In order to quickly and accurately find the radar knowledge information of interest to researchers in a large number of radar knowledge information and recommend it, this paper proposes a multi-modal feature fusion radar knowledge recommendation method based on attention model, which can learn high-level fusion feature representation from multiple modalities for the radar knowledge. Then the radar knowledge recommendation can be performed using the learned fusion feature. The proposed method consists of four stages, i.e., data preprocessing, mult-modal feature extraction, mult-modal feature fusion, and radar knowledge recommendation. Extensive experiments demonstrate that, compared to the methods using only single-modal features and simple concatenation of multi-modal features, the multi-modal fusion features learned by our method achieves significant improvement in precision, recall, and F1 Value for radar knowledge recommendation. It shows that the multi-modal feature fusion method proposed in this paper is effective for radar knowledge recommendation.