A novel point of interest (POI) location based recommender system utilizing user location and web interactions

Location aware mobile devices have increased the availability of user trajectory information making point of interest recommenders a popular service on mobile devices. However, one of the main challenges in this area is sparsity of the historical trajectory data. So far, most of the recommender systems take users' historical trajectory information into consideration to recommend different places. Web interactions reveal rich information on the user interests, and hence a recommender system should take into consideration such data.In this study, we present a model that combines and associates users interest/taste information, obtained from their web interactions together with location information obtained from the Open Street Map (OSM). Then, we combine this information with the users' real time trajectory information (longitude, latitude and timestamp) to present a list of recommended points of interest close to the current location.

具有位置感知功能的移动设备增加了用户轨迹信息的可用性，使得兴趣点推荐器成为移动设备上的一项热门服务。然而，该领域的主要挑战之一是历史轨迹数据的稀疏性。到目前为止，大多数推荐系统都考虑用户的历史轨迹信息来推荐不同的地点。网络交互揭示了丰富的用户兴趣信息，因此推荐系统应该考虑此类数据。在这项研究中，我们提出了一个模型，该模型将从用户网络交互中获取的兴趣/偏好信息与从开放街道地图（OSM）获取的位置信息相结合并关联起来。然后，我们将这些信息与用户的实时轨迹信息（经度、纬度和时间戳）相结合，以呈现靠近当前位置的推荐兴趣点列表。