调度模型训练方法和装置、调度方法和装置
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
- Filing Date
- 2023-05-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies model the courier scheduling problem as a vehicle routing problem, which cannot effectively consider the road area division of orders, and the model solves slowly and is prone to getting trapped in local optima.
A reinforcement learning method is used to train the scheduling model. The simulation model is used to simulate road zone division and individual scheduling strategies. The decision model is combined to optimize the road zone division and individual scheduling strategies. The reinforcement learning method is used to adjust the model parameters to improve the accuracy and efficiency of the scheduling model.
It improved the efficiency of delivery personnel in delivering orders in different road areas, enhanced the accuracy and solution speed of the scheduling model, and avoided local optima problems.
Smart Images
Figure CN119047535B_ABST