When a person looks at a document to identify what that document is, they rarely would start reading that document left to right and top to bottom. They would look at the attributes of the document and based on what they see in a split second they can identify what it is. Attributes could be the size of the document, the layout of the text, the presence of picture, logos or tables, prominent words, or phrases or simply just the familiarity of a document they have seen many times before.
ancora’s Intelligent Document Classification software does exactly the same thing, our artificial intelligence algorithms mimics the way a human would identify a document by looking at the attributes of the document as listed above and doing a comparison to similar documents it has seen before. ancora’s classification software works differently than anyone else in our space today, and we actually have 2 US patents on our technology.