聚类是将数据对象分组成多个簇（Cluster），同一个簇内

部的任意两个对象之间具有较高的

），同一个簇内

部的任意两个对象之间具有较高的 相似度，而属于不同簇

的两个对象间具有较高的

，而属于不同簇

的两个对象间具有较高的 相异度。相异度可以根据描述对

象的属性值计算，对象间的距离是最常采用的度量指标。-Clustering is a data object into a plurality of clusters (the Cluster), with a cluster having between any two objects inside higher), having a high degree of similarity between any two of the same objects inside a cluster, and between two objects belonging to different clusters with high, but between two objects belonging to different clusters have a high degree of difference. Dissimilarity can describe the object' s property values to calculate the distance between objects is the most commonly used metrics.