Cognitive Computing Application for Defense Contracting

MICA was selected and awarded to ARiA under SBIR Topic AF151-194, technically managed by AFRL/RITB with SAF/AQ-OTI as the sponsor organization. Under prior Phase I and II SBIR efforts ARiA developed, trained, and tested the Machine Interface for Contracting Assistance (MICA). MICA leverages academic and commercial-sector advances in cognitive-computing, deep learning, graph storage, informational retrieval, machine learning, and semantic search. The cloud-based system provides users from both government and current and prospective contractor organizations a clear, intuitive, and comprehensive natural-language query interface to defense-contracting statutes, regulations, practices, and policies such as the Federal Acquisition Regulations (FAR) and Defense Federal Acquisition Regulation Supplement (DFARS). By making the process of understanding acquisition regulations more efficient and comprehensive, MICA achieves efficiencies, reduces risk, and removes barriers to acquiring more innovative and cost-effective solutions. MICA has been user-tested and at the end of the first Phase II effort was considered to be at TRL 5 (prototype system demonstrated and tested in relevant environment).