near duplicate technology
The Near Duplicate Problem
It is estimated that in enterprise environments, 20% to 50% of all electronic information are near duplicates. Near-duplicate files are documents with minor differences. For example, contract versions containing a few different words.
The Near Duplicate Solution
Near duplicate detection technology (NDD) can be used to detect files with the same content but which are in different formats, for example, MS Word and PDF versions of the same document. Also files with the same content but which have different formatting can be identified using NDD. NDD can also be applied across OCR documents (scanned paper), which covers your entire document population end-to-end.
Near de-duplication creates order from chaos by grouping documents with similar content together and highlighting this to the user. Whilst exact de-duplication can result in the removal of up to 50% of duplicates in potentially discoverable electronic file repositories, near de-duplication can result in finding up to a further 50%. This means faster review and thereby greater time and cost savings.
Being able to group near-duplicates together greatly assists in document review by:
- Presenting the user with sets of near duplicates to review
- Rather than reading each document, small differences can be highlighted for review
- Ensuring consistent treatment of near duplicates
The result is that a document review can be conducted more efficiently, coherently and accurately because documents are grouped together and differences highlighted.
Less cost, less time and less risk !
Whilst using Equivio’s content-centric technology efficiently addresses the near duplicate problem for both paper and electronic documents, it does not completely address the problem of email threads.
Read more about email threading
Equivio™, Equivio>NearDuplicates™, Equivio>EmailThreads™, Equivio>Compare™ and Read less, Think more, Win big™ are trademarks of Equivio. Other product names mentioned may be trademarks or registered trademarks of their respective owners. All specifications are subject to change without prior notice