Method and system for extraction of table data from documents for robotic process automation

Abstract

Improved techniques to access content from documents in an automated fashion. The improved techniques permit content of tables within documents to be retrieved and then used by computer systems operating various software programs (e.g., application programs). Consequently, Robotic Process Automation (RPA) systems are able to accurately understand the content of tables within documents so that users, application programs and / or software robots can operate on the documents with increased reliability and flexibility. The documents being received and processed can be electronic images of documents. For example, the documents can be business transaction documents which include tables, such as purchase orders, invoices, delivery receipts, bills of lading, etc.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application claims priority to: (i) U.S. Patent Provisional Application No. 63 / 087,844, filed Oct. 5, 2020, and entitled “METHOD AND SYSTEM FOR EXTRACTION OF TABLE DATA FROM DOCUMENTS FOR ROBOTIC PROCESS AUTOMATION,” which is hereby incorporated herein by reference; (ii) U.S. Patent Provisional Application No. 63 / 087,851, filed Oct. 5, 2020, and entitled “METHOD AND SYSTEM FOR EXTRACTION OF DATA FROM DOCUMENTS FOR ROBOTIC PROCESS AUTOMATION,” which is hereby incorporated herein by reference; and (iii) U.S. Patent Provisional Application No. 63 / 087,847, filed Oct. 5, 2020, and entitled “MACHINED LEARNING SUPPORTING DOCUMENT DATA EXTRACTION,” which is hereby incorporated herein by reference.[0002]This application is related to: (i) U.S. patent application Ser. No. ______ [Att.Dkt.No. 108-P004 / 20022], filed Jan. ______, 2021, and entitled “METHOD AND SYSTEM FOR EXTRACTION OF DATA FROM DOCUMENTS FOR ROBOTIC PROCESS AUTOMATION,” which is ...

AI Technical Summary

Benefits of technology

This patent is about a better way to extract data from documents, specifically images of documents. It describes a method that can detect and categorize different objects within a document and process them differently based on their type. This results in a more accurate and precise extraction of data from the document. The patent also discusses improved techniques to access content from tables within documents using computer systems and software programs, which can make the documents easier to operate on. The documents can be electronic images of documents.

Problems solved by technology

While OCR processing of documents can recognize text contained therein, such process is not well suited to capture data from tables contained in the documents, such as invoices, purchase orders, or more generally tables.

Images