Reasonable flight combination scheme filter based on travel-distance polynomial regression relationship

Abstract

The invention relates to the field of air transportation, in particular to a reasonable flight combination scheme filter based on a travel-distance polynomial regression relationship, which comprises the following steps: S1, acquiring historical sales data from an open market; step S2, cleaning and preprocessing the collected data; s3, utilizing a polynomial regression method to fit the relationship between the total flight travel and the linear distance; s4, in the route combination process of the virtual intermodal transport, calculating the linear distance between a given departure place and a given destination; s5, the flight combination scheme with the total journey exceeding the flight total journey range is regarded as unreasonable and filtered out. The method is completely based on objective market data, and limitation of subjective judgment and artificial experience is avoided; the automatic filtering and optimization of the flight combination scheme are realized, and the intelligent level of the virtual combined transport system is improved; the method does not depend on specific airlines or airlines, and has high universality and expandability.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of air transportation, and particularly relates to a reasonable flight combination scheme filter based on a trip-distance polynomial regression relationship. BACKGROUND

[0002] Virtual intermodal product is a new service mode in air transportation, aiming to provide passengers with more flexible and economical travel options by combining flights of different airlines. However, in practical application, virtual intermodal systems face a key problem: how to determine which flight combinations are reasonable and acceptable to passengers. Traditional flight combination schemes are often based on simple distance or time rules, which are difficult to fully reflect the actual needs and preferences of passengers, resulting in poor performance of some combination schemes in actual operation.

[0003] In the prior art, some systems attempt to evaluate the reasonableness of flight combinations through historical selection data of passengers or market research, but these methods have problems such as difficulty in data acquisition, poor real-time performance, and inability to fully cover all potential combinations. In addition, existing methods rely heavily on human experience or simple statistical analysis, lacking in-depth exploration of the internal logical relationship of flight combinations, making it difficult to achieve automated and intelligent decision support.

[0004] Therefore, there is an urgent need for a new technical solution that can automatically identify and filter out reasonable flight combination schemes based on objective market data, improving the market competitiveness and user satisfaction of virtual intermodal products. SUMMARY

[0005] The present application provides a reasonable flight combination scheme filter based on a trip-distance polynomial regression relationship, which obtains the polynomial relationship between the two through historical data regression analysis and applies it to the virtual intermodal flight combination splicing link to solve the above problems existing in the prior art.

[0006] To achieve the above purpose, the present application adopts the following technical solution: a reasonable flight combination scheme filter based on a trip-distance polynomial regression relationship, the scheme filter comprising the following steps:

[0007] Step S1, obtaining historical sales data from the public market, including the total flight distance of the sold flight combination and the corresponding straight-line distance between the departure and destination;

[0008] Step S2, cleaning and preprocessing the collected data, including removing outliers, handling missing data, and calculating straight-line distance, which is obtained through a geographic coordinate calculation formula;

[0009] Step S3, the relationship between the total flight distance and the straight-line distance is fitted by using a polynomial regression method. The polynomial regression can capture the nonlinear relationship and is suitable for describing the complex correlation between the total flight distance and the straight-line distance. Through training the model, a function capable of predicting the reasonable total flight distance is obtained.

[0010] Step S4, in the route combination process of virtual intermodal transport, for a given departure and destination, the straight-line distance is calculated, and the reasonable total flight distance range is predicted.

[0011] Step S5, the flight combination scheme whose total distance exceeds the flight total distance range will be considered unreasonable and filtered out, and the combination scheme within the reasonable range is retained.

[0012] Preferably, in step S1, the data is obtained through the channels of airlines, online travel agencies or aviation data service providers, including departure, destination, transfer, flight number and flight distance.

[0013] Preferably, in step S2, through data cleaning and preprocessing, the records with repeated records, missing key information and abnormal records with zero total flight distance or straight-line distance are removed.

[0014] The straight-line distance is calculated by using the Haversine formula, which is as follows, for calculating the total flight distance of each flight combination and the straight-line distance between the departure and destination:

[0015]

[0016] Wherein, r represents the radius of the earth, φ1 and φ2 represent the latitudes of the starting point and the ending point respectively, and λ1 and λ2 represent the longitudes of the starting point and the ending point respectively.

[0017] Preferably, in step S3, the following sub-steps are further included:

[0018] S3-1, a polynomial regression model is selected, and the polynomial degree is set to 2;

[0019] S3-2, the straight-line distance is taken as the independent variable, and the total flight distance is taken as the dependent variable, and the model is trained;

[0020] S3-3, the least square method is used to estimate the model parameters, and the fitting effect of the model is evaluated by cross-validation;

[0021] S3-4, a second-order polynomial function is finally obtained:

[0022] y=a×x+b×x 2c

[0023] Wherein, (a, b, c) are model parameters, x is distance, and y is total distance.

[0024] Preferably, in step S4, the following sub-step is further included:

[0025] S4-1, in the route combination process of virtual intermodal transport, for each potential flight combination, the straight-line distance of its origin-destination is calculated;

[0026] S4-2, using the trained polynomial model, a reasonable total flight range is predicted.

[0027] The technical solutions provided by the present application have at least the following beneficial effects:

[0028] 1. Improve the rationality of flight combination: the present application automatically identifies and filters unreasonable flight combination schemes through a data-driven method, ensuring that the flight combination provided by the virtual intermodal transport product is more in line with market rules and passenger expectations.

[0029] 2. Improve passenger acceptance: based on the analysis of historical sales data, the present application can better reflect the actual needs and preferences of passengers, thereby improving passenger satisfaction and acceptance of virtual intermodal transport products.

[0030] 3. Optimize virtual intermodal transport system performance: the present application reduces the consumption of computing resources by the system in generating and processing unreasonable combination schemes through an automated filtering mechanism, improving the system's operating efficiency and response speed.

[0031] 4. Innovation and practicality: the present application uses polynomial regression methods to mine the internal logical relationship of flight combinations, which is an innovative data analysis application with high practical value and market potential.

[0032] In summary, compared with the prior art, the present application is completely based on objective market data, avoiding the limitations of subjective judgment and manual experience; it realizes automatic filtering and optimization of flight combination schemes, improving the intelligent level of the virtual intermodal transport system; it does not depend on specific airlines or routes, and has strong universality and scalability. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0034] Fig. 1 The method flowchart provided by the embodiments of the present application.

[0035] Fig. 2To evaluate the fitting effect of the cross-validation model of the present application. DETAILED DESCRIPTION

[0036] To further clarify the technical means and effects taken by the present application to achieve the predetermined inventive purpose, the following describes in detail the specific embodiments, structure, features and effects of a reasonable flight combination scheme filter based on a flight-distance polynomial regression relationship according to the present application, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0038] The following examples are for illustrative purposes only and are not intended to limit the scope of the present application.

[0039] The following describes in detail the specific scheme of a reasonable flight combination scheme filter based on a flight-distance polynomial regression relationship provided by the present application.

[0040] Please refer to Figs. 1-2 which shows a method flowchart of a reasonable flight combination scheme filter based on a flight-distance polynomial regression relationship provided by one embodiment of the present application, which includes the following steps:

[0041] Step S1, obtaining historical sales data from the public market, including the total flight distance (i.e. the sum of actual flight distances) of the on-sale flight combination and the corresponding straight-line distance between the origin and destination;

[0042] Step S2, cleaning and preprocessing the collected data, including removing outliers, processing missing data, and calculating straight-line distance, etc. The straight-line distance is obtained through a geographic coordinate calculation formula (such as the Haversine formula);

[0043] Step S3, using a polynomial regression method to fit the relationship between the total flight distance and the straight-line distance. Polynomial regression can capture non-linear relationships and is suitable for describing the complex relationship between the total flight distance and the straight-line distance. By training the model, a function that can predict the reasonable total flight distance is obtained;

[0044] Step S4, in the route combination process of virtual intermodal transport, for a given origin and destination, calculate the straight-line distance and predict the reasonable total flight distance range;

[0045] Step S5, any flight combination scheme whose total flight distance exceeds the range will be considered unreasonable and filtered out, and the combination scheme within the reasonable range is retained.

[0046] In step S1, the data is obtained through channels such as airlines, online travel agencies (OTAs), or aviation data service providers, including departure, destination, transfer, flight number, and flight distance.

[0047] In step S2, through data cleaning and preprocessing, remove duplicate records, records missing key information, and abnormal records with total flight distance or straight-line distance of zero;

[0048] The straight-line distance is calculated using the Haversine formula, as follows, to calculate the total flight distance of each flight combination and the straight-line distance between the departure and destination:

[0049]

[0050] Where r represents the radius of the earth, φ1 and φ2 represent the latitudes of the starting point and the ending point respectively, and λ1 and λ2 represent the longitudes of the starting point and the ending point respectively.

[0051] In step S3, it also includes the following sub-steps:

[0052] S3-1, select a polynomial regression model, set the polynomial degree to 2 (which can be adjusted according to the data fitting effect);

[0053] S3-2, take the straight-line distance as the independent variable and the total flight distance as the dependent variable, and train the model;

[0054] S3-3, estimate the model parameters using the least squares method and evaluate the fitting effect of the model through cross-validation;

[0055] S3-4, finally obtain a second-order polynomial function:

[0056] y = a x x + b x 2c

[0057] Where (a, b, c) are model parameters, x is distance, and y is total distance.

[0058] In step S4, it also includes the following sub-steps:

[0059] S4-1, in the route combination process of virtual intermodal transport, for each potential flight combination, calculate the straight-line distance between the departure and destination;

[0060] S4-2, use the trained polynomial model to predict a reasonable total flight distance range, for example, the predicted value ± a certain threshold (which can be set according to business requirements).

[0061] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A reasonable flight combination filter based on the journey-distance polynomial regression relationship, characterized in that: The scenario filter consists of the following steps: Step S1, obtaining historical sales data from the open market, including the total flight itinerary and the corresponding departure-destination straight-line distance of the flight combinations on sale; Step S2: Cleaning and preprocessing the collected data, including removing outliers, processing missing data, and calculating straight-line distances. The straight-line distances are obtained using the geographic coordinate calculation formula. Step S3: Using a polynomial regression method to fit the relationship between the total flight distance and the straight-line distance, polynomial regression can capture nonlinear relationships and is suitable for describing the complex relationship between the total flight distance and the straight-line distance. By training the model, a function that can reasonably predict the total flight distance is obtained. Step S4, in the virtual intermodal route combination process, for a given departure point and destination, the straight-line distance is calculated to predict a reasonable total flight range; Step S5: Flight combination plans whose total itinerary exceeds the total flight itinerary range will be considered unreasonable and filtered out, and combinations within a reasonable range will be retained.

2. The reasonable flight combination solution filter based on the trip-distance polynomial regression relationship according to claim 1, characterized in that: In step S1, the data is obtained through airlines, online travel agencies or aviation data service providers, including departure place, destination, transit place, flight number and flight distance.

3. The reasonable flight combination solution filter based on the trip-distance polynomial regression relationship according to claim 1, characterized in that: In step S2, duplicate records, records with missing key information, and abnormal records with zero total flight distance or straight-line distance are removed through data cleaning and preprocessing; The straight-line distance is calculated using the Haversine formula, as follows, to calculate the total flight distance and the straight-line distance between the departure point and the destination for each flight combination: Where r is the radius of the earth, φ1 and φ2 are the latitudes of the starting and ending points, and λ1 and λ2 are the longitudes of the starting and ending points, respectively.

4. The reasonable flight combination solution filter based on the trip-distance polynomial regression relationship according to claim 1, characterized in that: In step S3, the following sub-steps are also included: S3-1, select the polynomial regression model and set the polynomial degree to 2; S3-2, use straight-line distance as the independent variable and total flight distance as the dependent variable to train the model; S3-3, use the least squares method to estimate model parameters and evaluate the model fit through cross-validation; S3-4, finally we get a second-order polynomial function: y=a×x+b×x 2c Among them, (a, b, c) are model parameters, x is the distance, and y is the total distance.

5. The reasonable flight combination solution filter based on the trip-distance polynomial regression relationship according to claim 1, characterized in that: In step S4, the following sub-steps are also included: S4-1, in the process of virtual intermodal route combination, for each potential flight combination, the straight-line distance between the origin and the destination is calculated; S4-2, using the trained polynomial model, predicts a reasonable total flight range.

Images