At the heart of Docxonomy is text analysis through machine learning algorithms, our system doesn’t just see words – it sees words in context with one another, at the sentence level. But what about the document as a whole? We’ve got that covered too!
As humans, we find it easy to look at a document and know what it “is”. We can easily pick out an invoice versus a contract versus a resume. But for a machine to do so is quite difficult. This is why, if you’ve ever worked with a file management system, it’s typically the job of a user to select the “document type”. Those days are over!
One of Docxonomy’s best features is its ability to automatically classify documents. Our system comes pre-trained with 25 document types and more are added all the time. All you have to do is allow our system to index your files (either by uploading or via one of our pre-built connectors) and we’ll automatically classify them for you. Let’s put that in perspective. If you’ve got hundreds of files (and possibly many more), scattered in multiple locations, then this feature is for you. Point our connectors at your files and then just open Docxonomy and search for a file type – we’ll bring back all your contracts for you, regardless of where you’ve got them stored! Then use our other search features to zero in on what you’re looking for.
And we can even take this a step further. What about your own file classifications? Do you have file types that are very specific to your line of business or to your departments? No problem. We can automatically classify those too! All you have to do is log into your Docxonomy account and train our system with some examples of those files. From that point forward, our system can automatically detect those file types too and classify against them.
You have the files… and now you can find them!
July 23, 2018
Connectors, Document Types, File Classifications, Machine Learning, Text Analysis