CAJ | 학술논문

计算机智能组卷的关键技术在于组卷算法，蚂蚁算法在初期信息素缺乏导致搜索时间较长；遗传算法需要在一组解中寻找最优解而产生大量的重复数据，导致算法效率较低。为了开发出一个具有高效性和鲁棒性的组卷算法，提出了一种融合遗传算法与蚂蚁算法的机器组卷算法，算法利用遗传算子操作的全局收敛快的特点，将最优结果作为蚂蚁算法的初始信息素分布，按照蚂蚁算法的并行反馈信息、求解效率高的特点进行信息更新求得最优解，优势互补。实验表明，算法在收敛性和寻优性都有很好的效果。
계산궤지능조권적관건기술재우조권산법，마의산법재초기신식소결핍도치수색시간교장；유전산법수요재일조해중심조최우해이산생대량적중복수거，도치산법효솔교저。위료개발출일개구유고효성화로봉성적조권산법，제출료일충융합유전산법여마의산법적궤기조권산법，산법이용유전산자조작적전국수렴쾌적특점，장최우결과작위마의산법적초시신식소분포，안조마의산법적병행반궤신식、구해효솔고적특점진행신식경신구득최우해，우세호보。실험표명，산법재수렴성화심우성도유흔호적효과。
The key of Computer auto-examination system lies on Auto-generating Examination Paper algorithm, pheromone lack of Ant algorithm in the initial leads to search for a long time, Genetic algorithm needing to find the optimal solution in a set of solutions will generate a large amounts of duplicate data, and algorithm efficiency is low.In order to achieve the efficient Auto-generating Examination Paper algorithm, this paper proposes a algorithm based on genetic algorithm and ant algorithm, to obtain the optimal results by speed of genetic operator as the initial information of ant algorithm and to update the information according to the ant algorithm of parallel feedback information, the efficiency high characteristic, finding the optimal solution . Simulation shows that the algorithm has a good effect in convergence and optimization.