In this study, using a one-step dynamic numerical analysis and optimization method, a tertiary model describing the growth of total viable count in sauced pig head meat was developed for real-time freshness prediction under fluctuating temperature (2–35 ℃). The validation results showed that the root mean square error (RMSE) of the prediction model for total viable count was 0.26 (lg(CFU/g)), and the residual mean and standard deviation were –0.047 (lg(CFU/g)) and 0.125 (lg(CFU/g)), respectively, which were within the normal experimental error range. The results of this study can be used to predict the changes of total viable count during cold chain and temperature abuse, and obtain a real-time freshness prediction model for pre-packaged sauced pig head at 2–35 ℃, thereby providing a theoretical basis for the real-time monitoring of the freshness of prepackaged sauced pig head at fluctuating temperatures.