Abstract: In group discussion, because the thinking of experts is uncertainty and information is unstructured, group discussion is difficult to reach consensus. To solve this problem, this article gives a information model which is composited of natural and artificial property. Mechanism of how to extract uncertainty information is studied with argument frame- work,valid arguments group and distribution function. A method is discussed,which is information fusion based on a- verage argument. All is to promote awareness of the spiral and groups to reach consensus. Finally, a case is provided to prove feasibility and effectiveness of model and method,which is discussion about customer's demand of car.

Key words: Group discussion, Structured information, Information fusion