In order to study the relationship between the abnormal variations of earthquake precursory information and the occurrences of earthquakes, and also the correlations among precursory data subjects, taking the big earthquake in Wenchuan as an example, the four order Daubechies family wavelet is used to amplify the two layers of high frequency components so as to highlight the abnormal information of the signal; and then the abnormal signal of precursory data is quickly extracted with a sliding threshold method before binary processing; The minimum support and minimum confidence are set, and the Apriori method is used to calculate the strong and weak association rules between seismological events and the precursory subjects and also between various disciplines. The results show that the correlation between the earthquake and the east-west component of the electric field is stronger than that of other components. The vertical geomagnetic component is more sensitive to geomagnetic anomalies than the horizontal component, while in the Guzan-Seismic-Station where it is close the earthquake zone, a strong association rule was generated between the north-south component and the occurrence of earthquake event, indicating that the north-south strain component can better monitor the earthquake within certain range of the epicenter, providing a feasible approach for short-term earthquake forecasting.