Unsupervised multi-keyword text clustering method based on word frequency sorting and pruning

• Main Authors: WANG JIAN, WANG PEIWEN, HUANG CHUNNA, ZHU PEIJUN, ZHONG BEI, ZHAN XIAN
• Format: Patent
• Language: Chinese; English
• Published: 24.03.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention belongs to the technical field of text analysis, and particularly relates to an unsupervised multi-keyword text clustering method based on word frequency sorting and pruning. According to the method, the limitation of manual text analysis can be solved, meaningful preliminary classification results are provided for reference of analysts, and the analysts are assisted in further analysis. According to the method, firstly, importance sorting of text content can be well represented to a certain extent based on word frequency sorting, secondly, multiple keywords are proposed to describe text classification, and finally, an analysis mode giving consideration to both result quality and execution efficiency is provided through a pruning mode. 本发明属于文本分析的技术领域，特别是涉及一种基于词频排序及剪枝的非监督多关键词文本聚类方法。本发明能解决人工分析文本的局限性，提供有意义的初步分类结果供分析人员参考，辅助分析人员作进一步的分析。首先基于词频排序在一定程度上能很好地代表文本内容的重要性排序，其次提出了多关键词来描述文本分类，最后通过剪枝的方式提供一种兼顾结果质量和执行效率的分析方式。