Method and device for filtering Internet web page information

Abstract

The invention provides a method and device for filtering Internet web page information. The method comprises the steps that a valid information text is extracted by preprocessing web page information;Chinese word segmentation is conducted on the text, and a forward iteration maximum matching algorithm of a string matching algorithm is adopted; feature extraction is conducted, and feature extraction of resulTS after Chinese word segmentation is conducted and texTS in a prepared corpus is conducted simultaneously to obtain feature vectors; text classification is conducted, if a text is the textcontaining unhealthy information, a system shows that a web page contains the unhealthy information, and the URL address of the web page is put on a URL address blacklist, so that when accessing is performed next time, the web page is immediately identified by the system as an unhealthy web page, and accessing of the web page by a user is prohibited. According to the method, the unhealthy information is filtered before the unhealthy information is viewed by the user, so that the network environment is purified to an extent, routes for a netizen to obtain the unhealthy information can be reduced, and the method is particularly important for development of physical and mental health of youths.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method and device for filtering Internet web page information. Background technique [0002] The Internet is one of the important ways for our modern people to obtain information, and it is an important window for us to communicate with the outside world, and its importance has become particularly important. In daily life and work, people will always obtain various information from the Internet more or less, but those anti-bad information will also quietly enter people's field of vision and pollute the entire Internet environment. Bad information on the Internet refers to all kinds of information on the Internet that violates human morality and laws, incites, confuses, superstitions, and erodes human mental health. [0003] Therefore, the realization of network information identification and filtering technology is particularly important. By preprocessing bad information...

AI Technical Summary

Problems solved by technology

In daily life and work, people will always obtain various information from the Internet more or less, but those anti-bad information will also quietly enter people's field of vision, polluting the entire Internet environment

Images