A medical institution dynamic risk early warning method, device and storage medium

Abstract

The application discloses a kind of medical institutions dynamic risk early warning method, equipment and storage medium.It relates to the field of intelligent medical technology.The method realizes the dynamic threshold early warning of load self-adaption based on quantile regression forest model by real-time acquisition equipment parameters;The influence score of the associated equipment is quantified using the pre-constructed knowledge graph;And with the help of digital twin model, fault injection simulation is carried out, the root cause is verified by comparing simulation data and real data, and finally accurate early warning information is pushed to the person in charge.The application solves the problem of high false alarm and missed alarm rate of traditional fixed threshold early warning, and realizes accurate and automatic fault diagnosis and early warning.

Images