Intelligent generating test paper based on improved genetic algorithm

Abstract

A new algorithm for intelligent test based on genetic algorithm is proposed in this paper. Firstly, this algorithm improves the basic genetic algorithm for two times, furthermore, the cross-probability and variation-probability of the genetic algorithm can be adjusted according to the degree of individual adaption. In this way, the individual structure of high fitness is not destroyed, and the phenomenon of slow search speed is overcome, thereby it effectively improves the speed and quality of the test paper. The experimental results show that the improved algorithm significantly improves the global optimization ability and speed, it has high robustness.