Extracting structured information from unstructured documents

Embodiments of the invention provide a method, a computer program product, and a system. Embodiments of the present invention may extract structured information for unstructured document analysis. Embodiments of the present invention may extract structured information for unstructured document analysis by identifying tables and columns in a database corresponding to business terms of a business term table. Embodiments of the invention may then receive a specification of a business term of interest for identification in the unstructured document. Embodiments of the invention may then generate an analysis module based on the identified tables and columns, the analysis module enabling identification or identification of attribute values for attributes of the tables and columns. Embodiments of the invention may then use an analysis module to automatically extract values for at least a portion of the attributes from the unstructured document based on the designation of the business terms of interest. 本发明的实施例提供了方法、