Method and system for forecasting passenger taking taxi time distribution interval

Abstract

The invention relates to a method and a system for forecasting a passenger taking taxi time distribution interval. The method comprises steps of acquiring a time at which a plurality of passengers use a taxi platform to take a taxi in a preset area and a first preset time period to form a historical taxi taking timing sequence; performing unbiased estimation of the variance of the historical taxi taking time sequence according to a preset variance unbiased estimation formula; predicting, in the preset area, the time distribution interval in a second preset time period in accordance with the variance estimated from the unbiased estimation when the user takes a taxi by using the taxi platform. The method and system estimates the variance of the historical taxi taking time sequence to master the approximate distribution of the taxi taking times, so that the distribution interval of the passenger's taxi taking time in the future time period can be predicted, and more vehicles are dispatched in the passenger taxi time concentrated distribution interval and fewer vehicles are dispatched in the passenger taxi time scattered distribution interval, thereby avoiding conditions that lots of vehicles have no passenger and demand exceeds supply.

Description

Method and system for predicting the distribution interval of passenger taxi time technical field The invention relates to the field of data processing, in particular to a method and system for predicting the distribution interval of passengers' taxi-hailing time. Background technique At present, taxi-hailing software has become an important tool for people's daily travel, and the dispatch center dispatches vehicles according to people's car-use requests in the taxi-hailing software to meet their car-use needs. In practice, because the number of passengers with vehicle demand varies in different regions and at different time periods, there may be too many vehicles in an empty state, and of course there may be a situation in which the supply exceeds demand. Therefore, if you want to avoid the situation that there are many unloaded vehicles and the supply exceeds demand, it is necessary to know the approximate distribution of passenger taxi times in a certain period of time...

AI Technical Summary

Problems solved by technology

In practice, because the number of passengers with vehicle demand is different in different regions and different time periods, there may be too many vehicles in an empty state, and of course there may be a situation in which the supply exceeds demand

Images