数据结构MOOC系统的设计与实现

发布时间：2018-01-21 12:09

本文关键词： MOOC LTSA 资源评估学习行为评估遗传算法个性化学习　出处：《西安科技大学》2017年硕士论文　论文类型：学位论文

【摘要】：随着互联网技术的迅速发展,网络课程在国内外已经取得了令人骄傲的成果,先后出现了许多优秀的网络课程资源,此外,MOOC作为网络课程的一种新型表现形式,它在教育领域引起了的巨大变革,但是在实际的运行中,网络课程的实施仍面临着很大的问题。资源更新率低,资源管理不当,学习者被动,课程辍学率高,个性化应用服务缺失等问题成为当前绝大数网络课程可持续发展的瓶颈,导致很多课程出现了只有教师的“教”,严重缺少学生的“学”的现象。本文以数据结构课程为背景,针对上述问题,设计并实现数据结构MOOC系统。首先借鉴MOOC课程的运行模式,分析并设计数据结构MOOC系统运行模式,在学生学习过程和教师教学过程中,教师和学生以及学生和学生之间的互动是系统运行的内在动力,资源是二者互动的基础,因此学习者的学习和资源的构建息息相关。在充分分析了课程运行模式之后,结合传统经典的LTSA框架,对其进行改进,提出数据结构MOOC学习管理框架,主要增加了学习者资源代理元件,学习者成绩代理元件,学习者资源数据库和三级代理模型。设计资源评估模型实现资源代理,设计学习行为评估模型实现学习者成绩代理,设计三级代模式提高资源管理和学习行为评估的时效性和可操作性。最后,在对学生学习效果评估的数据基础上,运用遗传算法设计了智能组卷的组卷策略,并通过实验验证了遗传算法的收敛性和试卷的相关性,达到个性化学习的目的。总之,数据结构MOOC系统通过对学习管理系统框架的改进,以“学习者”为中心,实现了资源的动态构建,建立了学生学习行为评估模型,设计的智能组卷满足个性化应用的需求,对未来网络课的发展具有重大影响。
[Abstract]:With the rapid development of Internet technology, online courses have made proud achievements at home and abroad. As a new manifestation of online courses, MOOC has caused great changes in the field of education. However, in the actual operation, the implementation of online courses is still faced with a lot of problems, and the rate of resource upgrading is low. Improper management of resources, passive learners, high dropout rate of courses, lack of personalized application services and other problems have become the bottleneck of the sustainable development of most online courses, leading to the emergence of "teaching" only by teachers in many courses. There is a serious lack of students'"learning" phenomenon. In this paper, the data structure MOOC system is designed and implemented against the background of the data structure course. Firstly, the operating mode of the MOOC course is used for reference. This paper analyzes and designs the operation mode of data structure MOOC system. In the process of students' learning and teaching, the interaction between teachers and students, as well as between students and students, is the internal motive force of the system. Resources are the basis of interaction between the two, so learners' learning is closely related to the construction of resources. After fully analyzing the course operation mode, combining with the traditional classical LTSA framework, we improve it. A data structure MOOC learning management framework is proposed, which mainly adds learner resource agent component and learner achievement agent component. Learner resource database and three-level agent model. Design resource evaluation model to implement resource agent, design learning behavior evaluation model to realize learner achievement agent. Third generation model is designed to improve the timeliness and maneuverability of resource management and learning behavior evaluation. Finally, on the basis of the data of students' learning effect evaluation, genetic algorithm is used to design an intelligent test paper generation strategy. The convergence of genetic algorithm and the relevance of test paper are verified by experiments. In a word, the data structure MOOC system improves the framework of learning management system by improving the framework of learning management system. Taking "learner" as the center, the dynamic construction of resources is realized, and the evaluation model of students' learning behavior is established. The intelligent test paper is designed to meet the needs of individualized application, which has a great influence on the development of network course in the future.
【学位授予单位】：西安科技大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：G434;TP311.12-4

【参考文献】