摘要
To facilitate the travel preparation process to a city, a lot of work has been done to recommend a POI or a sequence of POIs automatically to satisfy users＇ needs. How- ever, most of the existing work ignores the issue of planning the detailed travel routes between POIs, leaving the task to online map services or commercial GPS navigators. Such a service or navigator in terms of suggesting the shortest travel distance or time, which cannot meet the diverse requirements of users. For instance, in the case of traveling by driving for leisure purpose, the scenic view along the travel routes would be of great importance to users, and a good planning ser- vice should put the sceneries of the route in higher priority rather than the distance or time taken. To this end, in this paper, we propose a novel framework called ScenicPlanner for route recommendation, leveraging a combination of get- tagged image and check-in digital footprints from location- based social networks （LBSNs）. First, we enrich the road net- work and assign a proper scenic view score to each road seg- ment to model the scenic road network, by extracting relevant information from get-tagged images and check-ins. Then, we apply heuristic algorithms to iteratively add road segment and determine the travelling order of added road segments with the objective of maximizing the total scenic view score while satisfying the user-specified constraints （i.e., origin, desti- nation and the total travel distance）. Finally, to validate the efficiency and effectiveness of the proposed framework, we conduct extensive experiments on three real-world data sets from the Bay Area in the city of San Francisco, which con- tain a road network crawled from OpenStreetMap, more than 31 000 geo-tagged images generated by 1 571 Flickr users in one year, and 110 214 check-ins left by 15 680 Foursquare users in six months.
To facilitate the travel preparation process to a city, a lot of work has been done to recommend a POI or a sequence of POIs automatically to satisfy users＇ needs. How- ever, most of the existing work ignores the issue of planning the detailed travel routes between POIs, leaving the task to online map services or commercial GPS navigators. Such a service or navigator in terms of suggesting the shortest travel distance or time, which cannot meet the diverse requirements of users. For instance, in the case of traveling by driving for leisure purpose, the scenic view along the travel routes would be of great importance to users, and a good planning ser- vice should put the sceneries of the route in higher priority rather than the distance or time taken. To this end, in this paper, we propose a novel framework called ScenicPlanner for route recommendation, leveraging a combination of get- tagged image and check-in digital footprints from location- based social networks （LBSNs）. First, we enrich the road net- work and assign a proper scenic view score to each road seg- ment to model the scenic road network, by extracting relevant information from get-tagged images and check-ins. Then, we apply heuristic algorithms to iteratively add road segment and determine the travelling order of added road segments with the objective of maximizing the total scenic view score while satisfying the user-specified constraints （i.e., origin, desti- nation and the total travel distance）. Finally, to validate the efficiency and effectiveness of the proposed framework, we conduct extensive experiments on three real-world data sets from the Bay Area in the city of San Francisco, which con- tain a road network crawled from OpenStreetMap, more than 31 000 geo-tagged images generated by 1 571 Flickr users in one year, and 110 214 check-ins left by 15 680 Foursquare users in six months.
基金
Chao Chen and Xia Chen contributed equally on this work. The work was partially supported by the National Natural Science Foundation of China （Grant Nos. 61602067, 61402369 and 61572048）, the Fundamental Research Funds for the Central Universities （106112015CD- JXY180001）, Open Research Fund Program of Shenzhen Key Laboratory of Spatial Smart Sensing and Services （Shenzhen University）, and Chongqing Basic and Frontier Research Program （cstc2015jcyjA00016）.
