In recent years, the massive use of positioning systems has symbolized the emergence of location-based services. This market success creates the opportunity to learn urban activity patterns in order to improve human’s ability on his move, namely, mobility intelligence.
In this demo, we describe our approach to enhance taxi drivers’ intelligence. First, we calculate the spatial-temporal distribution of taxies to infer the demand distribution of the crowd, and we use the data to describe the activity attraction of the determined area, such are CBD, railway station, and night clubs.
Second, we classify the taxi drivers by their income and do a further evaluation of seniors and juniors to find out why seniors earn more than juniors. We are also using an ethno-methodological approach to study the different ways taxi drivers operate in the city and analyzing the role of context in this dynamic, namely, where and when a driver operates according to the event lists and the surrounding environment.
We are currently collecting data from 3000 taxi drivers’ GPS trace augmented by interview with the managers of taxi companies. The study concentrates on the taxi drivers of the city of Shenzhen, China. This community consists of people from different provinces in China with different educational and cultural backgrounds. As the result, we feed back the analysis output to the taxi companies and the drivers. Revenue survey shows that the suggestion really works. The taxi drivers get more money with less cost.
Phd student in Tongji University who works on Shenzhen Traffic