垂直搜索的算法研究计算机软件与理论专业论文.docxVIP

摘要 随着互联网上的信息量越来越大，传统的通用搜索引擎对信息的查找、索引越发显 得力不从心，逐渐显露出“准确性差、时效性差、覆盖率低”等弊端。通用搜索引擎立 意于满足用户的公共信息查询需求，它根据用户输入的查询串与索引页面在内容上的匹 配程度的高低来筛选、返回页面。这种检索方式不但带回大量的无关页面，而且缺乏准 确性与实效性，已不能满足人们日益增长的对个性化服务的需求。 针对以上情况，另一种搜索引擎悄然出现，它可以在一定范围内取得比传统搜索引 擎更令人满意的结果，这就是垂直搜索引擎。垂直搜索引擎的核心部分是垂直搜索算法。 本文首先介绍通用搜索算法的基本原理和关键技术，并对这些算法的优缺点进行了 分析，并在此基础上提出了垂直搜索算法。本文对通用的 PageRank 算法和 Hits 算法进 行了改进:适当的增加主题关键词的权值，对相关的属性赋予适当比重的权值。针对传统 的搜索算法产生“主题漂移”和 “属性漂移”的问题，本文适当的调整了算法的权重因 子，使算法尽可能的避免这类问题。本文对算法阀值的选取进行了讨论，并指出了需要 考虑的因素及其对算法结果的影响。 作者针对改进的算法设计了一个简单的实验环境，并对改进的算法进行了验证，实 验表明，改进的算法能够适当的避免主题漂移等问题。 关键词: 垂直搜素，搜索算法，权重因子，阀值 ABSTRACT With more and more information appears on the inter net, the traditiona l genera l search engines for information search gradua lly revea led more and more problems, likeaccuracy lack ness, poor timeliness,low covera ge. The General search engine can satisfy the users public information query dema nds,and it according to user input index page query strings in content with the matching degree level ,and return to the page. This kind of met hods not only has brought lack of accuracy and low page effectiveness, and already cannot satisfy people grow ing’s individ ualized service needs. In view of the above situation, anot her kind of search engine, it can provide more satisfactor ied results tha n traditiona l search engine in certain scope,which is called vertica l search engine. The core of vertica l search is vertica l search algor ithm. First, this paper introduces the basic principle s of universa l search algor ithms and the key technologys, and then analyzes the advantages and disad vantages of them,and proposed in this foundation the new vertica l search algor ithm. This paper uses PageRa nk algor ithm and the Hits algor ithm to improve: increase the proper weights of subject keywords and give related properties proper proportion weights. In traditiona l search algor ithms produce topic drift and attributes drift roblems,t he paper adjuste the weighting factor in the algor ithms , as far a