Domestic flight price prediction method

A price forecasting and flight technology, applied in market forecasting, neural learning methods, biological neural network models, etc., can solve problems such as inability to obtain a large number of flight-related changes and unsatisfactory effects.

Pending Publication Date: 2020-10-20
深圳市活力天汇科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Experiments have shown that neither of these two methods works very well, a

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Domestic flight price prediction method
  • Domestic flight price prediction method
  • Domestic flight price prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0016] The embodiment of the present invention is a domestic flight price prediction method, the flow chart is as follows figure 1 shown, including the following steps:

[0017] S101, encode the flight characteristics, make a Mapping table, so that each characteristic value has a unique number; the flight characteristics at least include: flight number, airline, departure place, destination, departure time;

[0018] S102, perform Embedding conversion on the eigenvalues ​​in the Mapping table, reduce the data dimension, and obtain the vector representation of the eigenvalues;

[0019] S103. Input the vector representation of the eigenvalues ​​into the DeepFM model to obtain low-order feature outputs and high-order feature outputs respectively;

[0020] S104, input the historical price data of the flight into the LSTM model, and perform Embedding conversion o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a domestic flight price prediction method. The method comprises the following steps: encoding flight features, and making a Mapping table to enable each feature value to have aunique number; carrying out Embedding conversion on the feature values in the Mapping table, and reducing data dimensions to obtain vector representations of the feature values; inputting the vectorrepresentations of the feature values into a DeepFM model, and obtaining a low-order feature output and a high-order feature output respectively; inputting the historical price data of the flight intoan LSTM model, and performing Embedding conversion on the output of the LSTM model to obtain vector representation of the historical price data; fusing the output data of the DeepFM and the LSTM, andoutputting the predicted price of the flight through an output layer. Since the DeepFM model and the LSTM model are used for respectively extracting the characteristics of different attributes. Compared with the prior art, the method improves the price prediction precision obviously.

Description

technical field [0001] The invention belongs to the technical field of air ticket inquiry, and in particular relates to a domestic flight price prediction method. Background technique [0002] At present, in the domestic aviation market, there are nearly 20,000 routes per day, involving more than 200 cities. The price change of each route is closely related to various attributes such as its region and season. If we can timely and accurately predict the price changes of future departure routes, certain economic benefits will be generated. Through the statistics, graphic display and analysis of the air ticket price data in the last two years, it is found that the air ticket price has the following characteristics: First, the regularity of the air ticket price change is not strong. By displaying the price data in charts, no obvious rules were found in the dimension of the number of days from the take-off time interval or the historical price dimension of the same day; the seco...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q30/02G06N3/04G06N3/08
CPCG06Q30/0206G06N3/049G06N3/08G06N3/044G06N3/045
Inventor 邹延迪李尚锦常福
Owner 深圳市活力天汇科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products