Seven More Patents!

Reston, VA – Finch Computing, a provider of innovative data and analytics solutions that enable new ways of interacting with information, was granted seven new patents at the end of 2016 in the categories of entity disambiguation & knowledge discovery, search, text analytics, and in-memory database management system technology. This brings the company’s IP portfolio to a total of 22 issued patents, after filing 25 unique patent applications just two years ago, in December of 2014.

A team of seven staff inventors contributed to the development of each invention, including: Chief Technology Officer, Scott Lightner; Chief Architect, Franz Weckesser; Director of Data Science, Sanjay Boddhu; Consulting Modeling and Analytics Engineer, Rakesh Dave; Data Science Architect, Robert Flagg; Senior Software Engineer, Joe Becknell; and Software Architect, Telford Berkey.

“This is an incredible validation that the work we are doing is differentiated and valuable,” said Operations Lead Caryn Alagno. “We continue to offer dramatically different real-time analytics experiences for our customers, and this recognition is the result of long and hard work put forward by our team.”

The newly-issued patents include:

  • Patent #9,507,834: Search Suggestions Via Fuzzy-Score Matching and Co-Occurrence – Employing a co-occurrence knowledge base to allow a user to submit partial or complete queries, which are processed on-the-fly to detect entities, their misspelled variations, and other conceptual features. (Inventors: Scott Lightner, Franz Weckesser, Rakesh Dave, Sanjay Boddhu, Joe Becknell)


  • Patent #9,424,294: Faceted Search and Search Suggestion Method – Generating facets and corresponding frequency counts as part of the search process by running them as part of the query in an in-memory database. (Inventors: Franz Weckesser, Scott Lightner)


  • Patent #9,424,524: Extracting Facts from Unstructured Text – Associating extracted facts with other features retrieved from the text and employing a fact-template store containing commonly used fact-sentence structures. (Inventors: Rakesh Dave, Sanjay Boddhu)


  • Patent #9,430,547: Design and Implementation of Clustered IMDBMSs – Broad system architecture of our in-memory computing platform, FinchDB. (Inventors: Scott Lightner, Franz Weckesser, Telford Berkey, Joe Becknell, Bryan Zimmerman, Mats Persson)


  • Patent #9,544,361: Event Detection through Text Analysis via Dynamic, Self Learning Module – Learning different event types by extracting entities and topic vectors and comparing them to existing entities and topic vectors; developing new knowledge base entries as new entities and topic vectors are discovered. (Inventors: Sanjay Boddhu, Rakesh Dave)


  • Patent #9,547,701: Discovering and Exploring a Feature Knowledge Base – An on-the-fly, analytics-based search mechanism for live and large data streams. (Inventors: Scott Lightner, Sanjay Boddhu, Robert Flagg)


  • Patent #9,542,477: Automated Discovery of Topic Relatedness – Computing topic relatedness based on topic models and using those relationships as a supplementary feature in various data and text analytics. (Inventors: Scott Lightner, Franz Weckesser, Sanjay Boddhu, Rakesh Dave, Robert Flagg)


For the full list of patents, visit Finch Computing’s IP library page: