Extracting searchable information from a digitized document

US10318593B2 · kind B2 · utility

Assignee

• ACCENTURE GLOBAL SOLUTIONS LIMITED · IE

Inventors

• Prakash Ghatage · Bengaluru, IN
• Nirav Sampat · Mumbai, IN
• Kumar Viswanathan · San Jose, US
• Suvendu Kumar Mahapatra · Chennai, IN
• Srikanth Narayanan · Chennai, IN
• Rekha Mani · Chennai, IN
• Aravind Krishnan · Chennai, IN
• Rahul Kotnala · Dehradun, IN
• Kameshkumar Lakshminarayanan · Cuddalore, IN
• Ashish Jain · Austin, US

Key dates

• Filing date: Aug 21, 2017
• Grant date: Jun 11, 2019
• Expiry date: Aug 21, 2037

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04N2201/218
• WIPO field: Audio-visual technology
• WIPO sector: Electrical engineering

Abstract

Data extraction and automatic validation from digitized documents in non-editable formats is disclosed. Paper documents are digitized or converted into formats suitable for storage on computers or other digital devices. The digitized documents are classified into one of a plurality of document types and based on the document type, document processing rules are selected for analyzing the digitized documents to enable data extraction and automatic validation. The positions and values of the data fields in the digitized documents are obtained using machine learning techniques. The data field values are automatically validated and assigned confidence scores. Data fields with low confidence scores are flagged for manual review.