Making security recommendations

Embodiments of a method are disclosed. The method includes determining a plurality of recommended actions based on the security accident using an action model trained to make recommendations. The method further includes determining a plurality of targets similar to the target of the security accident using a collaborative filtering model trained to assign confidence values of similarity between the two targets. The method further includes assigning a plurality of weights to the recommended action based on the one or more actions taken by the similar target and the confidence value, and a success or failure of the recommended action. In addition, the method includes generating a prioritized list of recommended actions ordered based on the assigned weights. 公开了一种方法的实施例。该方法包括：使用被训练以做出推荐的动作模型，基于安全事故来确定多个推荐动作。该方法还包括：使用被训练以分配两个目标之间的相似性的置信度值的协同过滤模型，确定与安全事故的目标相似的多个目标。该方法还包括：基于以下各项将多个权重分配给推荐动作：由相似目标采取的一个或多个动作和置信度值，以及推荐动作的成功或失败。另外，该方法包括：生成基于所分配的权重排序的推荐动作的优先化列表。