Planet Data Issued Patent for eDiscovery Text Extraction Process

uspto-patent-trademark-office-logo

Planet Data, a global innovator in the creation and development of eDiscovery technologies, services and solutions, proudly announces that the U.S. Patent and Trademark office has granted US Patent 8,924,395 B2 for its eDiscovery text extraction process.

The patent, titled System and Method for Indexing Electronic Discovery Data, is an invention for text extraction from embedded documents and objects during eDiscovery processing. Through the proprietary Planet Data process, text is extracted in a unique way to ensure search results are more accurate.

Embedded objects are prevalent in most types of data, including email, MS Office applications, PDFs, and others. In fact, at Planet Data, we find that across projects, over 10% of data collections contain embedded documents. Our extraction process represents text both semantically and physically in the data set, thus matching what appears visually in the document. The Planet Data approach can increase the accuracy of proximity and concept search results for Early Case Assessment/Early Data Assessment (ECA/EDA) and document review.

“This patent further validates our approach to managing data” states Michael Wade, Planet Data Chief Technology Officer and chief architect of the Exego Platform. “In the legal and information governance environment, preserving the author’s intent in a document is critical, especially during litigation.”

In our process, the embedded object is extracted as a child document where it is 100% searchable so data is not lost or missed. Typically, processing platforms bring the entire embedded object into the parent document. This approach can affect the search results by not maintaining the integrity of the embedded object and overwhelm users by the large number of embedded documents present in the parent document.

Why is this important? In a recent 25 million document project managed by Planet Data, over three million embedded documents (12% of the collection) were extracted through the process in our Exego Platform. Planet Data’s Exego Early Case Assessment Platform enabled the legal team to utilize this technology when conducting proximity/phrase and/or concept search queries.

Without this Planet Data technology, these searches may not be as accurate and complete, and in some cases, these problems could affect the outcome of the litigation. Planet Data continues to expand patent protection of all of our intellectual property encompassing proprietary data identification, processing, and searching methodologies.