METHOD AND SYSTEM FOR IDENTIFYING HARMFUL PICTURE ON BASIS OF USER IP

摘要

A method and system for identifying a harmful picture. The method comprises: when determining that page elements of a web page comprise a URL path of a picture, identifying the IP address or IP address field of a user recorded in the content of the web page, obtaining a domain name contained in the URL or the IP address to which the URL points according to the URL path of the picture, and outputting a first weighting factor and a second weighting factor on the basis of relevant query of the IP address and the domain name; further obtaining the picture, extracting a direct current coefficient in a compressed domain of the picture so as to identify the picture after partially decompressing the picture, and outputting a third weighting factor according to the picture identification resu and combining the first weighting factor, the second weighting factor, and the third weighting factor to identify whether the picture is a harmful picture. According to the present invention, in combination of a database created with big data, a solution for identifying harmful pictures can be provided in multiple modes by using a minimum of image processing means.