Vehicle queue length prediction method and device
By acquiring the attribute data and time series of the target vehicle, and using XGBoost, LSTM and Transformer models to analyze vehicle queuing time, the problem of insufficient prediction accuracy and timeliness in existing technologies is solved, and more accurate vehicle queuing time prediction is achieved.
CN120218325BActive Publication Date: 2026-06-05内蒙古伊泰信息技术有限公司
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 内蒙古伊泰信息技术有限公司
- Filing Date
- 2025-03-11
- Publication Date
- 2026-06-05
Smart Images
Figure CN120218325B_ABST
Abstract
Embodiments of the present specification provide a vehicle queuing time length prediction method and device, wherein the vehicle queuing time length prediction method comprises: obtaining target attribute data corresponding to a target vehicle and a time sequence associated with entry behavior of the target vehicle, wherein the target attribute data refers to attribute data related to the target vehicle and affecting the queuing time length of the target vehicle, and the time sequence comprises a plurality of historical change data affecting the queuing time length of the target vehicle; based on the target attribute data, analyzing the association between the target attribute data and the queuing time length of the target vehicle, and predicting a first queuing time length; based on the time sequence, analyzing the change rule of the plurality of historical change data, and predicting a second queuing time length; and determining a target queuing time length of the target vehicle according to the first queuing time length and the second queuing time length. The multi-dimensional analysis of data is realized, and the accuracy of queuing time length prediction is improved.
Need to check novelty before this filing date? Find Prior Art