Multi-target software defect prediction method based on multi-task multi-view learning

The invention provides a multi-target software defect prediction method based on multi-task multi-view learning. Defects in to-be-detected codes with unknown defect conditions can be predicted based on historical codes with known defect conditions of target software. The problem that a traditional software defect prediction method can only complete one defect prediction target, and when different prediction methods are adopted for different defect prediction targets, the use complexity and resource consumption are large is solved, and the misinformation and missing report conditions of a static analysis tool can be effectively improved. Multi-view feature information including code measurement features, defect space structure features and defect typical semantic features can be extracted based on an integrated static analysis method. Through the constructed multi-task multi-view neural network model, the defect tendency, position and type prediction of the target code is completed, defect prediction informati