A k-anonymous location privacy protection method of dummy based on geographical semantics

Dummy is one of the main methods used to protect location privacy. In existing methods, the efficiency of dummy generation is low, and the geographical semantic information of location is not fully taken into account. In order to solve these problems, a k-anonymous location privacy protection method of dummy based on geo-graphical semantics was proposed in this paper. Firstly, the location data set in the rectangle region containing the real location is obtained from WiFi APs. Secondly, adopting the multicenter clustering algorithm based on max-min distance, some locations are selected. Its geo-graphical distance between them is the farthest, and a candidate set of dummies is generated. Finally, by calculating the edit-distance between geographic name's information of locations, the semantic similarity between any two locations in the candidate set is obtained, and k-1 locations with the minimum semantic similarity are selected as dummies. Experimental results show that the proposed method can ensure the physical dispersion and semantic diversity of locations, as well as the improvement of the efficiency of dummy generation. Meanwhile, the balance between privacy protection security and query service quality is achieved. © 2019 Femto Technique Co., Ltd.