摘要
为了解用户对仓储产品或服务的意见和满意度,提高仓储运营的效率和竞争力,提出基于卷积神经网络(Convolutional Neural Networks,CNN)的仓储评论数据分类系统。首先,爬取仓储评论数据,并进行处理;其次,构建改进的结合字符和词的双输入卷积神经网络模型(Improved Char and Phrase Convolutional Neural Networks,ICP-CNN),并对文本进行正负向情感分类;最后,利用Flask框架构建Web系统,实现界面的可视化展示。
To understand user opinions and satisfaction with warehouse products or services,improve the efficiency and competitiveness of warehouse operations,a warehouse comment data classification system based on Convolutional Neural Networks(CNN)is proposed.Firstly,crawl the warehouse review data and process it.Secondly,construct an Improved Char and Phrase Convolutional Neural Networks(ICP-CNN),and perform positive and negative sentiment classification on the text.Finally,use the Flask framework to build a Web system and achieve visual display of the interface.
作者
陈见飞
高军
杨世军
马越
狄广义
CHEN Jianfei;GAO Jun;YANG Shijun;MA Yue;DI Guangyi(Guoneng Digital Intelligence Technology Development(Beijing)Co.,Ltd.,Beijing 100011,China;Shandong Chengxin Engineering Construction Supervision Co.,Ltd.,Jinan Shandong 250098,China)
出处
《信息与电脑》
2024年第2期112-114,118,共4页
Information & Computer
关键词
卷积神经网络(CNN)
仓储评论数据
分类
Convolutional Neural Networks(CNN)
warehouse review data
classification