Generative Text Engine for Form Completion

The U.S. Navy requires that ships have all their systems ready to perform specific missions as tasked by their operational commanders. These highly complex systems require preventive and restorative maintenance to be performed regularly to maintain optimal performance. Data accuracy, in the form of documented maintenance actions, is critical to deriving consistent meaning from the aggregated pool of input. This Phase II project will address how to incorporate automated curation as a part of the existing maintenance documentation process. It will incorporate advanced Machine and Deep Learning tools, specifically Natural Language Processing and Generative Pre-trained Transformers (GPT) that are part of Generative Artificial Intelligence (GenAI) models to increase the accuracy of end-user input in operational environments. The project will incorporate specialized language/jargon without having to have the end user train the system; run speech-to-text functionality on appropriate mobile hardware, taking the place of manual methods such as the “wheel book;” run a suitable GenAI model on a local system (edge); and implement a prompting workflow that drives form completion. Phase II will consist of implementing what we learned from our Phase I questions, developing a  practical solution, and assessing the solution through a combination of technical analysis and practical testing to determine which solutions are the most suitable. Based on our experience with integrated systems involving GenAI, we will derive a working prototype.