Method, system and equipment for inspecting website through IP (Internet Protocol) and judging website category, and medium

Abstract

The invention relates to a method, a system, equipment and a medium for inspecting a website through an IP (Internet Protocol) and judging the category of the website. The method comprises the following steps: capturing webpage content of a target website; extracting effective characters and pictures in the webpage; carrying out classification labeling on the extracted effective characters and pictures; constructing and training a network model for the character and picture data; the method comprises the following steps: respectively taking pictures and characters crawled from a webpage in a website as inputs of respective corresponding models to obtain classification prediction results of the pictures and the characters in the webpage, and setting weights of an image classification result and a character classification result; counting prediction results of all pictures and characters under the website, and generating distribution of picture classification and distribution of character classification; and obtaining a final classification result through calculating scores. According to the method, webpage browsers in reality are simulated, the artificial intelligence technology is adopted, website information such as specific content, covered videos, pictures and characters in a website is directly analyzed, and a website content judgment result is comprehensively formed.

Description

technical field [0001] The invention relates to the field of computer image processing, in particular to a method, system, device and medium for inspecting websites through IP and judging the category of the websites. Background technique [0002] At present, there are mainly the following ways to solve the website classification in the market: [0003] 1) Based on webpage text; [0004] A. By establishing a website classification dictionary, analyze the effective words of the webpage to be judged to determine the type of website; [0005] B. It is purely aimed at explaining the similarity between texts through algorithms such as deep learning CNN; [0006] C. Classify the text through machine learning methods such as logistic regression and Bayesian. [0007] 2) Classify based on the structural characteristics of the website. [0008] 3) Classify based on website log data. [0009] However, these methods only extract some features of the website, such as the text infor...

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problem of low classification accuracy of the above classification methods, considering that images and text are the most direct manifestation of website content classification, the present invention proposes a method, system and device for patrolling websites through IP and judging website categories And medium, can improve the classification accuracy to more than 85%

Images