Software Defect Evaluation Methods for Embedded Real-Time Control System Based on Transfer Learning

In order to reduce the impact of environmental changes on software defect evaluation, an embedded real-time control system software defect evaluation method based on transfer learning is proposed. Firstly, the defect software measurement index is selected. On this basis, the relevant index features are divided into the same cluster by using the feature clustering technology. According to the distribution similarity of the features between the two items, the relevant features are found and the features with large distribution differences are removed. Select high-quality features from the source project to build the training data set, and select better evaluation data from the source project through weight adjustment to realize the accurate evaluation of software defects. The mapping results have clear objectives, and the error rate of the evaluation results of the design method is within 8.7, which has a good evaluation effect.