Transfer learning(TL) aims to solve related but different target domain problems by using plenty of labeled source domain data. When the task from one new domain comes, new domain samples are relabeled costly, and it would be a waste to discard all the old domain data. Therefore, an algorithm called TL-SVM based on the SVM algorithm is proposed, which uses a small amount of target domain tag data and a large number of source domain old data to build a high-quality classification model. The method inherits the advantages of the maximum interval SVM based on empirical risk minimization and makes up for the defects that traditional SVM can not migrate knowledge. Experimental results show the effectiveness of the proposed algorithm.