路径挖掘方法、装置、电子设备与存储介质
By combining time series forecasting models with real-time and historical data, the problem of insufficient accuracy in predicting popular routes in existing route planning technologies has been solved, enabling efficient route mining and scheduling optimization for instant logistics delivery.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- RAJAX NETWORK &TECHNOLOGY (SHANGHAI) CO LTD
- Filing Date
- 2022-12-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately predict popular routes in route planning, leading to low delivery efficiency, especially in on-demand delivery services. Current methods rely on historical order averages for prediction, which is neither accurate enough nor computationally expensive.
A path mining method based on time series prediction model is adopted. By obtaining the real-time order volume of candidate paths and inputting it into a trained machine learning model, the future order volume of the route is predicted, thereby identifying popular paths. The model integrates historical order volume and weather features to improve prediction accuracy.
It enables precise discovery and differentiation of popular routes, improving the efficiency of instant logistics delivery and the accuracy of the scheduling system, and supporting differentiated control.
Smart Images
Figure CN116307310B_ABST