基于关联关系的仿真模型实时智能推荐方法

发布时间：2018-01-15 21:22

本文关键词：基于关联关系的仿真模型实时智能推荐方法　出处：《工程科学学报》2017年04期 　论文类型：期刊论文

【摘要】：当全球导航卫星系统(global navigation satellite system,GNSS)分布式仿真环境中共享的模型数量非常多时,检索模型和配置仿真任务将成为一个比较复杂的工程.为提高仿真模型选取和仿真任务配置的效率,设计了一套针对GNSS分布式仿真环境中仿真模型的实时智能推荐方法,方法中首先定义了模型关联关系和接口形状的概念,然后提出了一种条件约束下的频繁模式树(FP-tree)结构,并从理论上分析了该结构在检索任务量方面的减少程度,设计并推导了模型关联关系度的计算方法,以及整套智能推荐方法的运行流程.推荐方法在GNSS分布式仿真环境中进行了仿真验证,仿真结果与传统智能推荐方法做对比分析,分析结果表明,该方法针对仿真模型推荐时运行时间短,推荐结果准确度高,能够实时为用户推荐合适的模型.
[Abstract]:When the global navigation satellite system (global navigation satellite system, GNSS) the number of sharing model of distributed simulation environment is very large, retrieval model and configuration simulation tasks will become a complicated project. In order to improve the efficiency of simulation model selection and Simulation of task allocation, designed a set of recommended methods according to the simulation of GNSS distributed simulation environment the model of real-time intelligent method, firstly defines the concept of relationship model and interface shape, and then propose a frequent pattern tree condition (FP-tree) structure, and analyzes the structure in the retrieval task quantity to reduce the degree from the theory, design and calculating method of relationship model the operation process and recommendation method. This intelligent recommendation method is verified by simulation in GNSS distributed simulation environment, the simulation results with the traditional intelligent push A comparative analysis of recommendation methods is carried out. The analysis results show that the proposed method is accurate and accurate when it is recommended for simulation models, and it can recommend suitable models for users in real time.

【作者单位】：北京理工大学宇航学院;宁夏大学机械工程学院;
【基金】：国家自然科学基金资助项目(61502257,41304031)
【分类号】：TN967.1;TP391.3
【正文快照】： 全球导航卫星系统(global navigation satellite sys-tem,GNSS)分布式仿真环境(GNSS distributed simula-tion environment,GDSE)是最近被提出来的一种GNSS仿真环境.该环境在面向互联网的前提下,结合了广义云计算(cloud computing,CC)核心理念——“对计算资源进行共享”[1-7]

【相似文献】