METHOD AND SYSTEM FOR SAMPLING WEB DOCUMENTS INFORMATION

摘要

A method for extracting the structural information of a web document and a system thereof are provided to extract the attributes of a corresponding web site automatically although the learning is performed by tagging a small amount of data in the web site. By learning a web document, in which attributes are manually tagged and which is collected from a web site to be extracted, an attribute learning processing device(100) generates a studying model. An attribute extraction processing device(200) extracts attributes from an original web document. A boundary recognition studying model database(300) provides a database of a boundary recognition studying model among the studying models to the attribute extraction processing device. An attribute recognition studying model database(302) provides a database of the attribute recognition studying model among the studying models to the attribute extraction processing device.