Research And Application In Auto-generating Paper Based On GA

The establishment of the item bank based on computer and realization of automatic paper-design is the important measure to make the examination more standard and scientific and a key way to separate the examination from teaching. Several algorithms have been applied in test paper auto-generation, such as priority strategy, randomization, and trace and trial strategy, genetic algorithm and so on. When encountering with big solution space, multimodal problems, these algorithms are usually inclined to run into local extremism or difficult to solve.This paper focuses on the analysis of the papers of evaluation criteria, indicators and the role of several important indicators of the relationship between them. In the knowledge base on the use of indicators constructed distribution model into volumes, According volume and pattern definition into the evaluation of the quality of the papers preferences, and setting up paper and Finally, we draw a generation of paper layered weighted objective function.Details on the improvement of the dynamic hierarchical algorithm used in genetic Test Paper steps to solve the problem, covering one of the key technologies; including the mock examination papers for the establishment of Test Paper strategy, coding programs, fitness function identification, choice of crossover and mutation operator, dynamic hierarchical genetic algorithm realization.In use of ASP.NET Dynamic website technology and SQL Server 2000 database, this paper Designed and realized of the corresponding Hierarchical Dynamic Test Paper genetic algorithm software, and conducted a lot of experiments. The result of the experiments shows that the method is reasonable and effective.