Abstract: Traditional schemes of location privacy protection mostly focus on the researches of location data analysis in geographical space. However, there is a lack of studies on personalized privacy protection for users. In view of this, we propose a user portrait-based customized location privacy protection scheme (UP-CLPP). The basic portrait of users was generated by the three-layer classifier. User familiarity and user curiosity were modelled to generate the psychological portrait of users. The location transfer matrix based on the user portrait was built to transfer the real location to the anonymous location. The amount of privacy was modelled, in order to quantify the demand of privacy protection of target user. Experimental results illustrate that UP-CLPP scheme not only provides personalized location privacy protection for target users, but also has the higher anonymous success rate.