A semantic based approach for automatic patent document summarization

With the rapid increase of patent documents, patent analysis becomes an important issue for creating innovative products and reducing time-to-market. A critical task for R&D groups is the analysis of existing patents and the synthesis of existing product knowledge. In order to increase knowledge visibility and sharing among R&D groups, a conconcurrent engineering approach is used to facilitate patent document summarization and sharing. The purpose of this research is to automate patent docment summarization as a key step toward efficient patent analysis and knowledge management. The goal of this research is to develop a semantic-based methodology for capturing patents and to summarize this content for design team collaboration. The system automatically marks, annotates, and highlights the nodes of an ontology tree which correspond to words and provides a visual figure summary. Patents for power hand tools and chemical mechanical polishing tools were downloaded to evaluate the automatic summarization system. For these cases, the accuracy of classification reached 93% and 92% respectively demonstrating 20% summarization improvements over previous methods.