News file auditing method and system based on sensitive words

• Main Authors: ZHOU SHIWEI, YANG XIAOMENG, LI QING
• Format: Patent
• Language: Chinese; English
• Published: 05.07.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention provides a news file auditing method and system based on sensitive words, and the method comprises the following steps: constructing a sensitive word library; training and extracting a sensitive word matching rule according to the sensitive word lexicon; obtaining a to-be-audited news file; the news file to be audited is preprocessed; and judging whether the preprocessed news file to be audited is a safe news file or not by adopting the sensitive word matching rule. According to the method and the device, the matching accuracy of the sensitive word matching rule can be ensured, so that the file auditing accuracy can be ensured, in addition, the file auditing efficiency can be improved, and the labor cost can be reduced. 本发明提供了一种基于敏感词的新闻类文件审核方法和系统，其中，所述方法包括以下步骤：构建敏感词词库；根据所述敏感词词库训练提取敏感词匹配规则；获取待审核新闻类文件；对所述待审核新闻类文件进行预处理；采用所述敏感词匹配规则判断预处理后的所述待审核新闻类文件是否为安全新闻类文件。本发明能够保证敏感词匹配规则的匹配准确率，从而能够确保文件审核的准确性，此外，还能够提高文件审核的效率，并能够降低人工成本。