Fraud identification method and device, electronic equipment and computer readable storage medium

The invention provides a fraud identification method and a device, electronic equipment and a computer readable storage medium. The method is applied to the technical field of knowledge maps. The method comprises the following steps: extracting topological characteristics of the target credit main body; therefore, the differentiated information of the entity nodes in the graph structure and the heterogeneous structure of the association relationship can be better reserved, in addition, the fraud probability of the target credit main body is identified based on the combined characteristics of the target credit main body determined by the attribute characteristics and the topological characteristics, and the accuracy and reliability of fraud identification are improved. 本申请提供了一种欺诈识别方法、装置、电子设备及计算机可读存储介质，应用于知识图谱技术领域，其中该方法包括：提取目标信贷主体的拓扑特征，从而能更好的保留图结构中实体节点的差异化信息及关联关系的异构结构，此外，基于由属性特征与拓扑特征确定的目标信贷主体的组合特征，进行目标信贷主体欺诈概率的识别，提升了欺诈识别的准确性与可靠性。