CN113379443A - Flight flow simulation method and system - Google Patents
Flight flow simulation method and system Download PDFInfo
- Publication number
- CN113379443A CN113379443A CN202110504001.XA CN202110504001A CN113379443A CN 113379443 A CN113379443 A CN 113379443A CN 202110504001 A CN202110504001 A CN 202110504001A CN 113379443 A CN113379443 A CN 113379443A
- Authority
- CN
- China
- Prior art keywords
- flight
- passenger
- information
- demand
- price
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The invention relates to a flight flow simulation method and a flight flow simulation system, wherein the flight flow simulation method comprises the following steps: step S1: according to the flight segment transport capacity, passenger attributes and passenger requirements are obtained through simulation; step S2: according to the passenger demand and flight information, passenger ticket booking information is generated in a simulation mode; step S3: adjusting flight information according to passenger ticket booking information; step S4: and inputting the passenger demand, the passenger ticket booking information and the flight information into the flight flow simulation model to generate the flight flow information. The flight flow simulation method and the flight flow simulation system provided by the invention combine a real service scene, simulate the whole process of passenger demand, ticket purchase of a passenger and price adjustment of an airline crew, and increase the linkage between the influence factor and the flight flow. In addition, due to the mutual correlation between the modules, a competitive relationship exists between flights, and a price adjusting decision regression tree model is added to optimize the price, so that flight traffic information and flight price generated by the simulation model are more realistic.
Description
Technical Field
The invention belongs to the field of aviation income management, and particularly relates to a flight flow simulation method and system.
Background
With the development of the aviation field and the relaxed control of the Chinese civil aviation central office on the price of the flight, the airline companies basically master the pricing right of the air tickets, and thus, the competition among the airlines is more and more intense. In order to develop an airline company, if the market needs to be fully understood and fully mastered, the flight traffic needs to be fully analyzed and researched, so as to further adjust the fare scheme of the airline company to achieve the maximum benefit of the flight. However, for an airline company, only flight traffic data in the local airline department service can be analyzed and studied, and the data is not enough to reflect the real customer needs. If the relationship between flight traffic and pricing is to be analyzed completely, especially for economy class, there is a lack of data from other competing airlines.
Therefore, how to solve the problem that the data of the airline company is not enough to develop the aviation revenue management research becomes a problem to be solved urgently.
Disclosure of Invention
In order to solve the technical problem, the invention provides a flight flow simulation method and a flight flow simulation system.
The technical solution of the invention is as follows: a flight traffic simulation method comprises the following steps:
step S1: according to the flight segment transport capacity, passenger attributes and passenger requirements are obtained through simulation;
step S2: according to the passenger demand and the flight information, passenger ticket booking information is generated in a simulation mode;
step S3: adjusting flight information according to the passenger ticket booking information;
step S4: and inputting the passenger demand, the passenger ticket booking information and the flight information into a flight flow simulation model to generate flight flow information.
Compared with the prior art, the invention has the following advantages:
the flight flow simulation method and the flight flow simulation system provided by the invention combine a real service scene, simulate the whole process of passenger demand, ticket purchase of a passenger and price adjustment of an airline crew, and increase the linkage between the influence factor and the flight flow. In addition, due to the mutual correlation between the modules, a competitive relationship exists between flights, and a price adjusting decision regression tree model is added to optimize the price, so that flight traffic information and flight price generated by the simulation model are more realistic.
Drawings
FIG. 1 is a flow chart of a flight flow simulation method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating the generation of passenger booking information in a flight flow simulation method according to an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating flight information adjustment in a flight flow simulation method according to an embodiment of the present invention;
fig. 4 is a block diagram of a flight traffic simulation system according to an embodiment of the present invention.
Detailed Description
The invention provides a flight flow simulation method and a flight flow simulation system, which solve the problem that the data of an airline company is insufficient so that the aviation income management research cannot be developed.
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 present invention provides a flight traffic simulation method, including the following steps:
step S1: according to the flight segment transport capacity, passenger attributes and passenger requirements are obtained through simulation;
step S2: according to the passenger demand and flight information, passenger ticket booking information is generated in a simulation mode;
step S3: adjusting flight information according to passenger ticket booking information;
step S4: and inputting the passenger demand, the passenger ticket booking information and the flight information into the flight flow simulation model to generate the flight flow information.
In one embodiment, the step S1: according to the flight segment transport capacity, passenger attributes and passenger requirements are obtained through simulation; the method comprises the following steps:
obtaining the total demand of the flight segment according to the flight segment transport capacity, and simulating to obtain the passenger attribute and the passenger demand according to the total demand of the flight segment; wherein the passenger demand is the passenger demand for each flight segment to check tickets each day before takeoff; the passenger attributes include: passenger type, departure city, arrival city, check date, flight date, time sensitivity, and price sensitivity.
The attributes of the passengers reveal the degree of dependence of the passenger on travel, the passenger type determines the time sensitivity (acceptable time range) and price sensitivity (acceptable price range) of the passenger, which in turn determine the degree of importance of the journey. For example, business travelers are more sensitive to time and less sensitive to price, while casual travelers are more sensitive to price and less sensitive to time.
In the step, firstly, summation calculation is carried out according to the seat number of flights under different flight segments every day, and the transport capacity of each flight segment is obtained. For example, the capacity of the PEK-SZX flight segment with 1 month and 1 day of departure is the sum of the seats of flights with PEK in all departure cities and SZX in all arrival cities.
And secondly, determining the total demand of each flight section according to the transportation capacity of the flight section and influence factors such as slack season, busy season, holidays, flight price, important events and the like. When the influence of the dead season or the negative event occurs, the total demand is correspondingly reduced, and when the influence of the dead season, the holiday and the positive event occurs, the total demand is correspondingly increased. The flight price also has an influence on the total demand to a certain extent, and the total demand is reduced for the flight with high price, otherwise, the total demand is increased.
According to the total demand of each flight segment, the passenger attributes and the passenger demands of the flight segments can be obtained through simulation. Where passenger demand is the amount of passenger demand that each flight segment checks tickets daily before takeoff. In the embodiment of the invention, the distribution of the passenger demands is sold from 30 days before the departure date (D30) to the day of the departure date (D0) for each flight segment, and the number of the passenger demands from D30 to D0 is distributed in a Poisson mode, and the maximum value is generally about D7. And when the passenger demand has positive influence factors such as busy seasons, holidays or important meetings, a normal distribution with a peak value lower than the peak value of the poisson distribution is generally added at D15, so that the departure city, the arrival city, the ticket checking date and the flight date in the passenger attributes are determined. The passenger type, the acceptable time range, and the acceptable price range are all proportionally determined and randomly distributed to each passenger attribute to determine the passenger type, time sensitivity, and price sensitivity for each passenger.
Accordingly, embodiments of the present invention may simulate the passenger attributes and passenger requirements for each leg from D30 to D0 prior to takeoff for all legs in a year.
In one embodiment, the passenger ticket booking information in step S2 includes:
the passenger's origin, arrival, ticket purchase date, departure date, flight number, and price of the ticket.
As shown in fig. 2, in this step, the passenger requirements are segmented according to their ticket-checking time sequence, and each passenger requirement in a time segment is traversed according to the ticket-checking time sequence. Firstly, obtaining the flight selectable in the flight section from the latest flight information according to the departure place, the arrival place and the flight date of the passenger; then, judging whether the passenger is a commercial passenger or not according to the attributes of the passenger, if so, judging whether the time can be accepted or not, and if so, directly purchasing to form passenger ticket booking information; otherwise, the purchase is abandoned. For the leisure passengers, whether the price is acceptable is judged in addition to whether the time is acceptable, and if the time is acceptable, the leisure passengers buy flights; if the price is too high, whether a suitable transfer flight exists is considered, if so, the transfer flight is purchased to form passenger ticket booking information; otherwise, checking the number of days from the takeoff date, giving up the purchase if the number of days is less than a certain threshold value, changing to other vehicles or not going out, selecting to wait for observation if the number of days is greater than a certain threshold value, and modifying the ticket checking date of the passenger to be added into the passenger requirement.
In one embodiment, the step S3: adjusting flight information according to the passenger ticket booking information; the method comprises the following steps:
the airline personnel adjust the flight information according to the passenger ticket booking information and in combination with the disturbance factor; wherein, the disturbance factor comprises: long-term factors, short-term factors, market factors, burst factors, and constraints; the flight information comprises: city of departure, city of arrival, economy class full price, flight number, airline, departure time, arrival time, model, total seat number, price, discount, departure date, and remaining seat number.
As shown in fig. 3, in this step, the airline personnel adjust the flight information before the departure date according to the passenger booking information and the disturbance factor. Wherein the perturbation factors include: long-term factors, short-term factors, market factors, burst factors, and constraints. Long-term factors include GDP concordant variation; the short-term factors comprise ring ratio data, on-sale reservation data and sale progress; the market factors comprise competitor price, distance takeoff days and air flight change price; the burst factors comprise holidays, important meetings and important exhibitions; the restrictions include the airline's perception of price and private freight rate agreements, and airline manual, among others. The airline personnel decide to increase or decrease the discount of the flight ticket according to a preset threshold value, adjust the departure time of the flight, or change the passenger seat rate of the flight, and the like, thereby realizing the update of the flight information.
In one embodiment, the step S4: inputting the passenger demand, passenger ticket booking information and flight information into a flight flow simulation model to generate flight flow information, wherein the flight flow simulation model comprises the following steps:
the flight flow simulation model predicts the total demand of the flight segment by using an LSTM model and updates the demand of passengers; and predicting the adjusted flight information according to the passenger ticket purchasing requirements by utilizing a decision regression tree model, and finally generating flight flow information according to the passenger ticket booking information.
Training a long-time and short-time memory network (LSTM) model according to historical flight prices and flight segment requirements, adding characteristics of influences such as holidays and important events on a final full-connection layer, and finally outputting to obtain total flight segment demand. And by using the historical flight price and other influence factors of the unknown flight segment as characteristics, predicting by using a learned model to obtain the total demand of the flight segment, thereby updating the passenger demand and the passenger attribute and generating the passenger booking information. According to the embodiment of the invention, the passenger demand is obtained through LSTM model learning, so that the demand quantity is not fixed, and the uncertainty of the passenger demand and the relevance between the passenger demand and the price are increased.
Historical flight booking information and flight information of a certain airline department are combined with derivative information of the flight booking information and the flight information to be converted into characteristics for model learning, and the historical flight price is used as a label to train the decision regression tree model. And then, predicting the characteristics of the passenger after converting the booking information, the existing flight information and the derivative information by using the learnt decision regression tree model, obtaining the result which is the flight information after adjusting the simulation data, and finally generating the flight flow information by combining the booking information of the passenger. The embodiment of the invention optimizes the price through a model trained by real data, so that the flight price adjusted by an airline operator is more realistic.
The flight flow simulation method provided by the invention combines a real service scene, simulates the whole process of passenger demand, ticket purchase of a passenger and airline personnel price adjustment, and increases the linkage between the influence factor and the flight flow. In addition, due to the mutual correlation between the modules, a competitive relationship exists between flights, and a price adjusting decision regression tree model is added to optimize the price, so that flight traffic information and flight price generated by the simulation model are more realistic.
Example two
As shown in fig. 4, an embodiment of the present invention provides a pedestrian travel classification system based on position data, including the following modules:
the passenger ticket purchasing demand obtaining module 41 is used for obtaining passenger attributes and passenger demands in a simulated mode according to the flight segment transport capacity;
the passenger ticket booking information generating module 42 is used for simulating and generating passenger ticket booking information according to passenger requirements and flight information;
a flight price adjusting module 43, configured to adjust flight information according to passenger ticket booking information;
and the flight flow information generating module 44 is used for inputting the passenger demand, the passenger booking information and the flight information into the flight flow simulation model to generate the flight flow information.
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 (6)
1. A flight traffic simulation method is characterized by comprising the following steps:
step S1: according to the flight segment transport capacity, passenger attributes and passenger requirements are obtained through simulation;
step S2: according to the passenger demand and the flight information, passenger ticket booking information is generated in a simulation mode;
step S3: adjusting flight information according to the passenger ticket booking information;
step S4: and inputting the passenger demand, the passenger ticket booking information and the flight information into a flight flow simulation model to generate flight flow information.
2. The flight traffic simulation method according to claim 1, wherein the step S1: according to the flight segment transport capacity, passenger attributes and passenger requirements are obtained through simulation; the method comprises the following steps:
obtaining the total demand of the flight segment according to the flight segment transport capacity, and simulating to obtain the passenger attribute and the passenger demand according to the total demand of the flight segment; wherein the passenger demand is a passenger demand for each flight segment to check tickets per day before takeoff; the passenger attributes include: passenger type, departure city, arrival city, check date, flight date, time sensitivity, and price sensitivity.
3. The flight traffic simulation method according to claim 1, wherein the passenger booking information in step S2 includes:
the passenger's origin, arrival, ticket purchase date, departure date, flight number, and price of the ticket.
4. The flight traffic simulation method according to claim 1, wherein the step S3: adjusting flight information according to the passenger ticket booking information; the method comprises the following steps:
the airline personnel adjust the flight information according to the passenger ticket booking information and in combination with the disturbance factor; wherein the perturbation factor comprises: long-term factors, short-term factors, market factors, burst factors, and constraints; the flight information comprises: city of departure, city of arrival, economy class full price, flight number, airline, departure time, arrival time, model, total seat number, price, discount, departure date, and remaining seat number.
5. The flight traffic simulation method according to claim 1, wherein the step S4: inputting the passenger demand, the passenger booking information and the flight information into a flight flow simulation model to generate flight flow information, wherein the generating of the flight flow information comprises the following steps:
the flight flow simulation model predicts the total demand of the flight segment by using an LSTM model, updates the passenger demand and generates the passenger booking information; and predicting the adjusted flight information according to the passenger ticket purchasing demand by utilizing a decision regression tree model, and finally generating flight flow information according to the passenger ticket booking information.
6. A flight flow simulation system is characterized by comprising the following modules:
the passenger ticket buying demand obtaining module is used for obtaining passenger attributes and passenger demands in a simulated mode according to the flight segment transport capacity;
the passenger ticket booking information generating module is used for simulating and generating passenger ticket booking information according to passenger requirements and flight information;
the flight price adjusting module is used for adjusting flight information according to passenger ticket booking information;
and the flight flow information generating module is used for inputting the passenger requirements, the passenger booking information and the flight information into a flight flow simulation model to generate flight flow information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110504001.XA CN113379443B (en) | 2021-05-10 | 2021-05-10 | Flight flow simulation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110504001.XA CN113379443B (en) | 2021-05-10 | 2021-05-10 | Flight flow simulation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113379443A true CN113379443A (en) | 2021-09-10 |
| CN113379443B CN113379443B (en) | 2023-10-17 |
Family
ID=77571032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110504001.XA Active CN113379443B (en) | 2021-05-10 | 2021-05-10 | Flight flow simulation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379443B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909383A (en) * | 2017-09-28 | 2018-04-13 | 天津伊翔运达网络科技有限公司 | A kind of Dynamic Pricing method of combination passenger information |
| US20180204146A1 (en) * | 2015-05-13 | 2018-07-19 | Wns Global Services Private Limited | Automated rebooking system and method for airlines |
| CN111144946A (en) * | 2019-12-27 | 2020-05-12 | 上海携程商务有限公司 | Revenue management method, system, medium, and electronic device for airline company |
| CN111899059A (en) * | 2020-08-12 | 2020-11-06 | 科技谷（厦门）信息技术有限公司 | Navigation driver revenue management dynamic pricing method based on block chain |
-
2021
- 2021-05-10 CN CN202110504001.XA patent/CN113379443B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180204146A1 (en) * | 2015-05-13 | 2018-07-19 | Wns Global Services Private Limited | Automated rebooking system and method for airlines |
| CN107909383A (en) * | 2017-09-28 | 2018-04-13 | 天津伊翔运达网络科技有限公司 | A kind of Dynamic Pricing method of combination passenger information |
| CN111144946A (en) * | 2019-12-27 | 2020-05-12 | 上海携程商务有限公司 | Revenue management method, system, medium, and electronic device for airline company |
| CN111899059A (en) * | 2020-08-12 | 2020-11-06 | 科技谷（厦门）信息技术有限公司 | Navigation driver revenue management dynamic pricing method based on block chain |
Non-Patent Citations (1)
| Title |
|---|
| 安磊等: "基于recurrent neural networks的网约车供需预测方法", 《计算机应用研究》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113379443B (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ploetner et al. | Long-term application potential of urban air mobility complementing public transport: an upper Bavaria example | |
| Abed et al. | An econometric analysis of international air travel demand in Saudi Arabia | |
| Ashford et al. | Airport engineering: planning, design, and development of 21st century airports | |
| Lurkin et al. | Accounting for price endogeneity in airline itinerary choice models: An application to Continental US markets | |
| Truitt et al. | Evaluating service quality and productivity in the regional airline industry | |
| US8694346B2 (en) | Travel-related prediction system | |
| Zhang et al. | Air transport services in regional Australia: Demand pattern, frequency choice and airport entry | |
| Baik et al. | Forecasting model for air taxi, commercial airline, and automobile demand in the United States | |
| Mancuso | An analysis of the competition that impinges on the Milan–Rome intercity passenger transport link | |
| Cho et al. | The impact of low-cost carriers on airport choice in the US: A case study of the Washington–Baltimore region | |
| Chen et al. | Spatial distribution characteristic of Chinese airports: A spatial cost function approach | |
| Mohammadian et al. | Airline capacity decisions under supply-demand equilibrium of Australia’s domestic aviation market | |
| Hao et al. | Fueling for contingencies: the hidden cost of unpredictability in the air transportation system | |
| Zijlstra | A border effect in airport choice: Evidence from Western Europe | |
| Amoroso et al. | Vertical take-off and landing air transport to provide tourist mobility | |
| Chou et al. | Evolutionary bi-level model for optimizing ticket fares and operations profit of Taiwan high-speed rail | |
| Zhang et al. | A data-driven quantitative assessment model for taxi industry: the scope of business ecosystem’s health | |
| Presto et al. | Flight frequency regulation and its temporal implications | |
| CN113379443B (en) | Flight flow simulation method and system | |
| Daramola et al. | Air travel and airline operations in Nigeria: Market potentials and challenges | |
| Kuo et al. | Air passengers’ willingness to pay for counter check-in services | |
| Luo et al. | An incentive subsidy mechanism for bus lines based on service level | |
| Ripoll-Zarraga | Airports’ public infrastructure and sources of inefficiency | |
| CN112907158B (en) | Flight passenger flow generation method and system based on game learning | |
| Gleave | HSIPR Best Practices: Ridership and Revenue Forecasting |
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 |