Effective knowledge support in knowledge-intensive environments can place great demands on information filtering (IF) strategies. An IF system that relies on traditional information retrieval technology and user models (e.g., user profiles) is regarded as an effective approach for supporting long-term information needs. To provide a more effective knowledge support, we propose a task-stage knowledge support model that incorporates the advantages of the traditional IF model with the characteristics of each task-stage. A correlation analysis method is proposed to determine a worker's task-stage (e.g., pre-focus, focus formulation, and post-focus task stages), and an ontology-based topic discovery method is proposed to examine the variety of a worker's information needs for specific topics. Consequently, the knowledge support is achieved by coupling user information needs with task-stage identification.