METHODS FOR PREDICTING A VEHICLE'S DESTINATION

VN10062150BActive Publication Date: 2026-11-02GRABTAXI HOLDINGS PTE LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
VN1202207864
Authority / Receiving Office
VN · VN
Patent Type
Patents
Current Assignee / Owner
Filing Date
2020-04-30
Publication Date
2026-11-02
Estimated Expiration
2040-04-30
Patent Text Reader

Abstract

This invention proposes a method for predicting the destination location of a vehicle. This method includes processing a user's local preference graph with nodes corresponding to previously visited locations by a first-order neural network; processing one or more of the following: a spatial graph representing information about the geographical proximity of locations; a temporal graph representing information about locations visited sequentially and the time between visits; and a preference graph representing information about locations visited sequentially and the total number of visits by a second-order neural network. It also combines the results of the first-order neural network processing and the results of the second-order neural network processing using at least one neural network layer and uses the output of at least one neural network layer to predict the destination location.
Need to check novelty before this filing date? Find Prior Art