In order to solve the problem that deep learning defect detection methods require many labeled samples for training and insulator defect samples are difficult to obtain， a few-shot insulator defect detection method based on transfer learning was proposed. Firstly， an Efficient Multi-scale Attention （EMA） mechanism was added to the backbone network to enhance the model’s ability to represent target features. Secondly， a hierarchical sampling-based Region Proposal Network （RPN） was constructed to select anchors in the feature pyramid uniformly， thereby improving the model’s ability to capture new class objects at different scales. Finally， the classification heads were decoupled， and the positive and negative samples were processed by the positive and negative heads， respectively， so that the model was able to adapt to the new class of objects more effectively. Experimental results show that compared with the baseline method TFA （Two-stage Fine-tuning Approach）， on public dataset PASCAL VOC， the proposed method improves the mean Average Precision （mAP） （with IoU （Intersection over Union） of 0.5） of new class by 9.5 percentage points on average； on the insulator defect dataset， the proposed method has the mAP₅₀ in detection tasks of 1-shot， 5-shot， 10-shot， 20-shot， and 30-shot increased by 15.8， 12.2， 17.4， 7.3 and 7.1 percentage points， respectively.

As for the disadvantages of available user interests modeling methods in social tagging systems: always use a set of scattered tags to represent users' interests but ignore the combination use of tags, a new user modeling method was proposed, which introduced co-occurrence techniques into the naive approach. The proposed method added some tag pairs on the basis of naive approach to user model, which reflects tags relationship and considers tags weight. The experimental results on dataset PKDD2009 show that the new model can achieve a higher precision and recall rate, which outperforms the nave method and co-occurrence method.