Patent retrieval method, storage medium and device

The invention discloses a patent retrieval method, a storage medium and a device, and relates to the technical field of computers. The method comprises the steps of performing semantic and surface information feature extraction on a to-be-retrieved patent according to a pre-established neural network model, and splicing an obtained semantic feature vector and an obtained surface information feature vector to obtain a fused feature vector; and matching patents of which the similarity meets a preset similarity condition from a preset feature database according to the fused feature vector to obtain a retrieval result. The method is suitable for retrieval of similar texts of patent documents, accurate retrieval results can be obtained, relevance between different patents can be fully mined, and therefore the credibility of the retrieval results is improved. 本发明公开了用于专利的检索方法、存储介质及装置，涉及计算机技术领域。该方法包括：根据预先建立的神经网络模型分别对待检索专利进行语义和表面信息的特征抽取，将得到的语义特征向量和表面信息特征向量进行拼接，得到融合特征向量；根据融合特征向量从预设的特征数据库中匹配相似度满足预设相似度条件的专利，得到检索结果。本发明适用于