Method and device for customizing public transport lines

Abstract

The invention discloses a method and device for customizing public transportation lines. Involving the field of route planning, the method obtains predicted line demand information, generates corresponding influence parameters based on the demand information, inputs the influence parameters into the trained passenger flow prediction neural network model, obtains the predicted passenger flow, and then obtains the preset starting point Sites, preset end sites and related predicted passenger flow, starting from the preset starting site, select the site that meets the predicted passenger flow as the next site until reaching the preset end site, and form a predicted route based on the optimization conditions. Predicting the attendance rate of unopened lines through historical passenger flow data provides a strong basis for customizing new public transportation lines. At the same time, it can accurately predict the passenger flow demand of unopened customized public transportation lines and provide urban public transportation managers with comprehensive public transportation line planning. It provides an important basis for network layout planning and mastering the development direction of customized public transportation.

Description

technical field [0001] The invention relates to the field of route planning, in particular to a method and device for customizing public transport routes. Background technique [0002] Public transportation passenger flow forecasting plays a very important role in the field of public transportation management and planning. For example, many public transportation route planning processes will use the forecasting of passenger flow. At present, there are many prediction methods for passenger flow. The commonly used forecasting models include time series methods , artificial neural network, support vector machine, decision tree, etc., its algorithms and models are relatively mature. However, most of the current research is based on long-term passenger flow analysis, and the number of studies on short-term public transport passenger flow forecasting is relatively small. With the intelligent development of public transport in my country, the demand for short-term public transport ...

AI Technical Summary

Problems solved by technology

However, most of the current research is based on long-term passenger flow analysis, and the number of studies on short-term public transport passenger flow forecasting is relatively small. With the intelligent development of public transport in my country, the demand for short-term public transport passenger flow forecast is increasing. However, due to the poor adaptability of existing model algorithms to deal with short-term special situations, the randomness of special situations is high, making it difficult to guarantee the accuracy and timeliness of the prediction model

At present, the passenger flow forecast of the designed lines at home and abroad often adopts linear weighted prediction of the passenger flow of the original bus OD line, but the generation of passenger flow is a relatively complicated process, and there are many factors that affect passenger flow. It is not enough to rely solely on the original bus OD flow

Images