Intelligent diagnosis method and system based on intelligent elevator operation system

The embodiment of the invention provides an intelligent diagnosis method and system based on an intelligent elevator operation system, and the method comprises the steps: enabling a machine learning network to be applied to the saliency feature extraction of system operation state time sequence data; abnormal diagnosis point matching and labeling are performed on the saliency response diagram of the machine learning network according to the saliency feature data of the machine learning network, so that influence factors of a certain saliency feature extraction rule in the machine learning network can be prevented from being excessively aggregated, and the reliability of saliency feature extraction is improved; and the reliability of subsequent system abnormal point output is improved. 本发明实施例提供了一种基于智能电梯运行系统的智能诊断方法及系统，将机器学习网络应用于系统运行状态时序序列数据的显著性特征提取中，通过依据机器学习网络的显著性特征数据对机器学习网络的显著性响应图进行异常诊断点匹配与标注，可以避免机器学习网络中某种显著性特征提取规则的影响因子过于聚集，从而提高显著性特征提取的可靠性，进而提高后续系统异常点输出的可靠性。