Abstract: In WiFi-based indoor positioning technology, the traditional Weighed K-nearest Neighbor (WKNN) algorithm based on received signal strength (RSS) is not able to adaptively get valid access points (AP) as well as relatively high accuracy of reference point matching. Aiming at this problem, we propose WKNN algorithm with self-adaptive matching and preprocessing function in this paper. In this algorithm, the RSS values of AP are sorted according to the network state adaptively, and the top M AP coupled with the corresponding M AP in the reference points are selected to participate in the calculation of the matching in order to optimize the traditional fingerprint positioning algorithm. At the same time, indoor positioning and indoor maps are combined to make the reference point and location results visually displayed on the map, and the offline training process is simplified by using the map data. In addition, the indoor positioning system based on Android platform is designed and realized. The effectiveness of the proposed algorithm in single point positioning and mobile positioning is verified by this system. Experimental results show that the proposed algorithm can achieve more than 30% of the positioning error improvement which can effectively improve the positioning accuracy and positioning stability.