IP Library

OUR CAPABILITIES ARE BUILT ON DOZENS OF UNIQUE PIECES OF INTELLECTUAL PROPERTY

Each one of these inventions represents a transformative new innovation in the areas of text analytics, entity disambiguation, knowledge discovery, search, in-memory computing, and data compression.

These inventions are reflected in an IP portfolio of more than two dozen patents, filed in December 2014. To date, 30 of these patents have already been either issued or allowed – an astonishingly fast progression from their initial filing.

Below is an inventory of the individual pieces of intellectual property we’ve developed, the teams that developed them and their status.

Big Data Compression

Category: Compression
Description: Dramatically compressing the size of a dataset while preserving the ability to decompress a single record or field.
Inventors: Scott Lightner, Franz Weckesser, Bryan Zimmerman
Status: Issued: US Patents #9,025,892, #9,710,517

Automated Discovery of New Topics

Category: Entity Disambiguation & Knowledge Discovery
Description: Using co-occurring topics from different topic models to aid in entity disambiguation; extending conventional LDA topic modeling in so that each component is treated as conditionally-independent.
Inventors: Scott Lightner, Franz Weckesser, Sanjay Boddhu, Robert Flagg
Status: Issued: US Patents #9,177,262 and #9,626,623

Event Detection through Text Analysis via Trained Template Modes

Category: Text Analysis
Description: Using topic models to develop relationships between topics, events and entities; and further use of that data to detect and capture events.
Inventors: Sanjay Boddhu, Robert Flagg, Rakesh Dave, Scott Lightner
Status: Issued: US Patent #9,177,254

Search Suggestions Via Fuzzy-Score Matching and Co-Occurrence

Category: Search
Description: 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
Status: Issued: US Patents #9,208,204 and #9,507,834

Search Suggestions Via Fuzzy-Score Matching and Population Frequencies

Category: Search
Description: Extending existing search suggestion mechanisms to employ an entity co-occurrence knowledge base, a trends co-occurrence knowledge base, fuzzy matching modules and entity extraction modules.
Inventors: Scott Lightner, Franz Weckesser, Rakesh Dave, Sanjay Boddhu
Status: Issued: US Patent # 9,201,931

In-Loop, Human Validation of Disambiguated Features

Category: Entity Disambiguation & Knowledge Discovery
Description: Extending traditional feature disambiguation systems by providing a feedback mechanism to take human verification of the disambiguated results and update the knowledge base on-the-fly.
Inventors: Scott Lightner, Rakesh Dave, Sanjay Boddhu
Status: Issued: US Patent #9,223,833

Fault-Tolerant Architecture for Distributed Systems

Category: In-Memory DBMS Technology
Description: Providing fault-tolerance in a distributed system by automatically detecting failures and recovering from them by moving processing modules and their dependencies to other nodes in the system.
Inventors: Scott Lightner, Franz Weckesser
Status: Issued: US Patent #9,201,744, #9,785,521

Real-Time, Distributed In-Memory Search Architecture

Category: In-Memory DBMS Technology
Description: A system of multiple network segments with bandwidth and latency tiers, applied to a distributed in-memory data platform.
Inventors: Scott Lightner, Franz Weckesser
Status: Issued: US Patent #9,223,875

Search Suggestions Via Co-Occurrence

Category: Search
Description: A search suggestion generation mechanism that employs a co-occurrence knowledge base to suggest new search queries and possible search expansions or suggestions.
Inventors: Scott Lightner, Franz Weckesser, Sanjay Boddhu
Status: Issued: US Patents # 9,230,041, #9,613,166

Disambiguating Features in Unstructured Text

Category: Entity Disambiguation & Knowledge Discovery
Description: Employing an evolving and efficiently linkable feature knowledge base capable of storing secondary features to disambiguate entities.
Inventors: Scott Lightner, Franz Weckesser, Sanjay Boddhu, Rakesh Dave, Robert Flagg
Status: Issued: US Patent #9,239,875

Entity-Driven Alerts Based on Disambiguated Features

Category: Entity Disambiguation & Knowledge Discovery
Description: An alert mechanism based on user-specified disambiguated features, providing a framework to support collaborative knowledge sharing among different users.
Inventors: Scott Lightner, Franz Weckesser
Status: Issued: US Patent #9,336,280

Alerting System Based on Newly Disambiguated Features

Category: Entity Disambiguation & Knowledge Discovery
Description: Leveraging user-specified disambiguated features to provide better relevance and precision than traditional systems, as well as the ability to build alert specifications around secondary features.
Inventors: Scott Lightner, Franz Weckesser
Status: Issued: US Patent #9,317,565

Dependency Manager for Databases

Category: In-Memory DBMS Technology
Description: Technology to automate the deployment, installation and configuration of data, metadata and software of the primary data store of a distributed database.
Inventors: Franz Weckesser, Scott Lightner
Status: Issued: US Patent #9,348,573

Entity Enrichment Enabling Search Functionality

Category: Search
Description: Extending the search capabilities of contentment management systems with additional managed properties obtained through natural language processing of the underlying unstructured text content.
Inventors: Birali Hakizumwami, Scott Lightner
Status: Issued: US Patent #9,361,317

Non-Exclusionary Search in IMDBMSs

Category: In-Memory DBMS Technology
Description: Granting users the ability to specify a query and a detailed scoring/ranking specification as separate aspects in a search request.
Inventors: Franz Weckesser, Scott Lightner
Status: Issued: US Patent #9,355,152

Faceted Search and Search Suggestion Method

Category: Search
Description: 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
Status: Issued: US Patents #9,424,294, #9,720,944

Extracting Facts from Unstructured Text

Category: Text Analysis
Description: 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
Status: Issued: US Patent #9,424,524

Design and Implementation of Clustered IMDBMSs

Category: In-Memory DBMS Technology
Description: Broad system architecture of our in-memory computing platform, FinchDB.
Inventors: Scott Lightner, Franz Weckesser, Telford Berkey, Joe Becknell, Bryan Zimmerman, Mats Persson
Status: Issued: US Patent #9,430,547

Event Detection through Text Analysis via Dynamic, Self Learning Module

Category: Text Analysis
Description: 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
Status: Issued: US Patent #9,544,361

Discovering and Exploring a Feature Knowledge Base

Category: Entity Disambiguation & Knowledge Discovery
Description: An on-the-fly, analytics-based search mechanism for live and large data streams.
Inventors: Scott Lightner, Sanjay Boddhu, Robert Flagg
Status: Issued: US Patent #9,547,701

Automated Discovery of Topic Relatedness

Category: Entity Disambiguation & Knowledge Discovery
Description: 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
Status: Issued: US Patent #9,542,477

Searching Via Co-Occurrence

Category: Search
Description: Granting users the ability to find entities of interest via entity co-occurrence, even as the data is updated and new information is discovered.
Inventors: Scott Lightner, Franz Weckesser, Sanjay Boddhu
Status: Issued: U.S. Patent #9,619,571

Pluggable Architecture for Embedding Analytics in Clustered IMDBMSs

Category: In-Memory DBMS Technology
Description: Ensuring each database query can specify which analytics modules and parameters are to be applied on-the-fly to intermediate query answers without having to first retrieve data out of the database.
Inventors: Scott Lightner, Franz Weckesser
Status: Issued: U.S. Patent #9,659,108

Feature Co-Occurrence

Category: Search
Description: A feature co-occurrence knowledge base that exploits the full range of state-of-the-art natural language process tools.
Inventors: Scott Lightner, Rakesh Dave, Sanjay Boddhu
Status: Pending

Data Ingestion Module for Event Detection

Category: Text Analysis
Description: A generalizable framework to train customized and source-specific event templates and models for different input data streams.
Inventors: Rakesh Dave, Sanjay Boddhu
Status: Pending