METHOD AND SYSTEM FOR IDENTIFYING HARMFUL PICTURES BASED ON USER ID

摘要

Provided are a method and a system for identifying a harmful picture. The method comprises: when it is determined that a page element of a webpage comprises a URL path ofa picture, identifying a user ID recorded in a page content of the webpage, obtaining a domain name included in the URL or an IP address pointed to by the URL according to the URL path of the picture, and outputting a first weighting factor and a second weighting factor on the basis of related queries of the user ID, the IP address, and the domain name; and further acquiring the picture and extracting a DC coefficient from a compressed domain of the picture, so as to partially decompress the picture, identify the picture, and output a third weighting factor according to the result of identifying the picture; and combining the first weighting factor, the second weighting factor and the third weighting factor to identify whether the picture belongs to the harmful picture. Through the present disclosure, a scheme for identifying harmful pictures is realized by using a plurality of modes and and using as few image processing means as possible, in combination with a database created by big data.