A task scheduling method and device, electronic equipment and storage medium
By constructing an uncertainty matrix and sequence risk information, and combining entropy weight adaptive weighting, the problem of insufficient adaptability in existing task orchestration methods is solved, thereby improving the success rate and stability of task execution.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN SMARTCITY TECH DEV GRP CO LTD
- Filing Date
- 2026-06-16
- Publication Date
- 2026-07-21
AI Technical Summary
Existing task orchestration methods rely on static configuration and lack adaptive capabilities. Heuristic scheduling is prone to getting trapped in local optima, and single-dimensional evaluation metrics cannot fully characterize the task execution status, affecting the task execution success rate.
By generating uncertainty matrices and sequence risk information for multiple candidate task execution sequences, and combining them with entropy weight adaptive weighting, the target task execution sequence is selected, thereby improving the stability and adaptability of task orchestration.
It improves the success rate of task execution, reduces the possibility of risk misjudgment, and enhances the adaptability and stability of task orchestration.
Smart Images

Figure CN122431903A_ABST