Method and system for automatically filtering and processing illegal word-containing internet article

Abstract

The invention discloses a system for automatically filtering and processing an illegal word-containing internet article. The system comprises an illegal word lexicon collection module, a lexicon artificial checking module, a word segmentation processing module, an illegal word content conversion module, a foreground triggered access filtering module and a background editing issuing detection module. The invention also discloses a method for automatically filtering and processing the illegal word-containing internet article. The method comprises the following steps of step 1, creating an illegal word lexicon; step 2, managing the lexicon, and annotating a risk grade for each word; step 3, when a product and the article are edited and issued, screening and checking whether the illegal word is contained by use of a word segmentation detection technology, and performing different processing manners for the checked illegal word according to the risk grade of the word. The technical scheme can automatically and effectively filter and process the illegal word of the internet product and article contents and realize long-term and effective automatic detection processing of the data of theproduct and article contents and further improves the network information security.

Description

technical field [0001] The invention relates to a method and system for automatic filtering and processing of Internet articles containing illegal words. Background technique [0002] With the rapid development of the Internet and mobile Internet, there are more and more Internet users based on B-end and C-end, and each user will publish some articles or product content based on some official websites or products or platforms. However, at present, most netizens do not know enough or are not familiar enough with network information security. As a result, some illegal or prohibited words are also used and written in articles or product content and published, resulting in follow-up investigations, revisions and investigations. [0003] There is no way to effectively guarantee whether the content of products or articles published in the past contains illegal words. Illegal words or prohibited words will continue to increase or decrease according to time, stage, and social develo...

AI Technical Summary

Problems solved by technology

However, the official website, product, and platform personnel of each enterprise cannot constantly monitor the addition or reduction of illegal words and make corresponding processing or modification in a timely manner. At the same time, it takes a lot of time and cost to check and modify each time.

[0004] Most of the existing small, medium and micro enterprises on the Internet only consider the promotion of articles and products, and do not think too much about whether the contents of articles and products contain prohibited words. At the same time, most of them have no prevention or treatment measures. In the era of sharing and communication, there are certain hidden dangers to the improvement of network information security

Images