Navy Real-time Knowledge Sharing (RKS)

Navy personnel are increasingly operating in highly complex and rapidly changing environments. Nowhere is this truer than in Naval aviation. In addition to an already-large set of factors that need to be considered for aviation maintenance technician success, the increasing complexity of the aircraft, accelerating operational tempo, achieving enhanced skill sets faster and at a lower cost, create significant additional challenges that must be taken into account to achieve the Navy’s aircraft uptime requirements. MARi LLC, Carnegie Mellon University, and Google Cloud Platform are partnering to combine state of the art multimedia content tagging algorithms together with granular levels of task and Sailor analytics to ensure that knowledge objects can quickly move through a semi-automated, custom approval pathway - getting the latest and best information to the right person at the right time.   Phase I successfully demonstrated to the F/A-18 maintenance training transition customer that a fully developed Real-time Knowledge Sharing (RKS) solution could positively impact multi-billion dollar challenges the F/A-18 Maintainer community has with aircraft consistently missing Mission Capable Goals because of maintenance delays and trained personnel shortages [1, 2]. Phase II will build out the RKS UI/UX (user interface/experience) and AI/ML (artificial intelligence/machine learning) design that were customer-approved in Phase I into a fully functional chain-of-command validated, peer-to-peer knowledge sharing platform.    Carnegie Mellon University’s (CMU’s) experts in ML and human computer interaction (HCI) will develop RKS-specific algorithms to automatically 1) validate, tag and efficiently route KOs through the approval process; 2) flag KO changes to technical publications that impact KO accuracy; 3) rank KOs based on user interaction; and 4) push relevant content to appropriate users based on MARi’s whole-Sailor personal attribute profiles. The four primary benefits of our solution, are 1) ease of system maintenance and relevancy using built-in AI and ML knowledge-object intelligence that flags out-of-date KOs by comparing tech pub changes to active KOs in the system; 2) accuracy of tagging and routing using advanced classification, detection/tracking, action recognition, optical character recognition, content classification, and entity analysis; 3) personalized KO recommendations that push content to Sailors based on MARi’s “match, gap, recommend” functionality; and 4) expedited access to Navy SMEs and asset acquisition via our F/A-18 OEM partner, Boeing.