Video anomaly detection method and device, electronic equipment and storage medium

The invention provides a video anomaly detection method and device, electronic equipment and a storage medium, and relates to the technical field of computer vision. The method comprises the steps that a prompt sample set corresponding to a detection scene is acquired, the prompt sample set comprises at least one normal sample and at least one abnormal sample, the normal sample comprises a first sample video and first text description data corresponding to the first sample video, and the abnormal sample comprises a second sample video and second text description data corresponding to the second sample video; inputting the video features of the first sample videos, the text features of the first text description data, the video features of the second sample videos and the text features of the second text description data into a task coding model to obtain task codes; updating model parameters of the video anomaly detection model based on the task codes; and inputting video features of a to-be-detected video in