With the increasing amount of information (and knowledge) in organizational memories and the phenomenal growth of the World Wide Web, knowledge workers are increasingly suffering from information overload. Because of the growing complexity of knowledge-intensive tasks, a profiling technique is needed to deliver task-relevant documents to workers. In this study, we propose a task-stage identification technique that provides effective document support throughout the execution of a task. A pattern similarity analysis method based on the correlation value is used to identify a worker's task-stage. The results are incorporated into a profile adaptation process to generate the worker's current task profile. We conducted a pilot study in a research institute. The results confirm the effectiveness of the proposed document support process in a knowledge-intensive working environment.