Clear Document Vision for the Digital Workforce
In this day of Artificial Intelligence (AI) and Machine Learning, most software robots are still using decades-old, legacy Optical Character Recognition (OCR) technology to provide robot document vision. Basic pattern matching, hard-coded rule sets and fixed templates are the seeing-eye dog for cutting edge, robotic technology. Essentially, organizations are outfitting their digital workers with smudged, dirty digital glasses, and only getting part of a much larger, more valuable document story.
Introducing Smart Capture®
With Smart Capture® technology, OCR is the foundation of the technology stack. Raw text and basic document dimension information can be leveraged, along with fueling an intelligence layer that sits on top of this basic foundation. It’s this layer that provides the means to process difficult, unstructured content, allows for wide variations within documents and supplies robots with information for complex data extraction.
In addition, building document processing configurations are facilitated through sample documents using both supervised machine learning and point-and-click methods. This provides clear and undistorted vision for the robotic or digital worker when it comes to documents.
Robotic Value of Smart Capture
Smart Capture provides three core functions to the RPA digital workforce: classification, separation and extraction. Below is a quick overview of each:
Document Classification – With classification, robots can now immediately identify the type of document within a digital workflow. Quick identification allows for intelligent decision making and custom document handling. Classification not only applies to individual documents, but it extends to batches or sets of documents. For example, software robots can now understand when a PDF contains multiple documents within one file.
Document Separation – With classification, robots are now “aware” of not only the type of document, but also where documents start and end. This awareness allows for sets of documents to be split or separated into individual elements for processing. In the PDF example above, the PDF can now be split into individual documents.
Document Data Extraction – Smart Capture’s data extraction capabilities allow software robots in an RPA process to extract data from all types of documents and create structured data. This data can be individual elements, paragraphs or data tables. Without the need for fixed templates, robot document vision is now more accurate and can span a variety of document types.
APIs Are the Clear Glasses
To give robots the comprehensive and clear document “glasses” they require, simplified, tight access to Smart Capture services are necessary to onramp data. This is accomplished through OpenAPIs, which can provide both synchronous and asynchronous methods for processing individual documents or large batches. OpenAPIs allow RPA design interface integration and drag-and-drop capabilities for “Citizen Developers”. These OpenAPIs can provide an open feedback loop for software robots, providing real-time document vision and improved automation.
Learn More
Want to add to your RPA capabilities through Smart Capture? Want clear glasses for your robot vision? You can learn more through the links below or contact us today.
