Service processing control system, method and device

Abstract

The invention relates to the technical field of cloud. The invention particularly relates to a service processing control system, method and device. The system comprises an end side module, a plurality of access layer modules and a background service module, wherein the end side module adjusts a first processing strategy for the behavior track data according to the network transmission performance; the access layer modules adjust a forwarding strategy sent to a message queue according to the processing performance of the background service module; the background service module adjusts a secondprocessing strategy for processing each associated task request according to the behavior track data according to the processing performance; thus, through the scheduling strategy of each module in the system, the behavior track data production, sending, consumption speed and the like can be effectively controlled, the overall resource utilization rate of the system is improved, and the availability and performance of the system are improved.

Description

technical field [0001] The present application relates to the field of cloud technology, and in particular to a business processing control system, method and device. Background technique [0002] At present, computer vision (ComputerVision, CV) technology is more and more widely used. For example, it is applied in smart security, smart community, smart retail and other fields. It mainly captures real-time video streams through cameras, and then processes them through related CV algorithms. Send it to the background cloud server for face recognition, human body recognition, etc., and then complete a series of processes such as identity filing, face retrieval, and human behavior trajectory. The CV application system in the smart retail scene in related technologies relies entirely on one access layer services, and adopts the method of direct reporting and direct processing by the background cloud server, which reduces the performance and availability, data processing cannot b...

AI Technical Summary

Problems solved by technology

[0002] At present, computer vision (ComputerVision, CV) technology is more and more widely used. For example, it is applied in smart security, smart community, smart retail and other fields. It mainly captures real-time video streams through cameras, and then processes them through related CV algorithms. Send it to the background cloud server for face recognition, human body recognition, etc., and then complete a series of processes such as identity filing, face retrieval, and human behavior trajectory. The CV application system in the smart retail scene in related technologies relies entirely on one access layer services, and adopts the method of direct reporting and direct processing by the background cloud server, which reduces the performance and availability, data processing cannot be guaranteed, and it is easy to cause the computing resources to be exhausted quickly during the peak period, and the computing resources are in the idle state when they are idle. Very low utilization state, reducing resource utilization

Images