Abstract: In order to search or extract information in a special category from large data source，text automatic categorization has become a hot subject of research.KNN is an important method of text automatic categorization，it can deal with large data sets with more stability，but it faces with the problem of slow speed.Based on KNN classification，the semantic relation of feature items is introduced，and clustering to build center documents under it.This method reduces the number of documents which KNN should search，and increases the speed of classification.Simulation results show that the proposed algorithm improves the speed in the case of traditional classification precision.

Key words: Chinese text classification, k-Nearest Neighbor（KNN）, center documents, semantic similarity, clustering

摘要： 在浩瀚的数据资源中，为了实现对特定主题的搜索或提取，文本自动分类技术已经成为目前研究的热点。KNN是一种重要的文本自动分类方法，KNN能够处理大规模数据，且具有较高的稳定性，但面临分类速度较慢的问题。以KNN方法为基础，引入特征项间的语义关系，并根据语义关系进行聚类生成中心文档，减少了KNN要搜索的文档数，提高了分类速度。仿真实验表明，该算法在不损失分类精度的情况下，显著提高了分类的速度。

关键词: 中文文本分类, k最邻近, 中心文档, 语义相似度, 聚类