石油行业垂直搜索引擎技术研究

发布时间：2018-05-07 17:47

本文选题：垂直搜索 + 信息检索　；参考：《电子科技大学》2013年硕士论文

【摘要】：垂直搜索引擎是针对某一个行业的专业搜索引擎，是搜索引擎的细分和延伸，相比较通用搜索引擎的海量信息无序化，垂直搜索引擎则更加专注、具体和深入。随着油田信息化建设进程的推进，油田建设了具有自己特色的信息网和不同专业的信息管理系统。信息网网站规划非常庞大，信息内容十分丰富，因此，迫切需要一个搜索引擎系统，从限定范围的互联网上和企业内网上搜索到石油有关网页的有效信息，并结合石油行业的特殊需要，对信息进行处理，，为油田网络用户和科研、生产人员方便地提供所需要的信息。本文设计了石油行业垂直搜索引擎的处理流程，通过信息抓取、处理和索引实现了图片搜索功能、网页搜索功能和论坛搜索功能；通过搜集整理行业词汇，建立了石油百科知识词库；开发了石油垂直搜索引擎系统，研发了搜索器、处理器、索引器、检索器在内的全部四个子系统，实现了图片搜索自动提取、网页定向搜索提高及时性和论坛独立搜索提高检索准确性，最终形成了基于自然语言理解的一个个性化、智能化的网络信息搜集工具。石油行业的专业搜索引擎全国还没有，该技术的应用解决了目前网站信息采集和检索方面的问题，提高了网站的维护效率和网页查询效率。通过为石油各个专业领域、石油从业人群以及石油行业特定需求提供具有石油行业色彩的、而且“专、精、深”的有专业价值的信息和相关服务，提供更加专注、具体和深入的信息内容，搜索引擎将被打造成为石油系统最权威、最专业的信息引擎。该系统实现信息采集的自动化，能为网站用户搜索信息带来全新的使用体验，能让用户在最快的时间里找到最需要的信息，真正起到搜索引擎和导航的作用。实践证明该系统有很好的应用效果，为提高油田网站信息采集和信息检索水平发挥了重要作用。
[Abstract]:Vertical search engine is a professional search engine for a certain industry, which is the subdivision and extension of search engine. Compared with the mass information disorder of general search engine, vertical search engine is more focused, specific and in-depth. With the development of oilfield information construction, oil field has built its own characteristic information network and information management system of different specialties. The web site of the information network is very large in planning and rich in information content. Therefore, there is an urgent need for a search engine system to search for effective information from the limited range of the Internet and the intranet to the oil-related web pages. Combined with the special needs of the petroleum industry, the information is processed to provide the needed information conveniently for the oil field network users and scientific research personnel. This paper designs the processing flow of vertical search engine in petroleum industry, realizes image search function, web search function and forum search function through information grabbing, processing and indexing. Established the petroleum encyclopedia knowledge thesaurus, developed the petroleum vertical search engine system, developed all four subsystems, including the searcher, the processor, the indexer, the retrieval device, realized the picture search automatic extraction, Web page oriented search improves timeliness and forum independent search improves retrieval accuracy. Finally, a personalized and intelligent network information collection tool based on natural language understanding is formed. There is no professional search engine in petroleum industry in China. The application of this technology solves the problems of information collection and retrieval of websites and improves the efficiency of website maintenance and web search. By providing more focused information and related services of professional value to all areas of petroleum, the petroleum industry and the specific needs of the petroleum industry, which are "specialized, sophisticated and deep", Specific and in-depth information content, the search engine will be built into the most authoritative oil system, the most professional information engine. The system realizes the automation of information collection, can bring users a new experience in searching for information, can make users find the most needed information in the quickest time, and really play the role of search engine and navigation. The practice shows that the system has a good application effect and plays an important role in improving the level of information collection and retrieval of oil field website.
【学位授予单位】：电子科技大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：TP391.3

【参考文献】