分类数据

Brings forward data classification model and hierarchical structure management model on the basis of analyzing the data types that needs to manage.

描述了PDM系统在企业中的应用和结构与配置管理在产品信息管理系统中的作用，分析了产品结构与配置管理的功能特点，并根据管理数据的类型，提出了数据分类组织和结构分层管理模型，同时简述了数据建模时应该兼顾的主要问题，最后给出了结构与配置管理模块的结构模型。

The concept and the classification of forecasting are addressed. Aiming at the disadvantages of the current forecasting models, such as requirement for more data and narrow application extent, an improved GM(1,1)-transfer function-noise model for forecasting is proposed. In the first stage, the GM(1,1) model improving the generation method of neighborhood system is adopted so as to fulfil the forecasting by only using a few of data.

介绍了预测的概念与分类；针对现有产品回收预测模型数据需求量大和适用范围窄的不足，提出了改进GM(1，1)/传递函数噪声两阶段预测模型；产品回收初期数据缺乏，主要采用改进了邻域系生成方法的IGM(1，1)模型，从而实现少量数据情况下的准确预测。

This paper introduces a modified fuzzy decision tree model. Firstly, the data are fuzzed by the use of optimal division point with optimal division entropy. Secondly, uncertainty theory of fuzzy math is introduced and a tree is built according to uncertainty of classification and creation rule. Finally, each unit can be detected about whether or not it is a fraud according to rule match method.

介绍了一种改进的模糊决策二叉树模型，即采用最优分割熵方法确定最优割点来对数据模糊化，引入模糊数学中的不确定性理论，依据分类的不确定性建造树，生成规则，在此基础上利用规则匹配的方法检测任意的样本数据是否为欺诈数据。

This thesis expatiates on the theory and architecture and primary content of Reusable Design technology and Reusable Process Design technology, study the feasibility and practicability of some important technology about Reusable Process Design, adopt a special knowledge representation to describe reusable process design information and make use of "FenHua "to realize knowledge acquisition about fuzzy knowledge.Craft database system is the mostly important support of CAPP (Computer Aided Process Planning) system. To some extent, the essence of process design is a process that craft data is visited, used, dealt with and generated. This thesis expatiates on data base design technology. Based on the detailed analysis of the craft data"s characteristic and sort and the craft database"s component part, the author build craft database through detailed conceptual design and logical design and physical design for data base.the application and research of Web database technology becomes increasingly wide, which can make a close combination between Database technology and Web technology.

本文阐述了基于知识复用的可复用设计技术与可复用工艺设计技术的理论、体系结构与主要研究内容，研究了可复用工艺设计中的若干关键技术的可行性、实用性，采用了三表知识表示来描述工艺知识及利用"分划"的方法对灰色知识进行知识获取；工艺数据库系统是计算机辅助工艺设计系统的重要支撑系统，从某种程度将，工艺设计的实质就是对工艺数据库中工艺数据的访问、调用、处理和生成新的数据的过程，本文阐述了数据库系统设计技术，在详细分析工艺数据的特点、分类以及工艺数据库的数据库组成的基础上，通过对工艺数据库概念结构、逻辑结构、物理结构等几个方面的详细的分析与设计，建立了系统工艺数据库； Web数据库将数据库技术和Web技术很好的融合在一起，其应用研究日益广泛。

The main work in this paper as follows: the concept and system of the network user's behavior has been studied, and the user has been classified by those in this basic; the frame, step, module function of establishing network user's behavior analyzing system has been discussed and some common methods in network customer's behavior analyzing process have also been discussed; the information source of the network customer's behavior analysis system has been studied in this paper, and also combined the relevant processes which came out by web data mining methods; the data-processing software was developed by VC and SQL Server 2000. The Web log data in SWUST campus network have been analyzed by gathering type and regression.

本论文主要工作如下：研究了网络用户行为的概念与体系，并在此基础上进行了用户分类；探讨了建立网络用户行为分析系统的步骤、框架和系统各模块的功能，以及网络用户行为分析过程中的一些常用方法；研究了网络用户行为分析系统的数据源，并结合Web数据挖掘方法提出了相应的处理方法；利用VC和SQL Server 2000开发了用于数据处理的软件；利用聚类和回归分析方法，研究了西南科技大学校园网中的Web日志数据。

In this thesis, we focus mainly on exploring index-based skyline algorithms. Taking full use of indexing technology, we study skyline computing in any subspace of high dimensional dataset, the problem of sampling the large-size skyline and skyline computing in categorial database.

利用索引技术，分别解决了高维数据集中任意子空间上的skyline计算问题，查询数据集上skyline点输出数目过多的问题以及分类属性数据集上如何高效、动态地算出其skyline的问题。

In this paper, it studied on data preprocessing including data cleaning, data conversion and data clustery, especially categorical variable with more characteristic item in data.

数据预处理备包括：数据清洗、数据转换以及变量聚类等，特别是对特征项过多的分类变量做了深入分析。

After reading and integrating lots of correlative science and technology books, the domestic and international research on CRM is summarized, and then the system frame is built. The conception of relative degree is proposed in the theory, which involves some methods in economics, such as the lifecycle curve of product or technology and the principle of time sequence, and so on. So the foundation for researching the system is built. Applying the technology of data warehouse and the correlative arithmetic of data excavating and method for classifying the clients, the resource analysis module is built,and the problem of data disposing and service management is resolved. The clear relationship of clients and sale strategy is obtained and the valuable client resource is grubbed up by analyzing the information of the clients. The enterprises will gain more clients and businesses opportunity, accordingly, the effect of less investment and more output.is attained.

通过阅读与综合大量相关科技文献，总结和分析了当前国内外对于CRM理论的研究现状，在此基础上建立了系统概念和总体框架；提出了裙带度的概念，融入了经济学中的产品或技术生命周期曲线、时间序列原理等方法，为系统的研究打下了理论基础；采用数据仓库技术、数据挖掘的相关算法以及客户分类方法，构建了资源分析模块，从而解决了数据处理和服务管理问题；通过对客户信息分析与处理，得到清晰的客户关系和营销策略，可以发掘出有价值的客户资源，将有助于企业得到更多的客户和商机，达到少投入、高产出的效果。

After reading and integrating lots of correlative science and technology books, the domestic and international research on CRM is summarized, and then the system frame is built. The conception of relative degree is proposed in the theory, which involves some methods in economics, such as the lifecycle curve of product or technology and the principle of time sequence, and so on. So the foundation for researching the system is built. Applying the technology of data warehouse and the correlative arithmetic of data excavating and method for classifying the clients, the resource analysis module is built,and the problem of data disposing and service management is resolved. The clear relationship of clients and sale strategy is obtained and the valuable client resource is grubbed up by analyzing the information of the clients. The enterprises will gain more clients and businesses opportunity, accordingly, the effect of less investment and more output.is attained.

通过阅读与综合大量相关科技文献，总结和剖析了当前海内外对于CRM理论的研讨现状，在此基本上树立了体系概念和总体框架；提出了裙带度的概念，融入了经济学中的产品或技术性命周期曲线、时光序列原理等方式，为体系的研讨打下了理论基本；采取数据仓库技术、数据挖掘的相关算法以及客户分类方式，构建了资源剖析模块，从而解决了数据处置和服务管理题目；通过对客户信息剖析与处置，得到清楚的客户关系和营销策略，可以挖掘出有价值的客户资源，将有助于企业得到更多的客户和商机，到达少投入、高产出的后果。

Although any unimodality type partially expresses limited semantics less or more, video semantics are fully manifested only by interaction and integration of any unimodal. Video data comprises plentiful semantics, such as people, scene, object ,event and story, etc. A great deal of research has been focused on utilizing multi-modality features for better understanding of video semantics. Proposed in this paper is a new approach to detect semantic concepts in video using co-occurrence data embedding, SimFusion, and locality preserving projections from temporal associated co-occurring multimodal media data in video.

该方法对所提取视频镜头的多模态底层特征，根据共生数据嵌入(co-occurrence data embedding)和相似度融合进行多模态子空间相关性传递而得到镜头之间的相似度关系，接着通过局部不变投影(locality preserving projections)对原始数据进行降维以获得低维语义空间内的坐标，再利用标注信息训练分类模型，从而可对训练集外的测试数据进行语义概念检测，实现视频语义信息挖掘。

Neither the killing of Mr Zarqawi nor any breakthrough on the political front will stop the insurgency and the fratricidal murders in their tracks.

在对危险的南部地区访问时，他斥责什叶派民兵领导人对中央集权的挑衅行为。

In fact,I've got him on the satellite mobile right now.

实际上 我们已接通卫星可视电话了