Disk fault prediction method and device, equipment and storage medium

The invention discloses a disk fault prediction method and device, equipment and a storage medium, and the method comprises the steps: obtaining the current attribute data of a to-be-tested disk; under the condition that a target classifier corresponding to the to-be-tested disk does not exist in a plurality of pre-trained target classifiers, obtaining a training set correspondingly used when each target classifier is trained; determining the similarity between the current attribute data and each training set; and processing the current attribute data by using a target classifier of which the similarity meets a first condition to obtain a fault prediction result of the to-be-tested disk. In this way, the generalization ability of the disk fault prediction function can be improved. 本申请公开了磁盘故障预测方法及装置、设备、存储介质，其中，所述方法包括：获取待测磁盘的当前属性数据；在预先训练得到的多个目标分类器中没有所述待测磁盘对应的目标分类器的情况下，获取训练每一所述目标分类器时对应使用的训练集；确定所述当前属性数据与每一所述训练集之间的相似度；利用相似度满足第一条件的目标分类器，对所述当前属性数据进行处理，以得到所述待测磁盘的故障预测结果；如此，能够提高磁盘故障预测功能的泛化能力。