Web-based Intelligent Extraction of Symbology based on Contextual Information

To address the DHS need for intelligent symbology technologies, Physical Optics Corporation (POC) proposes to continue the development of Web-based Intelligent Symbology Extraction based on Context (WISEC), a unique enterprise symbology system that integrates state-of-the-art natural language processing (NLP) tools with our syntactic event attribute extraction and contextual event coreference algorithms. In Phase I, we demonstrated the feasibility and maturity of WISEC by developing its design and software prototype for incident management and crime information sharing applications, with mature functionalities (automatic symbol generation using open-source unstructured data, association of events from multiple sources, dynamic event status update, and platform-independent user interfaces for review and information "drill down"). In Phase II we will extend this software prototype in functionality, performance, and maintenance into a mature enterprise software system, test it with both DHS and local users, evaluate its performance in classification, coreference, and scalability, and deliver it to the DHS. The successful completion of this project at the end of Phase III will benefit the nation in both government and commercial sectors by providing intelligent symbology with standard representation that is sharable among various communities. Commercial applications for this technology include business intelligence, text analytics, and enterprise content management and archiving.