A Conflict Treatment Algorithm for Certainty Rule-based Knowledge
Chin-Jung Huang, Ying-Hong Lin · 2007
The rule-based knowledge expert system has traditionally emphasized the verification of structural errors in the rule base. For conflicting rules, designated rules are usually followed to implement prioritized. However, there exist no proper methods by which to resolve conflicts, inconsistencies in values. The citation of erroneous knowledge can lead to mistakes in reaching decisions. According to the group decision idea, this study proposes an algorithm is provided that uses a "reliability factor " to refer to the reliability level of the knowledge item with a conflict or inconsistency in value. Most users, 94% report perplexity at the moment that conflicting rules are cited. Moreover, 92% of users hold that the algorithm is helpful to knowledge application and as an aid to the decision-making process.