Automation Strategies: Dealing with High Variance & Unstructured Documents

Within document automation, also known as document capture, there are typically three types of documents identified: structured, semi-structured and unstructured. While this document identification is helpful, we need to provide more when a person is actually designing a document automation system.

For this reason, we always advise that you examine the level of variance within any of these three document categories to really understand the proper identification and extraction techniques you want to employ.