CN109961192A - Object event prediction technique and device - Google Patents
Object event prediction technique and device Download PDFInfo
- Publication number
- CN109961192A CN109961192A CN201910267176.6A CN201910267176A CN109961192A CN 109961192 A CN109961192 A CN 109961192A CN 201910267176 A CN201910267176 A CN 201910267176A CN 109961192 A CN109961192 A CN 109961192A
- Authority
- CN
- China
- Prior art keywords
- prediction
- object event
- reference data
- data
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012549 training Methods 0.000 claims description 19
- 238000013135 deep learning Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002441 reversible effect Effects 0.000 claims description 6
- 241000208340 Araliaceae Species 0.000 claims description 5
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 5
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 5
- 235000008434 ginseng Nutrition 0.000 claims description 5
- 230000001052 transient effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 208000025274 Lightning injury Diseases 0.000 description 47
- 238000010586 diagram Methods 0.000 description 15
- 230000001681 protective effect Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 230000000694 effects Effects 0.000 description 9
- 230000002411 adverse Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000003111 delayed effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- APTZNLHMIGJTEW-UHFFFAOYSA-N pyraflufen-ethyl Chemical compound C1=C(Cl)C(OCC(=O)OCC)=CC(C=2C(=C(OC(F)F)N(C)N=2)Cl)=C1F APTZNLHMIGJTEW-UHFFFAOYSA-N 0.000 description 2
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000422846 Sequoiadendron giganteum Species 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000926 separation method 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)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the present invention provides a kind of object event prediction technique and device.The described method includes: obtaining the reference data of the object event of target area；Wherein, the target area includes at least two subregions, and the reference data is the number that the object event occurs in previous predetermined period of object time for the subregion；The reference data includes the data of at least two groups difference predetermined time；The reference data is input to preset prediction model, the predetermined time of the object event in the latter predetermined period of object time is obtained, the prediction data of the prediction number of the object event occurs in each subregion.Object event prediction technique provided in an embodiment of the present invention and device can predict the bad weathers such as thunder and lightning in aviation operation field.
Description
Technical field
The present embodiments relate to technical field of data processing more particularly to a kind of object event prediction technique and devices.
Background technique
In recent years, as Civil Aviation Industry rapidly develops, air transportation amount is sharply increased, and all kinds of flight sortie of taking off and landing numbers continue
Increase.While air transportation amount increases, the efficiency and safety of AIRLINE & AIRPORT are also required to improve and protect evident.Specifically, civil aviaton
Flight operation is higher to the degree of dependence of weather, and the delay of flight caused by adverse weather accounts for very big in entire flight delay amount
Ratio, and thunder and lightning weather on it is delayed influence be particularly acute.
Thunder and lightning is the strong electric discharge phenomena in nature, itself belongs to explosive natural hazard, is mainly shown as with thunder
It rings, the electric discharge phenomena of lightning, and under the conditions of different atural objects, and there are different thunders and lightnings to show.From the general atural object condition of lightening activity
From the point of view of, building, receiving antenna, transmission line of electricity, big tree and other equipment for having point discharge characteristic are isolated in field,
Vulnerable to lightning stroke；Especially for equipment such as electronization, informationizations, harm performance is more obvious.
By taking current Civil Aviation Airport as an example, modernizes in airport construction and be gradually introduced more electronic equipment, such as runway
Navigation equipment, programme-controlled exchange command equipment, satellite receiving equipment, command centre's equipment, high frequency transceiver, thunder in control tower
Up to equipment, automatic message switching equipment and microwave telecommunication devices etc., these electronic equipments keep higher sensibility to thunder and lightning.Though
The performance of right current electronic device is constantly enhanced, adjusts, but due to being both needed to control within the scope of certain voltage in its operation, institute
To be difficult to cope with for thunder and lightning bring high pressure；It when electronic equipment is in operating status, is influenced by lightning stroke, it is likely that straight
Existing equipment damage problem is picked out, therefore related data documented by electronic equipment may also disappear, it will affect airport overall operation,
It is severely impacted aircraft safety.
Meanwhile if lightning stroke occurs in the operation process of airport will also result in serious accident.
Currently, the traffic management means that civil aviaton field uses generally include strategic phases and tactics stage.Strategic phases
Work is to reasonably adjust route structure, when reasonable arrangement formulates the flight of timetable table and flight proxima luce (prox. luc) to non-periodically flight
Quarter is coordinated.The work in tactics stage mainly when bad weather occurs, generally takes plan suitable the flight not taken off
Prolong, the flight to have taken off is generally taken and increases flight interval, spiraling in the air waits or make preparation for dropping to measures such as designated airports；
And when flow is excessive in control zone, sector is increased in time, limits other regulatory area aircrafts into this regulatory area time.For
The work for effectively completing the tactics stage, need to predict boisterous.
Therefore, in the prior art, prediction boisterous to thunder and lightning etc. is of great significance to aviation operation.
Summary of the invention
The embodiment of the present invention provides a kind of object event prediction technique and device, in aviation operation field to thunder and lightning etc.
Bad weather is predicted.
On the one hand, the embodiment of the present invention provides a kind of object event prediction technique, which comprises
Obtain the reference data of the object event of target area；Wherein, the target area includes at least two subregions,
The reference data is the number that the object event occurs in previous predetermined period of object time for the subregion；Institute
State the data that reference data includes at least two groups difference predetermined time；
The reference data is input to preset prediction model, obtains the object event after object time
The predetermined time in one predetermined period, the prediction that the prediction number of the object event occurs in each subregion
Data；Wherein, the prediction model is to carry out what deep learning obtained to the history reference data of the target area.
On the one hand, the embodiment of the present invention provides a kind of object event prediction meanss, and described device includes:
Obtain module, the reference data of the object event for obtaining target area；Wherein, the target area includes extremely
Few two sub-regions, the reference data are that in previous predetermined period of object time the target occurs for the subregion
The number of event；The reference data includes the data of at least two groups difference predetermined time；
Prediction module obtains the object event for the reference data to be input to preset prediction model
In each subregion the object event occurs for the predetermined time in the latter predetermined period of object time
Predict the prediction data of number；Wherein, the prediction model is to carry out depth to the history reference data of the target area
What acquistion was arrived.
On the other hand, the embodiment of the invention also provides a kind of electronic equipment, including memory, processor, bus and
The computer program that can be run on a memory and on a processor is stored, the processor is realized above-mentioned when executing described program
Step in object event prediction technique.
In another aspect, being stored thereon with the embodiment of the invention also provides a kind of non-transient computer readable storage medium
Computer program realizes the step in above-mentioned object event prediction technique when described program is executed by processor.
Object event prediction technique provided in an embodiment of the present invention and device, by the object event for obtaining target area
Reference data, and the reference data is input to preset prediction model, the object event is obtained in object time
The latter predetermined period in the predetermined time, the prediction number of the object event occurs in each subregion
Prediction data takes in advance object event corresponding precautionary measures based on prediction data, reduces the unfavorable shadow of object event bring
It rings；Especially the bad weathers such as thunder and lightning are predicted in aviation operation field, on the one hand stops dangerous operation, avoids safety
Accident；On the other hand when flight is delayed generation, passenger caused by the flight delay of deployment scheme reply in advance overstocks, is detained airport
The problems such as, it is ensured that passenger transport work safety is orderly, improves service guarantee quality.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is one of the flow diagram of object event prediction technique provided in an embodiment of the present invention；
Fig. 2 is one of the first exemplary target area schematic diagram of a scenario of the embodiment of the present invention；
Fig. 3 is the two of the first exemplary target area schematic diagram of a scenario of the embodiment of the present invention；
Fig. 4 is the second exemplary GRU model schematic of the embodiment of the present invention；
Fig. 5 is the two of the flow diagram of object event prediction technique provided in an embodiment of the present invention；
Fig. 6 is one of the exemplary lightning stroke incident schematic diagram of third of the embodiment of the present invention；
Fig. 7 is the two of the exemplary lightning stroke incident schematic diagram of third of the embodiment of the present invention；
Fig. 8 is the 4th exemplary air station flight operation schematic diagram of the embodiment of the present invention；
Fig. 9 is one of the 5th exemplary jobs node schematic diagram of the embodiment of the present invention；
Figure 10 is the two of the 5th exemplary jobs node schematic diagram of the embodiment of the present invention；
Figure 11 is the structural schematic diagram of object event prediction meanss provided in an embodiment of the present invention；
Figure 12 is the structural schematic diagram of server provided in an embodiment of the present invention.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Body embodiment is described in detail.In the following description, such as specific configuration is provided and the specific detail of component is only
In order to help comprehensive understanding the embodiment of the present invention.It therefore, it will be apparent to those skilled in the art that can be to reality described herein
Example is applied to make various changes and modifications without departing from scope and spirit of the present invention.In addition, for clarity and brevity, it is omitted pair
The description of known function and construction.
It should be understood that " embodiment " or " embodiment " that specification is mentioned in the whole text mean it is related with embodiment specific
Feature, structure or characteristic are included at least one embodiment of the present invention.Therefore, occur everywhere in the whole instruction " real
Apply in example " or " in one embodiment " not necessarily refer to identical embodiment.In addition, these specific features, structure or characteristic
It can combine in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be appreciated that the size of the serial number of following each processes is not meant to execute suitable
Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, the implementation without coping with the embodiment of the present invention
Process constitutes any restriction.
In embodiment provided herein, it should be appreciated that " B corresponding with A " indicates that B is associated with A, can be with according to A
Determine B.It is also to be understood that determine that B is not meant to determine B only according to A according to A, it can also be according to A and/or other information
Determine B.
Fig. 1 shows a kind of flow diagram of object event prediction technique provided in an embodiment of the present invention.
As shown in Figure 1, object event prediction technique provided in an embodiment of the present invention, the method specifically include following step
It is rapid:
Step 101, the reference data of the object event of target area is obtained；Wherein, the target area includes at least two
Sub-regions, the reference data are that in previous predetermined period of object time the object event occurs for the subregion
Number；The reference data includes the data of at least two groups difference predetermined time.
Wherein, object event can be with events such as bad weather events, such as lightning stroke, blast, heavy rain；Target area can be
One region for needing to protect object event, such as airport；In order to improve precision of prediction, target area is divided into multiple
Subregion.
As the first example, it is shown a target area with reference to Fig. 2, Fig. 2, is divided into 50*50 sub-regions, Mei Geju
Shape region is a subregion；Each subregion is recorded as shown in the data in Fig. 2 in each subregion, in reference data in mesh
Mark the number that object event occurs in moment previous predetermined period；By taking object event is lightning stroke incident as an example, then reference data
In be recorded as the number that each subregion is struck by lightning within the above-mentioned period, show 1 lightning stroke incident hair in the first row first
Raw, the first row second is shown 7 lightning stroke incidents and is occurred.
Predetermined period is the preset period, by the reference data of the previous predetermined period of object time, predicts mesh
Mark the related data of moment next cycle；And the reference data includes the data of at least two groups difference predetermined time, every group
There is time continuity between data.
At least two predetermined times have can be preset in each predetermined period, and each predetermined period has one group of data.Than
Such as, predetermined period is one hour, and is used as a predetermined time at interval of ten minutes, then six groups of data are shared in reference data.
Step 102, the reference data is input to preset prediction model, obtains the object event in target
The predetermined time in the latter predetermined period at moment, the prediction time that the object event occurs in each subregion
Several prediction data；Wherein, the prediction model is to carry out deep learning to the history reference data of the target area to obtain
's.
Wherein, prediction model is to carry out what deep learning obtained to the history reference data of the target area, history ginseng
Examine reference data of the data i.e. target area in predetermined period before；Using the form of big data, to history reference data
Deep learning is carried out, constantly training pattern and Optimized model, finally obtain the prediction model for meeting default precise requirements, in advance
If in precise requirements may include the specific value to precise requirements, such as 99%；Reference data is input to the prediction mould
Type, the prediction data of next predetermined period after obtaining object time.Corresponding in prediction data includes each predetermined time
Data, prediction of the data, that is, object event in each subregion frequency.
Still referring to Figure 2, the reference data in Fig. 2 is input in prediction model, obtains prediction data；By prediction data
In one group correspond in target area after, the schematic diagram of target area is as shown in Figure 3；In Fig. 3, the prediction of a certain predetermined time
It is indicated in data, predicts once lightning stroke incident generation respectively in the 3rd, 4 column of the first row；Have in the 3rd column prediction of the second row
Lightning stroke incident occurs three times, in the 4th column prediction once lightning stroke incident generation of the second row.
After obtaining the prediction data of the next predetermined period in target area, corresponding prevention can be taken to arrange according to prediction data
It applies, studies and judges deployment in advance, respond actively adverse effect.
In the above embodiment of the present invention, the reference data of the object event by obtaining target area, and by the reference
Data are input to preset prediction model, obtain institute of the object event in the latter predetermined period of object time
It states predetermined time, the prediction data of the prediction number of the object event occurs in each subregion, so as to based on prediction
Data take in advance object event corresponding precautionary measures, reduce object event bring adverse effect；Especially in aviation operation
The bad weathers such as thunder and lightning are predicted in field, are on the one hand stopped dangerous operation, are avoided safety accident；On the other hand it is navigating
When class's delay occurs, passenger caused by the flight delay of deployment scheme reply in advance overstocks, is detained the problems such as airport, it is ensured that Lv Keyun
Defeated work safety is orderly, improves service guarantee quality.
Optionally, in the above embodiment of the present invention, which comprises
By the history reference data one archetype of training, the prediction model is obtained.
Wherein, history reference data, that is, reference data of the target area in predetermined period before；It is with object event
For lightning stroke incident, the history Thundercloud data in the specific airfield protective area of many years are collected as example reference data.It adopts
With the form of big data, deep learning is carried out to history reference data, constantly training pattern and Optimized model, finally obtain symbol
Close the prediction model of precise requirements.
Specifically, described the step of training an archetype by the history reference data, obtaining the prediction model,
Include:
First history reference data are input to the archetype and obtain tentative prediction data by the first step；Described first
History reference data are the reference data in a historical forecast period；
Second step carries out the archetype by the second history reference data and the tentative prediction data reversed
Optimization, the model after being optimized；Wherein, the second history reference data are next prediction week in the historical forecast period
The reference data of phase；
Next first history reference data iteration after current reference data is input to the mould after the optimization by third step
Type, and Reverse optimization is carried out, until the number of iterations or precision of prediction meet preset rules, obtain the prediction model.
Wherein, after obtaining history reference data, history reference data are different according to the historical forecast period belonged to
Classify.In the first step, in the historical forecast period determined first against one, the history reference number in historical forecast period is obtained
According to the first history reference data are input to the archetype and obtain tentative prediction data, just by i.e. the first history reference data
Walk the prediction data of next predetermined period that prediction data is the current historical forecast period；In second step, next prediction week is obtained
The second history reference data (i.e. real data) of phase, pass through the gap between the second history reference data and tentative prediction data
Reverse optimization is carried out to the archetype, adjusts archetype, makes the prediction data of the archetype output to true number
According to drawing close.Next first history reference data iteration after current reference data is input to the mould after the optimization by third step
Type, circulation execute above-mentioned training, optimization process and obtain the prediction mould until the number of iterations or precision of prediction meet preset rules
Type.
Optionally, the archetype is gating cycle unit GRU model.
Wherein, gating cycle unit (Gated Recurrent Unit, GRU) is a kind of common gating cycle nerve net
Network (Gated Recurrent Neural Network, GRNN), GRNN can time step distances preferably in pull-in time sequence
Biggish dependence.
As the second example, referring to fig. 4, Fig. 4 show coding (the encoder)-decoding of a GRU based on deep learning
(decoder) network model, basic framework are as shown in Figure 4；Wherein Xi (x1, x2, x3, x4, x5, x6, x7, x8, x9, x10) is total
10 frame data are input variable, and every frame data are one group of reference data, are prefixed time interval between every frame data；
Totally 10 frame data are output variable to Yi (y1, y2, y3, y4, y5, y6, y7, y8, y9, y10), between every frame data
It also is the prefixed time interval.
Xi, Yi are the sample data with certain time interval, and are the matrix-vector of 50*50.
Still by taking airport is anti-lightning strike as an example, the time interval of every frame reference data is TCLIP minutes, for example x1 is current predictive
The reference data at the first TCLIP moment in period, y1 are the prediction data at the first TCLIP moment of next predetermined period；x2
For the reference data at the 2nd TCLIP moment in current predictive period, y2 is the pre- of the 2nd TCLIP moment of next predetermined period
Measured data.
Cascade encoder and decoder several n protects thunderstorm time (TMAX/) TCLIP to determine by airport longest,
Such as such as TMAX is 60 minutes, TCLIP 6, then 10) n takes.
In this way, the following TMAX hours thunder and lightning situations after prediction current time, using this encoder-decoder
Model realizes this prediction.
One, with reference to Fig. 2, the process for obtaining sample data is as follows:
(1) a 50*50 network centered on the center of traffic pattern is constructed, each lattice (ratio in grid
Such as 1 square kilometre) it is a sub-regions, during history reference data, collect the Thundercloud on specific airport each time
Data, 60 minutes before being started with Thundercloud start, and every TCLIP minutes takes a frame, until the Thundercloud end time；Have
It is several that several thunders and lightnings, which fall and just mark the value of the grid within a grid, such as: there is n thunder and lightning to fall in a certain grid, just label should
The value of grid is n, without thunderbolt, is then labeled as 0, thus obtains the matrix of a 50*50, the first frame data are denoted as x1.
(2) it according to the continuity of time series, is once cut according to every TCLIP minutes, TCLIP minutes data
It is handled in such a way that sample data (sample data, that is, history reference data) generates, generates the matrix of a 50*50.It sees
Examining window is TMAX1 hours, and label window is TMAX2 hours.
(3) it can be generated TMAX1*10 sample data in watch window TMAX1 hours, i.e. TMAX*10 50*50's
Matrix；10*TMAX2 sample data, i.e., the square of TMAX2*10 50*50 can be generated in label window this TMAX2 hours
Battle array.
Two, the process of model training and optimization is as follows:
(1) the history reference data based on specific airport many years, the sample data of generation is inputted into the GRU built
Encoder-decoder model carries out model training；Sample data is divided into two parts, training sample data and test sample number
According to.
Model carries out repetition training using training sample and tends towards stability until mean square error, using test sample to training
Model optimize the training effect with observation model, finally obtain the prediction model for meeting precise requirements.
Referring to Fig. 5, the embodiment of the invention also provides another object event prediction techniques, and the method specifically includes following
Step:
Step 501, the reference data of the object event of target area is obtained；Wherein, the target area includes at least two
Sub-regions, the reference data are that in previous predetermined period of object time the object event occurs for the subregion
Number；The reference data includes the data of at least two groups difference predetermined time.
Wherein, object event can be with bad weather event, such as lightning stroke, blast, Rainstorms；Target area can be one
Need the region protected object event, such as airport；In order to improve precision of prediction, target area is divided into multiple sons
Region.As the first example, it is shown a target area with reference to Fig. 2, Fig. 2, is divided into 50*50 sub-regions, each rectangle
Region is a subregion, and each subregion is recorded as shown in the data in Fig. 2 in each subregion, in reference data in target
The number of object event occurs in predetermined period before moment；By taking object event is lightning stroke incident as an example, then remember in reference data
The number being struck by lightning within the above-mentioned period for each subregion is carried, 1 lightning stroke incident is shown in the first row first and occurs, the
A line second is shown 7 lightning stroke incidents and is occurred.
Predetermined period is the preset period, by the reference data of the previous predetermined period of object time, predicts mesh
Mark the related data of moment next cycle；And the reference data includes the data of at least two groups difference predetermined time, every group
There is time continuity between data；At least two predetermined times, each predetermined period has can be preset in each predetermined period
With one group of data.For example, predetermined period is one hour, and it was used as a predetermined time at interval of ten minutes, then reference data
In share six groups of data.
Step 502, the reference data is input to preset prediction model, obtains the object event in target
The predetermined time in the latter predetermined period at moment, the prediction time that the object event occurs in each subregion
Several prediction data；Wherein, the prediction model is to carry out deep learning to the history reference data of the target area to obtain
's.
Wherein, prediction model is to carry out what deep learning obtained to the history reference data of the target area, history ginseng
Examine reference data of the data i.e. target area in predetermined period before；Using the form of big data, to history reference data
Deep learning is carried out, constantly training pattern and Optimized model, finally obtain the prediction model for meeting precise requirements；It will refer to
Data are input to the prediction model, the prediction data of next predetermined period after obtaining object time.It is corresponding in prediction data
Data comprising each predetermined time, prediction of the data, that is, object event in each subregion frequency.
Still referring to Figure 2, the reference data in Fig. 2 is input in prediction model, obtains prediction data；By prediction data
In one group correspond in target area after, the schematic diagram of target area is as shown in Figure 3；In Fig. 3, the prediction of a certain predetermined time
It is indicated in data, predicts once lightning stroke incident generation respectively in the 3rd, 4 column of the first row；Have in the 3rd column prediction of the second row
Lightning stroke incident occurs three times, in the 4th column prediction once lightning stroke incident generation of the second row.
After obtaining the prediction data of the next predetermined period in target area, corresponding prevention can be taken to arrange according to prediction data
It applies, studies and judges deployment in advance, respond actively adverse effect.
Step 503, for each subregion, according to the prediction data, determine the object event it is lasting when
Between；Wherein, the duration be the object event at the beginning of between the end time of the object event when
Between be spaced；
The time started is the predetermined time that the object event occurs for the first time in the latter predetermined period；
The end time is the predetermined time that the object event occurs for the last time in the latter predetermined period.
Wherein, after obtaining prediction data, for each subregion, the duration of its object event is determined, to be directed to
Object event takes corresponding precautionary measures.
The duration be the object event at the beginning of between the end time of the object event when
Between be spaced；Specifically, by taking lightning stroke incident as an example, as third example, with reference to Fig. 6, the time started is the object event in institute
State the predetermined time occurred in the latter predetermined period for the first time, i.e. first predetermined time occurring of lightning stroke incident, i.e., first
A lightning stroke enters in the subregion in airfield protective area.
It should be noted that if first time lightning stroke incident occurs between two predetermined times, then the lightning stroke incident is drawn
It is divided into previous predetermined time.
End time is the predetermined time that the object event occurs for the last time in the latter predetermined period, ginseng
Fig. 7 is examined, at the time of the end time, i.e. subregion was left in the last one lightning stroke；It should be noted that if last time lightning stroke incident
Occur between two predetermined times, then the lightning stroke incident is divided into the latter predetermined time.
For specific airport, the thunderstorm phase in airfield protective area is in a Thundercloud, first in airfield protective
Beginning of the time point of lightning stroke as Thundercloud, the last one lightning stroke terminates as Thundercloud in airfield protective, airport
Interval of the guard plot thunderstorm time between time started and end time.
Continue above-mentioned second example, is exported according to a series of total TMAX*10 Yi, can determine that the airfield protective area thunder of prediction
Sudden and violent start and end time.
Design an array lighting_time_arr, the total TMAX*10 element of the array；For Yi, if there is lightning stroke point
Cloth is at least one subregion that airfield protective area covers, then lighting_time_arr [i]=1, indicates prediction in (i-
1) there is lightning stroke in airfield protective area between * 6 minutes to i*6 minutes, otherwise lighting_time_arr [i]=0, indicates that prediction exists
(i-1) airfield protective area is not struck by lightning between * 6 minutes to i*6 minutes.
A certain predetermined time, whole arrays are as shown in table 1:
Table 1:
| 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 |
Assuming that current time is T0, then the Thundercloud time started is predicted at T0+12 minutes, the end time is at T0+48 points
The predetermined time that clock, i.e. first value of access group are 1 is the thunderstorm time started, and the predetermined time that the last one value is 1 is end
Time.
This array will appear following several situations:
1) predict thunderstorm time started and end time all in T0 between T0+TMAX in table 2:
Table 2:
| 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 |
Predict that the Thundercloud time started is T0+6 minutes, the end time is T0+48 minutes.
2) table 3, current time lightning stroke are occurring, and predict the thunderstorm end time in T0 between T0+TMAX:
Table 3:
| 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 |
Predict that the Thundercloud end time is T0+48 minutes.
3) table 4, the prediction thunderstorm time started, the end time was after T0+TMAX in T0 between T0+TMAX:
Table 4:
| 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
The last one value of array is 1, and the prediction Thundercloud time started is T0+12, it is assumed that end time T0+12+
TMAX*60。
4) table 5, current time Thundercloud are occurring, and predict the thunderstorm end time after T0+TMAX:
Table 5:
| 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
Predict that the Thundercloud end time is T0+TMAX*60 minutes.
5) table 6, array value have 0 between 1, and prediction result ignores the 0 intermediate moment, and prediction is provided as table 2 to table 5
As a result；
Table 6:
| 0 | 0 | 1 | 1 | 0 | 1 | 0 | 1 | 0 | 0 |
Table 6 is converted into table 7:
Table 7:
| 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 0 |
It is obtained with the guard plot Thundercloud time of prediction according to above method, predicts that the Thundercloud time started is
T0+12 minutes, the end time was T0+48 minutes.
Optionally, in the above embodiment of the present invention, after step 503, the method also includes:
According to the prediction data, the generation density of the object event is determined；The generation density is the target thing
Part is in total frequency in the duration and the ratio between the duration；
According to the generation density and preset strength grade threshold value, determine the object event in the subregion
Intensity occurs.
Wherein, it in order to predict the generation intensity of object event, according to prediction data, determines and density occurs；Further according to default
Strength grade threshold value, determine generation intensity of the object event in the subregion；It is gone through according to strength grade threshold value
What history reference data determined；Specifically, by taking lightning stroke incident as an example, Thundercloud will occur in target area to be effectively estimated
Power, defines the generation density of thunderstorm, and density occurs and is measured with being struck by lightning in definition region thunderbolt frequency, in obtainable history
In reference data, lightning stroke has detailed lightning stroke feature, such as location information (longitude and latitude) etc..Density occurs and is defined as airport
The number that is always struck by lightning in Thundercloud holds divided by Thundercloud for guard plot (for example traffic pattern center is the center of circle, in 10KM radius circle)
Continuous time (the number of minutes), such as in 3 hours Thunderclouds, 250 lightning strokes occur altogether in airfield protective area, then thunderstorm is close
Degree is 250/ (3*60), i.e., 1.388 times per minute.
By taking two strength grades as an example, respectively Strong Thunderstorm grade, weak thunderstorm grade；Collect largely going through for airfield protective area
History reference process (such as -2018 years 2013), shares N number of Thundercloud, the thunderstorm density Di of each Thundercloud, and statistics owns
This N number of thunderstorm density, average P；After obtaining mean value P, using mean value P as threshold value, if big to a certain Thundercloud thunderstorm density
In the threshold value, otherwise it is weak Thundercloud that defining the Thundercloud, which is Strong Thunderstorm process,.
Optionally, in the above embodiment of the present invention, generation of the determination object event in the subregion is strong
After the step of spending, the method also includes:
Obtain the pending event of the subregion；
According to the default corresponding relationship between the generation intensity and the implementation strategy of pending event, the determining and hair
The corresponding target implementation strategy of life intensity.
Wherein it is determined that object event determines subregion according to the duration after the generation intensity of each subregion
Pending event determines target according to the default corresponding relationship between the generation intensity and the implementation strategy of pending event
Implementation strategy.
Pending event can be the pending event in the latter predetermined period or in the duration；
By taking airport as an example, corresponding precautionary measures are taken according to prediction data, ensure operation.As the 4th example, referring to figure
8, air station flight operation mainly includes content shown in Fig. 8；Wherein, upper wheel shelves and remove wheel shelves between, respectively include shelter bridge/ladder vehicle
It docks, open passenger door, opening cargo door plus the main line of several pending events such as cabin oil and engineering inspection, dividing on every main line
Do not have serially and multiple is allocated as industry.
It is defined under each generation intensity in default corresponding relationship, the specific implementation strategy of pending event；Execute plan
It slightly may include stopping executing, suspending execution and continue to execute.
Partial content in default corresponding relationship is as shown in table 8:
Table 8:
Optionally, in the above embodiment of the present invention, the implementation strategy includes that pause executes and/or stops executing；
The method also includes:
According to the target implementation strategy, the prediction for adjusting the pending event executes the time.
Wherein it is determined that different according to target implementation strategy, the prediction for adjusting pending event is held after target implementation strategy
The row time, for example, will then need the time suspended to be added to pre- when target implementation strategy is that pause executes and/or stops executing
It surveys and executes the time.
Referring to Fig. 8, still by taking the lightning stroke incident of airport as an example, from upper catch to catch is removed, there is a plurality of main line for ensureing job stream
Lu Jing is parallel between them, meanwhile, within each paths, there are one or more to be allocated as industry serial, maximum therein
(all on a paths serially to divide the sum of activity duration) determine removing the block time for estimation in path, and in Thunderstorm Weather condition
Under, it needs to ensure that node makes new estimation to flight.
According to prediction data, at the beginning of obtained airport Thundercloud and the end time.As the 5th example, referring to
Fig. 9, it is assumed that pending event P1 estimates each guarantee jobs node relationship as shown in figure 9, P1 is to stop in target implementation strategy with original
Only execute, then to lightning stroke incident after, then restart P1 event, as shown in Figure 10；And main line where recalculating P1
The job stream time is finally recalculated and newly removes the wheel shelves time.
In order to effectively estimate the time point of airport Coordination Decision, is proposed in the above embodiment of the present invention and use prediction model
Lightning stroke incident is predicted by the time that starts on airport, and the method for prediction Thundercloud intensity, thus to flight guarantee
Process node, which is made, timely to be adjusted, and each decision-making party more efficiently can complete operations task using airport coordinated decision system.
In the above embodiment of the present invention, the reference data of the object event by obtaining target area, and by the reference
Data are input to preset prediction model, obtain institute of the object event in the latter predetermined period of object time
It states predetermined time, the prediction data of the prediction number of the object event occurs in each subregion, be based on prediction data
Corresponding precautionary measures are taken object event in advance, reduce object event bring adverse effect；Especially in aviation operation field
The bad weathers such as thunder and lightning are predicted, on the one hand stops dangerous operation, avoids safety accident；On the other hand prolong in flight
When accidentally occurring, passenger caused by the flight delay of deployment scheme reply in advance overstocks, is detained the problems such as airport, it is ensured that passenger transport work
Make safe and orderly, raising service guarantee quality.
Object event prediction technique provided in an embodiment of the present invention is described above, introduces the present invention below in conjunction with attached drawing
The object event prediction meanss that embodiment provides.
Referring to Figure 11, the embodiment of the invention provides a kind of object event prediction meanss, described device includes:
Obtain module 111, the reference data of the object event for obtaining target area；Wherein, the target area packet
At least two subregions are included, the reference data is described in the subregion occurs in previous predetermined period of object time
The number of object event；The reference data includes the data of at least two groups difference predetermined time.
Wherein, object event can be with bad weather event, such as lightning stroke, blast, Rainstorms；Target area can be one
Need the region protected object event, such as airport；In order to improve precision of prediction, target area is divided into multiple sons
Region.As the first example, it is shown a target area with reference to Fig. 2, Fig. 2, is divided into 50*50 sub-regions, each rectangle
Region is a subregion, and each subregion is recorded as shown in the data in Fig. 2 in each subregion, in reference data in target
The number of object event occurs in predetermined period before moment；By taking object event is lightning stroke incident as an example, then remember in reference data
The number being struck by lightning within the above-mentioned period for each subregion is carried, 1 lightning stroke incident is shown in the first row first and occurs, the
A line second is shown 7 lightning stroke incidents and is occurred.
Predetermined period is the preset period, by the reference data of the previous predetermined period of object time, predicts mesh
Mark the related data of moment next cycle；And the reference data includes the data of at least two groups difference predetermined time, every group
There is time continuity between data；At least two predetermined times, each predetermined period has can be preset in each predetermined period
With one group of data.For example, predetermined period is one hour, and it was used as a predetermined time at interval of ten minutes, then reference data
In share six groups of data.
Prediction module 112 obtains the target thing for the reference data to be input to preset prediction model
In each subregion the object event occurs for the predetermined time of the part in the latter predetermined period of object time
Prediction number prediction data；Wherein, the prediction model is to carry out depth to the history reference data of the target area
What study obtained.
Wherein, prediction model is to carry out what deep learning obtained to the history reference data of the target area, history ginseng
Examine reference data of the data i.e. target area in predetermined period before；Using the form of big data, to history reference data
Deep learning is carried out, constantly training pattern and Optimized model, finally obtain the prediction model for meeting precise requirements；It will refer to
Data are input to the prediction model, the prediction data of next predetermined period after obtaining object time.It is corresponding in prediction data
Data comprising each predetermined time, prediction of the data, that is, object event in each subregion frequency.
Still referring to Figure 2, the reference data in Fig. 2 is input in prediction model, obtains prediction data；By prediction data
In one group correspond in target area after, the schematic diagram of target area is as shown in Figure 3；In Fig. 3, the prediction of a certain predetermined time
It is indicated in data, predicts once lightning stroke incident generation respectively in the 3rd, 4 column of the first row；Have in the 3rd column prediction of the second row
Lightning stroke incident occurs three times, in the 4th column prediction once lightning stroke incident generation of the second row.
After obtaining the prediction data of the next predetermined period in target area, corresponding prevention can be taken to arrange according to prediction data
It applies, studies and judges deployment in advance, respond actively adverse effect.
Optionally, in the above embodiment of the present invention, described device includes:
Model training module, for obtaining the prediction model by the history reference data one archetype of training.
Optionally, in the above embodiment of the present invention, the model training module includes:
Tentative prediction submodule obtains tentative prediction number for the first history reference data to be input to the archetype
According to；The first history reference data are the reference data in a historical forecast period；
Reverse optimization submodule, for passing through the second history reference data and the tentative prediction data to described original
Model carries out Reverse optimization, the model after being optimized；Wherein, the second history reference data are the historical forecast period
Next predetermined period reference data；
Iteration submodule, it is described excellent for next first history reference data iteration after current reference data to be input to
Model after change, and Reverse optimization is carried out, until the number of iterations or precision of prediction meet preset rules, obtain the prediction model.
Optionally, in the above embodiment of the present invention, the archetype is gating cycle unit GRU model.
Optionally, in the above embodiment of the present invention, described device further include:
Time determining module, for being directed to each subregion,
According to the prediction data, the duration of the object event is determined；Wherein, the duration is the mesh
Time interval at the beginning of mark event between the end time of the object event；
The time started is the predetermined time that the object event occurs for the first time in the latter predetermined period；
The end time is the predetermined time that the object event occurs for the last time in the latter predetermined period.
Optionally, in the above embodiment of the present invention, described device further include:
Density determining module, for determining the generation density of the object event according to the prediction data；The generation
Density is the object event in total frequency in the duration and the ratio between the duration；
Intensity determining module, for determining the target thing according to the generation density and preset strength grade threshold value
Generation intensity of the part in the subregion.
Optionally, in the above embodiment of the present invention, the strength grade threshold value is to be determined according to the history reference data
's.
Optionally, in the above embodiment of the present invention, described device further include:
Tactful determining module, for obtaining the pending event of the subregion；
According to the default corresponding relationship between the generation intensity and the implementation strategy of pending event, the determining and hair
The corresponding target implementation strategy of life intensity.
Optionally, in the above embodiment of the present invention, the implementation strategy includes that pause executes and/or stops executing；
Described device further include:
Time regulating module, when for being executed according to the prediction of the target implementation strategy, the adjustment pending event
Between.
In the above embodiment of the present invention, the reference data for obtaining the object event of target area by obtaining module 111, in advance
It surveys module 112 and the reference data is input to preset prediction model, obtain the object event in object time
In each subregion the pre- of the prediction number of the object event occurs for the predetermined time in the latter predetermined period
Measured data takes in advance object event corresponding precautionary measures based on prediction data, reduces object event bring adverse effect；
Especially the bad weathers such as thunder and lightning are predicted in aviation operation field, on the one hand stops dangerous operation, avoids safe thing
Therefore；On the other hand when flight is delayed generation, passenger caused by the flight delay of deployment scheme reply in advance overstocks, is detained airport etc.
Problem, it is ensured that passenger transport work safety is orderly, improves service guarantee quality.
On the other hand, the embodiment of the invention also provides a kind of electronic equipment, including memory, processor, bus and
The computer program that can be run on a memory and on a processor is stored, the processor is realized above-mentioned when executing described program
Step in object event prediction technique.
For example as follows, when electronic equipment is server, Figure 12 illustrates a kind of entity structure signal of server
Figure.
As shown in figure 12, which may include: processor (processor) 1210, communication interface
(Communications Interface) 1220, memory (memory) 1230 and communication bus 1240, wherein processor
1210, communication interface 1220, memory 1230 completes mutual communication by communication bus 1240.Processor 1210 can be adjusted
With the logical order in memory 1230, to execute following method:
The programme information and real-time heart rate information of the TV programme that smart television is sent are received, the programme information includes:
Program play times and program identification；According to the programme information and real-time heart rate information, the broadcasting of the TV programme is obtained
Procedural information.
In addition, the logical order in above-mentioned memory 1230 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
Substantially the part of the part that contributes to existing technology or the technical solution can be in other words for the technical solution of invention
The form of software product embodies, which is stored in a storage medium, including some instructions to
So that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation of the present invention
The all or part of the steps of example the method.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. it is various
It can store the medium of program code.
In another aspect, being stored thereon with the embodiment of the invention also provides a kind of non-transient computer readable storage medium
Computer program realizes the step in above-mentioned object event prediction technique when described program is executed by processor.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (12)
1. a kind of object event prediction technique, which is characterized in that the described method includes:
Obtain the reference data of the object event of target area；Wherein, the target area includes at least two subregions, described
Reference data is the number that the object event occurs in previous predetermined period of object time for the subregion；The ginseng
Examine the data that data include at least two groups difference predetermined time；
The reference data is input to preset prediction model, obtains the object event in the latter of object time
The predetermined time in predetermined period, the prediction number that the prediction number of the object event occurs in each subregion
According to；Wherein, the prediction model is to carry out what deep learning obtained to the history reference data of the target area.
2. the method according to claim 1, wherein the described method includes:
By the history reference data one archetype of training, the prediction model is obtained.
3. according to the method described in claim 2, it is characterized in that, described pass through the history reference data one original mould of training
Type, the step of obtaining the prediction model, comprising:
First history reference data are input to the archetype and obtain tentative prediction data；The first history reference data
For the reference data in a historical forecast period；
Reverse optimization is carried out to the archetype by the second history reference data and the tentative prediction data, is obtained excellent
Model after change；Wherein, the second history reference data are the reference number of next predetermined period in the historical forecast period
According to；
Next first history reference data iteration after current reference data is input to the model after the optimization, and is carried out anti-
To optimization, until the number of iterations or precision of prediction meet preset rules, the prediction model is obtained.
4. according to the method described in claim 2, it is characterized in that, the archetype is gating cycle unit GRU model.
5. the method according to claim 1, wherein described obtain the object event in the latter of object time
The predetermined time in a predetermined period, the prediction number that the prediction number of the object event occurs in each subregion
According to the step of after, the method also includes:
For each subregion,
According to the prediction data, the duration of the object event is determined；Wherein, the duration is the target thing
Time interval at the beginning of part between the end time of the object event；
The time started is the predetermined time that the object event occurs for the first time in the latter predetermined period；It is described
End time is the predetermined time that the object event occurs for the last time in the latter predetermined period.
6. according to the method described in claim 5, determining the target thing it is characterized in that, described according to the prediction data
After the step of duration of part, the method also includes:
According to the prediction data, the generation density of the object event is determined；The generation density is that the object event exists
Total frequency in the duration and the ratio between the duration；
According to the generation density and preset strength grade threshold value, generation of the object event in the subregion is determined
Intensity.
7. according to the method described in claim 6, it is characterized in that, the strength grade threshold value is according to the history reference number
According to determining.
8. according to the method described in claim 6, it is characterized in that, the determination object event is in the subregion
After the step of intensity occurs, the method also includes:
Obtain the pending event of the subregion；
It is determining to occur by force with described according to the default corresponding relationship between the generation intensity and the implementation strategy of pending event
Spend corresponding target implementation strategy.
9. according to the method described in claim 8, it is characterized in that, the implementation strategy includes that pause executes and/or stops holding
Row；
The method also includes:
According to the target implementation strategy, the prediction for adjusting the pending event executes the time.
10. a kind of object event prediction meanss, which is characterized in that described device includes:
Obtain module, the reference data of the object event for obtaining target area；Wherein, the target area includes at least two
Sub-regions, the reference data are that in previous predetermined period of object time the object event occurs for the subregion
Number；The reference data includes the data of at least two groups difference predetermined time；
Prediction module obtains the object event in mesh for the reference data to be input to preset prediction model
It marks the predetermined time in the latter predetermined period at moment, the prediction of the object event occurs in each subregion
The prediction data of number；Wherein, the prediction model is to carry out deep learning to the history reference data of the target area to obtain
It arrives.
11. a kind of electronic equipment, which is characterized in that on a memory and can be including memory, processor, bus and storage
The computer program run on processor, the processor are realized when executing described program such as any one of claims 1 to 9 institute
The step in object event prediction technique stated.
12. a kind of non-transient computer readable storage medium, is stored thereon with computer program, it is characterised in that: described program
The step in object event prediction technique as claimed in any one of claims 1-9 wherein is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910267176.6A CN109961192B (en) | 2019-04-03 | 2019-04-03 | Target event prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910267176.6A CN109961192B (en) | 2019-04-03 | 2019-04-03 | Target event prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109961192A true CN109961192A (en) | 2019-07-02 |
| CN109961192B CN109961192B (en) | 2021-11-26 |
Family
ID=67025595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910267176.6A Active CN109961192B (en) | 2019-04-03 | 2019-04-03 | Target event prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961192B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991625A (en) * | 2020-03-02 | 2020-04-10 | 南京邮电大学 | Surface anomaly remote sensing monitoring method and device based on recurrent neural network |
| CN113283589A (en) * | 2021-06-07 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Updating method and device of event prediction system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101479751A (en) * | 2006-06-30 | 2009-07-08 | Nhn公司 | On-line e mail service system, and service method thereof |
| CN104316754A (en) * | 2014-11-06 | 2015-01-28 | 重庆大学 | Thunder and lightning counter remote monitoring early warning system and method |
| CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
| CN108427041A (en) * | 2018-03-14 | 2018-08-21 | 南京中科九章信息技术有限公司 | Lightning Warning method, system, electronic equipment and storage medium |
| CN108898258A (en) * | 2018-07-06 | 2018-11-27 | 广州供电局有限公司 | The analysis method and system of cascading failure in power system risk under Lightning Disaster weather |
-
2019
- 2019-04-03 CN CN201910267176.6A patent/CN109961192B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101479751A (en) * | 2006-06-30 | 2009-07-08 | Nhn公司 | On-line e mail service system, and service method thereof |
| CN104316754A (en) * | 2014-11-06 | 2015-01-28 | 重庆大学 | Thunder and lightning counter remote monitoring early warning system and method |
| CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
| CN108427041A (en) * | 2018-03-14 | 2018-08-21 | 南京中科九章信息技术有限公司 | Lightning Warning method, system, electronic equipment and storage medium |
| CN108898258A (en) * | 2018-07-06 | 2018-11-27 | 广州供电局有限公司 | The analysis method and system of cascading failure in power system risk under Lightning Disaster weather |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991625A (en) * | 2020-03-02 | 2020-04-10 | 南京邮电大学 | Surface anomaly remote sensing monitoring method and device based on recurrent neural network |
| CN113283589A (en) * | 2021-06-07 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Updating method and device of event prediction system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961192B (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Narciso et al. | Robust gate assignment procedures from an airport management perspective | |
| Anderson et al. | Analysis and modeling of ground operations at hub airports | |
| CN109961192A (en) | Object event prediction technique and device | |
| US12230157B2 (en) | Informed de-icing procedures for aircraft flight preparations | |
| CN110570693A (en) | A Reliability-Based Flight Time Prediction Method | |
| Lim et al. | Re-planning of flight routes avoiding convective weather and the “three areas” | |
| CN107749195A (en) | A kind of more airport and terminal area flight ordering systems | |
| Ahmadian et al. | Heuristics for flights arrival scheduling at airports | |
| Yang et al. | Stochastic scheduling of ground movement problem integrated with taxiway routing and gate/stand allocation | |
| Zeng et al. | Threat impact analysis to air traffic control systems through flight delay modeling | |
| Hu et al. | Research on flight delay prediction based on Random Forest | |
| Shao et al. | Analysis of an aircraft accident model in Taiwan | |
| Wang et al. | A review of flight delay prediction methods | |
| Li et al. | Capacity assessment of vertiports with a scheduling algorithm considering quality of service | |
| CN114330086B (en) | An emergency scheduling method for large-scale flights under emergencies | |
| Li et al. | Prediction of flight arrival delay time using us bureau of transportation statistics | |
| Gołda et al. | Elements of the model positioning of aircraft on the apron | |
| Bevilacqua et al. | Air traffic management of an airport using discrete event simulation method | |
| Distefano et al. | Investigation of the causes of runway excursions | |
| CN106570655A (en) | Aircraft deicing process automatic management and control method | |
| WANG et al. | Influential node ranking and invulnerability of air traffic cyber physical system | |
| Neyshabouri et al. | Analysis of airport surface operations: a case-study of Atlanta Hartfield airport | |
| Ali et al. | The aircraft departure scheduling based on particle swarm optimization combined with simulated annealing algorithm | |
| Esmaeili et al. | Simulation of Air traffic control system using Petri nets | |
| Wang et al. | Local airspace traffic prediction and flow control strategy recommendation system |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230116 Address after: Room 401, Floor 4, Xingfa Building, No. 45, Zhongguancun Street, Haidian District, Beijing, 100089 Patentee after: BEIJING JOZZON CAS SOFTWARE CO.,LTD. Address before: Room 501, building 2, Shuanglong science and Technology Industrial Park, No. 2, Shuanglong street, Qinhuai District, Nanjing, Jiangsu 210006 Patentee before: NANJING ZHONGKE JIUZHANG INFORMATION TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |