Automated classification of documents and information

What is classification? Classification is to assign one or more tags/labels to documents and information. For example, a label could be a document type (letter, invoice, report, etc.), target group, or topic / theme. Based on a label, a document can then be properly included in a business process, or can also simply be stored in a (new) DMS / ECM system. 

It is easy to imagine the problem of doing a manual classification of documents. Although librarians and information specialists are highly skilled, it is difficult for a team to classify content consistently and unambiguously, even if they are following a standard template. Manual classification of documents is subjective, time consuming and often does not get the priority it needs. The accuracy, and therefore the usefulness of the classification is in question.

Xillio Classifier: classification of documents based on content

The Xillio Classifier is the solution to help successfully perform any migration, digitization, search and compliance project. While most automated solutions classify based on the structure and the appearance of a document, the Xillio Classifier goes a step further.

This intelligent tool can assign one or more labels to documents based on the actual content of a document, that is: grammar, spelling, word choice and repetition.

The Classifier achieves an accuracy of at least 90%!

 classifier_screenshot_ENG.png

Classification in practice

KWR, the Dutch institute for water research, deployed our classification software to automaticaly add metadata to hundreds of document in OpenText Content Server. 

 

Read case study

Key benefits of the Classifier

The Xillio Content ETL Platform supports documents from any given content system, such as ECM and DMS systems (e.g. OpenText, Corsa, EMC Documentum, FileNet, Alfresco, Decos), even custom-built legacy systems, or systems which are only partly in use. In short, you can access content from anywhere!

Key benefits of the Classifier:

  • Classifies based on content (grammar, spelling, word choice and repetition)
  • Supports any source and target systems, such as ECM and DM systems, including the ability to source from multiple systems at the same time
  • Realizes a minimum of 90% accuracy
  • User-friendly and intuitive interface
  • Significant improvements in productivity for a process or knowledge worker
  • Consistent and high-speed document classification

 

Want to know more about our Classifier? Care for a free demo? Just fill out the form and we will be in touch.

Request a demo
Fill out the form and we will contact you as soon as possible.