With current enabling technologies and cutting-edge applications and implementations of Digital Twin (DT) in the Architecture, Engineering, and Construction (AEC) industry, there are still various significant knowledge gaps that must be addressed through continuing study to make DT more capable, dependable, and practical in real-world applications. Recent years have seen a rise in the use of deep learning (DL) technologies in conjunction with advanced semantic modelling technologies in empowering DT with cognition capabilities. The notion of Cognitive Digital Twin (CDT) has emerged in numerous recent studies and is regarded as a potential development trend for the field of DT. The purpose of this chapter is to study Construction 4.0-based Digital Twins and to examine the CDT's vision and characteristics.