Riding recommendation system for reducing online car-hailing expenses by dynamic price prediction

Abstract

The invention discloses a riding recommendation system for reducing online car-hailing expenses by dynamic price prediction, and provides journey expense prediction to recommend a riding scheme with few riding expenses by aiming at the online car-hailing riding requirements of a user at a certain time and place in a city. The method comprises the following steps that: the system subdivides the city into a plurality of areas and uses an entropy and a Fano inequation to calculate the dynamic price predictability of an area; then, the system selects a Markov chain predictor or a neural network predictor to carry out dynamic price prediction by aiming at areas of different predicable sizes; and finally, the system predicts the riding expenses and recommends a riding scheme with reduced expenses, for example, the user can obtain lower riding price if the user waits for a period of time in situ or moves for a distance. An experiment result indicates that the prediction result of the system is roughly matched with survey data, so that the user reduces anxiety generated due to uncertain riding expenses, and travel expenditures are saved.

Description

technical field [0001] The invention relates to the field of spatiotemporal data mining for travel and recommendation systems, in particular to spatiotemporal data mining of online car-hailing orders. Background technique [0002] Ride-hailing platforms such as Uber and Didi are increasingly attracting attention as emerging on-demand services (RoD). As a supplement to traditional taxi services, RoD services attract passengers with features such as cleanliness, convenience, flexibility, and dynamic pricing. The other side appeals to drivers who want to take advantage of idle cars and don't want to apply for a license. The core and unique feature of the RoD service is dynamic pricing, which reflects the service's measure of controlling supply (number of vehicles) and demand (number of requests) at a particular location, bringing supply and demand into balance. In traditional taxi services, the travel price changes with the length of the trip, and passengers can roughly judge ...

AI Technical Summary

Problems solved by technology

In traditional taxi services, the travel price changes with the length of the trip, and passengers can roughly judge the travel cost based on life experience, but in the RoD service, the travel cost of passengers fluctuates greatly, sometimes when major events or weather occur In bad times, the dynamic price can become very high (up to 5 to 10 times the normal price)

Images