CN112132366A - Prediction system for flight clearance rate - Google Patents
Prediction system for flight clearance rate Download PDFInfo
- Publication number
- CN112132366A CN112132366A CN202011367710.XA CN202011367710A CN112132366A CN 112132366 A CN112132366 A CN 112132366A CN 202011367710 A CN202011367710 A CN 202011367710A CN 112132366 A CN112132366 A CN 112132366A
- Authority
- CN
- China
- Prior art keywords
- data
- target
- flight
- sample data
- weather
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 238000013498 data listing Methods 0.000 claims description 2
- 230000009977 dual effect Effects 0.000 abstract description 2
- 230000010006 flight Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000003897 fog Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a flight passing rate prediction system, which comprises a processor, a memory and a readable storage medium, wherein the processor is loaded and executed to realize the following steps: acquiring a sample data set A of an airport, wherein the sample data set A comprises a plurality of sample data lists, A = (A)1,A2,……,Ai,……,Am) Wherein, the sample data list AiThe current time point is a sample data list corresponding to the ith first time node; listing sample data on AiPreprocessing the sample data to obtain target data and a target data set corresponding to the target data; dividing the target data set into training data and prediction data; using training data input to the predictive model, adjustingPredicting model parameters; inputting the prediction data into the adjusted prediction model to obtain a predicted value of the flight clearance rate; the method can acquire all weather state data and all flight state data, train the model, integrate dual factors of weather and flight and accurately predict flight clearance.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a flight clearance prediction system.
Background
In recent years, with the great increase of flight traffic, a busy and complex flight transport network is formed, a great amount of flight delays are often caused by various reasons such as weather, traffic, passengers and the like, direct and indirect economic losses are gradually increased due to the flight delays, and meanwhile, the contradiction between passengers and airports and airlines caused by the flight delay problem becomes a serious social problem.
At present, the normal rate becomes an important assessment index of civil aviation airports and aviation departments, and most airports choose to predict flight delay instead of the normal rate; the flight delay prediction method is divided into the following steps: (1) machine learning methods such as random forests, decision trees, support vector machines and the like in data mining; (2) deep learning methods such as a deep neural network, a cyclic neural network, a convolutional neural network, and the like; (3) autoregressive differential moving average and exponential smoothing methods in the time series model; (4) probability density statistical method in probability science. The adopted data mainly comprises flight data such as flight departure time, delay time, station passing time, flight number and the like, then historical data of a part of airports are selected as research objects, the flight delay situation of the next time period is predicted, and flight delay judgment and delay time are common.
Therefore, the effective prediction of the normal rate and the flight delay in the same day and in the future can provide early warning for airlines, airports and related units, win time for making measures for relieving the flight delay, further reduce economic loss caused by the flight delay, be beneficial to improving the satisfaction degree of passengers on services and helping the airports and navigation departments to improve the self assessment conditions, and have important practical significance as the prediction of the normal rate and the flight delay on the civil aviation industry.
Disclosure of Invention
In order to solve the problems in the prior art, all weather state data and all flight state data are obtained, a model is trained, dual factors of weather and flights are integrated, and the flight release rate is accurately predicted, the embodiment of the invention provides a flight release rate prediction system. The technical scheme is as follows:
in one aspect, a system for predicting flight passing rate includes a processor, a memory and a readable storage medium, where the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the following steps:
obtaining a sample data set A of an airport, the sample data set A comprising a plurality of sample data lists, A = (A)1,A2,……,Ai,……,Am) M is an integer greater than 1, wherein the sample data list AiThe current time point is a sample data list corresponding to the ith first time node;
listing the sample data to be AiPreprocessing the sample data to obtain target data and a target data set corresponding to the target data;
dividing the target data set into training set data and prediction set data according to the target data set;
inputting the training set data into a prediction model, and adjusting parameters of the prediction model;
and inputting the prediction set data into the adjusted prediction model to obtain a predicted value of the flight clearance rate.
The flight clearance prediction system provided by the invention has the following technical effects:
the method and the device process flight status data with multiple characteristics and weather status data to form target data, screen the characteristics corresponding to the target data, and select the corresponding target data to predict based on the target flight release rate required to be predicted.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a graph comparing an actual normality rate of a flight with a predicted normality rate of the flight according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The present embodiment provides a system for predicting flight passing rate, including a processor, a memory and a readable storage medium, where the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the following steps:
s101, obtaining a sample data set A of an airport, wherein the sample data set A comprises a plurality of sample data lists, A = (A)1,A2,……,Ai,……,Am) M is an integer greater than 1, wherein the sample data list AiThe current time point is a sample data list corresponding to the ith first time node;
s103, listing the sample data in aiPreprocessing the sample data to obtain target data;
s105, dividing the target data into training set data and prediction set data;
s107, inputting the training set data into a prediction model, and adjusting parameters of the prediction model;
and S109, inputting the prediction set data into the adjusted prediction model to obtain a predicted value of the flight clearance rate.
In particular, the first time node is divided by time date, e.g. the AiThe first time node corresponding to the sample data list is 3 months and 15 days.
Specifically, the sample data list in the sample data set a is sorted according to the time sequence, that is, the sample data list in the sample data set a is sorted according to the time sequence ai-1The first time node corresponding to the sample data list is earlier than the AiThe time interval between the first time node corresponding to the sample data list and the adjacent second time node is generally 1 day, for example, when A isiThe first time node corresponding to the sample data list is 3 months and 15 days, wherein A isi-1Sample data List corresponds toThe first time node of (3) months and 14 days.
In a specific embodiment, the step S103 lists the sample data in the sample data list aiPreprocessing the sample data to obtain target data, and further comprising:
obtain sample data List AiSaid sample data Listing AiIncludes a plurality of sample data (A)i1,Ai2,……,Aij,……,Ain) N is an integer greater than 1, wherein A isijIs referred to asjSample data corresponding to the second time node;
performing data processing on the sample data to obtain target state data, wherein the target state data comprises first target state data and second target state data, the first target state data is data used for predicting flight release rate based on flight state, and the second target state data is data used for predicting flight release rate based on weather state;
and performing characteristic processing on the target state data to obtain target characteristics and target data corresponding to the target characteristics.
Specifically, the target data refers to data for predicting flight passing rate through a prediction model.
In particular, the second time node is divided by the time of the day, e.g., the AijThe second time node corresponding to the sample data list is 10 points.
In particular, the sample data set aiThe sample data in the middle is sorted according to the second time node sequence, namely the sample data Aij-1The second time node corresponding to the sample data is earlier than the AijA first time node corresponding to the sample data list, wherein the time interval of the adjacent second time node is generally 2 hours when A isijWhen the first time node corresponding to the sample data list is 10 points, the A pointij-1The first time node corresponding to the sample data list is 8 points.
Specifically, the sample data includes: the flight status data and/or the weather status data of the simultaneous weather sequences, that is, the flight status data and the weather status data correspond to the same second time node, for example, the second time node corresponding to the flight status data is 8 o 'clock of the day, and the second time node corresponding to the weather status data is also 8 o' clock of the day.
Further, the flight status data set comprises: real-time flight status data and/or full-time flight status data, wherein the full-time flight status data is an average of all real-time flight status data.
Further, the set of weather status data comprises: the weather state data comprises any one or more of real-time weather state data, predicted weather state data or full-time weather state data, wherein the full-time weather state time is the average value of all the real-time weather state data, and the predicted weather state data refers to the predicted weather state data of the next day.
In practical applications, the flight status is one of the important factors affecting flight delay, and the method further includes: performing data processing on the flight status data to obtain first target status data, wherein the data processing on the flight status data to obtain the first target status data further comprises:
performing feature extraction on the flight status data to obtain flight status features and a first vector list B = (B)1,B2,……,Bx,……,Bp) P is an integer greater than 1, wherein B isxRefers to the flight status feature vector corresponding to the x-th airport,
normalizing the characteristic value corresponding to the flight state characteristic in any flight vector to obtain a first target characteristic value;
and generating the first target state data according to the first target characteristic value corresponding to the first vector list.
Further, the first target characteristic value is a unique numerical value reflecting the flight status of the current time node.
Further, the flight status feature includes: any one or more of the combination of accumulated outbound flights, accumulated cancelled flights, accumulated outbound delayed flights or accumulated inbound delayed flights.
In some embodiments, the flight status characteristics are determined from a starting second time node to a current second time node on the same day.
In practical application, the weather state is also one of important factors influencing flight delay, when the sample data is weather state data, the weather state data is subjected to data processing to obtain second target state data, and the method further comprises the following steps:
performing feature extraction on the weather state data to obtain weather state features and a second vector list C = (C)1,C2,……,Cy,……,Cq) Q is an integer greater than 1, wherein C isyThe weather characteristic vector corresponding to the y airport is referred to;
fusing the characteristic values corresponding to the weather state characteristics in any weather vector to obtain a second target characteristic value, wherein the weather state characteristics are converted into corresponding characteristic values according to priorities;
and generating the second target state data according to the two target characteristic values corresponding to the second vector list.
Further, the weather status features include: visibility, wind power and weather conditions, wherein the weather conditions have various conditions, such as strong snow, heavy snow, thunderstorm, strong rain, strong dust storm, haze, floating dust, cloudy condition, sunny condition and the like.
Further, the weather state features are converted into corresponding feature values according to the priority, and for better understanding: the visibility features are divided into three priorities, and the visibility of more than 3000m is 0; visibility >1000 is grade 1; the rest is 2 stages; the wind power characteristics are divided into three priority levels, the wind power is greater than 9m/s and is set as level 2, the wind power is greater than 5m/s and is set as level 1, and the rest is level 0; for the weather state characteristics, because the weather state characteristics are qualitative variables, the weather state characteristics are quantized according to the influence degree of the weather state characteristics on flight delay, and are mainly divided into three priority levels, for example, weather such as strong snow, heavy snow, strong rain, thunderstorm, sandstorm and the like is divided into 2 levels; the weather such as snow, rain, light fog, smoke, sand and the like is divided into 1 grade; other cloudy, sunny, floating and sinking weathers are divided into 0 grade; wherein, the divided priority is the corresponding characteristic value.
In some embodiments, other data is input into the prediction model, for example, time heterogeneity of flight plans and activities, data corresponding to time characteristics such as time, season, month, etc.; the flight clearance can be predicted by combining various influence factors, and the accuracy of the predicted value of the flight clearance is improved.
In the embodiment, the target state data can be calculated together through the flight state data and the weather state data, so that the flight clearance rate predicted value is prevented from being influenced by single data, and the accuracy of the flight clearance rate predicted value is improved; meanwhile, all data of the unused airports are obtained, the influence of weather states or flight states of other airports is avoided, the data are enriched, and the accuracy of the predicted value of the flight clearance rate is improved.
In a specific embodiment, the system further includes a target feature determination module, and the target feature determination module implements the following steps:
obtaining a variance value of the target state data;
comparing the variance value with a preset variance threshold value;
and when the variance value is smaller than the preset variance threshold value, deleting the features in the target state data, and determining the undeleted features as target features.
Preferably, the preset variance threshold is 0.01.
Specifically, the variance value refers to a variance between a feature value corresponding to each feature and a corresponding average value thereof in the target state data.
In a specific embodiment, in step S107, the inputting the training set data into a prediction model to adjust the parameters of the prediction model further includes:
inputting the training set data into a prediction model to obtain a training value;
carrying out error processing on the training value to obtain an optimized value of the prediction model;
and adjusting the prediction model parameters according to the optimized value.
Specifically, the optimized value of the prediction model refers to an index value for optimizing a parameter of the prediction model.
Specifically, the error processing refers to calculating an optimized value by any one or more combinations of a mean square error method, a root mean square error method, or an average absolute error method, as shown in fig. 1, fig. 1 is a comparison graph of an actual normal rate of a flight and a predicted normal rate of the flight, for example, data with time nodes of 2019, 6 months and 7 months and 2020, 6 months, 1 day to 14 days is selected from training set data, data with time nodes of 2020, 6 months, 15 days to 19 days is selected from testing set data, a prediction model is input for training, and a training result of the testing set is obtained as shown in fig. 1, wherein the optimized value is 0.031 by the mean square error method, the optimized value is 0.027 by the root mean square error, and the flowering branch after fusion is 0.73.
In the embodiment, by carrying out error processing on the training value, the prediction model parameters can be accurately adjusted according to the optimized value, and the accuracy of obtaining the predicted value of the flight clearance rate according to the prediction set data is improved.
In a specific embodiment, the obtaining the predicted value of the flight passing rate by inputting the prediction set data to the adjusted prediction model in step S109 further includes:
determining the target flight passing rate;
determining characteristics required by the target flight passing rate from the target characteristics;
acquiring corresponding target data according to the characteristics required by the target flight passing rate;
and inputting the test set data in the target data into the adjusted prediction model to obtain the prediction data of the flight passing rate.
Specifically, the flight release rate refers to the number of flights in any airport that have executed standard flight missions, and the standard flight missions include standard take-off missions and standard landing missions, wherein the standard take-off missions take off within the airport ground sliding time specified after the planned cabin door closing time, and abnormal conditions such as return flight, standby landing and the like do not occur; the standard landing task is realized in a specified time period which is no later than the planned cabin door opening time, wherein the specified time period is 20-25 min.
Specifically, the target flight passing rate includes any one or more of a real-time day flight passing rate, a real-time next-day flight passing rate, or a final next-day flight passing rate.
In practical application, when the target flight release rate is determined to be the real-time next-day flight release rate, acquiring flight state data corresponding to a current time node, predicted weather state data corresponding to a next-day and same-time node and time data of a next day; inputting the data of the three parts into the adjusted prediction model to obtain the real-time next-day flight clearance rate; similarly, when the target flight clearance rate is determined to be the real-time current-day flight clearance rate, acquiring flight state data corresponding to a current-day time node, predicted weather state data corresponding to the current-day and current-day time node and current-day time data to obtain the real-time current-day flight clearance rate; similarly, when the target flight release rate is determined to be the final flight release rate of the next day, acquiring the flight status characteristics of the whole period of the day, the weather status data of the whole period of the day and the time data of the day; the method can predict various flight release rates and is convenient for the airport to uniformly arrange the flights.
Specifically, the prediction model is a LightGBM model, and the LightGBM is a fast, distributed and high-performance gradient lifting framework based on a decision tree algorithm, can be used in sequencing, classification, regression and many other machine learning tasks, can achieve faster training efficiency, low memory usage, higher accuracy, support of parallelization learning, can process large-scale data and features, is convenient to calculate flight clearance according to a plurality of features, and improves accuracy of the flight clearance.
The system provided by the embodiment processes flight status data and weather status data with a plurality of characteristics to form target data, screens the characteristics corresponding to the target data, and selects the corresponding target data for prediction based on the target flight clearance rate to be predicted.
Claims (9)
1. A system for predicting flight clearance rate, comprising a processor, a memory and a readable storage medium, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the steps of:
obtaining a sample data set A of an airport, the sample data set A comprising a plurality of sample data lists, A = (A)1,A2,……,Ai,……,Am) M is an integer greater than 1, wherein the sample data list AiThe current time point is a sample data list corresponding to the ith first time node;
listing the sample data to be AiPreprocessing the sample data to obtain target data;
dividing the target data into training set data and prediction set data according to the target data;
inputting the training set data into a prediction model, and adjusting parameters of the prediction model;
and inputting the prediction set data into the adjusted prediction model to obtain a predicted value of the flight clearance rate.
2. The system for predicting flight passing rate of claim 1, wherein the sample data list in the sample data set A is sorted in time order.
3. The system of claim 1, wherein the sample data is listed as sample data list AiPreprocessing the sample data to obtain target data and a target data set corresponding to the target data, and further comprising:
obtain sample data List AiSaid sample data Listing AiIncludes a plurality of sample data (A)i1,Ai2,……,Aij,……,Ain) Wherein, the A isijIs referred to asjSample data corresponding to a second time node, wherein the second time node is divided by time in the current day;
performing data processing on the sample data to obtain target state data, wherein the target state data comprises first target state data and second target state data, the first target state data is data used for predicting flight release rate based on flight state, and the second target state data is data used for predicting flight release rate based on weather state;
and performing characteristic processing on the target state data to obtain target characteristics and target data corresponding to the target characteristics.
4. A system for prediction of flight clearance rate according to claim 3, wherein the sample data comprises: flight status data and/or weather status data for a simultaneous weather sequence.
5. The system for predicting flight clearance rate of claim 4, wherein the method further comprises: performing data processing on the flight status data to obtain first target status data, wherein the data processing on the flight status data to obtain the first target status data further comprises:
performing feature extraction on the flight status data to obtain flight status features and a first vector list B = (B)1,B2,……,Bx,……,Bp) P is an integer greater than 1, wherein B isxRefers to the flight status feature vector corresponding to the x-th airport,
normalizing the characteristic value corresponding to the flight state characteristic in any flight vector to obtain a first target characteristic value;
and generating the first target state data according to the first target characteristic value corresponding to the first vector list.
6. The system for predicting flight passing rate according to claim 5, wherein when the sample data is weather state data, the weather state data is subjected to data processing to obtain second target state data, further comprising:
performing feature extraction on the weather state data to obtain weather state features and a second vector list C = (C)1,C2,……,Cy,……,Cq) Q is an integer greater than 1, wherein C isyThe weather characteristic vector corresponding to the y airport is referred to;
fusing the characteristic values corresponding to the weather state characteristics in any weather vector to obtain a second target characteristic value, wherein the weather state characteristics are converted into corresponding characteristic values according to priorities;
and generating the second target state data according to the two target characteristic values corresponding to the second vector list.
7. The system for predicting flight clearance rate of claim 3, further comprising a determine target feature module, the determine target feature module implementing the steps of:
obtaining a variance value of the target state data;
comparing the variance value with a preset variance threshold value;
and when the variance value is smaller than the preset variance threshold value, deleting the features in the target state data, and determining the undeleted features as target features.
8. The system for predicting flight clearance rate of claim 1, wherein the adjusting the predictive model parameters using the training set data input to a predictive model further comprises:
inputting the training set data into a prediction model to obtain a training value;
carrying out error processing on the training value to obtain an optimized value of the prediction model;
and adjusting the prediction model parameters according to the optimized value.
9. The system of claim 7, wherein the means for predicting flight clearance data input to the adjusted predictive model to obtain the predicted value of flight clearance data further comprises:
determining the target flight passing rate;
determining characteristics required by the target flight passing rate from the target characteristics;
acquiring corresponding target data according to the characteristics required by the target flight passing rate;
and inputting the test set data in the target data into the adjusted prediction model to obtain the prediction data of the flight passing rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011367710.XA CN112132366A (en) | 2020-11-30 | 2020-11-30 | Prediction system for flight clearance rate |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011367710.XA CN112132366A (en) | 2020-11-30 | 2020-11-30 | Prediction system for flight clearance rate |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112132366A true CN112132366A (en) | 2020-12-25 |
Family
ID=73852470
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011367710.XA Pending CN112132366A (en) | 2020-11-30 | 2020-11-30 | Prediction system for flight clearance rate |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112132366A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113313391A (en) * | 2021-06-01 | 2021-08-27 | 中国民航信息网络股份有限公司 | Flight space resource allocation method, device and server |
CN113610282A (en) * | 2021-07-23 | 2021-11-05 | 北京首都国际机场股份有限公司 | Flight taxi time prediction method |
CN114254840A (en) * | 2022-03-02 | 2022-03-29 | 中航信移动科技有限公司 | Data processing method, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190066519A1 (en) * | 2017-08-30 | 2019-02-28 | The Boeing Company | Aircraft flight planning apparatus and method |
CN109409587A (en) * | 2018-10-09 | 2019-03-01 | 南京航空航天大学 | A kind of airport excavated based on weather data is into traffic flow forecasting method of leaving the theatre |
CN109492334A (en) * | 2018-12-11 | 2019-03-19 | 青岛心中有数科技有限公司 | Delayed method for establishing model, prediction technique and device |
CN109523082A (en) * | 2018-11-20 | 2019-03-26 | 广东机场白云信息科技有限公司 | A method of based on CNN-LSTM flight, normally clearance rate is predicted |
CN110363333A (en) * | 2019-06-21 | 2019-10-22 | 南京航空航天大学 | The prediction technique of air transit ability under the influence of a kind of weather based on progressive gradient regression tree |
CN111160612A (en) * | 2019-12-03 | 2020-05-15 | 南京航空航天大学 | Off-site flight delay analysis and prediction method based on weather influence |
-
2020
- 2020-11-30 CN CN202011367710.XA patent/CN112132366A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190066519A1 (en) * | 2017-08-30 | 2019-02-28 | The Boeing Company | Aircraft flight planning apparatus and method |
CN109409587A (en) * | 2018-10-09 | 2019-03-01 | 南京航空航天大学 | A kind of airport excavated based on weather data is into traffic flow forecasting method of leaving the theatre |
CN109523082A (en) * | 2018-11-20 | 2019-03-26 | 广东机场白云信息科技有限公司 | A method of based on CNN-LSTM flight, normally clearance rate is predicted |
CN109492334A (en) * | 2018-12-11 | 2019-03-19 | 青岛心中有数科技有限公司 | Delayed method for establishing model, prediction technique and device |
CN110363333A (en) * | 2019-06-21 | 2019-10-22 | 南京航空航天大学 | The prediction technique of air transit ability under the influence of a kind of weather based on progressive gradient regression tree |
CN111160612A (en) * | 2019-12-03 | 2020-05-15 | 南京航空航天大学 | Off-site flight delay analysis and prediction method based on weather influence |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113313391A (en) * | 2021-06-01 | 2021-08-27 | 中国民航信息网络股份有限公司 | Flight space resource allocation method, device and server |
CN113313391B (en) * | 2021-06-01 | 2024-04-09 | 中国民航信息网络股份有限公司 | Flight space resource allocation method, device and server |
CN113610282A (en) * | 2021-07-23 | 2021-11-05 | 北京首都国际机场股份有限公司 | Flight taxi time prediction method |
CN114254840A (en) * | 2022-03-02 | 2022-03-29 | 中航信移动科技有限公司 | Data processing method, electronic equipment and storage medium |
CN114254840B (en) * | 2022-03-02 | 2022-06-03 | 中航信移动科技有限公司 | Data processing method, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112132366A (en) | Prediction system for flight clearance rate | |
CN107045788B (en) | Traffic road condition prediction method and device | |
CN110458336B (en) | Online appointment vehicle supply and demand prediction method based on deep learning | |
CN107818382B (en) | Flight arrival time prediction method | |
CN110570693B (en) | Flight operation time prediction method based on reliability | |
CN111178628B (en) | Luggage arrival time prediction method and device | |
CN108805337B (en) | Aviation operation control risk management and control method and system | |
CN110796315B (en) | Departure flight delay prediction method based on aging information and deep learning | |
CN113706931B (en) | Airspace flow control strategy recommendation method and device, electronic equipment and storage medium | |
Reitmann et al. | Advanced quantification of weather impact on air traffic management | |
Wang et al. | Modeling weather impact on ground delay programs | |
CN116432806A (en) | Rolling prediction method and system for flight ground guarantee node time | |
CN112232535A (en) | Flight departure average delay prediction method based on supervised learning | |
Dalmau et al. | A machine learning approach to predict the evolution of air traffic flow management delay | |
CN111161566A (en) | Flight delay early warning method, system, electronic equipment and medium | |
CN112258273A (en) | Bidding cabin ascending method and device | |
Schultz et al. | Classification of weather impacts on airport operations | |
CN110659773A (en) | Flight delay prediction method based on deep learning | |
CN114037122A (en) | Flight delay prediction method based on big data mining processing analysis | |
Palpialy et al. | Forecasting Passengers Arriving and Departing at Sentani International Airport Terminal Using the ARIMA Method | |
Ying et al. | Terminal Traffic Flow Prediction Method Under Convective Weather Using Deep Learning Approaches. | |
CN109657865A (en) | A kind of fund pool account facility extent prediction technique and device | |
CN114742458A (en) | Airport flight operation toughness assessment and prediction method in severe weather | |
Priyanka | Prediction of airline delays using K-nearest neighbor algorithm | |
Jiang et al. | A multi-index prediction method for flight delay based on long short-term memory network model |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201225 |