The invention discloses a big data-oriented potential adverse drug reaction data mining system and method. The system comprises a plurality of acquisition terminals, an electronic medical record acquisition module, a specific drug data mining module, a cloud terminal adverse event data processing module, a cloud generation module, a main control computer, a human-computer interaction interface anda data switch, the method comprises the following steps: S1, networking electronic medical record systems of hospitals; S2, capturing a patient who takes the specific medicine in the electronic medical record system; S3, establishing a database of related drugs and adverse reactions after the drugs are used; S4, screening data; and S5, performing feature classification. According to the invention, adverse reactions of specific drugs are analyzed by integrating electronic medical records of various hospitals, the data source is wider, various populations exist, and the analysis of reactions ofdrugs relative to various populations is facilitated. Useless data can be eliminated in the analysis process, analysis is facilitated, the data analysis workload is reduced, and the sample accuracy is improved.