Rank Algorithm of Web Education Resources Based on Fuzzy Set and RSS

Abstract

The level of education determines the technology introduction level of industrial interconnection and intelligent manufacturing.Starting from web structure mining, this paper makes an in-depth study on the typical algorithm PageRank in Web Education resource structure mining. To solve the problem that PageRank algorithm only considers the link relationship between web pages and ignores the text content of web pages, which leads to "topic drift" of search results, an improved algorithm based on the distance between hyperlinked pages and reinforcement learning, disrank, is proposed. In this algorithm, the distance between education resource pages is regarded as a "penalty" factor to calculate the grade value of Web Education resource pages and sort them. Firstly, we use the web crawling algorithm of education resources to grab a certain number of web pages based on a certain topic as training samples, and then store them in the education resources database. Finally, PageRank algorithm and improved algorithm disrank are used to test the effectiveness of the improved algorithm..