Accessibility web browsing method based on linkage cluster

Abstract

An accessibility web browsing method based on linkage cluster comprises the following steps: web pages are captured from the Internet to obtain the links in the web pages; the URL text content and anchor text content corresponding to each link are extracted, the text information of the web page corresponding to each link is extracted simultaneously; the key words in the URL text, the anchor text and the corresponding web text are obtained; the key words are used as characteristics to express the links of all the web pages as link vectors composed of the key word information formally and respectively, wherein di is the weight information of the i-th key word in the link vectors; and the clustering algorithm is utilized to cluster the link vectors to ensure that the links with the same subject are of a group and the web pages are displayed again in a grouping manner. The invention has the advantage that the links of each web page are clustered to ensure that the links of the web page are displayed in the more compact grouping manner; the web browsing method is suitable for all kinds of web pages, background manual operations are not required, the blind can adopt the method to realize accessibility web browsing, and the common users can also adopt the method to increase the quality of web browsing.

Description

technical field The invention relates to the technical field of barrier-free web page browsing methods, in particular to a barrier-free web page browsing method based on link clustering. technical background There are about 30 million blind people in the world, and there are about 5 million blind people in China, accounting for 18% of the world's total. With the high popularity of the Internet and the increasing importance of the Internet in daily life, the problem of blind people going online will become a barrier-free construction important issues in . Because blind people cannot receive information through vision, their Internet access problems are particularly prominent. Moreover, the content of the current website is more and more abundant, and the page structure is complex, especially for some large Internet companies, such as the homepages of websites such as Sina and Sohu, there are hundreds of links contained in a single page. Faced with such a huge number of link...

AI Technical Summary

Problems solved by technology

In order to overcome the disadvantages of inconvenient searching for information and low efficiency of web browsing when blind people read in the prior art, the present invention provides a link-based Clustering approach for accessible web browsing

Images