论文部分内容阅读
随着互联网的普及和网页数量的飞速增长,搜索引擎已经成为从网上获取信息的首选工具.然而,目前主流的搜索引擎在响应用户提交的检索请求时,往往以较长的一维列表形式分页展示结果,为了找到自己所需要的信息,用户必须对该结果列表进行耐心的浏览.为了进一步提高用户获取信息的效率和质量,减轻用户的劳动强度,研究者提出了对检索结果进行再挖掘、再组织的问题,聚类就是其中的研究热点之一.本文在分析现有检索结果聚类算法存在的问题的基础上,提出了基于查询相关性分析的标签驱动聚类算法,该算法通过分析短语与查询项的关联程度,提取作为候选簇标签的短语,然后根据这些标签确定网页摘要隶属的候选簇,最后基于对候选簇和标签的评价进行簇筛选和归并,得到聚类结果及每个簇的标签.在相同环境下进行的对比实验表明,所提出的算法优于相关工作,而且需要更少的信息资源支持.
With the popularity of the Internet and the rapid growth of the number of web pages, search engines have become the preferred tool for obtaining information from the Internet.However, the mainstream search engines often paginate long one-dimensional lists in response to user-submitted search requests To display the results, in order to find the information they need, the user must patiently browse the list of results.In order to further improve the efficiency and quality of users’ access to information and reduce the labor intensity of the users, the researchers proposed to re-excavate the search results, Clustering is one of the research hotspots.On the basis of analyzing the existing problems of the existing clustering algorithms for search results, this paper proposes a label-driven clustering algorithm based on query correlation analysis, which is based on the analysis of Phrases and query terms are extracted, the phrases that are the candidate cluster labels are extracted, and then the candidate clusters to which the page abstract belongs are determined based on these labels. Finally, the clustering results and the clustering results are obtained based on the evaluation of the candidate clusters and the labels, and each Clusters of labels.Comparative experiments carried out in the same environment show that the proposed algorithm is superior to the phase Off work, and requires less information resources to support.