A task processing method based on a cloud management platform and a cloud management platform
By evaluating and prioritizing high-priority session tasks, the cloud management platform solves the problem of mutual interference between different session task processing processes, improving task processing efficiency and user experience.
CN122309047APending Publication Date: 2026-06-30HUAWEI TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUAWEI TECH CO LTD
- Filing Date
- 2024-12-30
- Publication Date
- 2026-06-30
AI Technical Summary
Technical Problem
When the cloud management platform schedules a large language model to process multiple session tasks, the processing of different session tasks interferes with each other, resulting in excessive processing time and affecting user experience.
Method used
The cloud management platform analyzes the characteristics and processing order of subtasks to evaluate the priority of each session task, prioritizes high-priority session tasks, releases computing resources to speed up processing, and manages even higher-priority tasks through video memory management.
Benefits of technology
It reduces the time users spend waiting for tasks to be processed, improves the user experience, and ensures that high-priority tasks are completed quickly.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122309047A_ABST
Abstract
This application discloses a task processing method based on a cloud management platform, as well as the cloud management platform itself, which can improve user experience. The method includes: a user sending a task processing request to the cloud management platform, the request indicating a first session task containing multiple first subtasks and a second session task containing multiple second subtasks. After obtaining a third subtask from the multiple first subtasks and a fourth subtask from the multiple second subtasks, the cloud management platform determines the time required to obtain the inference result of the first session task based on the processing order of the third subtask among the multiple first subtasks, and determines the time required to obtain the inference result of the second session task based on the processing order of the fourth subtask among the multiple second subtasks. If the time required to obtain the inference result of the first session task is less than the time required to obtain the inference result of the second session task, the cloud management platform can instruct the large language model to prioritize processing the third subtask.
Need to check novelty before this filing date? Find Prior Art