In the indoor space, finding the nearest neighbour is of great importance in location-based services. Received Signal Strength Indication (RSSI) has received much attention due to its simplicity and compatibility with existing hardware, which has been widely used for indoor localization. Existing indoor nearest neighbour search methods are based on the real walking distance, which need ground survey and much labor work to measure many real distances. Crowdsourcing is a low-cost and efficient way to collect the RSSI of indoor space without expert surveyors and designated coordinates for RSSI collection points. The crowdsourced RSSIs can reflect the location of indoor objects and RSSI-based localization method is the simplistic method as it needs low hardware requirements, low deployment cost and no survey indoor distance. So we study how to search the nearest neighbour of indoor objects with crowdsourced RSSIs. To address this problem, we propose a graph with interval weights, called I-graph, which can connect the RSSIs and represent the topology of indoor space. We also construct a search tree index D-tree, which can index the graph with interval weights and search the nearest neighbour objects efficiently. We also propose a novel distance metric for RSSI and study the relationship between the RSSI distance and the indoor distance. To locate nearest neighbour of indoor objects with crowdsourced RSSIs, we devise efficient search algorithms and pruning strategies for computing the nearest neighbour query. We demonstrate the efficiency and effectiveness of the proposed solution through extensive experiments with two real data sets.

在室内空间中，找到最近的邻居在基于位置的服务中非常重要。接收信号强度指示（RSSI）由于其简单性和与现有硬件的兼容性而备受关注，该硬件已广泛用于室内定位。现有的室内最近邻搜索方法是基于真实的步行距离，这需要地面测量和大量的劳动来测量许多真实的距离。众包是一种收集室内空间RSSI的低成本高效方式，无需专家测量员和RSSI收集点的指定坐标。众包的RSSI可以反映室内物体的位置，基于RSSI的定位方法是一种简单的方法，因为它需要的硬件要求低，部署成本低并且无需测量室内距离。因此，我们研究了如何使用众包RSSI搜索室内物体的最近邻居。为了解决这个问题，我们提出了一个具有区间权重的图，称为I-graph，可以连接RSSI并表示室内空间的拓扑。我们还构造了一个搜索树索引D-tree，它可以使用间隔权重索引该图并有效地搜索最近的邻居对象。我们还提出了一种新颖的RSSI距离度量标准，并研究了RSSI距离与室内距离之间的关系。为了使用众包RSSI定位室内对象的最近邻居，我们设计了有效的搜索算法和修剪策略来计算最近邻居查询。我们通过使用两个真实数据集进行广泛的实验来证明所提出的解决方案的效率和有效性。