作 者: ;
机构地区: 广东工业大学华立学院
出 处: 《计算机技术与发展》 2019年第12期99-103,共5页
摘 要: 对智能家居物联网用户的行为模式进行准确有效的挖掘,提高智能家居物联网的优化组网能力,实现智能家居的优化控制,提出一种基于大数据的智能家居物联网用户的行为模式挖掘方法。构建智能家居物联网用户行为模式的大数据分析模型,采用模糊调度方法对用户行为特征进行关键行为特征点定位,采用资源标识方法进行用户行为模式自适应标定和状态重组,建立用户行为模式的大数据分类模型。根据用户行为特征的聚类性实现智能家居物联网用户行为特征挖掘和自适应聚类,采用极限机学习算法进行智能家居物联网用户行为模式挖掘的收敛性控制,提高用户行为模式挖掘的自适应性。仿真结果表明,采用该方法进行智能家居物联网用户的行为模式挖掘的准确性较高,挖掘过程的收敛性较好。 The behavior pattern of smart home users are accurately and effectively excavated to improve the networking capability of the intelligent home Internet of things and to realize the optimal control of intelligent home.A method of mining the behavior pattern of smart home users based on big data is proposed.We construct a big data analysis model of smart home user behavior pattern,use fuzzy scheduling method to locate the key behavior feature points of user behavior characteristics,and adopt resource identification method to self-adaptively calibrate and reorganize user behavior mode.The big data classification model of user behavior pattern is established,and user behavior feature mining and adaptive clustering are realized according to the clustering of user behavior characteristics.The limit machine learning algorithm is used to control the convergence of user behavior pattern mining in the Internet of things in smart home,and the self-adaptability of user behavior pattern mining is improved.The simulation shows that the proposed method is accurate and convergent.