K-means解决聚类问题，以欧式距离作为相似度测度，它是求对应某一初始聚类中心向量V最优分类，使得评价指标J最小。算法采用误差平方和准则函数作为聚类准则函数。-K-means solves the problem of clustering, taking the Euclidean distance as the similarity measure, which is the optimal classification of the V of the J of the initial clustering center vector, which makes the　uation index is the smallest. In the algorithm, the error square and criterion function is used as the criterion function of clustering.