基于深度学习的情感化设计

Emotional Design Based on Deep Learning

目的使用深度学习实现情感化设计,满足用户个性化的情感需求,加速传统设计过程,提升用户体验。方法研究深度学习中可用于情感化设计的算法,使用卷积神经网络(CNN)实现名画复制品的个性化自动生成;抓取互联网数据,使用LSTM模型挖掘用户真实需求,进行当前流行游戏的周边产品设计;以张裕葡萄酒庄旅游纪念品设计为例,使用深度学习基于用户个人信息和行为数据推荐个性化的葡萄酒包装。结论基于CNN的名画复制品的个性化生成丰富了图像的可修改空间,满足了用户个性化的情感诉求;基于LSTM的用户需求分析高效和准确地反映了用户的真实需求,加速了传统用户调研过程;基于深度学习的旅游纪念品个性化设计进一步提升了用户体验。将深度学习应用于情感化设计有利于挖掘用户内心的真实需求,节省人力物力,满足用户情感诉求和提升用户体验,进一步为设计学与计算机科学的交叉提供了有效方法。

It applies deep learning methods to the emotional design, to meet the personalized emotional needs of users, to accelerate the traditional design process and to enhance the user experience. It studies the deep learning algorithms that can be used for emotional design. First, Convolutional Neural Network is adopted to realize the automatic generation of personalized replicas of famous paintings. Then, we crawl the Internet data and use LSTM model to analyze the user needs and design the current popular game peripheral products. Finally, taking the tourism souvenir design of Changyu winery as an example, the deep learning methods are used to recommend personalized packaging based on user＇s personal information and behavioral data. CNN based automatic generation of personalized replicas of famous paintings provides massive styles for image modification and meets the personalized emotional needs of users. LSTM based user needs analysis efficiently and accurately reflects the user＇s real needs and accelerates the traditional user research process. Deep learning based personalized design of tourist souvenirs further enhances the user experience. The application of deep learning in the emotional design is conducive to mine the user＇s real needs, greatly reduces labor costs, meets the user＇s emotional appeal and enhances the user experience. It provides practical methods for interdisciplinary research of computer science and design.