CN111161566B - Flight delay early warning method, system, electronic equipment and medium - Google Patents
Flight delay early warning method, system, electronic equipment and medium Download PDFInfo
- Publication number
- CN111161566B CN111161566B CN201911395635.5A CN201911395635A CN111161566B CN 111161566 B CN111161566 B CN 111161566B CN 201911395635 A CN201911395635 A CN 201911395635A CN 111161566 B CN111161566 B CN 111161566B
- Authority
- CN
- China
- Prior art keywords
- model
- early warning
- flight
- flight delay
- data set
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000007477 logistic regression Methods 0.000 claims abstract description 18
- 238000003066 decision tree Methods 0.000 claims abstract description 14
- 230000015654 memory Effects 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 16
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 3
- 230000010006 flight Effects 0.000 abstract description 13
- 238000012545 processing Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0043—Traffic management of multiple aircrafts from the ground
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a flight delay early warning method, a flight delay early warning system, electronic equipment and a medium, wherein the flight delay early warning method comprises the following steps: constructing a flight delay data set; constructing characteristic data according to the flight delay data set; generating an early warning model by adopting a mode of fusing a gradient lifting decision tree and a logistic regression model according to the characteristic data; and generating early warning information according to the early warning model. The invention realizes the prediction of the delay condition of the long-time flights in the future.
Description
Technical Field
The invention belongs to the technical field of flight delay early warning, and particularly relates to a flight delay early warning method, a flight delay early warning system, electronic equipment and media.
Background
With the rapid development of big data technology, flight delay prediction has become a research hotspot in the field of civil aviation. In 2014, a flight delay prediction system is constructed by L.Belcastro based on a Random Forest algorithm (Random Forest), and is mainly used for predicting flight delay caused by weather factors. In the same year, Rebollo et al developed a delay early warning model using data mining technology that can predict the departure delay of a departure flight within 2-24 hours in the future in the united states. In 2016, Kim et al proposed a flight delay prediction method based on LSTM (Long Short-Term Memory). In the industry, some companies are also currently making flight delay predictions, for example, "Google Flights" of Google corporation, "flight accuracy" of flight friend science and technology, and the like can provide flight delay prediction services for users.
However, most of the current delay early warning models can only give a prediction result hours before the flight takes off, most flight passengers usually order tickets days or even tens of days in advance, and the delay prediction only hours before the flight takes off is far from sufficient for users.
Disclosure of Invention
The invention aims to overcome the defect that flight delay early warning in the prior art can only give a prediction result hours before flight take-off, and provides a flight delay early warning method, a flight delay early warning system, electronic equipment and a medium.
The invention solves the technical problems through the following technical scheme:
the invention provides a flight delay early warning method, which comprises the following steps:
constructing a flight delay data set;
constructing characteristic data according to the flight delay data set;
generating an early warning model by adopting a mode of fusing a Gradient Boosting Decision Tree (GBDT) and a Logistic Regression (LR) model according to the characteristic data;
and generating early warning information according to the early warning model.
Preferably, the step of constructing the flight delay data set comprises:
and constructing a flight delay original data set, and performing data cleaning on the flight delay original data set to generate a flight delay data set.
Preferably, the step of constructing the characteristic data from the flight delay data set comprises:
and extracting basic flight attributes, delay information in a preset deadline, a preamble flight and weather features according to the flight delay data set to construct feature data.
Preferably, the step of generating the early warning model by adopting an XGBoost system framework and adopting a mode of fusing the gradient boost decision tree and the logistic regression model according to the feature data comprises:
the XGboost system framework constructs a binary vector according to the characteristic data, each element of the binary vector corresponds to a leaf node of a tree in the XGboost system framework, and the logistic regression model is trained according to the characteristic data and the binary vector to obtain the early warning model.
The invention also provides a flight delay early warning system which comprises a data set construction unit, a characteristic construction unit, a model generation unit and an early warning information generation unit;
the data set construction unit is used for constructing a flight delay data set;
the characteristic construction unit is used for constructing characteristic data according to the flight delay data set;
the model generation unit is used for generating an early warning model according to the characteristic data in a mode of fusion of a gradient lifting decision tree and a logistic regression model;
the early warning information generating unit is used for generating early warning information according to the early warning model.
Preferably, the data set constructing unit is further configured to construct a flight delay original data set, and perform data cleaning on the flight delay original data set to generate a flight delay data set.
Preferably, the feature construction unit is further configured to extract basic flight attributes, delay information within a preset deadline, a preamble flight, and weather features according to the flight delay data set to construct feature data.
Preferably, the gradient lifting decision tree adopts an XGboost system frame, the model generation unit is further used for adopting the XGboost system frame to construct a binary vector according to the feature data, each element of the binary vector corresponds to a leaf node of a tree in the XGboost system frame, and a logistic regression model is adopted to train according to the feature data and the binary vector to obtain the early warning model.
The invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the flight delay early warning method is realized.
The invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the flight delay warning method of the invention.
The positive progress effects of the invention are as follows: the invention realizes the prediction of the delay condition of the long-time flights in the future.
Drawings
Fig. 1 is a flowchart of a flight delay early warning method according to embodiment 1 of the present invention.
Fig. 2 is a schematic structural diagram of a flight delay early warning system according to embodiment 2 of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to embodiment 3 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
The embodiment provides a flight delay early warning method. Referring to fig. 1, the flight delay early warning method includes the following steps:
and step S101, constructing a flight delay data set.
And S102, constructing characteristic data according to the flight delay data set.
And S103, generating an early warning model by adopting a mode of fusion of a gradient lifting decision tree and a logistic regression model according to the characteristic data.
And step S104, generating early warning information according to the early warning model.
In specific implementation, in step S101, a flight delay original data set is constructed, and the flight delay original data set is subjected to data cleaning to generate a flight delay data set. In the flight delay original data set, if the arrival delay time of a flight is more than 30 minutes, the flight is considered to be delayed and marked as a positive sample needing prediction and identification, and if the arrival delay time of the flight is less than or equal to 30 minutes, the flight is marked as a negative sample. The data cleaning comprises the following steps: and (4) the shared flights are normalized, namely the shared flights exist in part of flights, only the records of the main carrier flights are kept, and the records of the shared flights are deleted. The data cleaning further comprises: and canceling the flight processing, namely deleting the record of canceling the flight. The data cleaning further comprises: and (4) carrying out reserve landing and return flight processing, namely reserving the flight record of the reserve landing and return flight and marking the flight record as a positive sample.
In step S102, the reason for flight delay is classified into severe weather, advanced flight late arrival and airspace flow control 3, and the following 4 types of features are constructed in combination with the professional knowledge of the civil aviation industry: flight basic attributes: such as flight number, departure and landing airport, affiliated boss, month, etc. Secondly, short-term delay condition: such as a delay of approximately 14 days at the airport. Third, flight: such as the interval between the flight scheduled departure time and the scheduled arrival time of the preceding flight, etc. Weather characteristics: such as airport visibility, rainfall, wind speed and direction, etc.
In step S103, in order to delay prediction of a flight that takes off in a long period of time in the future, a model prediction date (predictdate), a flight planned departure date (takeoffdate), and a prediction gap (gap-predictdate) are defined. According to the difference of the prediction gap, the model is divided into 3 sub-models: the system comprises a sub-model I (gap is more than or equal to 0 and less than or equal to 2), a sub-model II (gap is more than or equal to 3 and less than or equal to 10) and a sub-model III (gap is more than or equal to 11), wherein the sub-model I uses the weather characteristics of the hour level, the sub-model II uses the weather characteristics of the day level, and the sub-model III does not use the weather characteristics.
In step S103, a method of fusion of a gradient lifting decision tree and a logistic regression model is adopted, wherein an XGBoost system framework is used for GBDT. The concrete implementation is as follows: the method includes the steps that firstly, original features are input into XGboost, new features are constructed by using a tree learned by the XGboost, the new features are binary vectors, and each element of the vectors corresponds to a leaf node of the tree in the XGboost. And secondly, putting the original features and the new features into LR for training to obtain a final early warning model.
The early warning model is an off-line model, the trained early warning model is deployed on a Zeus (a data development platform) big data development platform, the input of the sub-model I is updated once every 4 hours, the input of the sub-model II and the sub-model III is updated once every day, and the prediction results are gathered and fall into a hive (a data warehouse tool) table for production calling.
This embodiment fuses the data of a plurality of channels, a plurality of dimensions, and application big data and machine learning technique predict the delay condition of future longer time flight, and the better planning journey of user of help taking journey reduces because the loss that the flight delay caused, promotes user experience, if: (1) when the passenger carries the journey to shop for the ticket, the delay probability of the flight is displayed to the passenger. (2) When the passenger changes the sign due to the flight change, the passenger is recommended the flight with low delay probability.
Example 2
The invention also provides a flight delay early warning system. Referring to fig. 2, the flight delay early warning system includes a data set constructing unit 201, a feature constructing unit 202, a model generating unit 203, and an early warning information generating unit 204.
The data set construction unit 201 is used to construct flight delay data sets. The feature construction unit 202 is configured to construct feature data from the flight delay data set. The model generating unit 203 is configured to generate an early warning model according to the feature data by using a gradient lifting decision tree and logistic regression model fusion method. The warning information generating unit 204 is configured to generate warning information according to the warning model.
In specific implementation, the data set constructing unit 201 constructs a flight delay original data set, and performs data cleaning on the flight delay original data set to generate a flight delay data set. In the flight delay original data set, if the arrival delay time of a flight is more than 30 minutes, the flight is considered to be delayed and marked as a positive sample needing prediction and identification, and if the arrival delay time of the flight is less than or equal to 30 minutes, the flight is marked as a negative sample. The data cleaning comprises the following steps: and (4) the shared flights are normalized, namely the shared flights exist in part of flights, only the records of the main carrier flights are kept, and the records of the shared flights are deleted. The data cleaning further comprises: and canceling the flight processing, namely deleting the record of canceling the flight. The data cleaning further comprises: and (4) carrying out reserve landing and return flight processing, namely reserving the flight record of the reserve landing and return flight and marking the flight record as a positive sample.
The feature construction unit 202 classifies the reasons of flight delay into 3 types of severe weather, advanced flight late arrival and airspace flow control, and constructs the following 4 types of features by combining with the professional knowledge of the civil aviation industry: flight basic attributes: such as flight number, departure and landing airport, affiliated boss, month, etc. Secondly, short-term delay condition: such as a delay of approximately 14 days at the airport. Third, flight: such as the interval between the flight scheduled departure time and the scheduled arrival time of the preceding flight, etc. Weather characteristics: such as airport visibility, rainfall, wind speed and direction, etc.
In order to delay prediction of a flight taking off in a longer period of time in the future, the model generation unit 203 defines a model prediction date (predictdate), a flight planned take-off date (takeoffdate), and a prediction gap (gap-predictdate). According to the difference of the prediction gap, the model is divided into 3 sub-models: the system comprises a sub-model I (gap is more than or equal to 0 and less than or equal to 2), a sub-model II (gap is more than or equal to 3 and less than or equal to 10) and a sub-model III (gap is more than or equal to 11), wherein the sub-model I uses the weather characteristics of the hour level, the sub-model II uses the weather characteristics of the day level, and the sub-model III does not use the weather characteristics.
The model generation unit 203 adopts a method of fusion of a gradient lifting decision tree and a logistic regression model, wherein the GBDT adopts an XGboost system framework. The concrete implementation is as follows: the method includes the steps that firstly, original features are input into XGboost, new features are constructed by using a tree learned by the XGboost, the new features are binary vectors, and each element of the vectors corresponds to a leaf node of the tree in the XGboost. And secondly, putting the original features and the new features into LR for training to obtain a final early warning model.
The early warning model is an off-line model, the trained early warning model is deployed on a Zeus big data development platform, the input of the sub-model I is updated once every 4 hours, the input of the sub-model II and the input of the sub-model III are updated once every day, and the prediction results are gathered and fall into a hive table for production calling.
This embodiment fuses the data of a plurality of channels, a plurality of dimensions, and application big data and machine learning technique predict the delay condition of future longer time flight, and the better planning journey of user of help taking journey reduces because the loss that the flight delay caused, promotes user experience, if: (1) when the passenger carries the journey to shop for the ticket, the delay probability of the flight is displayed to the passenger. (2) When the passenger changes the sign due to the flight change, the passenger is recommended the flight with low delay probability.
Example 3
Fig. 3 is a schematic structural diagram of an electronic device provided in this embodiment. The electronic device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the flight delay early warning method of embodiment 1. The electronic device 30 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
The electronic device 30 may be embodied in the form of a general purpose computing device, which may be, for example, a server device. The components of the electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, and a bus 33 connecting the various system components (including the memory 32 and the processor 31).
The bus 33 includes a data bus, an address bus, and a control bus.
The memory 32 may include volatile memory, such as Random Access Memory (RAM)321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
The processor 31 executes various functional applications and data processing, such as the flight delay warning method according to embodiment 1 of the present invention, by executing the computer program stored in the memory 32.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through input/output (I/O) interfaces 35. Also, model-generating device 30 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via network adapter 36. As shown, network adapter 36 communicates with the other modules of model-generating device 30 via bus 33. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the model-generating device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 4
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the steps of the flight delay warning method of embodiment 1.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation manner, the invention can also be implemented in the form of a program product, which includes program code for causing a terminal device to execute the steps of implementing the flight delay early warning method of example 1 when the program product runs on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (8)
1. A flight delay early warning method is characterized by comprising the following steps:
constructing a flight delay data set;
constructing characteristic data according to the flight delay data set;
generating an early warning model by adopting a mode of fusing a gradient lifting decision tree and a logistic regression model according to the characteristic data;
generating early warning information according to the early warning model;
the step of constructing feature data from the flight delay data set comprises:
extracting basic flight attributes, delay information within a preset deadline, a preamble flight and weather features according to the flight delay data set to construct feature data;
the early warning model is divided into three sub-models according to the prediction interval between the scheduled takeoff date of the flight and the model prediction date, wherein the three sub-models are respectively a first sub-model corresponding to the prediction interval being smaller than or equal to a first preset interval, a third sub-model corresponding to the prediction interval being larger than or equal to a second preset interval, and a second sub-model corresponding to the prediction interval being larger than the first preset interval and smaller than the second preset interval;
the first sub-model uses weather features at an hour level, the second sub-model uses weather features at a day level, and the third sub-model does not use weather features.
2. The flight delay early warning method of claim 1, wherein the step of constructing a flight delay data set comprises:
and constructing a flight delay original data set, and performing data cleaning on the flight delay original data set to generate the flight delay data set.
3. The flight delay early warning method as claimed in claim 1, wherein the gradient boost decision tree adopts an XGBoost system framework, and the step of generating the early warning model by fusing the gradient boost decision tree and a logistic regression model according to the feature data comprises:
the XGboost system framework constructs a binary vector according to the feature data, each element of the binary vector corresponds to a leaf node of a tree in the XGboost system framework, and the logistic regression model is trained according to the feature data and the binary vector to obtain the early warning model.
4. A flight delay early warning system is characterized by comprising a data set construction unit, a feature construction unit, a model generation unit and an early warning information generation unit;
the data set constructing unit is used for constructing a flight delay data set;
the characteristic construction unit is used for constructing characteristic data according to the flight delay data set;
the model generation unit is used for generating an early warning model according to the characteristic data in a mode of fusion of a gradient lifting decision tree and a logistic regression model;
the early warning information generating unit is used for generating early warning information according to the early warning model;
the characteristic construction unit is also used for extracting flight basic attributes, delay information in a preset deadline, a preamble flight and weather characteristics according to the flight delay data set so as to construct the characteristic data;
the early warning model is divided into three sub-models according to the prediction interval between the scheduled takeoff date of the flight and the model prediction date, wherein the three sub-models are respectively a first sub-model corresponding to the prediction interval being smaller than or equal to a first preset interval, a third sub-model corresponding to the prediction interval being larger than or equal to a second preset interval, and a second sub-model corresponding to the prediction interval being larger than the first preset interval and smaller than the second preset interval;
the first sub-model uses weather features at an hour level, the second sub-model uses weather features at a day level, and the third sub-model does not use weather features.
5. The flight delay early warning system of claim 4, wherein the data set constructing unit is further configured to construct a flight delay raw data set, and perform data cleaning on the flight delay raw data set to generate the flight delay data set.
6. The flight delay early warning system of claim 4, wherein the gradient lifting decision tree employs an XGboost system framework, the model generation unit is further configured to employ the XGboost system framework to construct binary vectors according to the feature data, each element of the binary vectors corresponds to a leaf node of a tree in the XGboost system framework, and the early warning model is obtained by employing the logistic regression model according to the feature data and the binary vectors through training.
7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the flight delay warning method of any one of claims 1-3 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the flight delay warning method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911395635.5A CN111161566B (en) | 2019-12-30 | 2019-12-30 | Flight delay early warning method, system, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911395635.5A CN111161566B (en) | 2019-12-30 | 2019-12-30 | Flight delay early warning method, system, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111161566A CN111161566A (en) | 2020-05-15 |
| CN111161566B true CN111161566B (en) | 2021-06-11 |
Family
ID=70559126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911395635.5A Active CN111161566B (en) | 2019-12-30 | 2019-12-30 | Flight delay early warning method, system, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111161566B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652427B (en) * | 2020-05-29 | 2023-12-29 | 航科院中宇（北京）新技术发展有限公司 | Flight arrival time prediction method and system based on data mining analysis |
| CN112580801B (en) * | 2020-12-09 | 2021-10-15 | 广州优策科技有限公司 | Reinforced learning training method and decision-making method based on reinforced learning |
| CN113657671B (en) * | 2021-08-18 | 2024-02-09 | 北京航空航天大学 | Flight delay prediction method based on ensemble learning |
| CN114707720B (en) * | 2022-03-30 | 2024-07-02 | 中国民航大学 | Longitudinal federal learning-based flight delay prediction method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122052A (en) * | 2017-12-19 | 2018-06-05 | 携程旅游网络技术（上海）有限公司 | Method for pushing, system, storage medium and the electronic equipment of flight delay information |
| CN108337316A (en) * | 2018-02-08 | 2018-07-27 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| 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 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019240989A1 (en) * | 2018-06-15 | 2019-12-19 | Walmart Apollo, Llc | System and method for managing traffic flow of unmanned vehicles |
| AU2018102040A4 (en) * | 2018-12-10 | 2019-01-17 | Chen, Shixuan Mr | The method of an efficient and accurate credit rating system through the gradient boost decision tree |
| CN109886349B (en) * | 2019-02-28 | 2019-11-19 | 成都新希望金融信息有限公司 | A kind of user classification method based on multi-model fusion |
-
2019
- 2019-12-30 CN CN201911395635.5A patent/CN111161566B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122052A (en) * | 2017-12-19 | 2018-06-05 | 携程旅游网络技术（上海）有限公司 | Method for pushing, system, storage medium and the electronic equipment of flight delay information |
| CN108337316A (en) * | 2018-02-08 | 2018-07-27 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 基于梯度提升决策树的航班延误分类预测;刘金元 等;《数学的实践与认识》;20180828;第48卷(第4期);第1-7页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111161566A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111161566B (en) | Flight delay early warning method, system, electronic equipment and medium | |
| EP3444763A1 (en) | Cumulative model for scheduling and resource allocation for airline operations | |
| US11748596B2 (en) | Context based vehicular traffic prediction | |
| Choi et al. | Artificial neural network models for airport capacity prediction | |
| US20210158174A1 (en) | Equipment maintenance assistant training based on digital twin resources | |
| US10252461B2 (en) | Cognitive-based driving anomaly detection based on spatio-temporal landscape-specific driving models | |
| US11017339B2 (en) | Cognitive labor forecasting | |
| US11847591B2 (en) | Short-term load forecasting | |
| Yang et al. | Airport arrival flow prediction considering meteorological factors based on deep‐learning methods | |
| US12025768B2 (en) | Generation of weather analytical scenarios translating likely airport capacity impact from probabilistic weather forecast | |
| CN111858690A (en) | Automatic adjustment method and system for limited sales number of flight space | |
| US11551173B2 (en) | Risk failure prediction for line assets | |
| CN116187154A (en) | Modeling climate data using machine learning | |
| US9153138B1 (en) | Agent-based airfield conflict resolution | |
| CN115994611A (en) | Training method, prediction method, device and storage medium for category prediction model | |
| CN111340536A (en) | Model training method, passenger seat rate progress prediction method, system, device and medium | |
| CN116629460A (en) | Subway passenger flow prediction method based on ST-RANet model | |
| CN116263899A (en) | Dynamic enhancement supply chain strategy based on carbon emission targets | |
| CN115019269A (en) | Environment recognition model training method, driving control method and related device | |
| US20210158175A1 (en) | Asset addition scheduling for a knowledge base | |
| García-Miranda et al. | AIRPORTS Metrics: A Big Data application for computing flights' performance indexes based on flown trajectories | |
| Falque et al. | Machine learning for predicting off-block delays: A case study at Paris—Charles de Gaulle International Airport | |
| Rodríguez-Sanz et al. | A data-driven approach for dynamic and adaptive aircraft trajectory prediction | |
| US11994782B2 (en) | Method for age portraying and painting in electrochromic automobile sheet | |
| US20170352113A1 (en) | Personal life disruption indicator |
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 |