International Journal of Scientific Research and Engineering Development

By utilizing a hybrid microservices architecture combining a robust PHP/React foundation with a Pythonbased FastAPI machine learning layer this system automates critical workflows. We demonstrate the practical application of Natural Language Processing (NLP) sentence-transformers to detect duplicate tasks. There is a lot of administrative work involved in tracking tasks, resources and timelines. Traditional issue trackers are dependent upon manual data entry by a human which introduces bias, delays and inaccuracies into the data. This paper describes the architecture and implementation of an AI-based Task Management System (TMS) that integrates into the entire project lifecycle and generate subtasks, alongside machine learning regression models meant to accurately predict task priority and estimate completion times based on historical data. The resulting intelligent TMS reduces managerial cognitive load and optimizes developer efficiency.

V.Udhayakumar, M.Aruljothi,"An Intelligent Task Management System: Integrating NLP and Automated Workflows" International Journal of Scientific Research and Engineering Development, V9(3): Page(1588-1596) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.