CN111008736A - Opening decision method and system for new airline - Google Patents
Opening decision method and system for new airline Download PDFInfo
- Publication number
- CN111008736A CN111008736A CN201911194946.5A CN201911194946A CN111008736A CN 111008736 A CN111008736 A CN 111008736A CN 201911194946 A CN201911194946 A CN 201911194946A CN 111008736 A CN111008736 A CN 111008736A
- Authority
- CN
- China
- Prior art keywords
- airline
- new
- factors
- airlines
- influence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003062 neural network model Methods 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 35
- 230000010006 flight Effects 0.000 claims description 35
- 230000007704 transition Effects 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for opening a decision-making for a new airline, and relates to the technical field of airline management. The method comprises the following steps: determining influence factors for opening a route; acquiring historical influence factor data and historical revenue data of a preset air route in a preset time period in a preset range as a training set; taking the influence factors as input, taking the income after the airline is opened as output, and training the neural network model according to a training set; acquiring influence factor data of the new airline, and inputting the influence factor data of the new airline into the trained neural network model to obtain the expected income of the new airline; and judging whether to open a new airline according to the expected income. The method for opening the decision is suitable for the opening decision of the new airline, the obtained expected income is more practical, more objective and more accurate, the accurate new airline opening decision can be realized, and the decision efficiency can be improved.
Description
Technical Field
The invention relates to the technical field of airline management, in particular to a method and a system for opening a decision of a new airline.
Background
At present, when an airline company opens a new airline, the new airline is determined by taking expected income, passenger flow and the like of the planned airline as consideration factors. However, the decision-making scheme of the new airline is based on manual experience, and after the new airline is opened, the specific scheme of the opened airline is adjusted according to the influence factors such as actual income, passenger flow and the like, so that the opening decision of the new airline is delayed, and the decision-making scheme is not accurate and reasonable enough depending on the subjective experience of a decision maker.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a system for opening a decision-making for a new airline aiming at the defects of the prior art.
The technical scheme for solving the technical problems is as follows:
an opening decision method for a new airline, comprising:
determining influence factors for opening a route;
acquiring historical influence factor data and historical revenue data of a preset air route in a preset time period in a preset range as a training set;
taking the influence factors as input, taking the income after the airline is opened as output, and training a neural network model according to the training set;
acquiring influence factor data of a new airline, and inputting the influence factor data of the new airline into the trained neural network model to obtain the expected income of the new airline;
and judging whether the new airline is opened or not according to the expected income.
The invention has the beneficial effects that: the method for opening decision-making provided by the invention is suitable for opening decision-making of new airlines, the neural network model is trained by taking historical influence factor data and historical profit data as a training set, the neural network model can form mapping between influence factors and profits of the airlines, so that objective and accurate influence conditions of the influence factors on the profits can be obtained, then the influence factor data of the new airlines to be opened are input into the trained neural network model to obtain the expected profits of the new airlines, the expected profits are taken as the basis for judging whether to open the new course, compared with the traditional method for judging by manual experience, the expected profits obtained in the method are more practical, more objective and more accurate, therefore, the accurate new airlines opening decision-making can be realized, and the neural network model is introduced for automatic decision-making in the decision-making process, whether a new air route is opened or not is judged without manually consulting a large amount of data, and decision-making efficiency can be improved.
Another technical solution of the present invention for solving the above technical problems is as follows:
an provisioning decision system for a new airline, comprising:
the first acquisition unit is used for determining influence factors for setting a route; acquiring historical influence factor data and historical revenue data of a preset air route in a preset time period within a preset range as a training set;
the modeling unit is used for taking the influence factors as input, taking the income after the airline is opened as output, and training the neural network model according to the training set;
the second acquisition unit is used for acquiring influence factor data of the new airline, inputting the influence factor data of the new airline into the trained neural network model, and obtaining the expected income of the new airline;
and the decision unit is used for judging whether to open the new airline according to the expected income.
The invention has the beneficial effects that: the invention provides an opening decision system which is suitable for the opening decision of a new airline, a neural network model is trained by taking historical influence factor data and historical profit data as a training set, the neural network model can form mapping between influence factors and profits of the airline, so that objective and accurate influence conditions of the influence factors on the profits can be obtained, then the influence factor data of the new airline to be opened is input into the trained neural network model to obtain the expected profits of the new airline, the expected profits are taken as the basis for judging whether to open the new course, compared with the traditional method of artificial experience judgment, the expected profits obtained in the application are more practical, more objective and more accurate, therefore, the accurate opening decision of the new airline can be realized, and the automatic decision is made by introducing the neural network model in the decision process, whether a new air route is opened or not is judged without manually consulting a large amount of data, and decision-making efficiency can be improved.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a schematic flow chart diagram provided by an embodiment of a method for a new airline provisioning decision of the present invention;
FIG. 2 is a schematic structural diagram of a neural network model provided by an embodiment of the decision-making method for a new airline of the present invention;
FIG. 3 is a block diagram of an architecture provided by an embodiment of the present invention for a new airline decision making system.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth to illustrate, but are not to be construed to limit the scope of the invention.
As shown in fig. 1, a schematic flow chart is provided for an embodiment of a provisioning decision method for a new airline of the present invention, where the provisioning decision method includes:
and S1, determining influence factors for setting the route.
It should be noted that the influencing factors refer to factors related to the airline and possibly influencing the revenue of the airline, the planned flight, the airworthiness model, the plan execution cycle, the stop and go points, and may include geographic factors, traffic factors, economic factors, social factors, and the like.
For example, taking geographic factors as an example, assuming that mountainous areas are arranged between an originating waypoint and an arriving waypoint, if the originating waypoint and the arriving waypoint are far away from each other, it is obvious that the geographic factors influence the selection of the travel mode of people, and the selection of the airplane for travel is more inclined, so that the geographic factors can be used as influence factors influencing the opening of a new airline.
For another example, taking traffic factors as an example, assuming that a high-speed rail line is assumed between the starting waypoint and the arrival waypoint, the operation of the airline is competitive, when people select a trip mode, the high-speed rail is taken as an optional trip mode of the same level as the airplane to shunt customers selecting the airplane, so that the decision of opening the airline is influenced, and obviously, the traffic factors can also be taken as influence factors influencing the opening of a new airline.
For another example, taking economic factors as an example, assuming that the economic development situation between the starting waypoint and the arriving waypoint is poor, and the per-capita GDP is far lower than that in other areas in China, when people select a travel mode, it is obviously inclined to select a travel mode with a relatively reduced price, such as a railway or a passenger car, so that the decision of opening an airline company in the airline is influenced, and it is possible to attract cheap air to operate in the airline, and thus, it is also possible to use the economic factors as influencing factors influencing the opening of a new airline.
For another example, assuming that an arrival waypoint is a tourist city, social factors are taken as an example, and thus, during a public holiday, the travel destinations of a large number of passengers are the arrival waypoints, and the demand for the airline increases during the period, so that the social factors also have a certain influence on the opening of the airline and can be used as influence factors influencing the opening of a new airline.
It should be understood that the above is only an exemplary illustration, and does not represent that the influencing factors are only the ones listed above, and those skilled in the art can select other factors capable of influencing the opening decision of the new airline as the influencing factors without creative effort.
It should be understood that the geographic factors may also include other influencing factors, such as whether there is a natural barrier, for example, a desert, a cross river or a mountain, etc., such as whether the ground traffic takes too long time, for example, the mountains in Yunnan are too many to build a railway, the traveling is mainly a road, the road traffic travels in the mountain area, the traveling takes long time and has a low safety factor, which can be considered as influencing factors, and other traffic factors, economic factors, social factors, and the like are not listed here.
And S2, acquiring historical influence factor data and historical income data of the preset air route in the preset range in a preset time period as a training set.
It should be understood that the preset range may be set according to actual requirements, for example, if the trained neural network model is expected to be more universal, a nationwide preset route may be selected, if an international route is expected to be opened, a worldwide preset route may be selected, and if the trained neural network model is expected to be more accurate for a specific region, the preset range may be selected as the region.
The preset route can also be selected according to actual requirements, for example, if an airline company wants to open a route between a and B, a route with an origin waypoint a and a destination waypoint B can be selected as the preset route, and/or a route with an origin waypoint B and a destination waypoint a can be selected as the preset route, for example, some temporary routes or seasonal routes and the like can be removed, so as to improve the prediction accuracy of the neural network model.
It should be understood that to facilitate the training of the neural network model, the historical influencing factor data and the historical revenue data need to be normalized, non-dimensionalized, etc. to be converted into data that can be identified by a computer.
For example, if 3 rivers exist between the routes AB, no high-speed rail exists, 1 river exists between the routes BC, and high-speed rail lines exist, it is difficult to directly train the routes by directly inputting the routes into the model, and therefore, the data can be normalized and normalized to be converted into a designated data domain, so that all the influencing factors can be uniformly and quantitatively expressed as training data.
After the training data is generated, 20% of the training data can be selected as a test set, 80% of the training data can be selected as a training set, and after the neural network model is trained through the training set, the neural network model is tested through the test set.
And S3, taking the influence factors as input, taking the income after the airline is opened as output, and training the neural network model according to the training set.
The neural network model may be selected according to actual requirements, for example, it may be a BP network, a SOM self-organizing feature mapping model, or an RBF network, or it may also be a convolutional neural network, a deep convolutional neural network, or a cyclic neural network, and is not described herein any more.
An exemplary BP network architecture is shown in fig. 2, and will be described below in conjunction with this schematic.
The BP network structure comprises an input layer, an intermediate layer and an output layer, wherein the inputs are x respectively1、x2、x3、…….、xnN influencing factors determined according to the steps are respectively output as y1、y2、……、ymThe m gains are output respectively.
After the influence factors are input, the calculation process consists of a forward calculation process and a backward calculation process. And in the forward propagation process, the input influencing factors are processed layer by layer from the input layer through the hidden unit layer and are transferred to the output layer, and the state of each layer of neurons only influences the state of the next layer of neurons. If the expected output cannot be obtained on the output layer, the reverse propagation is carried out, the error signal is returned along the original connecting path, the error is minimized by modifying the weight of each neuron, and the number of the nodes in the middle layer can be set according to the actual requirement of a user.
And S4, acquiring influence factor data of the new airline, and inputting the influence factor data of the new airline into the trained neural network model to obtain the expected income of the new airline.
And S5, judging whether to open a new airline according to the expected income.
It should be understood that after the expected revenue is obtained, whether to open a new airline can be determined by combining the financial budget, the operating conditions, the development plan and the like of the airline company, whether the revenue meets the preset revenue expected value can be judged through automatic processing of a computer, if so, the new airline is opened, and if not, the new airline is not opened.
The method for opening decision-making provided by the embodiment is suitable for opening decision-making of a new airline, the neural network model is trained by taking historical influence factor data and historical profit data as a training set, the neural network model can form mapping between influence factors and profits of the airline, so that objective and accurate influence conditions of the influence factors on the profits can be obtained, then the influence factor data of the new airline to be opened is input into the trained neural network model to obtain expected profits of the new airline, the expected profits are taken as a basis for judging whether to open the new course, compared with the traditional method for judging by manual experience, the expected profits obtained in the method are more practical, more objective and more accurate, therefore, the accurate opening decision-making of the new airline can be realized, and the neural network model is introduced for automatic decision-making in the decision-making process, whether a new air route is opened or not is judged without manually consulting a large amount of data, and decision-making efficiency can be improved.
Optionally, in some embodiments, determining the influence factor for routing specifically includes:
acquiring information of opened routes within a preset range, and determining the number of flights of each route according to the information of opened routes;
determining alternative influencing factors, wherein the alternative influencing factors comprise: geographic factors, traffic factors, economic factors and social factors, wherein each alternative influence factor comprises multiple types of influence factors;
determining the association degree between each alternative influence factor and the number of flights, and taking the alternative influence factors of which the association degree is greater than a first preset threshold value as influence factors for setting the routes;
and determining the association degree between each type of influence factor and the number of flights in the influence factors for opening the routes, and removing the influence factors of which the association degree is smaller than a second preset threshold value from the influence factors for opening the routes.
It should be understood that the association degree refers to the degree of influence of various types of influence factors or influence factors on the number of flights, only the influence factors with a relatively large correlation degree are given above, and may also include climate factors, humanistic factors, and the like, and it is assumed that after the association degrees of the factors and the number of flights are calculated, the association degrees are found to be smaller than a first preset threshold value, which indicates that the factors have a relatively small influence on the number of flights, and therefore, the factors are not used as influence factors for routing. The calculation of the specific relevance can be determined by counting the information of the opened routes and the influence factors of the corresponding regions, counting in a statistical mode, modeling, and obtaining a relatively accurate relevance value by taking the influence factors and the number of flights as input and the relevance of the influence factors and the number of flights as output through a neural network model.
For example, the economic factors may include: the total area development value, the per-capita GDP, the average annual income, the proportion of the total income occupied by travel or the average trip expenditure and the like of the starting waypoint and the arriving waypoint, wherein the total area development value, the average per-capita GDP and the average annual income have relatively small influence on the number of flights, the proportion of the total income occupied by travel and the average per-capita trip expenditure and the like have relatively large influence on the number of flights, and the relevance between the influence factor and the number of flights can also be obtained by a statistical method or a neural network modeling.
It should be understood that the first preset threshold and the second preset threshold may be set according to actual requirements.
In the embodiment, the influence factors which can generate larger influence on the establishment scheme of the flight are determined through the association degree, valuable influence factors can be screened out, the training precision of a subsequent neural network model is improved, the interference of unnecessary factors is reduced, a more accurate expected income prediction result is obtained to be used as a decision basis for opening a new flight path, compared with a mode of artificial experience decision, the influence factors as many as possible can be selected through the association degree, the interaction among the influence factors is usually difficult to determine, the interaction among the influence factors can be avoided by manual judgment through the mode of association degree screening, the influence degree of each influence factor on the number of the flights is expressed through the parameter of the association degree, so that the comprehensive and reasonable influence factors are determined, the value of the influence factors input into the neural network model is improved, and the training precision of the neural network model is improved, thereby helping the airline make a reasonable decision.
On the basis, the embodiment also calculates the association degree between the specific influence factor in the determined influence factors and the number of flights, removes the influence factor with the association degree smaller than the second preset threshold, and can further improve the effectiveness of the influence factors, thereby further improving the training precision of the neural network model.
Optionally, in some embodiments, the method further comprises:
when the new airline is judged to be opened, acquiring historical flight data of other airlines with the new airline already opened with the airline;
determining a transition probability matrix of flight quantity change of each airline company in the new airline according to historical flight data;
predicting the predicted flight data of other airlines in the new airline according to the transition probability matrix;
and determining a flight opening scheme of the new airline according to the predicted flight data.
Specifically, historical flight data for the last year/quarter/month may be obtained, and predicted flight data for the next year/quarter/month may be predicted.
For convenience of explanation, the airline company is classified into 5 levels according to the number of flights it offers, and the prediction of the number of flights in the next year is taken as an example for explanation. The 5 levels are respectively a first level, a second level, a third level, a fourth level and a fifth level, wherein the first level, the second level, the third level, the fourth level and the fifth level respectively represent that the number of flights is very large, medium, small and very small, the number of flights corresponding to each level can be set according to actual needs, and then the transition probability matrix P is:
wherein, Pij＝mij/miWherein i is 1,2, 3, 4, 5; j is 1,2, 3, 4, 5; m isijM representing the last year of the transition from an airline in the order of i to a number of airlines in the order of jiRepresenting the number of airlines in the order of i in the last year.
For example, it is assumed that there are 50 other airlines that have opened routes in the new route, the number of airlines that opened the first level flight number in the previous year is 10, the number of airlines that opened the second level flight number is 10, the number of airlines that opened the third level flight number is 10, the number of airlines that opened the fourth level flight number is 10, and the number of airlines that opened the fifth level flight number is 10.
Assuming that, so far, the number of airlines from the first level to the first level is 1, the number of airlines from the first level to the second level is 2, the number of airlines from the first level to the third level is 3, the number of airlines from the first level to the fourth level is 1, and the number of airlines from the first level to the fifth level is 3;
the number of the airlines from the second level to the first level is 1, the number of the airlines from the second level to the second level is 2, the number of the airlines from the second level to the third level is 2, the number of the airlines from the second level to the fourth level is 3, and the number of the airlines from the second level to the fifth level is 2;
the number of airlines from the third level to the first level is 2, the number of airlines from the third level to the second level is 1, the number of airlines from the third level to the third level is 2, the number of airlines from the third level to the fourth level is 2, and the number of airlines from the third level to the fifth level is 3;
the number of airlines from the fourth level to the first level is 3, the number of airlines from the fourth level to the second level is 1, the number of airlines from the fourth level to the third level is 1, the number of airlines from the fourth level to the fourth level is 3, and the number of airlines from the fourth level to the fifth level is 2;
the number of airlines from the fifth level to the first level is 3, the number of airlines from the fifth level to the second level is 2, the number of airlines from the fifth level to the third level is 1, the number of airlines from the fifth level to the fourth level is 3, and the number of airlines from the fifth level to the fifth level is 1.
Wherein, P1iRepresenting the probability that the airline which offers the first-level number of flights on the new route shifts to the 5-level flight number state, and so on, with P1iThe calculation process is illustrated by way of example, namely:
calculate P sequentiallyijWhen i is 1,2, …, 5, j is 1,2, … 5, then:
after the transition probability matrix P is obtained, the number of flights opened by each airline company in the new airline at the next year t can be calculated according to the following formula.
P(t)＝P(t0)*P
Wherein P (t) is the number of flights opened by each airline in the new route in the next year t, P (t)0) Is the last year t0The number of flights that each airline offers on the new airline is also known.
In this embodiment, the state transition probability matrix is used to analyze the change of the number of flights of the airline company having opened the airline on the new airline, so that the management decision condition of each airline company for the airline can be reflected according to the change, thereby assisting the airline company in making a decision on opening the new airline.
In contrast, the flight number planning of each airline for each airline in the next year is a commercial secret, and is usually difficult to obtain to help the airline to plan the flight number planning, and the flight planning of each airline in the next year is predicted by the state transition probability matrix by taking the flight planning change of each airline in the previous year to open a new airline, so that the problem is effectively solved.
The flight operation arrangement of each airline company for the airline reflects the profit condition of the airline to a certain extent, and the like, and can be used as a reference to give guidance for opening the airline, for example, if the fact that most airlines select to reduce the number of flights in the next year after analysis shows that the benefits of the airline may be relatively too small, the information can be used as flight scheme data of the airline company which plans to open a new airline, and the number of set flights is reduced, so that loss is avoided.
Optionally, in some embodiments, before determining the flight offering plan of the new airline according to the predicted flight data, the method further includes:
acquiring the transport capacity information of other airlines;
and according to a preset comparison rule, carrying out similar comparison on the transportation capacity information of other airlines and the transportation capacity information of the local airline, and removing the predicted flight data of the new airline of the other airlines with the similarity larger than a third preset threshold.
It should be noted that the capacity information refers to capacity resources of the airline company, and includes, for example: available models, number of each model, airline being opened and full-value/low-cost airline, etc.
The capacity information reflects the overall situation of one airline company to a certain extent, so that the availability and accuracy of data can be further improved by removing predicted flight data of other airlines dissimilar to the airline company through a preset comparison rule.
Preferably, the comparison rule may be that each type of transportation capacity information is quantitatively described by a numerical value, the numerical value of each type of transportation capacity information is compared, and the similarity is calculated according to the difference obtained by the comparison. It should be understood that the third preset threshold may be set according to actual requirements.
For example, the third preset threshold may be 10. For convenience of explanation, two types of capacity information are assumed: and multiplying the total number of the airplanes by a coefficient to obtain a first comparison value, setting the total number of the airplanes to be 10, and setting the cheap number of the airplanes to be 0 as a second comparison value.
Then assume that the total number of airplanes for the airline is 100, and that it is cheap aviation, denoted by a; the number of all airplanes of an airline company B is 500, and the airline company B is full-price aviation; c airlines total number of airplanes is 70, for cheap aviation, then assuming a coefficient of 0.1, then after calculation, we get:
first comparative value: a is as follows: 100 × 0.1 ═ 10, B is: 500 x 0.1 ═ 50, C is: 70 × 0.1 ═ 7;
second comparative value: a is 0, B is 10, C is 0;
the similarity between company B and company A is first calculated:
the first comparison result: 50-10 ═ 40, second comparison: 10-0 ═ 10;
then the first comparison result may be added to the second comparison result to yield a similarity, 40+ 10-50;
and then calculating the similarity between the company C and the company A:
the first comparison result: 10-7 ═ 3, second comparison: 0-0 ═ 0;
then the first comparison result may be added to the second comparison result to obtain the similarity, 3+ 0-3;
it should be understood that, since the direct addition method is adopted, the greater the value of the similarity, the greater the difference between the airline and the local airline, and it is determined that the similarity 50 of the B airline is greater than the third preset threshold 10, so that the predicted flight data of the B airline is removed, and the similarity 3 of the C airline is less than the third preset threshold 10, so that the predicted flight data of the C airline is retained.
Preferably, each comparison result is weighted to obtain a more realistic similarity judgment result.
For example, the weight values a and b may be set, where the weight value b has a larger weight, and for an airline company, the judgment of whether the full-price airline/cheap airline is similar to the two airline companies has a larger influence, and therefore, the weight value b may be assigned to this comparison result, so that the decision is more accurate.
It should be understood that, since the basic situation of competitors is relatively known to those skilled in the art, the predicted flight data of dissimilar airlines can also be directly removed by means of manual judgment. And the overall decision-making efficiency is improved.
In this embodiment, the airline companies that are not similar to the airline company are removed through the similarity judgment, so that the interference items can be further reduced, and the predicted flight data for determining the flight offering scheme of the new airline is closer to the actual situation of the airline company, thereby improving the accuracy of the decision.
Optionally, in some embodiments, the method further comprises: and judging the income range of the expected income of the new airline, and adjusting the flight establishment scheme of the new airline according to the income range.
It should be understood that the profit margin can be determined according to the actual demand of the user, for example, if the expected profit is in the high profit margin, the number of opened flights can be increased appropriately, the white class flights can be increased, the passing points can be increased, the models capable of taking more passengers can be used, and the like.
It is understood that some or all of the alternative embodiments described above may be included in some embodiments.
As shown in fig. 3, a structural framework diagram is provided for an embodiment of the provisioning decision system for a new airline of the present invention, the provisioning decision system comprising:
the first acquisition unit 1 is used for determining influence factors for setting a route; acquiring historical influence factor data and historical revenue data of a preset air route in a preset time period within a preset range as a training set;
the modeling unit 2 is used for taking the influence factors as input, taking the income after the airline is opened as output, and training the neural network model according to the training set;
the second acquisition unit 3 is used for acquiring influence factor data of the new airline, and inputting the influence factor data of the new airline into the trained neural network model to obtain the expected income of the new airline;
and the decision unit 4 is used for judging whether to open a new airline according to the expected income.
The opening decision system provided by the embodiment is suitable for the opening decision of the new airline, the neural network model is trained by taking the historical influence factor data and the historical profit data as a training set, the neural network model can form the mapping between the influence factors and the profits of the airline, so that the influence condition of the objective and accurate influence factors on the profits can be obtained, then the influence factor data of the new airline to be opened is input into the trained neural network model to obtain the expected profits of the new airline, the expected profits are taken as the basis for judging whether to open the new course, compared with the traditional method of artificial experience judgment, the expected profits obtained in the application are more practical, more objective and more accurate, therefore, the accurate opening decision of the new airline can be realized, and the neural network model is introduced for automatic decision in the decision process, whether a new air route is opened or not is judged without manually consulting a large amount of data, and decision-making efficiency can be improved.
Optionally, in some embodiments, the obtaining unit is specifically configured to obtain information of an opened airline within a preset range, and determine the number of flights of each airline according to the information of the opened airline; determining alternative influencing factors, wherein the alternative influencing factors comprise: geographic factors, traffic factors, economic factors and social factors, wherein each alternative influence factor comprises multiple types of influence factors; determining the association degree between each alternative influence factor and the number of flights, and taking the alternative influence factors of which the association degree is greater than a first preset threshold value as influence factors for setting the routes; and determining the association degree between each type of influence factor and the number of flights in the influence factors for opening the routes, and removing the influence factors of which the association degree is smaller than a second preset threshold value from the influence factors for opening the routes.
Optionally, in some embodiments, the method further comprises: the third obtaining unit is used for obtaining historical flight data of other airlines which have opened airlines on the new airline when the new airline is judged to be opened;
the prediction unit is used for determining a transition probability matrix of flight quantity change of each airline company in the new airline according to historical flight data; predicting the predicted flight data of other airlines in the new airline according to the transition probability matrix; and determining a flight opening scheme of the new airline according to the predicted flight data.
Optionally, in some embodiments, the method further comprises: the fourth acquisition unit is used for acquiring the transport capacity information of other airlines;
the first judging unit is used for carrying out similar comparison on the transportation capacity information of other airlines and the transportation capacity information of the local airline according to a preset comparison rule and removing the predicted flight data of the new airline of the other airlines with the similarity degree larger than a third preset threshold value.
Optionally, in some embodiments, the method further comprises: and the second judging unit is used for judging the income range of the expected income of the new airline and adjusting the flight establishment scheme of the new airline according to the income range.
It is understood that some or all of the alternative embodiments described above may be included in some embodiments.
It should be noted that the above embodiments are product embodiments corresponding to the previous method embodiments, and for the description of each optional implementation in the product embodiments, reference may be made to corresponding descriptions in the above method embodiments, and details are not described here again.
The reader should understand that in the description of this specification, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described method embodiments are merely illustrative, and for example, the division of steps into only one logical functional division may be implemented in practice in another way, for example, multiple steps may be combined or integrated into another step, or some features may be omitted, or not implemented.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for a new airline decision-making for provisioning, comprising:
determining influence factors for opening a route;
acquiring historical influence factor data and historical revenue data of a preset air route in a preset time period in a preset range as a training set;
taking the influence factors as input, taking the income after the airline is opened as output, and training a neural network model according to the training set;
acquiring influence factor data of a new airline, and inputting the influence factor data of the new airline into the trained neural network model to obtain the expected income of the new airline;
and judging whether the new airline is opened or not according to the expected income.
2. The method for the new airline provision decision-making according to claim 1, wherein determining the influencing factors for providing the airline specifically comprises:
acquiring information of opened routes within a preset range, and determining the number of flights of each route according to the information of opened routes;
determining alternative influencing factors, wherein the alternative influencing factors comprise: geographic factors, traffic factors, economic factors and social factors, wherein each alternative influence factor comprises multiple types of influence factors;
determining the association degree between each kind of the alternative influence factors and the number of flights, and taking the alternative influence factors with the association degree larger than a first preset threshold value as the influence factors for opening the routes;
and determining the association degree between each type of influence factor and the number of flights in the influence factors for opening the routes, and removing the influence factors of which the association degree is smaller than a second preset threshold value from the influence factors for opening the routes.
3. The provisioning decision method for new airlines as defined in claim 1 or 2, further comprising:
when a new airline is judged to be opened, acquiring historical flight data of other airlines of which the new airline is opened;
determining a transition probability matrix of flight quantity change of each airline company in the new airline according to the historical flight data;
predicting the predicted flight data of other airlines on the new airline according to the transition probability matrix;
and determining a flight opening scheme of the new airline according to the predicted flight data.
4. The method of claim 3, wherein prior to determining the flight offering plan for the new airline based on the predicted flight data, further comprising:
acquiring the transport capacity information of other airlines;
and according to a preset comparison rule, carrying out similar comparison on the transportation capacity information of other airlines and the transportation capacity information of the local airline, and removing the predicted flight data of the new airline of other airlines with the similarity degree larger than a third preset threshold.
5. The provisioning decision method for new airlines as defined in claim 3, further comprising: and judging the income range of the expected income of the new airline, and adjusting the flight establishment scheme of the new airline according to the income range.
6. An provisioning decision system for a new airline, comprising:
the first acquisition unit is used for determining influence factors for setting a route; acquiring historical influence factor data and historical revenue data of a preset air route in a preset time period within a preset range as a training set;
the modeling unit is used for taking the influence factors as input, taking the income after the airline is opened as output, and training the neural network model according to the training set;
the second acquisition unit is used for acquiring influence factor data of the new airline, inputting the influence factor data of the new airline into the trained neural network model, and obtaining the expected income of the new airline;
and the decision unit is used for judging whether to open the new airline according to the expected income.
7. The system for opening a decision-making system for a new airline as claimed in claim 6, wherein the obtaining unit is specifically configured to obtain information of an opened airline within a preset range, and determine the number of flights of each airline according to the information of the opened airline; determining alternative influencing factors, wherein the alternative influencing factors comprise: geographic factors, traffic factors, economic factors and social factors, wherein each alternative influence factor comprises multiple types of influence factors; determining the association degree between each kind of the alternative influence factors and the number of flights, and taking the alternative influence factors with the association degree larger than a first preset threshold value as the influence factors for opening the routes; and determining the association degree between each type of influence factor and the number of flights in the influence factors for opening the routes, and removing the influence factors of which the association degree is smaller than a second preset threshold value from the influence factors for opening the routes.
8. The provisioning decision system for new airlines as defined in claim 6 or 7, further comprising: the third obtaining unit is used for obtaining historical flight data of other airlines which have opened airlines on the new airline when the new airline is judged to be opened;
the prediction unit is used for determining a transition probability matrix of flight quantity change of each airline company in the new airline according to the historical flight data; predicting the predicted flight data of other airlines on the new airline according to the transition probability matrix; and determining a flight opening scheme of the new airline according to the predicted flight data.
9. The provisioning decision system for a new airline of claim 8, further comprising: the fourth acquisition unit is used for acquiring the transport capacity information of other airlines;
the first judging unit is used for performing similar comparison on the transportation capacity information of other airlines and the transportation capacity information of the local airline according to a preset comparison rule, and removing the predicted flight data of the new airline of other airlines with the similarity degree larger than a third preset threshold.
10. The provisioning decision system for a new airline of claim 8, further comprising: and the second judging unit is used for judging the income range of the expected income of the new airline and adjusting the flight establishment scheme of the new airline according to the income range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911194946.5A CN111008736A (en) | 2019-11-28 | 2019-11-28 | Opening decision method and system for new airline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911194946.5A CN111008736A (en) | 2019-11-28 | 2019-11-28 | Opening decision method and system for new airline |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111008736A true CN111008736A (en) | 2020-04-14 |
Family
ID=70112447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911194946.5A Pending CN111008736A (en) | 2019-11-28 | 2019-11-28 | Opening decision method and system for new airline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008736A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966926A (en) * | 2020-07-02 | 2020-11-20 | 海南太美航空股份有限公司 | Target route measuring and calculating method and system |
| CN111966927A (en) * | 2020-07-02 | 2020-11-20 | 海南太美航空股份有限公司 | Target route measuring and calculating method and system |
| CN116362788A (en) * | 2023-03-27 | 2023-06-30 | 中国南方航空股份有限公司 | Method, device, equipment and storage medium for predicting opening of new airlines |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010047264A1 (en) * | 2000-02-14 | 2001-11-29 | Brian Roundtree | Automated reservation and appointment system using interactive voice recognition |
| US20020082902A1 (en) * | 2000-12-22 | 2002-06-27 | Fujitsu Limited | Method of predicting initial input of new product, system for predicting initial input of new product, and recording medium |
| US20080300737A1 (en) * | 2007-05-29 | 2008-12-04 | Thales | Method and device for calculating a flight plan |
| US8200549B1 (en) * | 2006-02-17 | 2012-06-12 | Farecast, Inc. | Trip comparison system |
| CN107688867A (en) * | 2017-07-31 | 2018-02-13 | 多维新创（北京）技术有限公司 | Regular service route method of adjustment and system |
| CN108537327A (en) * | 2018-03-28 | 2018-09-14 | 北京航空航天大学 | One kind being based on time series BP neural network prediction technique and device |
| EP3444763A1 (en) * | 2017-08-18 | 2019-02-20 | General Electric Company | Cumulative model for scheduling and resource allocation for airline operations |
| CN109816174A (en) * | 2019-02-02 | 2019-05-28 | 南京航空航天大学 | Open prediction technique in course line based on network evolution impact factor |
| CN109829577A (en) * | 2019-01-17 | 2019-05-31 | 北京交通大学 | Track train operating status prediction technique based on deep neural network structural model |
| CN110363433A (en) * | 2019-07-17 | 2019-10-22 | 携程旅游网络技术（上海）有限公司 | Appraisal procedure, system, electronic equipment and the medium of the new line that sets sail |
-
2019
- 2019-11-28 CN CN201911194946.5A patent/CN111008736A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010047264A1 (en) * | 2000-02-14 | 2001-11-29 | Brian Roundtree | Automated reservation and appointment system using interactive voice recognition |
| US20020082902A1 (en) * | 2000-12-22 | 2002-06-27 | Fujitsu Limited | Method of predicting initial input of new product, system for predicting initial input of new product, and recording medium |
| US8200549B1 (en) * | 2006-02-17 | 2012-06-12 | Farecast, Inc. | Trip comparison system |
| US20080300737A1 (en) * | 2007-05-29 | 2008-12-04 | Thales | Method and device for calculating a flight plan |
| CN107688867A (en) * | 2017-07-31 | 2018-02-13 | 多维新创（北京）技术有限公司 | Regular service route method of adjustment and system |
| EP3444763A1 (en) * | 2017-08-18 | 2019-02-20 | General Electric Company | Cumulative model for scheduling and resource allocation for airline operations |
| CN108537327A (en) * | 2018-03-28 | 2018-09-14 | 北京航空航天大学 | One kind being based on time series BP neural network prediction technique and device |
| CN109829577A (en) * | 2019-01-17 | 2019-05-31 | 北京交通大学 | Track train operating status prediction technique based on deep neural network structural model |
| CN109816174A (en) * | 2019-02-02 | 2019-05-28 | 南京航空航天大学 | Open prediction technique in course line based on network evolution impact factor |
| CN110363433A (en) * | 2019-07-17 | 2019-10-22 | 携程旅游网络技术（上海）有限公司 | Appraisal procedure, system, electronic equipment and the medium of the new line that sets sail |
Non-Patent Citations (2)
| Title |
|---|
| 吴薇薇等: "航线开辟优选方案模型的集对分析研究", 《工业技术经济》 * |
| 骆嘉琪: "《多类别旅客出行异质偏好下高铁民航竞合博弈机理研究》", 《中国优秀博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966926A (en) * | 2020-07-02 | 2020-11-20 | 海南太美航空股份有限公司 | Target route measuring and calculating method and system |
| CN111966927A (en) * | 2020-07-02 | 2020-11-20 | 海南太美航空股份有限公司 | Target route measuring and calculating method and system |
| CN111966927B (en) * | 2020-07-02 | 2023-12-01 | 海南太美航空股份有限公司 | Target route measuring and calculating method and system |
| CN111966926B (en) * | 2020-07-02 | 2023-12-01 | 海南太美航空股份有限公司 | Target route measuring and calculating method and system |
| CN116362788A (en) * | 2023-03-27 | 2023-06-30 | 中国南方航空股份有限公司 | Method, device, equipment and storage medium for predicting opening of new airlines |
| CN116362788B (en) * | 2023-03-27 | 2024-01-30 | 中国南方航空股份有限公司 | Method, device, equipment and storage medium for predicting opening of new airlines |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428096B (en) | Ticket information-based urban rail transit multi-traffic-road transportation organization optimization method | |
| Chen et al. | Design of limited-stop bus service with capacity constraint and stochastic travel time | |
| WO2021212866A1 (en) | Vehicle travel volume prediction model construction method, and prediction method and system | |
| CN101436345B (en) | System for forecasting harbor district road traffic requirement based on TransCAD macroscopic artificial platform | |
| CN108364467B (en) | Road condition information prediction method based on improved decision tree algorithm | |
| CN104102953B (en) | A kind of logistics delivery line optimization generation method and system | |
| Arias-Rojas et al. | Solving of school bus routing problem by ant colony optimization | |
| CN111008736A (en) | Opening decision method and system for new airline | |
| CN108898838A (en) | A kind of aerodrome traffic congestion prediction technique and device based on LSTM model | |
| CN110176141B (en) | Traffic cell division method and system based on POI and traffic characteristics | |
| CN103984994B (en) | Method for predicting urban rail transit passenger flow peak duration | |
| CN112330983B (en) | Integrated intelligent recovery method for abnormal flight | |
| CN115527369B (en) | Large passenger flow early warning and evacuation method under large-area delay condition of airport hub | |
| CN115409256B (en) | Route recommendation method for avoiding congestion area based on travel time prediction | |
| CN110836675A (en) | Decision tree-based automatic driving search decision method | |
| CN111582750A (en) | Method and system for identifying reverse passengers and determining riding class of rail transit | |
| Wadud | Simultaneous modeling of passenger and cargo demand at an airport | |
| Terekhov et al. | A concept of forecasting origin-destination air passenger demand between global city pairs using future socio-economic scenarios | |
| CN110222912A (en) | Railway stroke route method and device for planning based on Time Dependent model | |
| Marcos et al. | A machine learning approach to air traffic route choice modelling | |
| CN114580751B (en) | Method, system, storage medium and terminal for predicting evacuation time of passengers arriving at airport | |
| Lapamonpinyo et al. | Real-time passenger train delay prediction using machine learning: A case study with amtrak passenger train routes | |
| CN114781704A (en) | Flight delay prediction method based on station-passing flight guarantee process | |
| Terekhov et al. | Forecasting a global air passenger demand network using weighted similarity-based algorithms | |
| Huang et al. | Analysing taxi customer-search behaviour using Copula-based joint model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200414 |