Behavior subject detection method and device, equipment, medium and program product

The invention provides a behavior subject detection method which can be applied to the technical field of artificial intelligence and finance. The behavior subject detection method comprises the steps that behavior data are acquired, the behavior data comprise carrier information and user information, and the carrier information represents software and hardware information of an implementation behavior; a pre-trained behavior detection model is adopted to classify the behavior data to obtain classification labels, and the behavior detection model is obtained based on behavior data feature fusion training of different dimensions corresponding to the behavior data. And determining an execution subject of the behavior according to the classification label. The invention further provides a behavior subject detection device and equipment, a storage medium and a program product. 本公开提供了一种行为主体检测方法，可以应用于人工智能和金融技术领域。该行为主体检测方法包括：获取行为数据，行为数据包括载体信息和用户信息，载体信息表征实施行为的软硬件信息。采用预先训练的行为检测模型对行为数据进行分类，得到分类标签，行为检测模型基于与行为数据相应的不同维度的行