Next Generation Graph (NG2)

Award Information
Agency: Department of Defense
Branch: Special Operations Command
Contract: H9240519P0028
Agency Tracking Number: S191-004-0003
Amount: $149,891.04
Phase: Phase I
Program: SBIR
Solicitation Topic Code: SOCOM191-004
Solicitation Number: 2019.1
Solicitation Year: 2019
Award Year: 2019
Award Start Date (Proposal Award Date): 2019-05-24
Award End Date (Contract End Date): 2019-11-25
Small Business Information
201 Loudoun Street SW, Leesburg, VA, 20175
DUNS: 069650682
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: N
Principal Investigator
 Stephane Fellah
 (703) 669-5510
Business Contact
 Harry Niedzwiadek
Phone: (703) 669-5510
Research Institution
Significant progress has occurred in understanding the importance of reliable tools and approaches for managing large bodies of machine-encoded structured knowledge for well-defined problems. An open, adaptive, interoperable, distributed, high-performance approach is lacking. Adaptive models, methods, and services are lacking for Cloud implementation in master repository-like settings, where curated knowledge about subjects of interest can be produced and shared. There are countless sources and methods for compiling source data for knowledge graphs (KG), but these have issues with uniformity, quality, availability, reliability, and consistency. This project addresses deciding what information types can and/or need to be stored and shared as KGs, and devising universal ways of encoding and sharing this information. KGs contain the information we know about things. They provide means to share information about mission-critical things. We will examine first-class objects (OBI) and complex first-class phenomena: events, activities, and situations (ABI). Another challenge is determining contextualization methods. Our focus is on how to encode and exploit inter-relationships between subjects/objects, events, activities, and situations. Contextualization also necessitates methods of semantic enrichment, and using embedded model behaviors that apply graphs with runtime reasoning and logic. This is crucial to achieving context-sensitive, mission-specific operations, and to applying AI techniques to graphs.

* Information listed above is at the time of submission. *

Agency Micro-sites

SBA logo
Department of Agriculture logo
Department of Commerce logo
Department of Defense logo
Department of Education logo
Department of Energy logo
Department of Health and Human Services logo
Department of Homeland Security logo
Department of Transportation logo
Environmental Protection Agency logo
National Aeronautics and Space Administration logo
National Science Foundation logo
US Flag An Official Website of the United States Government