Research and Application of XML Documents Query Based on Weight Cost

In order to meet the Web-based XML data similar to the information search, data mining, information classification and data exchange needs, analysis of the XML document similarity measure Ways - set metric methods, measurement methods and the cost of linear measure. Based on weights cost for machine learning of XML document similarity measure algorithm. The methods for query expansion to find the most represent the user's query intention to expand the weight of the query words. Experiments show that the algorithm extends the XML query document the scope of the document to improve full-search ratio and accurate search ratio.