面向移动学习的云资源信息流无源定位技术

Technology of Passive Location for Cloud Resource Information of Mobile Learning

在移动学习过程中,需要对云资源信息流节点准确定位,提高网络学习效率,增强学习网络转换信道均衡能力。传统方法中采用基于向量随机学习的网络信道切换队列整合方法,实现对信任节点的定位,但当出现信任时隙局部性交叉项时,定位性能不好。提出一种改进的面向移动学习的云资源信息流无源定位技术。采用M-learning随机场学习模型,通过局部性交叉项补偿进行信息链单流量解析模型设计,在大数据环境下,对信任节点的数据种类进行无源定位分类,然后通过云资源信息流节点任务调度方法,提高网络的信任度,由此提高对云资源信息流的无源定位能力。仿真结果表明,该算法能有效提高对M-learning环境下的云资源信息流的定位精度,提高学习效率和资源分配能力。在学习资源共享调度等领域具有较好的应用价值。

In the process, the need for cloud resource information flow node position accurately, improve the network learning efficiency, enhance network conversion channel equalization ability of learning. Integration method of network channel handoff queue random vector based on learning by traditional method, realize the localization of the trust of nodes, but when local trust time slot cross terms, the positioning performance is not good. Put forward a kind of improved cloud resource information for mobile learning flow of passive location technology. Using the M-learning random field model of learning, through local cross term compensation information chain single flow analytical model design, in large data environment, type of data on trust node passive location and classification, and then through the cloud resource information flow node task scheduling method, enhancing the degree of belief network, thereby improving the passive location ability of cloud resources the flow of information. The simulation resuhs show that the algorithm can effectively improve the accuracy of localization of M-learning under the environment of cloud resource information flow, improve the learning efficiency and resource allocation. It has good application value in the fields of learning resource sharing scheduling.