To support the group decision-making in emergency response, it is important to research on how to reach consensus quickly and reliably in the procedure of group decision-making. This paper proposes a new planning method to improve the efficiency of group decision-making based on Markov chain model and uses a real case example of New Orleans Hurricane Katrina to illustrate the usefulness and effectiveness of the proposed approach. The approach is quicker than conventional process in terms of two points. (1) It minimizes the human interventions and makes the most of computer system support to speed up the interactions between the decision-maker and the system. (2) It researches into the important hidden pattern in the group decision-making process, predicts the possible decision in the future and thus further speeds up the decision-making process. The authors hope that analysis of the dynamic procedure of decision-maker's preference adjustment will assist researchers not only in better understanding of group decision-making procedure but also in better design of Group Decision Support Systems for emergency response.