System and method for predicting arrival time of buses in real time

Abstract

The invention relates to a system and method for predicting the arrival time of buses in real time. The system comprises an intelligent acquiring module, a predicting processing module and a displaying module which are arranged on the bus; the intelligent acquiring module is used for acquiring the real-time position information of the buses and transmitting the real-time position information of the buses to the predicting processing module through a 3G network; the predicting processing module is used for establishing a road section consumption time model according to the received position information of the buses, predicting the arrival time of the buses of each road section and transmitting the arrival time of the buses to the displaying module through the 3G network; and the displaying module is used for displaying the received arrival time of the buses. The system is characterized in that the data reported in real time of the buses on the road section between the current bus and the station is used as the reference and a plurality of feature information is used for prediction so that the accuracy of predicting the arrival time of buses is improved. The system has good real-time performance, self adaptability and expandability.

Description

technical field [0001] The invention relates to a bus arrival time prediction technology, in particular to a bus arrival time real-time prediction system and method. Background technique [0002] As a key technology of bus system informatization, bus arrival time prediction has attracted great attention from researchers at home and abroad. In the known prior art, the prediction technology of the arrival time of the bus mainly includes a historical data model prediction model, an artificial neural network model, a Kalman filter model, and the like. [0003] The arrival time prediction model based on historical data is based on a large amount of historical data, assuming that the traffic pattern has a cyclical change rule, and the historical travel time in a specific road segment is consistent with the current travel time. The principle of this model is very simple, intuitive, and easy to operate, so most of the current electronic stop sign display time predictions in most ci...

AI Technical Summary

Problems solved by technology

The Kalman filter model uses continuous approximation to obtain higher prediction accuracy, but at the same time, it has a large amount of calculation and poor real-time performance

Images