In recent years, researches on Location-Based service have attracted extensive attentions due to the wide applications. Among them, one of the active topics is Cloud-based Trip Planning for meeting user's personal requirements. Although a number of studies on this topic have been proposed in literatures, most of them only regard the user-specific constraints as some filtering conditions for planning the trip. In fact, immersing the constraints into travel recommendation systems to provide a personalized trip is desired for users. Furthermore, time complexity of trip planning from a set of attractions is sensitive to the scalability of travel regions. Hence, how to reduce the computational cost by parallel cloud computing techniques is also a critical issue. In this paper, we propose a novel system named Touch Map to efficiently recommend the personalized trips meeting multiple constraints of users by mining user's check-in behaviors. In Touch Map, a POI search module is first proposed to select POIs which are desired for user-specific constraints. Then, we adopt our previous work, Trip-Mine, to efficiently plan the trip that satisfies multiple user-specific constraints. As a whole, we propose a novel framework for cloud-based travel recommendation that considers the issues of multiple constraints. Through comprehensive experimental evaluations, PTR is shown to deliver excellent performance.