In order to study the influence of high temperature on the residual strength and microstructure evolution of hybrid fiber reinforced concrete (HFRC), the basic mechanical properties of HFRC at different temperatures were tested. The microstructure of the interface between fiber and cement paste was studied by scanning electron microscopy and the compressive strength of HFRC after different heat treatment temperatures was predicted by BP neural network. The results show that the synergistic effect of fiber significantly improves the high temperature resistance of concrete, and the compressive strength and splitting tensile strength of HFRC are higher than those of plain concrete after high temperature. The compressive strength and splitting tensile strength of HFRC reach the maximum value when the volume fraction of cellulose fiber and basalt fiber is 0.15%. The internal structure of HFRC is dense, and the basalt fiber is filled in the pores and has good bonding with the matrix, which effectively inhibits the crack propagation. The prediction data based on neural network matches with the experimental data, and the BP neural network well predicts the compressive strength of HFRC after high temperature.