基于Web源的客户需求获取及分析方法  

Methodology of exploring and analyzing the VOC based on extensive web data source

作　　者：郭伟[1] 胡明艳[1] 

机构地区：[1]天津大学机械工程学院,天津300072

出　　处：《计算机集成制造系统》2004年第9期1165-1170,共6页Computer Integrated Manufacturing Systems

基　　金：国家863/CIMS主题资助项目(2003AA415220)。~~

摘　　要：为把握市场动态和了解客户需求,提出一种从广域网中及时获取及分析客户信息的方法。在对比分析分散式和集中式Web信息源优劣特征的基础上,提出了由集中式Web原始信息源到市场分析数据集间的映射关系,建立了以产品生命周期特征为基础的信息分析知识库以及相应的量化处理规则集。该方法基于所建立的知识库和分析规则,采用规则驱动的数据挖掘技术,首先进行原始Web信息单元特征定位分析,进而对信息单元中的客户需求进行词频统计分析和内容分析,以形成产品市场整体趋势以及系统的客户需求分布。最后结合典型行业的信息源进行了具体应用。In order to track the market trends and obtain full understanding of Voice of Customers (VOC), a new method of analyzing dynamic product information through the web media was presented. Based on the analysis of advantages/disadvantages of the distributed and concentrated web data source, a systematic mapping relationship, from the original web source to structured marketing data setting, was established. Then a knowledge base organized on features of Products' Lifecycle Stage (PLS), as well as the involved quantitative rules used in classifying the VOC information, was developed. So, the rule-driven data mining method was applied to identify the PLS classification of the original data cell. Furthermore the methods of frequency counting and content analyzing were conducted to the data cell consequently so that both market trend and a systematic understanding of VOC could be obtained. Finally, a detailed process was presented by using typical web data on automotive product.

关 键 词：源信息 客户需求 数据挖掘 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]