The challenges facing precise prevention and control stem from the need to innovate the design of health codes.
This article raises questions about the phenomenon of "excessive measures" (often referred to as "adding layers on top") currently observed in epidemic prevention efforts. It argues that simply increasing the number of health codes does not reflect precise control measures; instead, it creates administrative obstacles and wastes resources. The author points out that traditional health codes, which are binary (green/red), fail to quantify risk levels. Consequently, the article proposes establishing a dynamic infection probability model based on spatio-temporal trajectories and contact density, known as a "Safety Score" system. This system calculates the degree of spatio-temporal overlap between an individual and confirmed cases, and recursively updates each person's infection probability by incorporating nucleic acid test results, thereby replacing static administrative codes. This quantification mechanism enables precise epidemic prevention: individuals with low risk can move freely, while those with high risk automatically trigger enhanced monitoring and nucleic acid screening. Furthermore, multiple negative test results can significantly lower an individual's risk score. The author emphasizes that while strict epidemic prevention is necessary, AI and big data should be leveraged to improve execution efficiency, replacing simple and crude "one-size-fits-all" policies to achieve scientific control at a lower social cost.