Objective Taking pig kidney as an example, through a series of comparative and analogical experiments, this paper analyzes the influencing factors of the change of the pressure stress in the relaxation stage of biological tissue, and establishes a more accurate and widely applicable biomechanics model of the relaxation stage. Methods The stress relaxation experiments of pig kidney under different conditions were carried out by using the self built mechanical experiment platform. The collected data were analyzed and mapped, and various factors affecting the change of relaxation force were summarized. Based on the conclusion, the neural network learning algorithm is used to model the force change process in the relaxation stage of pig kidney. Results The analysis of the experimental data shows that the pre extrusion pressure and relaxation time are the main influencing factors of the stress change in the relaxation stage of biological tissue. The results of model validation experiment show that the average error of test sample validation experiment is 0.0064N, the average prediction error of generalization sample validation experiment is 0.0349N, so the modeling effect is good. Conclusions Neural network modeling algorithm has the advantages of strong generalization ability and good fault tolerance, which is conducive to provide more realistic force tactile feedback prediction for virtual surgery system. It is also a new idea for nonlinear biological tissue mechanics modeling.