Abstract: The traditional genetic algorithm’s strategy of choice lacks of diversity protection mechanism, it easily appears premature convergence. To solve the problem of intelligent test generation, this paper adopts niche technology to complete the genetic operation of population’s evolution mechanism, setting the adaptive mutation operator to ensure the diversity of the population and prevent population from the local convergence by the size of the individual concentration; adding the threshold is to ensure that when the algorithm is close to the optimal solution, the algorithm returns to the adaptive genetic algorithm in order to simplify the algorithm and accelerate the convergence speed. This paper proposes an adaptive and niche technology combined genetic algorithm, in a balance of the global searching algorithm and local rapid development ability. Finally, an example verifies the effectiveness of the proposed algorithm.

Key words: genetic algorithm, niche technology, intelligent generation, adaptive mutation, threshold