A signature automation software that integrates technologies from Instabase and Satsyil has been selected for pilot tests by the U.S. Patent and Trademark Office.
The platform works to eliminate the need for manual matching of names and signatures in inventor oaths and reviewing of patent application documents, Instabase said Thursday.
Instabase uses deep learning architecture to extract and match names with corresponding signatures throughout a document despite differences in formats and languages. This capability was integrated into Satsyil’s workflow and infrastructure, which uses artificial intelligence and machine learning in data analysis.
The software is meant to enable USPTO to automatically cross-check for variations in the same applicant’s names and signatures, and correctly count the number of their submissions.
“Instabase allows us to quickly tap into more of the trapped data found in our unstructured patent applications with ease and accuracy,” said Scott Beliveau, chief of enterprise advanced analytics at USPTO.