Research On Design Of Item Bank And Auto-generating Test Paper Based On Genetic Algorithms

With the development of the computer technology and artificial intelligence,the research on the Autogenerating Test Paper System has aroused the concern of more and more experts. In the literature,Firstly, the theoretical foundation of the item bank construction were probed, the evaluation standard of an examination paper and the parameters of the test papers and the examination questions were analyzed. Secondly, the building of the database structure were reconstructed and designed on the basis of the design idea of the autogenerating test paper,it set the better stage for improving the accomplishment rate of th auotgenerating test paper. The algorithms were reseached on the basis of analyse from a number of domestic and overseas literature. The mathemetics model was builded with the degree of difficulty, types of questions, teaching distinguish ,total time as the major controlling parameters. The improvement method based on the Genetic Algorithms were offered. Characterized by its automatic researching ability, artificial intelligence searching technology and its high speed of convergence, this algorithm can be used to resolve the problems in traditional autogenerating test paper such as the over-long coding, the difficulty of calculating the adaptability function, which hence, meets the demands of autogenerating test paper. It also brought forth a new structure of chromosome and the fitness function, designed the genetic operation. The thesis developed on autogenetating test paper. It set the stable stage for the farther and perfect construction of the autogenerating test paper.