基于信息抽取技术的知识搜索系统

发布时间：2018-05-08 06:01

本文选题：信息过载 + 搜索引擎　；参考：《华中科技大学》2013年硕士论文

【摘要】：近年来，随着互联网的迅速普及和发展，特别是当智能手持设备和移动互联网普及以来，人们获取信息的渠道得到了空前的扩展。随着以微博为代表的一系列自媒体网络应用的风靡，互联网已经演化为一个复杂的实时信息发布和传播平台。信息量的空前爆炸对老旧的信息获取方式提出了新的挑战。目前，社会信息已经超过了个人或系统所能接受、处理或有效利用的范围。这种现象集中表现为受传者对信息反应的速度远远低于信息传播的速度，大众媒介中的信息量大大高于受众所能消费、承受或需要的信息量，而且大量无关的没用的冗余的数据信息严重干扰了受众对相关有用信息的准确性的选择。以Google为代表的传统的搜索引擎为人们检索信息来带了很大的便利。然而，索搜引擎的功能仅仅是对网页进行检索，并不能直接返回用户需要的信息和知识，并不能很好的解决信息过载带来的种种挑战。因此，能够根据用户的请求直接返回其需要的知识的搜索技术成为下一代搜索引擎的研究热点。本课题提出了一种基于信息抽取和倾向性分析技术的知识获取和搜索系统，希望通过这一探索为整理和获取互联网上的知识，并为用户提供更具特色的服务提供一些新的思路。
[Abstract]:In recent years, with the rapid popularization and development of the Internet, especially when the smart handheld devices and mobile Internet become popular, people's access to information has been expanded unprecedented. With the popularity of a series of self-media network applications represented by Weibo, the Internet has evolved into a complex real-time information publishing and dissemination platform. The unprecedented explosion of information presents a new challenge to the old ways of obtaining information. At present, social information has exceeded the range that individuals or systems can accept, process or effectively use. This phenomenon is manifested in the fact that the speed at which the information is transmitted is far slower than the speed at which the information is transmitted, and the amount of information in the mass media is much higher than the amount of information that the audience can consume, bear or need. Moreover, a large amount of irrelevant and useless redundant data seriously interferes with the audience's choice of accuracy of relevant useful information. The traditional search engine, represented by Google, provides great convenience for people to retrieve information. However, the function of search engine is only to search the web pages, which can not directly return the information and knowledge that users need, and can not solve all kinds of challenges caused by information overload. Therefore, the search technology which can directly return the knowledge required by the user has become the research hotspot of the next generation search engine. This paper presents a knowledge acquisition and search system based on information extraction and orientation analysis technology, hoping to provide some new ideas for collating and acquiring knowledge on the Internet and providing users with more characteristic services.
【学位授予单位】：华中科技大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：TP391.3

【参考文献】