【摘要】 由于医疗数据中含有大量患者的隐私信息，为降低隐私数据的泄露风险，提出了一种基于联邦优化算法的传染病风险评估模型。该模型以复杂网络理论为基础，从网络视角对确诊病例之间构建联系，使用联邦学习对风险评估模型进行学习训练，保证模型的训练效果。实验结果表明，该模型在保护患者隐私的前提下构建了分布式风险评估及自动预警机制，能够有效进行传染病预警。更多还原

【Abstract】 Medical data contains a lot of private information about patients. An infectious disease risk assessment model based on federal optimization algorithm is proposed to reduce the risk of privacy data disclosure. Based on complex network theory, the study constructs the model to connect confirmed cases from the perspective of network, and uses federated learning to train the risk assessment model to ensure the training effect of the model. The experimental results show that the model builds a distributed risk assessment and automatic early warning mechanism under the premise of protecting the privacy of patients. It can effectively conduct early warning of infectious diseases.更多还原