A novel framework of knowledge transfer system for construction projects based on knowledge graph and transfer learning
作者：
Highlights：
• A framework to automatically and intelligently transfer project knowledge.
• Knowledge graph and transfer learning are combined for efficiently transfer.
• PBG-MMD algorithm outperforms traditional ways in measuring project similarity.
• deepTL_LSTM model has been evaluated by real data from 17 construction projects.
• “What to transfer” and “how to transfer” have been answered by this framework.
摘要
•A framework to automatically and intelligently transfer project knowledge.•Knowledge graph and transfer learning are combined for efficiently transfer.•PBG-MMD algorithm outperforms traditional ways in measuring project similarity.•deepTL_LSTM model has been evaluated by real data from 17 construction projects.•“What to transfer” and “how to transfer” have been answered by this framework.
论文关键词：Construction project,Knowledge transfer,Project similarity,Knowledge graph,Transfer learning
论文评审过程：Received 16 May 2021, Revised 18 March 2022, Accepted 20 March 2022, Available online 23 March 2022, Version of Record 25 March 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116964
