基于改进神经网络算法的微博热点预测系统设计  

Design of micro-blog hot spot prediction system based on improved neural network algorithm

作　　者：金海[1] JIN ttai(Chong Qing Normal University Foreign Trade and Business College, Chongqing 401520, China)

机构地区：[1]重庆师范大学涉外商贸学院,重庆401520

出　　处：《现代电子技术》2018年第12期157-160,共4页Modern Electronics Technique

基　　金：重庆师范大学涉外商贸学院重点科研项目(KY2015002)~~

摘　　要：针对传统预测系统一直存在预测结果不准确、系统稳定性差的问题,提出并设计了基于改进神经网络算法的微博热点预测系统,其硬件部分主要对数据采集模块、微博信息传播趋势分析模块、微博热点判别模块进行了分析并设计,软件部分主要引进了改进神经网络算法,对原有系统进行了优化。实验结果表明,采用改进系统对微博热点进行预测时,其预测稳定性相比传统预测系统要优越,在相同时间内,出现波动的次数降低了2~4次,具有一定的优势。In allusion to the long-existing problems of inaccurate prediction results and poor system stability of the traditional prediction system,a micro-blog hot spot prediction system based on improved neural network algorithm is proposed and designed. For the hardware part of the system,the data acquisition module,micro-blog information propagation trend analysis module,and micro-blog hot spot discrimination module are mainly analyzed and designed. For the software part,the improved neural network algorithm is mainly introduced to optimize the original system. The experimental results show that the improved micro-blog hot spot prediction system has superior prediction stability than the traditional prediction system,and the number of fluctuations is reduced by 2~4 times within the same time,which has a certain advantages.

关 键 词：微博热点 预测系统 改进神经网络算法 数据采集 微博信息传播 预测稳定性 

分 类 号：TN911-34[电子电信—通信与信息系统]