Representation of qualitative user preference by quantitative belief functions

Many intelligent systems employ numeric degrees of belief supplied by the users to make decisions. However, the users may have difficulties in expressing their belief in terms of numeric values. The authors present a method for generating belief functions from symbolic information such as the qualitative preference relationships. The method of generating belief functions provides a practical interface between the users and a decision support system. It can be argued that the ability to generate numeric judgments with nonnumeric inputs is essential in the development of approximate reasoning systems. The proposed method can provide an important component for these systems by transforming qualitative information into quantitative information