We design a multi-label classification system based on a machine learning approach for the NTCIR-7 Patent Mining Task. In our system, we employ a lo-gistic regression model for each International Patent Classification (IPC) code that determines the IPC code assignment of research papers. The logistic re-gression models are trained by using patent documents provided by task organizers. To mitigate the overfitting of the logistic regression models to the patent docu-ments, we design the feature vectors of the patent doc-uments with feature weighting and component selec-tion methods utilizing a research paper set. Using a test collection for the Japanese subtask of the NTCIR-7 Patent Mining Task, we confirmed the effectiveness of our multi-label classification system.