Document key information extraction method and system based on keyword splitting technology

• Main Authors: ZHAO ZENGTAO, SHE JUN, LUO YONG, YU SHAOFENG, LIAO CHONGYANG
• Format: Patent
• Language: Chinese; English
• Published: 28.12.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a document key information extraction method and system based on a keyword splitting technology, and relates to the field of document key information extraction. The method comprises the steps: converting an obtained target document into an XML format document; carrying out key information extraction on the XML format document based on a keyword splitting detection technology; and obtaining a target document and converting the target document into an XML format document. XML is an extensible markup language, and is a markup language used for marking an electronic file to enable the electronic file to have a structural property. Therefore, the target document is converted into the XML format document, and subsequent information extraction is facilitated. Key information extraction is carried out on the XML format document based on a keyword splitting detection technology. In the step, structured key field information can be extracted from a continuous natural language text. The problem t