How intelligent capture works: Part 3 — Understanding imperfection Brainware ensures critical data from your structured and unstructured content is captured swiftly and accurately

Photo by Fakurian Design on Unsplash

This is Part 3 of a high-level series about how intelligent capture works. In Part 1, Danielle Simer introduced critical nature of image optimization and the role it plays in the next steps of intelligent automation; in Part 2, she explained how intelligent capture needs to adapt to variation and learn over time in order to be an effective starting point for the clean and accurate data you need to fuel intelligent automation.


Tech-focused readers and in-the-know business leaders know intelligent capture tools are essential for fueling any intelligent automation solution. Great tools automate the capture, extraction and verification of data from documents and images, and give users access to key metrics and performance indicators.

But wait, there’s more!

The best tools take it a step further and provide a pathway to human-like intelligence by recognizing and learning from patterns, understanding variance and responding with a high level of flexibility.

With advanced features to clean up document images early on and the ability to use pattern recognition to identify document classes and improve over time, tools like Brainware, Hyland’s intelligent capture platform, ensure critical data from your structured and unstructured content is captured swiftly and (most important) accurately — with as little human intervention as possible.

How does Brainware work?

Brainware leverages a neural network of 13 different engines and algorithms that work like a human brain. It learns conceptually and responds with flexibility when classifying and extracting data, without memorization or templates.

The flexibility of our intelligent capture solution is what makes Hyland’s solution unique: Brainware responds with flexibility. But how?

In Part 1, I talked about how traditional capture tools rely on consistency and clean documents to be successful. In real business settings these can be hard to come by. Brainware excels over traditional capture in part due to its ability to cope with variance across documents, whether by cleaning up an image from the start (see Part 1) or understanding imperfections within the text to be read and extracted.


Case study: Brainware in action
See how global powerhouse Siemens gained invoice efficiencies and reduced the need for manual intervention by 90 percent
Read the case study >>


Nobody’s perfect, and neither are documents

As documents come in and data is extracted, many capture tools (including Brainware) can validate that information against other systems of record to ensure that first, it’s extracted correctly, and second, that the right information is sent downstream for processing.

But what happens when there’s a typo or inconsistency? What happens when the vendor address, for example, says “Mian St” instead of “Main Street”?

Using intelligence called fault tolerant search, Brainware understands when information is misspelled or slightly different on incoming content, and it can still make matches to core systems and master data. It does this not by searching for matches to specific words but rather by searching for pieces of words known as trigrams.

Brainware breaks down the content on incoming documents into trigrams. For example, the trigrams for the word “Hyland” are “Hyl,” “yla,” “lan” and so on. Brainware applies an algorithm to these trigrams to create a search pool of the known data. As Brainware performs its searches and comparisons against the master data in the core system, it uses the trigrams — not entire words — to identify matches.

Because it’s only looking for pieces of each word and not the word itself, Brainware increases the chances of finding the right match. It’s this human-like deduction that allows Brainware to search using large sections of the document’s optical character recognition (OCR) words, validate extracted data, or even provide additional content not found on the document (i.e. patient ID), despite abbreviations, OCR errors, typos or misspellings in the document’s content.

The takeaway? Brainware’s ability to overcome document imperfections reduces the need for human intervention and validation, while speeding up the information capture process without sacrificing accuracy.

The brains behind Brainware

The engines and algorithms powering Brainware didn’t create themselves, of course. A dedicated team of PhD scientists with backgrounds in neuroscience, physics and engineering collaborated to design and develop the intelligence that drives Brainware. Leveraging their expert knowledge of the human brain and sensory processing, as well as close to 20 years of software development experience, they continually develop and enhance the intelligent layers within the solution.

Combined, these layers of image optimization, learning through pattern recognition, and the ability to understand imperfection deliver the intelligence to intelligent capture.

Learn more about what’s behind Brainware here.

Danielle Simer

Danielle Simer is a marketing portfolio manager at Hyland. Her mission is to share best practices and evangelize the power of enterprise content management (ECM) as a tool to automate... read more about: Danielle Simer

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.