基于内容的齐鲁文化资源推荐系统的设计与实现

发布时间：2018-06-23 18:42

本文选题：齐鲁文化 + Visual　；参考：《山东师范大学》2017年硕士论文

【摘要】：资源共享与推荐是目前国内外学术研究的热点之一,齐鲁文化资源受到国内外学者的广泛关注。本文研究的数据资源包括前期与齐鲁文化研究人员合作建立的考古文献资源数据库、古典文献资源数据库、齐鲁文化论著索引资源数据库等160000多条数据。在三大数据库的基础上,本文完成了基于内容的齐鲁文化资源推荐系统的设计与实现。论文的主要工作包括以下五个方面:1.通过阅读大量文献,对现阶段的推荐算法有了充分的了解;通过梳理考古文献资源、古典文献资源、齐鲁文化论著索引资源三大数据库,分析齐鲁文化资源的特点,完成了系统的需求分析。2.根据齐鲁文化资源的实际特点和属性,设计了具体的齐鲁文化资源推荐算法。该方法首先根据齐鲁文化的特点,采取专家打标签的方式提取资源的特征关键词;其次,采用隐式评分来获得用户偏好,也就是根据用户的历史操作来构建用户配置文件;最后,通过Jaccard算法计算齐鲁文化书籍资源和用户配置文件的相似度,推荐与当前用户配置文件相似度最高的前几个齐鲁文化资源。3.依据前期的需求分析完成了系统的总体设计。本系统采用三层结构模型确定系统的主要功能。主要功能包括:资源检索功能,查看浏览历史功能,推荐功能,收藏功能,评论功能等。本阶段还进行了数据库设计,包括系统的E-R图和数据库逻辑设计。4.根据系统的总体设计,实现了具体的基于内容的齐鲁文化资源推荐系统。该系统采用SQL Server 2005、Visual studio 2008开发工具,根据齐鲁文化资源的特点,设计实现了系统的各个功能模块,给出了主要功能的关键代码、流程图和运行结果图,并进行了系统测试,经测试本系统运行效果良好,可以投入到实际应用中。5.目前国内还没有针对齐鲁文化资源的信息服务系统,本文设计的基于内容的齐鲁文化资源推荐系统,实现了对现有的齐鲁文化资源的数字化处理和专家打标签处理,根据其内容特点实现了资源检索、资源推荐、资源收藏、浏览历史和资源评论等功能。
[Abstract]:Resource sharing and recommendation is one of the hot topics of academic research at home and abroad. Qilu cultural resources are widely concerned by scholars at home and abroad. The data resources studied in this paper include more than 160000 data such as archaeological literature database, classical literature resource database and Qilu culture index resource database, which were established in the early period with Qilu cultural researchers. On the basis of three databases, this paper completes the design and implementation of Qilu cultural resource recommendation system based on content. The main work of the thesis includes the following five aspects: 1. Through reading a large number of documents, we have a full understanding of the current recommendation algorithm, through combing the archaeological literature resources, classical literature resources, Qilu cultural literature index resources three databases, analyze the characteristics of Qilu cultural resources, Completed the system requirements analysis. 2. According to the actual characteristics and attributes of Qilu cultural resources, a specific algorithm for recommending Qilu cultural resources is designed. Firstly, according to the characteristics of Qilu culture, the expert tagging is adopted to extract the feature keywords of the resource. Secondly, the implicit score is used to obtain the user preference, which is to construct the user profile according to the user's historical operation. Finally, the Jaccard algorithm is used to calculate the similarity between Qilu cultural book resources and user profiles, and the first few Qilu cultural resources with the highest similarity to current user profiles are recommended. The overall design of the system is completed according to the previous requirement analysis. This system adopts three-layer structure model to determine the main function of the system. Main functions include: resource retrieval function, view browsing history function, recommendation function, collection function, comment function and so on. This stage also carries on the database design, including the system E-R diagram and the database logic design. 4. According to the overall design of the system, the content-based Qilu cultural resources recommendation system is implemented. According to the characteristics of Qilu cultural resources, the system is designed and implemented with the development tools of SQL Server2005 Visual studio 2008. The key codes, flow charts and running results of the main functions are given, and the system tests are carried out. After testing, the system runs well and can be put into practical application. At present, there is no information service system for Qilu cultural resources in China. The content based Qilu cultural resources recommendation system is designed in this paper, which realizes the digital processing and expert tagging of the existing Qilu cultural resources. According to its content characteristics, the functions of resource retrieval, resource recommendation, resource collection, browsing history and resource review are realized.
【学位授予单位】：山东师范大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP391.3

【参考文献】