Font Size: a A A

Optimization Design And Application Of Automatic Test Paper System Based On Genetic Algorithm

Posted on:2020-07-23Degree:MasterType:Thesis
Country:ChinaCandidate:H Y ZhangFull Text:PDF
GTID:2428330578465508Subject:Computer technology
Abstract/Summary:PDF Full Text Request
At present,along with the rapid development of information technology,all walks of life are inseparable from the help of computers.Online test systems based on automatic test paper generation system have been widely applied in various tests.The application of the automatic test paper generation system can not only reduce the teachers' working pressure and save the time spent on test paper design,but also effectively reduce teachers' individual subjective factors during test paper design,improve the quality of the test paper,and enhance the standardization of the test.The essence of paper generation problem is to solve multi-objective optimization problems.As an efficient global parallel search algorithm,it is very suitable for solving such multi-objective optimization problems using the genetic algorithm because of its simplicity and robustness.With the automatic test paper generation system as the object of research,this paper focuses on the optimization problem model of automatic test paper generation system and how to realize it using the genetic algorithm.Firstly,based on a large number of domestic and foreign literatures,this paper analyzes the important question attributes and test paper indexes in the test paper generation system,and clarifies the basic steps of test paper generation.Then combined with the key attributes of the test questions,the key constraints of test paper generation are determined,thus establishing a suitable mathematical model and minimizing the objective function.The genetic algorithm is introduced to solve the test paper generation problem.Finally,the experimental results show that this algorithm can be used to generate the test paper successfully and improve the quality of the test paper.The genetic algorithm is then appropriately modified.Design coding methods and population initialization methods,as well as design genetic operators and algorithm termination conditions.Finally,experiments show that the system using the algorithm in this paper can successfully roll up the volume and effectively improve the quality of the test paper.In the development of the system,C/S architecture,C # development language and VS development platform are used,and the database is connected combined with ADO.NET data.It is proved that the system runs stably and has certain application value.
Keywords/Search Tags:automatic test paper, Genetic Algorithm, Genetic operator, Multi-objective Optimization
PDF Full Text Request
Related items