Method and system for filtering sensitive web page based on multiple classifier amalgamation

Abstract

The invention discloses a sensitive webpage filtering system and method based on multi-classifier fusion. The processing object is a webpage, and the processing result is whether the webpage contains sensitive content. Sensitivity here can be defined as pornography, reactionary, violence, etc. Unhealthy Internet Content. The system includes data stream acquisition and preprocessing unit, image and text stream filtering unit, image filter and text filter information fusion unit. Next, obtain the source code of the web page, and split the text and image in the preprocessing stage to obtain text information and effective image information; use the decision tree algorithm to divide the input web page into three styles; use continuous text classifier, discrete sensitive text The classifier and the image classifier identify the webpage, perform fusion calculation according to the output results of each classifier identification, give the discriminant factor, and return the final result to the browser.

Description

technical field [0001] The invention relates to the technical field of information filtering, in particular to a method for identifying webpages containing sensitive information. Background technique [0002] Because Internet sensitive information has caused great harm to Internet users, especially young people, it has attracted extensive attention from researchers and the industry. [0003] There are currently many sensitive information filtering methods, including black and white lists, IP filtering, keyword matching and other filtering methods. Generally speaking, on the one hand, these filtering technologies adopt a very mechanical method, which can achieve 100% filtering efficiency for some sensitive web pages, and the response time is also very short, but the update cycle of filtering parameters can only follow the actual sensitive web pages The appearance of the website changes, and it cannot cope with the rapid changes of the actual sensitive website. On the other ...

AI Technical Summary

Problems solved by technology

[0006] Similar to the mechanical filtering method, the above methods do not make good use of web features and cannot achieve satisfactory results at present. For example, text-based sensitive webpage recognition cannot identify normal webpages related to sensitive topics. Based on Sensitive web page recognition of images has a high false positive rate

The existing fusion algorithm is only fused by AND or operation, which cannot fundamentally improve the recognition rate

Images