挖掘

Based on cognition psychology and information entropy the author has proposed a simplifying algorithm that reduced the construction complexity degree.

2在粗糙集理论与挖掘算法的基础之上，研究了概念格的理论与知识表达方法，提出了具有完备性的分类知识的挖掘算法，构建了基于概念格的分类知识表达结构模型，并在认知心理学与信息熵的理论基础上，研究了降低概念格构造复杂度的简化算法。

Then, reductive dimension methods is analyzed and applied to documents classification.

文中给出了分类挖掘的形式化定义，分析了分类挖掘的基本机理。

In addition, the information which demonstrate the rule with high repetitiveness by data mining, though such information can help designer understand trend of the data, however, it is difficult to get the chance that hidden in the data.

另外，经资料探勘挖掘出的资讯是资料里呈现出重复性高的规则的资讯，虽然这样的资讯可以帮助决策者了解资料里的趋势，但是，却不容易去挖掘出隐藏在资料里的机会。

Then, after reviewing former research, we combine the solution of industry and academy, a new architecture called BWADM based on the researches above is proposed, it is a distributed data mining system based on Web services and Agent in Electronic commerce environment. Web service composition rules and execution of Web service composition are discussed. These modules are introduced detailedly in Electronic commerce environment; there are algorithm management module, control center module, algorithm database module and model representation module. Lastly, a prototype system of distributed data mining is given in Electronic commerce.

在此基础上，结合业界和学术界对Web服务和移动Agent的研究成果，将Web服务和Agent最新技术引入了电子商务环境中分布式数据挖掘，提出了电子商务环境下基于Web服务和移动Agent技术的数据挖掘架构BWADM，并论述了组合服务规范与组合服务的执行，具体阐述了此架构的数据预处理组件、算法管理组件、控制中心组件、算法库组件和模型表示组件。

based on fuzzy toolbox and ROSETTA with rough set to data mining of mass continuous attribute value is proposed.

针对大量连续属性值的数据挖掘，提出了一种基于模糊工具箱和ROSETTA软件的粗糙集数据挖掘方法。

Hence, it is an important challenge to develop efficient and scalable methods for XML data mining.

因此，开发出有效的针对XML的数据挖掘方法成为数据挖掘领域和XML技术领域的一项重要课题。

This algorithm preserved privacy of individual values by computing scalar product, meanwhile the algorithm of computing scalar product was given and the security was analyzed.

给出了数量积算法和隐私挖掘的步骤，最后举例说明了如何利用数量积算法进行垂直型分布式数据挖掘。

The contents contained data transformation, similarity match, prediction, classification, clustering, segmentation and visualization of time series.

在综合分析近年来时间序列数据挖掘相关文献的基础上，讨论了时间序列数据挖掘的最新进展，对各种学术观点进行了比较归类，并预测了其发展趋势。

The framework focuses on: Data fusion process; Knowledge presentation in communication network management; and, Frequent episode rule discovery in network alarm sequence. A frequent episode rule mining algorithm ERDISWIN (Episode Rule Discovery by Sliding WINdows) is provided.

在DFSKDS框架下，重点探讨了数据融合过程，适应于通信网络管理的知识表示方法，以及告警序列中的频繁情景规则挖掘，提出并实现了一种基于滑动窗口的情景规则挖掘算法ERDISWIN(Episode Rule DIscovery by S1iding WINdows)。

The first solution is how to set up the CRM system in enterp

第一个阶段的解决方案是如何从无到有来建立企业的CRM系统，第二个阶段的解决方案是对已有CRM系统并积累了大量客户交易原始数据的企业如何进行数据仓库的建设和数据挖掘，并在企业运作中应用数据挖掘的结果来提高企业的运作效率。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。