应用于Sakai平台的中文智能搜索引擎的研究与设计

发布时间：2018-07-27 18:25

【摘要】：随着网络技术的快速发展以及教育信息化的普及,越来越多的人开始使用网络辅助学习和工作,网络教育已经成为我国高等教育信息化的重要组成部分。2010年,北京邮电大学为了推动高校信息化建设,专门设立了青年基金项目——基于海量资源的通用教学平台的研究与开发,论文作者全程参与了该项目的研究与开发,并重点对网络教学平台中的站内搜索子系统、中文智能搜索引擎等方面展开研究。网络教学活动的指导思想是以学习者为中心的教育理念,旨在通过学习者的自主学习、协作学习提高自身的学习能力。网络教学平台的出现与使用,为学习者和教师提供了可以共享教学资源的平台,但是,由于网络教学平台中的海量教学资源(课程内容、课后习题、参考资料、教学课件等)的内容和形式具有多样性等特点,使得教师和学习者在教学活动中快速搜索和应用资源变得困难。如何才能最大程度地实现教学资源共享,使学习者能够从已有的资源上快速精确地找到自己所需要的资源,是教育领域搜索引擎发展的主要任务,而开发出一个可以应用于网络教学平台中的资源搜索工具是解决这一问题的核心。本研究在分析了网络教学平台的特点以及网络教育的特点的基础上,结合网络学习者的学习能力评价标准,印证了搜索工具在网络教学平台中的理论价值,在充分分析了搜索引擎的工作原理以及关键技术的基础上,设计了基于开源搜索框架——Lucene的站内搜索系统的总体架构,在该框架中引入信息推送技术以及智能知识库技术,提高了搜索引擎的智能化水平,此外,分析并比较了现有搜索引擎的中文分词器存在的不足之处,提出了中文分词优化方案,并对搜索结果排序技术进行优化,使搜索工具更加适合学习者在教学平台中对海量资源进行搜索和查询,能够快速定位用户所需数据的位置,并将符合需求的资源搜索结果反馈给用户,进一步提高搜索引擎的搜索质量。
[Abstract]:With the rapid development of network technology and the popularization of education informatization, more and more people begin to use network to assist learning and work. Network education has become an important part of higher education informatization in our country. In order to promote the information construction of universities, Beijing University of posts and Telecommunications has set up a youth fund project, the research and development of a general teaching platform based on massive resources, and the author of the paper participated in the research and development of the project. And focus on the network teaching platform in the site search subsystem, Chinese intelligent search engine and so on. The guiding ideology of online teaching activities is the learner-centered educational concept, which aims to improve the learning ability of learners through autonomous learning and collaborative learning. The emergence and use of the network teaching platform provides a platform for learners and teachers to share teaching resources. However, due to the massive teaching resources (course content, after-class exercises, reference materials) in the network teaching platform, the network teaching platform provides a platform for learners and teachers to share teaching resources. The diversity of contents and forms makes it difficult for teachers and learners to quickly search and apply resources in teaching activities. How to realize the sharing of teaching resources to the greatest extent, so that learners can quickly and accurately find the resources they need from the existing resources, is the main task of the development of search engine in the field of education. Developing a resource search tool which can be applied to network teaching platform is the core of solving this problem. Based on the analysis of the characteristics of the network teaching platform and the characteristics of the network education, this study confirms the theoretical value of the search tool in the network teaching platform, combining with the evaluation criteria of the learning ability of the network learners. Based on the analysis of the working principle and key technologies of search engine, the paper designs the overall framework of the in-station search system based on open source search frame-Lucene, and introduces information push technology and intelligent knowledge base technology into the framework. The intelligence level of the search engine is improved. In addition, the shortcomings of the Chinese word particifiers in the existing search engines are analyzed and compared, and the optimization scheme of the Chinese word segmentation is put forward, and the ranking technology of the search results is optimized. Make the search tool more suitable for learners to search and query the massive resources in the teaching platform, can quickly locate the location of the data required by the user, and feedback the search results to the user. Further improve the search engine search quality.
【学位授予单位】：北京邮电大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：TP391.3

【参考文献】