Toward a federated cross-organizational construction safety knowledge recommendation: A dual-incentive mechanism integrating worker satisfaction

Despite the effectiveness of personalized safety knowledge enhancement training, existing research overlooks the challenges posed by fragmented worker data and strict privacy regulations. To overcome these challenges, this study proposes a novel FedCSKR framework aimed at achieving privacy-preserving cross-organizational construction safety knowledge recommendation (CSKR). Nonetheless, the effectiveness of CSKR depends on the decisions of both requesters and providers. We develop a game model to capture their interactions and show, through evolutionary analysis, that spontaneous collaboration is unsustainable, leading the system to a noncooperative equilibrium without external incentives. To promote cooperation, we propose a dual-incentive mechanism that integrates model training performance with worker satisfaction, encouraging providers to allocate more resources to safety knowledge recommendation. Modeling and simulations show that the dual-incentive mechanism yields stronger incentive intensity, higher provider effort, and greater requester benefits versus single-model training incentives, while remaining robust across cost and risk variations. Specifically, incentive intensity can be increased by over 98.3% and provider effort levels by more than 197.4%, while simultaneously helping to mitigate the requester's exposure to uncertainty arising from model performance variability. Theoretical contributions of this study include the integration of federated learning with incentive-driven contract design in CSKR, representing the first effort, to our knowledge, that incorporates worker satisfaction into the incentive mechanism of the FedCSKR. Practically, this study offers a structured decision-making framework to assist construction managers in implementing privacy-compliant, effective, and collaborative CSKR. Overall, this study facilitates cross-organizational collaboration in CSKR and contributes to advancing personalized safety training.