Equivio>NearDuplicates detects and groups near-duplicate files. While existing technology can detect exact duplicates, Equivio offers a unique capability for detection of near-duplicates. Near-duplicate files are documents with minor differences; e.g. contract versions containing a few different words.
Equivio>NearDuplicates identifies near-duplicates and organizes them into sets for efficient and coherent handling. This streamlines the document review process:
-
Assign the near-duplicate sets to reviewers, ensuring that one reviewer handles a document and its near-duplicates in a systematic manner.
-
Start review of a near-duplicate set with the pivot document, the most representative document in the near-duplicate set. After reading the pivot, the reviewer decides whether the rest of the documents in the near-duplicate set can be skipped or require granular review.
-
Using the compare facility, the user zooms in on the differences in each near-duplicate vis-ֳ -vis the pivot document. As a result, the user needs to read only the differences. Moreover, the user is sure not to miss minor, yet potentially critical, differences.
-
The user can bulk handle a near-duplicate set. The Equivio groupings help ensure the consistent treatment of like documents -- for example, when marking documents as privileged or responsive.
Benefits
By grouping near-duplicate documents, Equivio eliminates data redundancy, exposing the unique data. The result:
-
Reduced costs. Equivio directs the reviewer to what's important; viz. to documents that contain unique information, and to the unique information within each document. Proven in hundreds of cases, Equivio's technology consistently reduces review and handling costs by 30 to 50%.
-
Consistent treatment. The Equivio groupings ensure consistent treatment of near-duplicate documents. Near-duplicates can be bulk handled, for example, in applying responsive/privilege tags in litigation review, classification policies in homeland security, and document release policies in response to a regulatory request.
-
Enhanced findability of data: The near-duplicate groupings enable more compact presentation of search results, organizing the documents into groups of very similar documents. This allows users to focus on the unique data they need, enhancing data findability and reducing the risk of missing critical information.
Use Scenarios
By reducing complexity, Equivio's technology gives the winning edge in data review and management applications:
-
In data review, Equivio enables the suppression of redundancy, allowing users to focus on the information they need for the task at hand. The focus on unique data is critical for information workers, whether youג€™re an attorney defending your corporate client against a litigation suit or an intelligence analyst researching a homeland security issue.
-
In data management, Equivio's ability to group similar documents ensures the consistent application of archiving policies, release decisions and treatment annotations.
-
In data search, Equivio allows the structured presentation of documents retrieved by a search engine. Equivio enables the search results to be presented in a compact manner, grouped into sets of near-duplicate documents.
Applications
Equivio is offered as a specialized component for integration within third-party services and applications for:
-
Litigation review: Equivioג€™s data groupings reduce the cost and enhance the quality of litigation review.
-
Content management: The grouping of near-duplicates enables the more compact organization of data in primary and secondary storage systems, including content management and litigation readiness applications.
-
Intelligence: Equivioג€™s near-duplicate technology is used in intelligence analysis applications to reduce data volumes and focus on unique data.
Integration
Equivio is built for straightforward plug-in as an OEM component, using the Equivio SDK, or as a standalone application, using the Equivio GUI, integrated within a broader third-party solution or service offering. | 
