Service instance deployment method and device, server and storage medium

By dynamically adjusting the number of service instances of the AI ​​service platform, and based on the request processing efficiency and expected amount, the problem of low computing resource utilization caused by the fixed number of instances is solved, and timely response to business party requests and efficient resource utilization is achieved.

CN119149198APending Publication Date: 2024-12-17BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411190244.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-12-17

Smart Images

  • Figure CN119149198A_ABST
    Figure CN119149198A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a service instance deployment method and device, a server and a storage medium, and relates to the technical field of computers.The method comprises the steps that efficiency description information of a first service is obtained, and the efficiency description information is used for describing the request processing efficiency of the first service; obtaining an expected quantity of to-be-processed requests of the first service and expected completion time consumption of the to-be-processed requests; determining an expected number of instances of the first service according to the efficiency description information, the expected number and the expected completion time consumption; and deploying instances of the first service based on the expected number. By applying the technical scheme provided by the embodiment of the invention, the service platform can respond to the service request of the business party in time, and the utilization rate of computing resources is improved.
Need to check novelty before this filing date? Find Prior Art