Research on Intelligent Paper Composition Based on Improved Multi-Population Genetic Algorithm

摘要

Concerning intelligent paper composition, the article puts forward an improved genetic algorithm (GA) based on the multi-population division. According to the ideas of population division, the genes of individuals in the population which control the same characters are further divided into the same sub population so that they can be performed by the genetic operators. In order to avoid the local optimum, the optimal solution of each sub population is selected to be recombined global optimum. Compared with the simple genetic algorithm (SGA), this algorithm significantly reduces the search space of the problem solution and accelerates convergence speed. Finally, the algorithm is verified in the problem of intelligent paper composition and the results indicate that the algorithm has obviously improved the quality of the intelligent paper composition compared with the SGA.