Efficient search of patents with trend prediction

• Main Author: D.Shanthoshigaa
• Other Authors: Anwitaman Datta
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Document and text processing
• Online Access: http://hdl.handle.net/10356/73998
• Institution: Nanyang Technological University

The aim of this project is to provide a fast and efficient system to facilitate patent search and predict trends by analysing patent search. Therefore, a web-based text search engine was built to enhance browsing capability and visualization tools were implemented to analyse patent search. Patents were crawled from USPTO (United States Patent and Trademark Office). Search engine was built on Solr and web interface was created on ASP.NET platform. Web interface includes charts to yield observation of analysis results with the support of Google Charts. Patents of 2000 to 2016 with a total of 4738 patents were crawled from USPTO and imported and indexed to Solr within 4s. Patent search engine combined with visualization tools provides various benefits. Patent search facilitates in narrowing down preferred technology and checking for existence of similar patents to protect novelty of a patent. As a result, going through a patent database ensures that inventors are progressing in the right direction. Integration with visualization tools helps businesses in various ways such as learning competitors that support a certain technology.