A quick and effective emergency rescue of geo-hazards under the conditions of extreme snow and ice disasters relies heavily on information technology tools, particularly decision support system; as the core content of decision support system, reasoning mechanism is significant because it directly determined the decision efficiency of the system and the accuracy of decision results. According to the characteristics of decision of geo-hazards emergency rescue, a rule-based (RBR) and case-based (CBR) hybrid reasoning mechanism is introduced into the emergency rescue decision support system of geo-hazards under the conditions of extreme snow and ice disasters (ERDSS-GHESID). The reasoning mechanism of ERDSS-GHESID is designed by the object-oriented programming method. It is showed that RBR and CBR hybrid reasoning mechanism can better simulate the inference procedure of human experts in the process of emergency rescue decision of geo-hazards under the conditions of extreme snow and ice disasters, showing a high practical value in the ERDSS-GHESID.