Reverse k Nearest Neighbor (RkNN) queries retrieve all objects that consider the query as one of their k most influential objects. Given a set of user U, a set of facilities F and a value k, a facility f is said to be influential to a user u if f is one of the k closest facilities to u. As a complement of RkNN query, Reverse Approximate Nearest Neighbor (RANN) query considers relaxed definition of influence, where a user u is influenced by not only its closest facility, but also by every other facility that is almost as close to u as its closest facility is. In this paper, we study RANN query on road network. Existing RANN techniques and algorithms only work for queries on Euclidean space and are not directly applicable for RANN queries on road network. We propose pruning techniques that utilize Network Voronoi Diagram (NVD) to efficiently solve RANN query on road network. We conduct extensive experimental study on different real data sets and demonstrate that our algorithm is significantly better than the competitor.

反向k最近邻居（R k NN）查询检索将查询视为其k个最有影响力的对象之一的所有对象。给定一组用户U，一组设施F和一个值k，如果f是与u最接近的k个设施之一，则设施f被认为对用户u有影响。作为R k NN查询的补充，反向近似最近邻（RANN）查询考虑宽松的影响定义，其中用户u不仅通过其最近设施，也受到所有其他设施，几乎接近影响ü作为其最接近的设施。在本文中，我们研究了道路网络上的RANN查询。现有的RANN技术和算法仅适用于在欧几里得空间上的查询，不适用于路网上的RANN查询。我们提出了利用网络Voronoi图（NVD）来有效解决道路网络上RANN查询的修剪技术。我们对不同的真实数据集进行了广泛的实验研究，并证明了我们的算法明显优于竞争对手。