A Parallel Mapping Algorithm for E-Commerce Web Pages to Semantic Concepts

摘要

How to find useful information is always a hot topic for researchers. Concepts recognition is a key problem in semantic information searching. A new semantic concepts framework EWO of web pages was built at first. Based on EWO, we proposed a parallel mapping algorithm for E-Commerce Web pages to semantic concept, which adopts two-stages concept mining method. The first stage is to implement local semantic schema; the second step is to implement global mining, and bridging relationship between local data semantic and global sharable ontology. Through combine ontology and web pages, the web pages and semantic concept can be mapping together for semantic searching. Experiments on several web pages sets show that it can outperform other methods in terms of precision and recall.