首页> 外国专利> MEC Deep Learning Based Caching System and Method for Self-Driving Car in Multi-access Edge Computing

MEC Deep Learning Based Caching System and Method for Self-Driving Car in Multi-access Edge Computing

机译:多访问边缘计算中基于MEC深度学习的无人驾驶汽车缓存系统和方法

摘要

A caching system is disclosed. The caching system determines the caching content based on a first predicted value including an object requiring content provision and a probability of requesting the content from the object in an allocated area and a predicted rating of the content, and the determined A multi-access edge computing (MEC) server for caching and downloading caching content from a content provider, wherein the object is a k-means algorithm for the first predicted value and a second predicted value that is a predicted value for the user's characteristics of the object. And a recommendation module for identifying and recommending recommended contents among the caching contents by applying binary classification, and inquiring an available MEC server on the moving path of the object, and selecting the recommended contents among the available MEC servers. A caching system comprising a deep learning-based caching module for selecting an optimal MEC server to download and downloading and caching the recommended content from the optimal MEC server.
机译:公开了一种缓存系统。缓存系统基于第一预测值来确定缓存内容,该第一预测值包括需要内容提供的对象以及在分配的区域中从对象请求内容的概率以及该内容的预测等级,以及所确定的多访问边缘计算(MEC)服务器,用于从内容提供者缓存和下载缓存内容,其中,对象是针对第一预测值和第二预测值的k均值算法,第二预测值是针对对象的用户特征的预测值。以及推荐模块,用于通过应用二进制分类在缓存内容中识别并推荐推荐内容,并在对象的移动路径上查询可用的MEC服务器,并在可用的MEC服务器中选择推荐内容。一种缓存系统,包括基于深度学习的缓存模块,用于选择最佳MEC服务器以从最佳MEC服务器下载和缓存推荐内容。

著录项

  • 公开/公告号KR102148704B1

    专利类型

  • 公开/公告日2020-08-27

    原文格式PDF

  • 申请/专利权人 경희대학교 산학협력단;

    申请/专利号KR20180133873

  • 发明设计人 홍충선;은디쿠마나 안셀미;

    申请日2018-11-02

  • 分类号H04N21/433;G06N3/08;G06Q50/10;H04N21/414;H04N21/466;

  • 国家 KR

  • 入库时间 2022-08-21 11:03:58

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号