In order to quickly and accurately find the radar knowledge and information that researchers are interested in and make recommendations from a large number of radar knowledge data, 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, multi-modal feature extraction, multi-modal feature fusion, and radar knowledge recommendation. Extensive experiments demonstrate that, compared to the existing methods using only single-modal features and simple concatenation of multi-modal features, the multi-modal fusion features learned by the proposed method achieves significant improvement in precision, recall, and F₁ value for radar knowledge recommendation, suggesting its effectiveness for radar knowledge recommendation.