摘要
为了提高社交网络用户浏览行为数据去冗检测能力,提出基于随机森林的社交网络用户浏览行为数据去冗方法.采用模糊度参数辨识的方法实现对社交网络用户浏览行为数据的特征提取,构建社交网络用户浏览行为数据统计模型,依据社交网络用户浏览行为推荐的约束参数,提高社交网络用户浏览行为数据的挖掘和检测能力,进行社交网络用户浏览行为数据的语义特征分解,采用随机森林学习算法实现对社交网络用户浏览行为数据的冗余信息滤波,结合形状相似性特征分析方法实现社交网络用户浏览行为数据的模糊信息融合,进行社交网络用户浏览行为数据去冗优化.仿真结果表明,采用该方法实现社交网络用户浏览行为数据挖掘的精度较高、数据去冗性能较优.
In order to improve the redundancy detection ability of social network users′browsing behavior data,a method for removing redundancy in social network user browsing behavior data based on random forest is proposed.The method of fuzzy parameter identification is used to extract the features of social network users′browsing behavior data.The statistical model of social network users′browsing behavior data is constructed.Improve the mining and detection capabilities of social network users′browsing behavior data based on the recommended constraint parameters of social network users′browsing behavior.This method decomposes the semantic features of social network users′browsing behavior data,and uses a random forest learning algorithm to achieve redundant information filtering of social network users′browsing behavior data.In addition,this method combines the shape similarity feature analysis method to achieve fuzzy information fusion of social network users′browsing behavior data.Use the above framework to optimize the browsing behavior data of social network users.The simulation results show that the proposed method has higher accuracy and better data reduplication performance.
作者
朱毓
ZHU Yu(Information Engineerin,Anhui Industry Polytechnic,Tongling Anhui 244000)
出处
《宁夏师范学院学报》
2021年第1期73-78,共6页
Journal of Ningxia Normal University
关键词
随机森林
社交网络
用户浏览行为
数据去冗
Random Forest
Social Networks
User Browsing Behavior
Data Reduplication
