The application of GCN algorithm in Building Construction Knowledge Graph updating under the combination of artificial intelligence and knowledge management

作者：Lü He, Hu Xu · 发表于：International Journal of Cognitive Computing in Engineering · 年份：2024 · DOI：10.1016/j.ijcce.2024.11.001 · 被引用次数：7 · 研究领域：Educational Technology and Pedagogy、Advanced Decision-Making Techniques、Advanced Computational Techniques and Applications

• Deep learning and computer vision integration: Research combines deep learning and computer vision technology to improve knowledge graph updating in building construction applications. • Zero sample learning technology: Utilizes zero sample learning technology to enhance prior information in updating knowledge graphs, showing better performance during the update iteration of the backward process. • Performance analysis: The zero sample action recognition model achieves peak TOP-1 accuracy of 99 %, 53 %, and 86 % at different data proportions. The zero sample object detection model attains peak TOP-1 accuracy of 77 %, 30 %, and 45 %, respectively. To promote the updating and iteration of the construction field, the construction knowledge graph can expand the professional knowledge system within the field and provide scientific and reasonable management decisions. The research adopts deep learning technology to update the knowledge graph in computer vision. The specific update method is to extract entities and analyze entity relationships in the framework of the knowledge graph, to achieve the application of the knowledge graph in the field of construction. Afterwards, a graph convolutional neural network is used to integrate semantic information and construct a network model of semantic embedding vectors. Finally, zero sample learning technologies are combined to enhance prior information during the construction process, thus demonstrating a better backward process for updat...