Association recommendation method based on audit knowledge graph and related equipment

The invention provides an association recommendation method based on an audit knowledge graph and related equipment. The method comprises the following steps: receiving query information input by a user; determining first associated information matched with the query information by using a pre-constructed audit knowledge graph; inputting the first associated information into a trained first deep learning model, and outputting second associated information associated with the first associated information through the first deep learning model; and recommending the first associated information and the second associated information to the user, so that the technical problem that the associated information recommended to the user based on the query information input by the user is not predictable in the prior art is solved, and the query efficiency of the user is improved. 本申请提供一种基于审计知识图谱的关联推荐方法及相关设备，所述方法包括接收用户输入的查询信息；利用预先构建的审计知识图谱确定与所述查询信息相匹配的第一关联信息；将所述第一关联信息输入至经过训练的第一深度学习模型，经由所述第一深度学习模型输出与所述第一关联信息相关联的第二关联信息；将所述第