Abnormality detection method, device, smart device and storage medium

Abstract

The invention discloses an abnormality detection method, device, intelligent equipment and storage medium. Wherein, the method includes: when the smart device executes the target task, acquiring a scene image of the scene to be detected, wherein the scene to be detected is a scene corresponding to a preset target task that requires abnormal detection; according to the scene image of the scene to be detected, Anomaly detection for workflows where smart devices execute targeted tasks. The method can enable the smart device to have its own workflow anomaly detection function, to ensure that the smart device can provide effective services, and human detection is not required in the whole process, which greatly reduces labor costs.

Description

technical field [0001] The present invention relates to the field of intelligent equipment control, in particular to an abnormality detection method, device, intelligent equipment and computer-readable storage medium. Background technique [0002] With the continuous improvement of people's living standards, smart devices (such as intelligent robots in anthropomorphic form, mechanical arms, etc.) are more and more used in people's lives and services to achieve various interactions with humans. At present, when designing smart devices, more consideration is given to how to solve the interaction between devices and people. For example, in interactive methods such as touch screen and voice, smart devices will obtain feedback information from users to determine the next workflow. [0003] When smart devices provide services for users, they also interact with other things in the environment. The perception of interactive scene information is equally important, and even directly a...

AI Technical Summary

Problems solved by technology

However, various situations may occur in this interaction scenario due to external reasons. For example, after the robot arm presses the button of the milk cabinet, the milk tube on the milk cabinet does not produce milk, while the smart device in the prior art In the absence of a corresponding anomaly detection strategy, the anomaly detection of the robotic arm is usually achieved through manual monitoring, which often wastes a lot of labor costs and weakens the intelligence of the robotic arm.

Images