The classification of microseismic signals represents a fundamental preprocessing step in microseismic monitoring and early warning. A microseismic signal source rock classification method based on a convolutional neural network is proposed. First, the characteristic parameters of the microseismic signals are extracted, and a convolutional neural network is constructed for the analysis of these parameters; then, the mapping relationship model between the characteristic parameters of the microseismic signals and the rock class is established. The feasibility of the proposed method in differentiating acoustic emission signals under different load conditions is verified by using acoustic emission data from laboratory uniaxial compression tests, Brazilian splitting tests, and shear tests. In the three distinct laboratory experiments, the proposed method achieved a source rock classification accuracy of greater than 90% for acoustic emission signals. The proposed and verified method provides a new basis for the preprocessing of microseismic signals.