Since 2019, China's urbanization rate has exceeded 60%. Cities are densely populated, economically developed, and highly concentrated areas of social wealth. With global warming, the frequency of extreme weather impacts on cities has increased. For the losses caused, it is necessary to integrate the urban operation data and meteorological data to realize risk warning. Based on the Bayesian network, it provides a new idea for the risk visualization analysis of urban block disaster chain in extreme low temperature weather. By collecting spatial data such as public service facilities, number of residents and public security incidents in a certain city block, reasoning training and risk visualization are carried out. Analyzing the evolutionary relationship between extreme low temperature weather and urban block safety is conducive to the promotion of smart and safe city construction planning.