基于用户画像的目标信息高精度推送仿真  

High-Precision Push Simulation of Target Information Based on User Portrait

作　　者：涂剑峰[1] 林立鑫 刘承启[3] TU Jian-feng;LIN Li-xin;LIU Cheng-qi(School of Information Engineering,Jiangxi University of Technology,Nanchang Jiangxi 330098,China;Network Information Center,Jiangxi University of Technology,Nanchang Jiangxi 330098,China;Office of Information Technology,Nanchang University,Nanchang Jiangxi 330031,China)

机构地区：[1]江西科技学院信息工程学院,江西南昌330098 [2]江西科技学院网络信息中心,江西南昌330098 [3]南昌大学信息技术办公室,江西南昌330031

出　　处：《计算机仿真》2023年第8期196-200,共5页Computer Simulation

基　　金：江西省教育厅科学技术研究项目(GJJ212011)。

摘　　要：信息精准推送性能过差会降低信息技术服务企业与用户之间的联系,使相关企业无法及时满足用户需求,为了给用户提供个性化服务,提出基于用户画像的信息精准推送模型。对单一数据来源和多样数据来源展开空间全方位、时间全过程的采集工作,获取贴合实际生活的用户信息,将用户信息与DVMD去噪方法结合,消除用户信息高频分量噪声,获取更为清晰的优化信息。将具备用户行为逻辑的优化信息作为用户画像,与支持向量机(SVM)和Storm、Storm steaming实时计算框架结合,建立信息精准推送模型。实验结果表明,所提方法用户满意度约为85%、且推送精度高。At present,the performance of accurate information push affects the relationship between enterprises and users of information technology services,making relevant enterprises unable to meet user needs in a timely manner.In order to provide users with personalized services,this paper designed a model for accurate information push based on user portrait.At first,the single data source and multiple data sources were collected in an all-round spatial and temporal way to obtain user information that was suitable for real life.Then,the user information was combined with DVMD denoising method to eliminate high-frequency component noise from user information,thus obtaining clearer information.After that,the optimized information with user behavior logic was used as a user portrait,and then it was combined with the support vector machine(SVM)and the real-time computing framework of Storm and Storm steaming to construct an accurate information push model.Experimental results show that the user satisfaction of the proposed method is about 85%,and the accuracy of information push is high.

关 键 词：用户画像 去噪 信息精准推送模型 关键词特征向量 支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]