数字文献资源内容服务推荐研究——基于本体规则推理和语义相似度计算

New Content Recommendation Service of Digital Literature

【目的】解决传统数字文献资源内容服务推荐中无法充分挖掘资源语义信息等问题。【方法】通过设定本体推理规则对用户查询关键词进行语义扩展,提出一种新的语义相似度计算方法计算文献资源内容相似度。按照相似度大小对搜索结果进行排序,将排名较高的文献推荐给目标用户。【结果】实验结果证明,该方法能够较准确地计算语义相似度,并能够对用户需求进行有效推荐。【局限】缺少对数字资源的大规模采集,实验案例较少。【结论】该方法充分挖掘数字文献资源的语义信息并进行有效推荐,为数字资源内容服务推荐提供一种新思路。

[Objective] This paper tries to improve the traditional content recommendation service of digital literature, which cannot fully exploit the semantic information of the literature. [Methods] First, we introduced the Ontology reasoning rules to the recommendation system, and then semantically extended the user＇s query. Second, we calculated the similarity of the literature to rank. Finally, we recommend those top ranked literature to the users. [Results] The proposed algorithm can calculate the semantic similarity among literature and successful recommend documents to the users. [Limitations] Only examined the new method with relatively small data sets. [Conclusions] The proposed algorithm could effectively exploit the semantic information digital resource to the users. of target literature and offer a new way to recommend