QoS多层本体的双向度量模型

发布时间：2018-04-29 19:13

本文选题：多层本体 + 服务质量(QoS)度量　；参考：《计算机工程与应用》2017年20期

【摘要】：针对传统质量评估模式中指标权重赋值依据单一的问题,首先将服务描述本体分为共享本体和专属本体两个抽象层次,构建具有"抽象-应用-度量"多层结构的QoS本体,用于QoS度量的对象描述和数据采集;然后建立基于深度信任网络和回归模型的双向度量模型DM-QSM,将服务描述信息和类似服务历史数据作为训练样本数据集对DM-QSM进行正向训练,再结合用户反馈对DM-QSM进行逆向调优,以实现QoS度量指标权重及其偏好度的自适应调节。最后选用可编程建模环境NetLogo为实验平台、公共服务数据集QWS为训练样本集、电子商务应用服务为测试样本集,验证了DM-QSM的可行性和有效性。关键词:多层本体;服务质量(QoS)度量;深度信任网络
[Abstract]:Aiming at the single problem of index weight assignment in traditional quality assessment model, the service description ontology is first divided into two abstract levels: shared ontology and exclusive ontology, and a multi-layer QoS ontology with "abstract-application-metric" structure is constructed. The object description and data collection used for QoS measurement, and then a bidirectional measurement model DM-QSMbased on deep trust network and regression model is established. The service description information and similar service history data are used as training sample data set to train DM-QSM forward. Combined with user feedback, the DM-QSM is adjusted inversely to realize the adaptive adjustment of the weights and preferences of the QoS metrics. Finally, a programmable modeling environment (NetLogo) is chosen as the experimental platform, a common service data set (QWS) as a training sample set and an electronic commerce application service as a test sample set. The feasibility and effectiveness of DM-QSM are verified. Keywords: multilayer ontology; QoS metric; deep trust network
【作者单位】：重庆师范大学计算机与信息科学学院;加州大学河滨分校伯恩斯工程学院;重庆理工大学计算机科学与工程学院;
【基金】：重庆市科委科学技术研究项目(No.cstc2014jcyj A40034);重庆市教委科学技术研究项目(No.KJ1400525)
【分类号】：TP393.09

【相似文献】