasting index.
Alternatively, in the present embodiment, above-mentioned storage medium can be included but is not limited to：USB flash disk, read-only storage (Read-
Only Memory, referred to as ROM), it is random access memory (Random Access Memory, referred to as RAM), mobile hard
Disk, magnetic disc or CD etc. are various can be with the medium of store program codes.
Alternatively, the specific example in the present embodiment may be referred to described in above-described embodiment and optional embodiment
Example, the present embodiment will not be repeated here.
In order that the description of the embodiment of the present invention is clearer, it is described with reference to preferred embodiment and is illustrated.
Embodiment 5
Supported to provide more intelligent requirement forecasting to airline's yield management, the present embodiment proposes a kind of civil aviaton
Demand index forecast model, each channel full dose inquiry data are gathered based on big data platform, and data source scope is wide, and market is felt
Intellectual is strong, and data, user's inquiry log data are embarked on journey as data source with civil aviation passenger anonymity, relates generally to anomaly, event
With demand index correlation, demand index predict etc. nucleus module.Date and record day of the anomaly to be calculated
Based on phase demand index curve, by analytical standard curve, exceptional value is calculated, the abnormal date is classified, and then
Realize anomaly.The calculating of event and demand index correlation, by building event and demand correlation models, by external source thing
Part input model is simultaneously calculated influence degree of the event to tomorrow requirement index.Demand index prediction first judges that the date has
It is without exception, whether there is event, then carried out by classification using data such as Standard Curve Database, abnormal curve storehouse and event influence powers pre-
Survey, obtain day level forecast demand index.
To achieve the above object, daily record of the civil aviaton's demand index forecast model that the present embodiment is provided from boat letter AVE systems
Middle acquisition demand index day DBMS, is stored in Hive tables, and its content needs to include such as flight takeoff date, departure place, purpose
Ground, user's query time etc..During external source event base is input into social event and demand index correlation models, thing is calculated
Part influence power, this module is independent off-line operation.Main system is first using demand index data initialization week standard curve, different
Normal curve is stored in Hive tables, realizes that anomaly algorithm finds that date curve wicket is stored in Hive tables extremely.Then
Using demand index data, standard curve data, abnormal curve data carry out demand index prediction, and can be periodically to standard curve
Storehouse and abnormal curve storehouse are iterated renewal.
Fig. 3 is the structural representation of civil aviaton's demand index forecast model according to the preferred embodiment of the invention, such as Fig. 3 institutes
Show, civil aviaton's demand index forecast model includes the external source event base developed by Java on unit, by Spark in Hadoop platform
The demand index results model of exploitation, Hive databases, event and demand correlation models, demand index forecast model, and
Predict the outcome output/display module.
Fig. 4 is the functional structure chart of civil aviaton's demand index forecast model according to the preferred embodiment of the invention, and Fig. 5 is basis
The Organization Chart of civil aviaton's demand index forecast model of the preferred embodiment of the present invention.With reference to the people that Fig. 4 and Fig. 5, the present embodiment are provided
The handling process of boat demand index forecast model is comprised the following steps and link：
1. data prediction：Day level demand index is calculated, and according to the Hive tables of certain format output storage to Hadoop
In.
2. Standard Curve Database is set up and is updated：Using demand index data, for different course lines to its same week attribute
Demand index data processed, be averaging after rejecting abnormalities point, the week standard curve for obtaining every course line is stored in standard
Curve library.Determine that whether normal its corresponding record date curve is according to date label, local updating week standard curve, if
Week, standard curve did not existed, then newly-increased week standard curve, will update or newly-increased result is stored in Hive tables.
3. abnormal curve storehouse is set up and is updated：Date corresponding many days (such as 80 days) for newly increasing has inquired about
Date curve, week standard curve corresponding with the date compares, and K- is carried out to the more abnormal collection of curves of form
Means is clustered, and is retained the center curve per class and is stored in abnormal curve storehouse.There is the Query Dates curve of certain product collection
And week standard curve, the curve of inquiry of the product collection is added into abnormal curve storehouse if exception is showed, and result is stored in
In Hive tables.
4. event and demand correlation calculations：Structure event and demand correlation models, by outer source event input model simultaneously
It is calculated influence of the event to tomorrow requirement index.
5. anomaly：It can be found that near the date whether there is on the course line demand influential abnormal time of tool with
Anomalous event.Using demand index data and date standard curve, record date standard curve, date curve is found
Wicket abnormality is stored in Hive tables.It is different by calculating date curve wicket in anomaly with reference to Fig. 6
Constant value, record date curve configuration exceptional value and record date curve abnormality value, are carried out by categorised decision tree to abnormal
Classification.
6. Fig. 7 is referred to, demand index predicts that this module first judges that the date has the without exception, event of whetheing there is to be divided into four species
Type, is then predicted using data such as Standard Curve Database, abnormal curve storehouse and event influence powers by above-mentioned different type, is obtained
To day level forecast demand index.
This preferred embodiment is described and illustrated below by instantiation.
The system for civil aviaton's demand index prediction that this example is proposed is built comprising data preprocessing module, Standard Curve Database
Formwork erection block, abnormal curve storehouse set up module, event and demand correlation module, anomaly algoritic module, demand index prediction
Module, Standard Curve Database update module, abnormal curve storehouse update module.Function to modules in table 1 is described.
The system module of table 1 is described
The model for civil aviaton's demand index prediction that this example is proposed, it is first determined from analysis current date is following 59 days
Fly date curve and each date 80 days record date curves of corresponding history；Then certain is determined according to anomaly algorithm
Individual date Exception Type label, mobile current date, the multiple record date curve abnormality type labels of generation judge record
Whether is date curve abnormality, sets up Standard Curve Database and abnormal curve storehouse；Mould is predicted finally according to different classes of demand index
Type, is adjusted to standard curve, exception and event influence power etc., and comprehensive Query Dates curve generates final demand index
Prediction curve.
As shown in Figure 3 and Figure 5, what this example was proposed is used to realize following steps for civil aviaton's demand index forecast model：
Step 1, data prediction：Day level demand index is calculated, and arrives Hadoop's according to certain format output storage
In Hive tables.Its table structure is as shown in table 2.
The storage organization of table 2
Step 2, Standard Curve Database is set up and is updated.Standard Curve Database is set up, using demand index data, for different boats
Line is processed the demand index data of its same week attribute, is averaging after rejecting abnormalities point, obtains every star in course line
Phase standard curve is stored in Standard Curve Database.For example, in one embodiment, the algorithm is according in January, 2016 in May, 2016
Demand index data, the traversal date generates Query Dates curve.To ensure that Query Dates curve number of days is 80, is set
Date scope on March 21st, 2016 between 1 day June in 2016, by the identical week attribute in same course line
Query Dates curve removal outlier average, obtain every the 7 of course line week standard curve, specific implementation procedure is such as
Under：
The Query Dates of a, acquisition all course line dates in the daily range of June 1 of 21 days to 2016 March in 2016
Curve；
B, the week attribute that the date attribute of the curve of Query Dates for obtaining is converted to the date；
C, according to course line and week attribute to Query Dates curve classification；
D, definition p are represented p-th point on a curve, and value is 0~79, and to certain A class ourve, same position demand refers to
Number and be sumIndex [p], same position demand index for 0 points and be number [p]；
If e, number [p] are not equal to 0, position mean aveIndex [p]=sumIndex [p]/number
[p], otherwise aveIndex [p]=0；
F, such curve is successively read, calculates whether its 80 points tempIndex [p] are outlier respectively, defining point
Departure degree, by result of calculation (Ratio) be compared in week standard curve outlier threshold value (ratioThreshold) as
Fruit Ratio>RatioThreshold, then be outlier, sumIndex [p]=sumIndex [p]-tempIndex [p],
Number [p]=number [p] -1；
G, the curve of Query Dates of the same week attribute in same course line are obtained with being averaging after position removal outlier
The one week standard curve in the course line, all week standard curves in all course lines are saved in Hive tables.
When newly-generated 80 days inquiry curves, in date in the corresponding week according to the curve, Standard Curve Database is updated
In corresponding week standard curve, the process is：If week standard curve is present, taking off day for curve was inquired about according to new 80 days
Phase label determines that whether normal its corresponding record date curve is, local updating week standard curve, if week standard curve is not deposited
It is corresponding week standard curve in, the curve, will updates or newly-increased result is stored in Hive tables.Specific flow is as follows：
A, the week standard curve for obtaining all course lines；
B, each date curve wicket include 3 points, therefore each date point possesses three abnormal labels,
First label for selecting the point is normal, tag as the abnormal conditions tag, tag=1 of the date point under current date
=0 is abnormal；
C, the abnormal conditions for obtaining each date point on date curve, take each date corresponding history
The demand index curve of 21 days；
D, to each product collection, if date corresponding label tag=1, judge whether week standard
Curve, if in the presence of taking 21 days demand index curves of the date corresponding history by weights to the right of week standard curve
Answering 21 points carries out local updating, otherwise, increases the corresponding part of week standard curve；
E, by after renewal or newly-increased week standard curve result is stored in Hive tables.
Step 3, abnormal curve storehouse is set up and is updated：Date, corresponding week standard curve compared, more abnormal to form
Line carries out K-means clusters, retains the center curve per class and is stored in abnormal storehouse.According in January, 2016 to the demand in May in 2016
Exponent data, the traversal date generates Query Dates curve.To ensure that Query Dates curve number of days is 80, setting is taken off
Date range on March 21st, 2016 between 1 day June in 2016, by Query Dates curve and its date pair
Answer week standard curve to be compared and obtain abnormal curve, abnormal curve is clustered, obtain class center curve and be stored to exception
Storehouse, specific implementation procedure is as follows：
A, the week standard curve for obtaining all course lines；
The Query Dates of b, acquisition all course line dates in the daily range of June 1 of 21 days to 2016 March in 2016
Curve；
C, Query Dates curve is read, sum is obtained to its 80 points summations respectively, if sum<
HisSumThreshold is then filtered, and wherein hisSumThreshold is to have inquired about exponent sum threshold value；
D, to filtering after Query Dates curve, obtain the date corresponding week attribute of every curve, calculate
The COS distance CosValue of Query Dates and its standard curve, if CosValue in week>CosThreshold is then designated as
Abnormal curve, wherein cosThreshold are COS distance exception judgment threshold；
E, setting abnormal curve classification sum are typeCount, carry out Kmeans algorithms to abnormal curve and cluster, and are obtained
To typeCount classes, position curve addition abnormal curve storehouse in Qu Qi centers is simultaneously stored in Hive tables.
There is the curve of Query Dates of certain product collection and week standard curve, added if exception is showed abnormal
Storehouse, result is stored in Hive tables, and specific implementation procedure is as follows：
A, acquisition all of old abnormal curve and newly-generated Query Dates curve；
B, Query Dates curve date corresponding week attribute is calculated, obtain Query Dates curve and its star
The COS distance CosValue of phase standard curveHC,SCIf, CosValueHC,SC<CosThreshold is then filtered；
The COS distance CosValue of c, the curve calculated in the remaining curve of Query Dates and abnormal curve storehouseHC,EC,
If CosValueHC,EC>CosThreshold then adds abnormal curve storehouse；
D, result is saved in Hive tables.
Step 4, event and demand correlation calculations：Structure event and demand correlation models, mould is input into by outer source event
Type is simultaneously calculated influence of the event to tomorrow requirement index.
Step 5, anomaly：Using demand index data and date standard curve, record date standard curve, hair
Existing date curve wicket abnormality is stored in Hive tables.By calculating date curve wicket exceptional value, note
Record date curve configuration exceptional value and record date curve abnormality value, are classified by categorised decision tree to abnormal, are had
The explanation of body exceptional value, implementation procedure and Trajectory are as follows.
A, calculating date curve wicket exceptional value：
Current time curve and the course line standard are not only allowed for when exceptional value in date curve wicket is calculated
The comparable situation of curve, also compares the wicket with other course lines with time inquiring situation, and considered current time
The overall fluctuation situation of curve.Wherein compare the physical distance of current curves and standard curve by Euclidean distance, by cosine
Distance compares the morphological differences of current curves and other course lines.Calculate after exceptional value again divided by " integrated curved subtracts standard curve
Standard deviation ", one be reflect whole piece curve fluctuation it is smaller, abnormal conditions are more prominent in the wicket；Two is by different course lines
The curve of varying number level is normalized in the range of an exceptional value.Specific date wicket exceptional value computing formula is such as
Under：
fdxOD,i∈ fd | current time inquires about i-th wicket curve of date of all OD in addition to the OD }
In above formula,
Sgn(fdOD,i-standardfdOD,i) represent certain OD dates i-th wicket of curve and subtract the OD and rise
Fly the symbol with after of i-th wicket of date standard curve.
Eud(fdOD,i,standardfdOD,i) represent certain i-th wicket of OD dates curve and the OD dates
The Euclidean distance of i-th wicket of standard curve.
Ave[Cosine(fdOD,i,fdxOD,i)] represent that certain i-th wicket of OD dates curve rises with every other OD
Fly the average value of the COS distance of date i-th wicket of curve.
StdDev(fdOD-standardfdOD) represent that certain OD date curve subtracts OD date standard curves
Standard deviation afterwards.
B, calculating record date curve configuration exceptional value：
Record date curve configuration reflects record date curve and the modal otherness of standard curve, specific meter
Calculate formula as follows：
In above formula, Cosine (rdOD,i,standardrdOD,i) represent i-th wicket institute of certain OD dates curve
The COS distance of the record date standard curve of corresponding record date curve and the wicket.
C, calculating record date curve wicket exceptional value：
Record date curve wicket exceptional value reflects the unusual condition in a certain window of record date curve, finds out and works as
Preceding record date curve differs maximum window with standard curve, then the Integrated comparative window and other course lines morphological differences,
And consider the overall fluctuation situation of the curve and draw exceptional value.
fdxOD,i,k∈ rd | it is right that current time inquires about i-th wicket institute of all OD dates curves in addition to the OD
Should
K-th wicket of record date curve }
In above formula,
max[Eud(rdOD,i,standardrdOD,i)] represent the corresponding record of certain i-th wicket of OD dates curve
The maximum of the Euclidean distance of the record date standard curve of date curve and the wicket.
Ave[Cosine(rdOD,i,k,rdxOD,i,k)] represent the corresponding record of certain i-th wicket of OD dates curve
K-th wicket (it is maximum that the wicket compares Euclidean distance with standard curve) and the every other OD dates of date curve
The average value of the COS distance of k-th wicket of record date curve corresponding to i-th wicket of curve.
StdDev(rdOD,i-standardrdOD,i) represent the corresponding record of i-th wicket of certain OD date curve
Date curve subtracts the standard deviation after the record date standard curve of the wicket.
D, by calculating anomaly classification method shown in exceptional value combination Fig. 6 and then completing anomaly and anomaly classification.
Step 6, demand index prediction：Time series forecasting generally requires four aspect factors of consideration：Long-term trend, season become
Dynamic, cyclical swing and erratic variation.First three items can be obtained by traditional prediction method, and erratic variation is then abnormal by analyzing
Obtained with event：According to early stage anomaly algorithm, window is converted to an exception extremely, judges whether certain date point is deposited
In exception；Searched in outer source event storehouse, judge whether certain city has event on date, by building event with demand correlation
Model, obtains the influence power that event is brought to demand.According to have it is without exception, whether there is event category model, according to Fig. 7 forecast models
Sorting technique, is predicted using data such as Standard Curve Database, abnormal curve storehouse and event influence powers by classification, obtains day level pre-
Survey demand index.The prediction process needs the principle for following as follows：
Whether abnormal, the history curve data in normative reference curve library or abnormal curve storehouse of the date according to prediction
It is predicted；
Date according to prediction whether there is event, if there is event, the influence force data of event be added pre-
Survey and be predicted in model.
In sum, by the above embodiment of the present invention, the effective prediction to following passenger flight demand can be realized,
It is input with passenger's history flight inquiring demand, abnormal curve is found out in the classification to passenger flight demand Self-variation trend, ties
Conjunction event obtains the changes in demand trend to following each date of a period of time to the influence of demand.By model
Calculate, can fast and accurately export and predict the outcome, the addition of event factor improves the accuracy of prediction.
The preferred embodiments of the present invention are the foregoing is only, is not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.It is all within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of civil aviaton's needing forecasting method based on event, it is characterised in that including：
Date according to current flight has without exception, and the outer source event that same day date will occur is to described
The factor of influence of civil aviaton's demand in course line, determines prediction class of the current flight in the date where current flight
Type；
Type of prediction according to the current flight in the date, predicts the current flight in the date
Tian Ji civil aviatons requirement forecasting index.
2. method according to claim 1, it is characterised in that having without exception according to the date of current flight, with
And same day date whether there is the event of influence civil aviaton demand, determines prediction of the current flight in the date
Before type, methods described also includes：
According to course line where the current flight week civil aviaton's demanding criteria curve and the course line civil aviaton's demand exception
Curve, determining the date of the current flight has without exception；
The outer source event that same day date will occur is obtained, and the outer source event is calculated to described according to preset strategy
The factor of influence of civil aviaton's demand in course line where current flight.
3. method according to claim 2, it is characterised in that in the week civil aviaton in the course line according to where the current flight
Demanding criteria curve and civil aviaton's demand abnormal curve in the course line, determine the date of the current flight whether there is
Before exception, methods described also includes：
Parse the journal file of Civil aviation information system and calculate Tian Ji civil aviatons demand data；
By the Tian Ji civil aviatons demand data of the identical week attribute in course line where the current flight, it is averaging after rejecting abnormalities point,
Obtain the week civil aviaton demanding criteria curve；
By the history Query Dates civil aviaton demand curve star corresponding with its date with course line where the current flight
Phase civil aviaton's demanding criteria curve is compared, and to paramorph history, Query Dates civil aviaton demand curve carries out K-means
Cluster, retains the center curve per class, as civil aviaton's demand abnormal curve in the course line.
4. method according to claim 3, it is characterised in that according to the current flight the date prediction
Type, predicts that Tian Ji civil aviaton requirement forecasting index of the current flight in the date includes：
Date that the type of prediction is the current flight is without exception and the current flight described in take off
The same day on date is by the outer source event for occurring to situation that the factor of influence of civil aviaton's demand in course line where the current flight is zero
Under, according to the history Query Dates civil aviaton demand curve and the week civil aviaton demanding criteria curve, predict described current
The Tian Ji civil aviaton requirement forecasting index of the flight in the date.
5. method according to claim 3, it is characterised in that according to the current flight the date prediction
Type, predicts that Tian Ji civil aviaton requirement forecasting index of the current flight in the date includes：
Have described in abnormal and described current flight in the date that the type of prediction is the current flight and take off
The same day on date is by the outer source event for occurring to situation that the factor of influence of civil aviaton's demand in course line where the current flight is zero
Under, according to the history Query Dates civil aviaton demand curve, the week civil aviaton demanding criteria curve and civil aviaton's demand
Abnormal curve, predicts the Tian Ji civil aviaton requirement forecasting index of the current flight in the date.
6. method according to claim 3, it is characterised in that according to the current flight the date prediction
Type, predicts that Tian Ji civil aviaton requirement forecasting index of the current flight in the date includes：
Date that the type of prediction is the current flight is without exception and the current flight described in take off
The feelings that to the factor of influence of civil aviaton's demand in course line where the current flight be not zero the outer source event for occurring by the same day on date
Under condition, the factor of influence is added on the week civil aviaton demanding criteria curve, and combines history Query Dates
Civil aviaton's demand curve, predicts the Tian Ji civil aviaton requirement forecasting index of the current flight in the date.
7. method according to claim 3, it is characterised in that according to the current flight the date prediction
Type, predicts that Tian Ji civil aviaton requirement forecasting index of the current flight in the date includes：
Have described in abnormal and described current flight in the date that the type of prediction is the current flight and take off
The feelings that to the factor of influence of civil aviaton's demand in course line where the current flight be not zero the outer source event for occurring by the same day on date
Under condition, according to the history Query Dates civil aviaton demand curve, the week civil aviaton demanding criteria curve and civil aviaton's need
Abnormal curve is sought, first Tian Ji civil aviaton requirement forecasting index of the current flight in the date is predicted；By the shadow
Ring the factor to be added on the week civil aviaton demanding criteria curve, and combine history Query Dates civil aviaton demand curve,
Predict second Tian Ji civil aviaton requirement forecasting index of the current flight in the date；According to the first Tian Ji civil aviatons
Requirement forecasting index and the second Tian Ji civil aviatons requirement forecasting index, determine institute of the current flight in the date
Shu Tianji civil aviatons requirement forecasting index.
8. a kind of civil aviaton's demand-prediction device based on event, it is characterised in that including：
First determining module, for having without exception according to the date of current flight, and same day date will be sent out
Raw outer source event determines the current flight described the factor of influence of civil aviaton's demand in course line where the current flight
The type of prediction of date；
Prediction module, for the type of prediction according to the current flight in the date, predicts that the current flight exists
The Tian Ji civil aviatons requirement forecasting index of the date.
9. device according to claim 8, it is characterised in that described device also includes：
Second determining module, for the week civil aviaton's demanding criteria curve and boat according to course line where the current flight
Civil aviaton's demand abnormal curve of line, determining the date of the current flight has without exception；
First computing module, for obtain same day date will occur outer source event, and according to preset strategy calculate
The factor of influence of the outer source event to civil aviaton's demand in course line where the current flight.
10. device according to claim 9, it is characterised in that described device also includes：
Second computing module, for parsing the journal file of Civil aviation information system and calculating Tian Ji civil aviatons demand data；
3rd computing module, for by the Tian Ji civil aviatons demand data of the identical week attribute in course line where the current flight, picking
Except being averaging after abnormity point, the week civil aviaton demanding criteria curve is obtained；
4th computing module, for by with the current flight where course line history Query Dates civil aviaton demand curve and its
Date, corresponding week civil aviaton demanding criteria curve was compared, to paramorph history Query Dates civil aviaton demand
Curve carries out K-means clusters, retains the center curve per class, as civil aviaton's demand abnormal curve in the course line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710004030.3A CN106779245B (en) | 2017-01-04 | 2017-01-04 | Event-based civil aviation demand prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710004030.3A CN106779245B (en) | 2017-01-04 | 2017-01-04 | Event-based civil aviation demand prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106779245A true CN106779245A (en) | 2017-05-31 |
| CN106779245B CN106779245B (en) | 2020-09-04 |
Family
ID=58949443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710004030.3A Active CN106779245B (en) | 2017-01-04 | 2017-01-04 | Event-based civil aviation demand prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779245B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451750A (en) * | 2017-08-10 | 2017-12-08 | 中国民航信息网络股份有限公司 | Civil aviaton's demand anomaly method and apparatus |
| CN109598378A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Medical insurance prediction technique, device, equipment and computer readable storage medium |
| CN109711894A (en) * | 2018-12-28 | 2019-05-03 | 携程旅游网络技术（上海）有限公司 | The detection method and system of course line demand exception |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831487A (en) * | 2012-08-13 | 2012-12-19 | 南京莱斯信息技术股份有限公司 | Flow predicted result verification method based on historical scheduled flight running data analysis |
| CN104036446A (en) * | 2014-06-13 | 2014-09-10 | 中国民航信息网络股份有限公司 | Civil aviation information system based system and method for predicting preorder flight of duty flight |
| CN104077915A (en) * | 2014-03-27 | 2014-10-01 | 中华电信股份有限公司 | Riding trend prediction device and method |
-
2017
- 2017-01-04 CN CN201710004030.3A patent/CN106779245B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831487A (en) * | 2012-08-13 | 2012-12-19 | 南京莱斯信息技术股份有限公司 | Flow predicted result verification method based on historical scheduled flight running data analysis |
| CN104077915A (en) * | 2014-03-27 | 2014-10-01 | 中华电信股份有限公司 | Riding trend prediction device and method |
| CN104036446A (en) * | 2014-06-13 | 2014-09-10 | 中国民航信息网络股份有限公司 | Civil aviation information system based system and method for predicting preorder flight of duty flight |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451750A (en) * | 2017-08-10 | 2017-12-08 | 中国民航信息网络股份有限公司 | Civil aviaton's demand anomaly method and apparatus |
| CN109598378A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Medical insurance prediction technique, device, equipment and computer readable storage medium |
| CN109711894A (en) * | 2018-12-28 | 2019-05-03 | 携程旅游网络技术（上海）有限公司 | The detection method and system of course line demand exception |
| CN109711894B (en) * | 2018-12-28 | 2020-10-30 | 携程旅游网络技术（上海）有限公司 | Method and system for detecting abnormal flight path requirements |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106779245B (en) | 2020-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108415789B (en) | Node fault prediction system and method for large-scale hybrid heterogeneous storage system | |
| CN109495296B (en) | Intelligent substation communication network state evaluation method based on clustering and neural network | |
| CN107067164B (en) | A kind of index Method of fast estimating and system | |
| EP4020315A1 (en) | Method, apparatus and system for determining label | |
| TW201615844A (en) | Method and system of cause analysis and correction for manufacturing data | |
| CN110674993A (en) | User load short-term prediction method and device | |
| CN111636891B (en) | Real-time shield attitude prediction system and construction method of prediction model | |
| CN105868373A (en) | Method and device for processing key data of power service information system | |
| CN105843189B (en) | A kind of efficient scheduling rule selection method for semiconductor production line based on simplified simulation model | |
| CN111367777B (en) | Alarm processing method, device, equipment and computer readable storage medium | |
| CN108470022A (en) | A kind of intelligent work order quality detecting method based on operation management | |
| Huang et al. | A weighted fuzzy C-means clustering method with density peak for anomaly detection in IoT-enabled manufacturing process | |
| CN106779245A (en) | Civil aviaton's needing forecasting method and device based on event | |
| CN117557299B (en) | Marketing planning method and system based on computer assistance | |
| CN109685567A (en) | Electricity customer portrait new method based on convolutional neural network and fuzzy clustering | |
| CN110689162A (en) | Bus load prediction method, device and system based on user side classification | |
| CN112860769A (en) | Energy planning data management system | |
| US20230402846A1 (en) | Data analysis system and method | |
| CN117668583A (en) | Investment optimization method based on artificial intelligent investment research | |
| CN115952914A (en) | Big data-based electric power metering operation and maintenance work judgment planning method | |
| CN103714251A (en) | Method, device and system for matching semiconductor product with machining device | |
| CN110866317A (en) | Design tool kit reconstruction method based on product historical information and design behavior analysis | |
| CN116308494A (en) | Supply chain demand prediction method | |
| Mao et al. | Naive Bayesian algorithm classification model with local attribute weighted based on KNN | |
| CN112330164B (en) | Data quality management system and method based on message bus |
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 |