At present, because the cuff method of blood pressure measurement cannot work in the high pressure environment, in order to solve the problem of blood pressure measurement in the high pressure environment, we proposed a k-Nearest Neighbor continuous non-invasive blood pressure prediction model combining pulse wave transit time and heart rate variability. In this study, rabbits were pressurized from normal pressure to a depth of 1000 m in a high-pressure chamber. During this process, electrocardiogram, photoplethysmography and invasive blood pressure of rabbits were collected. The average absolute error ± standard deviation of the k-Nearest Neighbor model for the prediction of the systolic and diastolic blood pressure and mean blood pressure of rabbit 1 is 2.2±1.5 mmHg and 1.9±1.4 mmHg, respectively. The results of SBP and DBP for rabbit 2 were 1.7±1.3 mmHg and 1.7±1.5 mmHg respectively. The results show that the method proposed in this paper achieves good results in predicting blood pressure of different individuals under high pressure environment, and provides ideas for blood pressure monitoring under high pressure.