公开(公告)号：US20240083438A1

公开(公告)日：2024-03-14

申请号：US18486519

申请日：2023-10-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Qing SU ,  Wenxiao HU

IPC: B60W30/18 ,  B60W50/14

CPC classification number: B60W30/18163 ,  B60W50/14 ,  B60W2050/143 ,  B60W2050/146 ,  B60W2540/20 ,  B60W2552/53

Abstract: A vehicle control method and apparatus 10, and a vehicle 100 are provided. The vehicle 100 has a cross-solid-line lane change permission switch 16. When the cross-solid-line lane change permission switch 16 is in an on state, and a driver switches a turn signal switch to a state that a left turn signal or a right turn signal is on, the vehicle 100 can cross a solid line to change a lane.

公开(公告)号：US20240232628A1

公开(公告)日：2024-07-11

申请号：US18615655

申请日：2024-03-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Tao MA ,  Qing SU ,  Ying JIN

IPC: G06N3/08 ,  G06F7/14 ,  G06F8/71 ,  G06F18/214 ,  G06F18/22 ,  G06N3/044 ,  G06N3/045 ,  G06N3/082 ,  G06N5/04 ,  G06Q40/00 ,  G06V20/58

CPC classification number: G06N3/08 ,  G06F7/14 ,  G06F8/71 ,  G06F18/214 ,  G06F18/22 ,  G06N3/044 ,  G06N3/045 ,  G06N3/082 ,  G06N5/04 ,  G06Q40/00 ,  G06V20/58

Abstract: This disclosure provides methods and apparatuses for training a neural network model. One example method performed by a terminal device includes: obtaining annotation data of a service, wherein the service is to be processed by a first neural network model and a second neural network model, and wherein precision of the first neural network model is lower than precision of the second neural network model, training a second neural network model by using the annotation data of the service to obtain a trained second neural network model, and updating a first neural network model based on the trained second neural network model.

公开(公告)号：US20230072438A1

公开(公告)日：2023-03-09

申请号：US17981120

申请日：2022-11-04

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Tao MA ,  Qing SU ,  Ying JIN

IPC: G06N3/04 ,  G06F8/71 ,  G06K9/62 ,  G06N3/08 ,  G06N5/04 ,  G06F7/14

Abstract: This application provides a method for training a neural network model and an apparatus. The method includes: obtaining annotation data that is of a service and that is generated by a terminal device in a specified period; training a second neural network model by using the annotation data that is of the service and that is generated in the specified period, to obtain a trained second neural network model; and updating a first neural network model based on the trained second neural network model. In the method, training is performed based on the annotation data generated by the terminal device, so that in an updated first neural network model compared with a universal model, an inference result has a higher confidence level, and a personalized requirement of a user can be better met.