基于KNN算法的电子档案信息文本自动分类方法  

Automatic Text Classification of Electronic Archive Information Based on KNN Algorithm

作　　者：杨易木 Yang Yimu(Baicheng City Retired Military Cadres Nursing Home,Jilin Province,Baicheng 137000,China)

机构地区：[1]吉林省白城市军队离休退休干部休养所,白城137000

出　　处：《办公自动化》2025年第5期14-16,共3页Office Informatization

摘　　要：文章深入探讨文本自动分类的领域,聚焦于一种广泛应用的基于内容的分类技术——KNN(K-Nearest Neighbors)算法,对其原理和应用进行重点介绍。采用KNN算法结合优化的词特征权重评估与文本相似性计算技术,实现文本的自动分类。经过KNN分类处理后,分类结果的准确率和召回率均显著提升。This paper explores in depth the field of automatic text classification,focusing on a widely used contentbased classification technique-the KNN(K-Nearest Neighbors)algorithm,highlighting its principles and applications.The KNN algorithm,combined with optimized word feature weighting and text similarity computation techniques,is employed to achieve automatic text classification.After applying KNN classification,both the accuracy and recall rates of the classification results show significant improvements.

关 键 词：KNN算法 文本自动分类 数据挖掘 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]