ABSTRACT

Digital twin models are computerized clones of physical assets or systems and have attracted much attention from academia and industries. Digital twin applications focus on smart manufacturing systems. Meanwhile, manufacturing products are driven increasingly by the needs of customers. Industrial production modes have evolved from mass production to personalized production. Understanding customers and meeting their personalized needs have become important issues in smart manufacturing. Social networks provide platforms for online customers to engage in different behaviors. In addition, personality recognition is a crucial issue for understanding people. In this study, a new technique is proposed to formalize personality as digital twin models by observing users’ posting content and liking behavior. A multitask learning deep neural network model is used to predict users’ personality through two types of data representation. Experimental results show that combining the two types of data can improve personality prediction accuracy.

摘要

数字孪生模型是物理资产或系统的计算机克隆，引起了学术界和工业界的广泛关注。数字孪生应用专注于智能制造系统。同时，制造产品越来越受到客户需求的驱动。工业生产模式已经从批量生产发展到个性化生产。了解客户并满足其个性化需求已成为智能制造中的重要问题。社交网络为在线客户提供了参与不同行为的平台。此外，个性识别是理解人的关键问题。在这项研究中，提出了一种新技术，通过观察用户的发布内容和喜欢行为，将个性形式化为数字孪生模型。多任务学习深度神经网络模型通过两种类型的数据表示来预测用户的个性。实验结果表明，结合两类数据可以提高个性预测的准确性。