An AI-Based Intelligent Task Management System with Dynamic Scheduling and Context-Aware Productivity Optimisation

Abstract

Traditional task management applications primarily rely on static task lists, reminders, and fixed scheduling mechanisms, offering limited support for intelligent decision-making and personalised assistance. This paper proposes an AI-based task management system that integrates machine learning, intelligent scheduling, stress detection, and context-aware recommendations to improve both productivity and work–life balance. The proposed framework dynamically prioritises tasks, predicts task completion time, adapts schedules based on user behaviour and workload, and provides personalised recommendations by analysing productivity history, mood, and stress levels. Furthermore, the system incorporates a stress detection module and an intelligent break recommendation engine to encourage healthier work habits and reduce user fatigue. Experimental evaluation demonstrates that the proposed system achieves 92% precision, 94% recall, 91.4% F1-score, 91% detection accuracy, and a 93% task completion rate, resulting in a 27% improvement in productivity compared with conventional task management approaches. These results indicate that integrating artificial intelligence with adaptive scheduling and well-being awareness significantly enhances task management efficiency while promoting sustainable productivity. The proposed framework provides a scalable and user-centric solution suitable for personal, academic, and professional productivity applications.