Numerical optimization of given objective functions is a crucial task in many scientific problems. Based on the outstanding characteristics of cloud model on the process of transforming a qualitative concept to a set of quantitative numerical values, and integrate with the basic principle of genetic algorithm, a novel adaptive evolutionary algorithm for continuous global optimization problems was proposed. With the instructions of qualitative knowledge, the extent of searching space is self-adjusted and the possibility of premature and the probability of trapping in local best optimization are greatly reduced, so the algorithm can find high accurate numerical solution within a short time. The algorithm avoids the process of coding and crossover so it is easy to be carried out. By the experiments on typical test functions, the precision, stability and convergence rate were well proved.