Vehicle trajectory similarity measurement method and system based on space-time consistency representation

The invention discloses a vehicle track similarity measurement method and system based on space-time consistency representation, and relates to the field of intelligent traffic, and the method mainly comprises the steps: carrying out the preprocessing of a vehicle track and a corresponding urban road network, and carrying out the map matching of the track and the road network; performing data enhancement on the trajectory by using a time drift and road replacement method to obtain a time and space enhancement view; performing spatial feature extraction on the trajectory by using road network features, and performing periodic time feature extraction on the trajectory by using week and day-based time coding; learning a sequence mode of the track by using a Transform encoder to obtain space-time sequence feature embedding of the track; constructing a positive sample pair and a negative sample pair of the time and space enhanced views, and obtaining space-time consistency trajectory representation by using compar