An Intelligent Test Paper Generation Method Based on Improved Differential Algorithm
JIANG Long
CAO Junhao
CHEN Zu'en
ZHANG Degang
Abstract：Intelligent generating test paper is a typical multi constrained combinatorial optimization problem. The user sets a number of qualified conditions for the paper. The system gives the optimal combination of test questions to meet the constraints. In line with the actual test paper model and efficient algorithm is the key to ensure the quality of the test paper. According to the actual demand of China Southern Power Grid test,for the differential algorithm premature convergence,and easy convergence to the local optimum problem,proposes a search database to generate the initial population by uniform,according to the value of the population to adapt to the dynamic fine-tuning of the mutation rate and crossover rate. Experiments show that the improved differential algo?rithm still has a good global optimization ability in the face of massive test questions,which has a high quality of the test paper and the efficiency.
Keywords：intelligent generating test paperdifferential evolutionintelligent optimization
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 1055-1057,1110 )