Interest Point Recommendation Algorithm Based on Spatiotemporal Trajectory Similarity
As to the problems of neglecting the dependency relationship between user trajectories in existing interest point recommendations and not fully considering the spatiotemporal interval between trajectories,this article proposes an interest point recommendation algorithm G-IPRTS based on spatiotem-poral trajectory similarity.This method first preprocesses the trajectory and converts it into meaningful dwell point trajectories.Secondly,Geohash encoding and time dimension filtering are used to improve the accuracy and speed of trajectory similarity in the processing of dwell point trajectory similarity.At the same time,the entropy weight method is used in interest point recommendation to construct a global attribute fusion scoring mechanism for interest points,which is combined with user local dynamic trajec-tory preferences to perform Top-K interest point recommendation.Finally,experimental comparison and analysis were conducted on two real datasets,and the experimental results showed that this method can better improve the processing of trajectory similarity and the performance of interest point recommendation.
POI recommendationstop point trajectorytrajectory similarityGeohash encodingentropy weight method
万方数据
维普
