CN113095731B - Flight regulation and control method and system based on passenger flow time sequence clustering optimization - Google Patents
Flight regulation and control method and system based on passenger flow time sequence clustering optimization Download PDFInfo
- Publication number
- CN113095731B CN113095731B CN202110504011.3A CN202110504011A CN113095731B CN 113095731 B CN113095731 B CN 113095731B CN 202110504011 A CN202110504011 A CN 202110504011A CN 113095731 B CN113095731 B CN 113095731B
- Authority
- CN
- China
- Prior art keywords
- flight
- normalized
- flight data
- data
- category
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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"
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a flight regulation and control method and a flight regulation and control system based on passenger flow time sequence clustering optimization, wherein the method comprises the following steps: step S1: performing grouping statistics according to the historical flight orders to obtain flight data; step S2: normalizing the flight data to obtain normalized flight data; and step S3: calculating KL divergence of the normalized flight data pairwise according to dates, and distributing the normalized flight data to a preset interval according to the KL divergence; and step S4: and clustering the normalized flight information of each interval to obtain the category of each normalized flight information, wherein the category is used as reference information for optimizing flight regulation and control. The method provided by the invention can effectively find out the similar situation of the air historical order, provides the similar situation for flight planning personnel as the reference for optimizing flight regulation and control, saves the planning cost and improves the efficiency.
Description
Technical Field
The invention relates to the field of aviation, in particular to a method and a system for optimizing flight regulation and control based on passenger flow time sequence clustering.
Background
With the development of the times, great progress and growth are made in the field of aviation from airport construction to flight number. By the end of 6 months in 2020, the number of China registered navigation airports has reached 296. Accordingly, the need for aviation jurisdictions has also risen. In the face of daily huge flight tasks, flight regulation is a very complicated task, and a commonly used method refers to data such as city scale, proportion, ring ratio and the like. But the method neglects the rules of the market and cannot well meet the market requirements. From the navigation department alone, the historical data cannot be used for referring to other areas of the market and the like. But with reference to other regions only, without considering the time factor, there is a large error.
Therefore, how to effectively find out the similar conditions of the ticketing rules in the historical orders of the air tickets to provide flight planning personnel with planning references for optimizing flight regulation and control becomes an urgent problem to be solved.
Disclosure of Invention
In order to solve the technical problem, the invention provides a flight regulation and control method and system based on passenger flow time sequence clustering optimization.
The technical solution of the invention is as follows: a passenger flow time sequence clustering-based flight regulation and control optimization method comprises the following steps:
step S1: performing grouping statistics according to the historical flight orders to obtain flight data;
step S2: carrying out normalization processing on the flight data to obtain normalized flight data;
and step S3: calculating KL divergence of the normalized flight data pairwise according to dates, and distributing the normalized flight data to a preset interval according to the KL divergence;
and step S4: and clustering the normalized flight information of each interval to obtain the category of each normalized flight information, wherein the category is used as reference information for optimizing flight regulation and control.
Compared with the prior art, the invention has the following advantages:
the invention discloses a passenger flow time sequence clustering-based flight regulation and control optimization method, which can effectively find out similar situations of air historical orders, provide similar situations for flight planning personnel as references for flight regulation and control optimization, save planning cost and improve efficiency.
Drawings
FIG. 1 is a flowchart of a method for optimizing flight regulation and control based on passenger flow time series clustering according to an embodiment of the present invention;
fig. 2 is a step S2 in the passenger flow time series clustering-based flight regulation and control optimization method in the embodiment of the present invention: normalizing the flight data to obtain a flow chart of the normalized flight data;
fig. 3 is a flowchart of a step S3 in a passenger flow time series clustering optimization-based flight regulation and control method in an embodiment of the present invention: calculating KL divergence of the normalized flight data by date pairwise, and distributing the normalized flight data to a preset interval according to the KL divergence;
fig. 4 is a step S4 in the passenger flow time sequence clustering optimization-based flight regulation and control method in the embodiment of the present invention: clustering the normalized flight information of each interval to obtain the category of each normalized flight information, and using the category as a flow chart of the reference information of flight regulation and control;
FIG. 5 is a schematic diagram of a time series clustering process in a passenger flow time series clustering optimization-based flight regulation and control method according to an embodiment of the present invention;
fig. 6 is a block diagram of a structure of a flight regulation and control system based on passenger flow time-series clustering optimization in an embodiment of the present invention.
Detailed Description
The invention provides a flight regulation and control method and system based on passenger flow time sequence clustering optimization, which can effectively find out similar situations of air historical orders, provide similar situations for flight planning personnel as references for flight regulation and control optimization, save planning cost and improve efficiency.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the invention provides a flight regulation and control method based on passenger flow time series clustering optimization, which includes the following steps:
step S1: performing grouping statistics according to the historical flight orders to obtain flight data;
step S2: carrying out normalization processing on the flight data to obtain normalized flight data;
and step S3: calculating KL divergence of the normalized flight data pairwise according to dates, and distributing the normalized flight data to a preset interval according to the KL divergence;
and step S4: and clustering the normalized flight information of each interval to obtain the category of each normalized flight information as reference information for optimizing flight regulation and control.
In one embodiment, the step S1: performing grouping statistics according to the historical flight orders to obtain flight data, wherein the method specifically comprises the following steps:
and obtaining historical orders of all flights of each department in a preset period, and carrying out grouping statistics according to the departure date to obtain flight data grouped according to the date.
And calling historical order data of each flight of each driver in a preset period, and grouping the data according to a departure city, a destination, a flight number and a flight departure date to ensure the uniqueness of the flight. And counting the grouped data according to days, recording a counting value, wherein the primary key Id = departure city + destination + flight number + departure date, and obtaining daily sales data of the flight at the moment.
As shown in fig. 2, in one embodiment, the step S2: normalizing the flight data to obtain normalized flight data, wherein the normalizing comprises the following steps:
step S21: fusing flight data of N days before flight take-off to form fused flight data with consistent length;
the obtained flight sales records are different in length due to different ticket selling periods of each flight. Therefore, the flight data is obtained in step S1. In the embodiment of the present invention, as shown in table 1 below, N =7 is preset so that the length of each set of flight data is N +1=8, and data 7 days before the departure of a flight is added as data on day 8. And fusing the data within 7 days from the takeoff to form fused flight data with consistent length as the original data used in the subsequent steps.
TABLE 1 fusion results of day-to-day flight data
| Id | D1 | D2 | D3 | D4 | D5 | D6 | D7 | D8+ |
The data of the nth row in table 1 may be represented as: x n ＝{x n1 ,x n2 ,x n3 ,x n4 ,x n5 ,x n6 ,x n7 ,x n8 ,}。
Step S22: normalizing the fused flight data according to the following formula (1) to obtain normalized flight data X * :
Wherein X is the fused flight data, sigma (X) is X variance, and E [ X ] is X mean. By normalizing each row of data according to the formula (1), the data can be more stable.
As shown in fig. 3, in one embodiment, the step S3: calculating KL divergence of the normalized flight data pairwise according to dates, and distributing the normalized flight data to a preset interval according to the KL divergence, wherein the KL divergence comprises the following steps:
step S31: calculating KL divergence of the normalized flight data pairwise according to dates to obtain KL divergence of the normalized flight data;
the Id in table 1 is analyzed, the entire table is sorted by the departure date, and the order data is stored, and data for each day is obtained at this time. Taking the day as a unit, calculating KL divergence of data on different dates pairwise. In order to ensure that the KL divergence can be distinguished, the embodiment of the invention takes 5 bits after the decimal point, so that the probability that the KL divergence is the same is one hundred thousand.
Step S32: and dividing the KL divergence distribution interval into K preset categories, and classifying the normalized flight data into the corresponding categories according to the KL divergence of the normalized flight data.
According to the preset K categories, the KL divergence obtained in the step S32 is within the range of the maximum value and the minimum value, K intervals can be divided, data in the same interval is classified into the same category, and flight data in the same category is combined into a table.
For example, if KL (D1, D2) =1.00001, KL (D2, D3) =1.00002, then KL (D1, D3) =1.00003, and depending on the interval range of KL divergence, the KL divergences for three days of D1, D2 and D3 belong to the same interval, and then D1, D2 and D3 belong to the same category.
As shown in fig. 4, in one embodiment, the step S4: clustering the normalized flight information of each interval to obtain the category of each normalized flight information as reference information for flight regulation, wherein the method comprises the following steps:
step S41: for each category, calculating the cross-correlation value and the SBD distance of pairwise normalized flight data in each category according to the following formulas (2) to (3);
wherein CC (cross-correlation) in the formula (2) is a cross-correlation function,
representing the ith data in the Kth category, wherein the F function is fast Fourier transform;
in the formula (3), R is an inner product function,
m is the length of the vector, wherein>
Expressed as the following equation (4):
the SBD value is between 0 and 2, and the closer the SBD values of the two pieces of normalized flight data are to 0, the more similar the two pieces of normalized flight data are.
Step S42: randomly selecting one normalized flight data
As an initialized clustered centroid vector;
step S43: presetting M categories, computing the centroid vectors of the time series clusters of the normalized flight data pairwise according to the following formula (5), and taking the maximum value M as the centroid vector;
wherein the content of the first and second substances,
is the current category.
Step S44: at present
In the category, calculating the SBD distance between each piece of normalized flight data and the centroid vector; if the SBD is smaller than a preset threshold value dist, the normalized flight data is classified as the category to which the centroid vector belongs;
step S45: and when the preset iteration times are reached, the iteration is ended, and the category of the centroid vector and the normalized flight information vectors of the same category are output, so that the category of each normalized flight information is obtained and is used as reference information for optimizing flight regulation and control.
As shown in fig. 5, a flow of performing time-series clustering in the embodiment of the present invention is shown. Firstly, the distance between the centroid and other flight information is calculated by taking randomly selected flight information as the centroid, the centroid is determined again, and the SBD distance is calculated again to determine the category of the flight.
After the steps are carried out, each flight is classified into the same category with other flights similar to the flight. The indexes of the same category are stored as a set, and the indexes are decomposed into different types of fields to be stored in a database. When the flight is scheduled, the relevant information can be inquired by screening according to different fields, and further, the optimization management and control are achieved.
The flight regulation and control method based on passenger flow time sequence clustering optimization provided by the invention utilizes a K-shape mode to perform time sequence clustering, can effectively find out similar conditions of ticket selling rules in historical orders of air plane tickets, provides reference planning for similar conditions of flight planning personnel, saves planning cost and improves efficiency.
Example two
As shown in fig. 6, an embodiment of the present invention provides a passenger flow time series clustering optimization-based flight regulation and control system, including the following modules:
the flight data acquisition module 51 is configured to perform grouping statistics according to the historical flight orders to obtain flight data;
the flight data normalization module 52 is configured to perform normalization processing on the flight data to obtain normalized flight data;
the normalized flight data partitioning module 53 is configured to calculate KL divergences of the normalized flight data by date pair, and allocate the normalized flight data to a preset interval according to the KL divergences;
and the normalized flight data classification module 54 is configured to cluster the normalized flight information of each interval to obtain a category of each normalized flight information, and the category is used as reference information for optimizing flight regulation and control.
The above examples are provided only for the purpose of describing the present invention, and are not intended to limit the scope of the present invention. The scope of the invention is defined by the appended claims. Various equivalent substitutions and modifications can be made without departing from the spirit and principles of the invention, and are intended to be within the scope of the invention.
Claims (5)
1. A flight regulation and control method based on passenger flow time sequence clustering optimization is characterized by comprising the following steps:
step S1: performing grouping statistics according to the historical flight orders and the departure dates to obtain flight data;
step S2: carrying out normalization processing on the flight data to obtain normalized flight data;
and step S3: calculating KL divergence of the normalized flight data by date pairwise, and distributing the normalized flight data to a preset interval according to the KL divergence; the method comprises the following steps:
step S31: calculating KL divergence of the normalized flight data pairwise according to dates to obtain KL divergence of the normalized flight data;
step S32: dividing the KL divergence distribution interval into K preset categories according to the KL divergence distribution interval, and classifying the normalized flight data into the corresponding categories according to the KL divergence of the normalized flight data; dividing K intervals according to preset K categories, wherein the obtained KL divergence is within the range of the maximum value and the minimum value, and classifying the data in the same interval into the same category;
and step S4: and clustering the normalized flight information of each interval to obtain the category of each normalized flight information, wherein the category is used as reference information for optimizing flight regulation and control.
2. The passenger flow time series clustering optimization flight regulation and control method based on claim 1, wherein the step S1: performing grouping statistics according to the historical flight orders to obtain flight data, wherein the method specifically comprises the following steps:
and obtaining historical orders of each flight of each department in a preset period, and carrying out grouping statistics according to the departure date to obtain the flight data grouped according to the date.
3. The passenger flow time series clustering optimization flight regulation and control method based on claim 2, wherein the step S2: normalizing the flight data to obtain normalized flight data, wherein the normalizing comprises the following steps:
step S21: fusing flight data of N days before flight take-off to form fused flight data with consistent length;
step S22: normalizing the fused flight data according to the following formula (1) to obtain normalized flight data X * :
Wherein X is the fused flight data, sigma (X) is X variance, and E [ X ] is X mean value.
4. The passenger flow time series clustering optimization flight regulation and control method based on claim 1, wherein the step S4: clustering the normalized flight information of each interval to obtain the category of each normalized flight information as reference information for flight regulation, wherein the method comprises the following steps:
step S41: for each category, calculating a cross-correlation value and an SBD distance of every two normalized flight data in each category according to the following formulas (2) to (3);
wherein CC (cross-correlation) in the formula (2) is a cross-correlation function,
representing the ith data in the Kth category, wherein the F function is fast Fourier transform;
in the formula (3), R is an inner product function,
m is the length of the vector; wherein it is present>
Expressed as the following equation (4): />
The SBD value is between 0 and 2, and the two pieces of normalized flight data are more similar as the two pieces of normalized flight data are closer to 0;
step S42: randomly selecting one normalized flight data
As an initialized clustered centroid vector;
step S43: presetting M categories, calculating the centroid vector of the time series cluster of the normalized flight data pairwise according to the following formula (5), and taking the maximum value M as the centroid vector;
wherein the content of the first and second substances,
is the current category;
step S44: at present
In the category, calculating the SBD distance between each normalized flight data and the centroid vector; if the SBD is smaller than a preset threshold value dist, the normalized flight data is classified as the category to which the centroid vector belongs;
step S45: and when the preset iteration times are reached, the iteration is ended, and the category of the centroid vector and the normalized flight information vectors of the same category are output, so that the category of each normalized flight information is obtained and is used as reference information for optimizing flight regulation and control.
5. A flight regulation and control system based on passenger flow time sequence clustering optimization is characterized by comprising the following modules:
the flight data acquisition module is used for carrying out grouping statistics according to the historical flight orders and the departure dates to obtain flight data;
the flight data normalization module is used for performing normalization processing on the flight data to obtain normalized flight data;
the normalized flight data partitioning module is used for calculating KL divergence of the normalized flight data pairwise by date, and distributing the normalized flight data to a preset interval according to the KL divergence, and comprises the following steps:
calculating KL divergence of the normalized flight data pairwise according to dates to obtain KL divergence of the normalized flight data;
dividing the KL divergence distribution interval into K preset categories according to the KL divergence distribution interval, and classifying the normalized flight data into the corresponding categories according to the KL divergence of the normalized flight data; dividing K intervals according to preset K categories, wherein the obtained KL divergence is within the range of the maximum value and the minimum value, and classifying the data in the same interval into the same category;
and the normalized flight data classification module is used for clustering the normalized flight information of each interval to obtain the category of each normalized flight information, and the category is used as reference information for optimizing flight regulation and control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110504011.3A CN113095731B (en) | 2021-05-10 | 2021-05-10 | Flight regulation and control method and system based on passenger flow time sequence clustering optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110504011.3A CN113095731B (en) | 2021-05-10 | 2021-05-10 | Flight regulation and control method and system based on passenger flow time sequence clustering optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113095731A CN113095731A (en) | 2021-07-09 |
| CN113095731B true CN113095731B (en) | 2023-04-18 |
Family
ID=76665166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110504011.3A Active CN113095731B (en) | 2021-05-10 | 2021-05-10 | Flight regulation and control method and system based on passenger flow time sequence clustering optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095731B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132128A1 (en) * | 2011-11-17 | 2013-05-23 | Us Airways, Inc. | Overbooking, forecasting and optimization methods and systems |
| CN108596362B (en) * | 2018-03-22 | 2021-12-28 | 国网四川省电力公司经济技术研究院 | Power load curve form clustering method based on adaptive piecewise aggregation approximation |
| CN109615014B (en) * | 2018-12-17 | 2023-08-22 | 清华大学 | KL divergence optimization-based 3D object data classification system and method |
| CN110533220A (en) * | 2019-07-29 | 2019-12-03 | 南京航空航天大学 | A kind of airport departure from port delay distribution method for digging of data-driven |
-
2021
- 2021-05-10 CN CN202110504011.3A patent/CN113095731B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113095731A (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10025753B2 (en) | Computer-implemented systems and methods for time series exploration | |
| US7627432B2 (en) | System and method for computing analytics on structured data | |
| US9244887B2 (en) | Computer-implemented systems and methods for efficient structuring of time series data | |
| Applegate et al. | Unsupervised clustering of multidimensional distributions using earth mover distance | |
| CN108427772B (en) | Online report generation method, system, equipment and storage medium | |
| Guigoures et al. | Discovering patterns in time-varying graphs: a triclustering approach | |
| US20150356175A1 (en) | System and method for finding and inventorying data from multiple, distinct data repositories | |
| Behere et al. | Aircraft landing and takeoff operations clustering for efficient environmental impact assessment | |
| CN116034379A (en) | Activity level measurement using deep learning and machine learning | |
| CN112116810A (en) | Whole road network segment travel time estimation method based on urban road checkpoint data | |
| CN113095731B (en) | Flight regulation and control method and system based on passenger flow time sequence clustering optimization | |
| CN112052405B (en) | Passenger searching area recommendation method based on driver experience | |
| CN112100177A (en) | Data storage method and device, computer equipment and storage medium | |
| CN113297336B (en) | Seasonal classification method, device and machine-readable medium for flights | |
| Tao | Analysis method for customer value of aviation big data based on LRFMC model | |
| Dzikrullah et al. | Implementation of scalable k-means++ clustering for passengers temporal pattern analysis in public transportation system (BRT Trans Jogja case study) | |
| Watanatada et al. | Forecasting urban travel demand for quick policy analysis with disaggregate choice models: A Monte Carlo simulation approach | |
| CN112926809B (en) | Flight flow prediction method and system based on clustering and improved xgboost | |
| CN113673889A (en) | Intelligent data asset identification method | |
| CN110909818B (en) | TBOX-based dimension reduction system for whole vehicle running data | |
| Sautot et al. | A methodology and tool for rapid prototyping of data warehouses using data mining: Application to birds biodiversity | |
| CN117171145B (en) | Analysis processing method, equipment and storage medium for enterprise management system data | |
| CN114492308B (en) | Industry information indexing method and system combining knowledge discovery and text mining | |
| CN113723459B (en) | Bus operation time interval division and one-way point recommendation method based on time aggregation | |
| CN117454892B (en) | Metadata management method, device, terminal equipment and storage medium |
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 |