With the rapid development of network information, document clustering technique has become focused problem to be inverstigated. Several document clustering algorithms based on vector space model are discussed in this paper, e.g., K-means algorithm and agglomerative hierarchical clustering algorithm. Because of their inefficiency, two ways of improving. BK-means algorithm and CFK-means algorithm are set forth. Finally BK-means algorithm is regarded as a better way of algorithm in document cluste...