Taxi Intelligent Carpooling Method Based on Swarm Intelligence

Abstract

The invention provides a crowd-sourcing-based intelligent car-pooling method for taxies. The intelligent car-pooling method includes the following steps that taxi client sides collect taxi travelling data and upload the data to a server; the server stores road condition information for all road sections; passenger client sides obtain own positions and destinations and upload the own positions and the destinations to the server; the server searches for car-pooling combinations and matches suitable users; the server sends matching information to one matched taxi client side and two matched passenger client sides; the passengers verify the matching result; the passengers complete the car-pooling process and report the process to the server. The crowd-sourcing technology is adopted, the information including vehicle positions and the like is collected through the client sides of taxi drivers, traffic conditions of all the road sections are obtained by the server through statistics, and a system can dynamically adapt to real-time traffic changes; an adopted algorithm allows car-pooling among the passengers whose starting points and the destinations are not adjacent, so that the car-pooling range of the users is effectively enlarged, and the success rate of car-pooling of the users is increased.

Description

technical field [0001] The present invention relates to the technical field of transportation and communication, in particular to a taxi intelligent carpooling method based on crowd intelligence. Background technique [0002] With the rapid development of the modern transportation industry, the taxi industry has become an important part of people's daily life. However, there is a problem that passengers are difficult to take a taxi in a street or a remote street during peak hours in the traditional way of soliciting taxis, which consumes a lot of waiting time. In order to solve this problem, many taxi sharing systems based on carpooling have been proposed. [0003] After searching the existing technical literature, it was found that PetrosLalos of the University of Athens proposed a location-based taxi sharing system in "AFrameworkfordynamiccarandtaxipoolwiththeuseofPositioningSystems" published in ComputationWorld: FutureComputing, ServiceComputation, Cognitive, Adaptive, ...

AI Technical Summary

Problems solved by technology

[0004] However, most of the existing taxi carpooling systems mostly have the following disadvantages: the carpooling algorithm is based on the distance between the taxi and the passenger, which cannot take into account the problem of prolonged vehicle arrival time due to traffic congestion

The above problems impair the practicality of the ride-sharing system and limit its scope of application

Images