一种改进的元搜索排序合成算法

搜索结果的合成是元搜索引擎系统中一个重要的技术问题。为了提高元搜索引擎的查询精度，提出了一种改进的元搜索结果合成算法。通过分析搜索结果列表中包含的文本信息，综合考虑搜索结果与查询的匹配完全程度和相关程度给出了文本分析的规范化方法，并结合搜索结果的排序信息计算文档的相关分值，据此实现对局部相似度的调整。利用成员搜索引擎的性能评价，提出了改进的影子文档方法估算非相关文档的相关分值。然后，采用基于群决策的合成方法对搜索结果进行一致性排序。在实际Web环境中进行了测试，实验结果表明采用本算法，搜索结果的相关性比Round-robin、CombSum和CombMNZ三种合成算法有较大提高。

An Improved Merging Algorithm for Meta-search

Results merging is one of the main technical problems for running a meta search engine. An improved result merging algorithm is proposed in order to improve the precision of meta search. By utilizing text-based information such as title and snippet obtained from search results, and considering both query-match grade and results relevancy, an approach on text normalization for meta search is described. The relevant scores of the documents are normalized by incorporating text analysis with ranks given by the search engines to adjust the local similarities. Based on the performance evaluation of underlying search engines, an improved shadow document method is presented to calculate the scores of non-relevant documents. Then, a merging method based on Group Decision Making activity is adopted to sort the search results. The proposed solution is tested in actual web environment and compared with other methods. Experimental results show that the proposed algorithm is more effective than other three merging algorithms of Round-robin, CombSum and CombMNZ.