一种电力信息系统工期的计算方法
By constructing a task dependency graph and a reinforcement learning model, the completion time of task nodes is dynamically adjusted, solving the problem of the inability to accurately model the dependencies between tasks in existing technologies, and realizing accurate prediction of the project duration of power information systems.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG POWER GRID CO LTD INFORMATION CENT
- Filing Date
- 2025-07-01
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for estimating project duration in power information systems cannot effectively model the complex dependencies and collaborative development relationships between tasks, resulting in rigid resource allocation that cannot adapt to dynamic adjustments, large deviations in project duration predictions, and failure to meet the requirements of precise management.
Construct a task dependency graph, determine the dependency awareness features and resource status features of task nodes, use a reinforcement learning model to train through a composite reward function, generate a target scheduling scheme, dynamically adjust the completion time of task nodes, and finally determine the target project duration.
It achieves accurate capture of the inherent complexity of the project, outputs a more accurate and reliable target schedule, adapts to dynamic adjustment needs, and improves the accuracy and reliability of schedule prediction.
Smart Images
Figure CN120875331B_ABST