The 20th and 21st joint COTA International Conference of Transportation Professionals (CICTP 2020-21)

With the development of big data technology, research on the temporal and spatial characteristics of urban traffic distribution has received more attention. This paper applies different grid meshing methods to mine frequent movement patterns in time and space with taxi trajectory data to discover the spatio-temporal distribution of taxi travel demand. First, three different meshing models are proposed (i.e. triangle, square and hexagon) to divide the study area into grids. Then, a matching algorithm is used to index the taxi trajectory points into the grid. Finally, according to the trajectory of the taxi, temporal, spatial and spatio-temporal frequent movement pattern are mined respectively. The experimental results show that the method proposed in this paper can effectively extract frequent movement patterns, and different grid models give different pattern extraction results. This study can provide taxi drivers with a path basis for frequent orders and help improve the efficiency of taxi operations.

grid model;spatio-temporal characteristic;frequent movement pattern;taxi trajectory