一种基于综合特征的服务分类方法  

A Service Classification Method Based on Comprehensive Features

作　　者：戴磊[2] 张立伟[2] 常浩伦 王芸 李玉辉 DAI Lei;ZHANG Li-wei;CHANG Hao-lun;WANG Yun;LI Yu-hui(CETC Ocean Information Co.,Ltd,Beijing 100041,China;China Academic of Electronics and Information Technology,Beijing 100041,China)

机构地区：[1]中电科海洋信息技术研究院有限公司,北京100041 [2]中国电子科学研究院,北京100041

出　　处：《中国电子科学研究院学报》2019年第12期1259-1263,共5页Journal of China Academy of Electronics and Information Technology

基　　金：海南省重点研发计划(ZDYF2017006)。

摘　　要：集成和优化网络服务资源是生成网络信息体系能力的重要手段。当前,服务发现和组合正向着智能化、自动化方向发展,而服务分类作为对未定义服务进行描述的关键技术,仍然面临着服务特征数据维度过高、建模周期过长等问题。本文面向高维、稀疏的服务语义及文本数据,提出了一种基于综合特征高效服务分类器建模方法。实验结果表明所述方法能够大幅消减冗余及无关数据,对分类结果无负面影响,更适用于复杂多变的网络信息体系环境。Gathering and optimizing network service resources is an important means to generate the abili・ty of network information system.At present,service discovery and composition are developing towards intelligence and automation Service classification has become the key technology for describing undefined services.However,there are still problems such as high data dimension and long modeling cycle.In this paper,an efficient service classifier modeling method based on comprehensive features is proposed for high-dimensional and sparse text and semantic information combined with data dimension reduction technology.The experimental results show that the proposed method can greatly reduce redundant and irrelevant data,and has no negative impact on the classification results.It is more suitable for dynamic network information system environment.

关 键 词：语义服务 服务分类 特征选择 卡方检验 C4.5决策树 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]