面向Web的企业竞争情报获取研究

发布时间：2018-11-05 13:58

【摘要】：在知识经济和信息化时代,竞争情报已成为企业的“第四核心竞争力”。随着Web技术的快速发展,如何从Web上及时有效地获取企业竞争情报成为竞争情报研究中的前沿问题。但已有的方法局限在“网页驱动”的网页搜集和文本搜索上,即主要借助搜索引擎或文本挖掘工具实现竞争情报搜集和分析。这种方式缺乏对Web信息的深度抽取和理解,所得到的抽取结果与用户的实际需求脱节,阻碍了Web环境下企业竞争情报理论与应用的进一步发展。本论文围绕Web环境下的企业竞争情报搜集需求,针对目前面向Web的企业竞争情报获取中存在的关键问题,重点研究Web环境下企业竞争情报的表示模型以及基于不同视角的Web环境下企业竞争情报获取方法。Web可以看成是由Web网页、Web网站以及Web用户构成的一个信息资源平台。基于此观点,我们着重研究了基于Web网页的企业竞争情报获取方法、基于Web网站的企业竞争情报获取方法、基于Web日志的企业竞争情报获取方法,以期能够构建系统性的面向Web的企业竞争情报获取框架,为Web环境下的企业竞争情报研究与实际应用奠定基础。总体而言,本论文的主要工作和贡献可总结为以下几个方面： (1)研究了Web环境下的企业竞争情报语义问题,提出并建立了基于实体的Web环境下企业竞争情报表示模型,在此基础上提出了一个基于实体和关系抽取的Web环境下企业竞争情报获取框架。 (2)研究了面向Web网页的企业竞争情报获取问题,提出了企业商业关系的一个分类框架,并提出了一种基于句子时态标注的企业收购关系抽取方法,获得了较好的抽取效果。 (3)研究了面向Web网站的企业竞争情报获取问题,给出了一种利用Web网站信息进行企业竞争对手分析的框架并进行了实证研究,为Web竞争情报获取与分析提供了新的思路。 (4)研究了基于Web日志的企业竞争情报获取问题,给出了利用Web用户行为日志进行竞争对手分析的框架,并基于实际的互联网用户行为日志分析了电子商务企业之间的竞争关系,为Web竞争情报获取与分析提供了新的参考。
[Abstract]:In the era of knowledge economy and information, competitive intelligence has become the fourth core competence of enterprises. With the rapid development of Web technology, how to obtain enterprise competitive intelligence from Web in a timely and effective manner has become a frontier problem in competitive intelligence research. However, the existing methods are limited to the "web-driven" web page collection and text search, that is, mainly using search engines or text mining tools to achieve competitive intelligence collection and analysis. This method lacks the depth extraction and understanding of Web information, and the result of extraction is out of step with the actual demand of users, which hinders the further development of the theory and application of enterprise competitive intelligence in Web environment. This paper focuses on the demand of enterprise competitive intelligence gathering under the Web environment, aiming at the key problems existing in the enterprise competitive intelligence acquisition for Web at present. This paper focuses on the representation model of enterprise competitive intelligence in Web environment and the method of obtaining enterprise competitive intelligence in Web environment based on different perspectives. Web can be regarded as an information resource platform composed of Web web pages, Web websites and Web users. Based on this viewpoint, we focus on the methods of obtaining enterprise competitive intelligence based on Web web page, the method of obtaining enterprise competitive intelligence based on Web website, and the method of obtaining enterprise competitive intelligence based on Web log. The purpose of this paper is to construct a systematic framework of enterprise competitive intelligence acquisition for Web, and to lay a foundation for the research and practical application of enterprise competitive intelligence under the Web environment. In general, the main work and contributions of this thesis can be summarized as follows: (1) the semantic problem of enterprise competitive intelligence in Web environment is studied. A representation model of enterprise competitive intelligence in entity-based Web environment is proposed and a framework for enterprise competitive intelligence acquisition in Web environment based on entity and relation extraction is proposed. (2) the problem of enterprise competitive intelligence acquisition for Web web pages is studied, a classification framework of business relations is proposed, and a method of extracting enterprise acquisition relationship based on sentence temporal tagging is proposed, which has a good extraction effect. (3) the problem of enterprise competitive intelligence acquisition for Web website is studied, and a framework of enterprise competitor analysis based on Web website information is presented, which provides a new way for Web competitive intelligence acquisition and analysis. (4) the problem of enterprise competitive intelligence acquisition based on Web log is studied, and the framework of competitor analysis based on Web user behavior log is given. Based on the actual Internet user behavior log, this paper analyzes the competitive relationship between e-commerce enterprises, which provides a new reference for the acquisition and analysis of Web competitive intelligence.
【学位授予单位】：中国科学技术大学
【学位级别】：博士
【学位授予年份】：2013
【分类号】：TP393.09

【相似文献】