Device-cloud collaborative processing method and device

Abstract

Embodiments of the present application provide a device-cloud collaborative processing method and device. In the embodiment of the present application, a task deployment component, a data stream processing component that supports device-side deployment, and a computing container that supports consistent device-cloud deployment cooperate to implement the device-cloud collaboration method. Specifically, the task deployment component provides a terminal for machine learning tasks. Deployment services between clouds. Data stream processing components are deployed on the device side to provide data services and trigger services for machine learning tasks. Compute containers provide a multi-end, end-cloud consistent operating environment and computing engine for machine learning tasks. Supports the execution of machine learning tasks. The embodiments of this application consider the characteristics of the device side and the cloud side, realize the complementary advantages of the device and the cloud, and provide a more real-time, more reasonable, and more secure collaborative service of the device and cloud seamless connection for mobile devices, so that machine learning tasks can be performed on the cloud side and the device. Works seamlessly between sides.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a device-cloud collaborative processing method and device. Background technique [0002] In recent years, the new generation of artificial intelligence (AI) technology represented by deep learning has developed rapidly, making continuous breakthroughs in the fields of image, speech, and natural language processing, and has gradually entered the stage of application landing. Cloud computing technology can provide massive computing, storage and other services for AI applications that rely on machine learning tasks. It has been widely used in language translation, speech recognition, big data, etc., so the machine learning tasks that existing AI applications rely on are usually Deployed on cloud-side devices. [0003] As the terminal-side device with the widest coverage of users, the most frequently used users, and the most abundant application scenar...

AI Technical Summary

Problems solved by technology

[0004] The existing method of centralized execution of machine learning tasks through cloud-side devices has problems such as poor real-time response and low utilization of device-side capabilities, especially when the computing power and storage capabilities of mobile devices have been significantly improved. The huge potential contained in it has not been fully utilized

Images