公开(公告)号：US10358142B2

公开(公告)日：2019-07-23

申请号：US15461468

申请日：2017-03-16

Applicant: QUALCOMM Incorporated

Inventor： Gregory Hobert Joe ,  Arthur James ,  Srdjan Miocinovic ,  Sandipan Kundu

IPC: B60W40/08 ,  B60W50/00 ,  B60W10/04 ,  B60W10/30 ,  B60W50/14 ,  A61B5/18 ,  A61B5/00 ,  A61B5/021 ,  A61B5/024 ,  B60K28/02 ,  B60K28/06 ,  B60W40/04 ,  B60W40/06 ,  B60W40/09 ,  G06N20/00 ,  G01S19/13 ,  H04L29/08

Abstract: A method for providing safe-driving support of a vehicle includes obtaining occupant data and vehicle data received at a vehicle hub. The occupant data is related to an identity and health status of an occupant and the vehicle data is related to a status of the vehicle. The method also includes obtaining action data based on an application of the occupant data and vehicle data to a machine learning safe-driving model. The machine learning safe-driving model is associated with a user profile of the occupant that is identified from among a plurality of user profiles based on the occupant data. A server maintains a plurality of user profiles, each having a respective machine learning safe-driving model. The action data relates to an action to be performed by the vehicle while the occupant is located in the vehicle.

公开(公告)号：US20180234302A1

公开(公告)日：2018-08-16

申请号：US15429482

申请日：2017-02-10

Applicant: QUALCOMM Incorporated

Inventor： Arthur James ,  Srdjan Miocinovic ,  Gregory Hobert Joe ,  Joel Linsky ,  Sandipan Kundu

IPC: H04L12/24 ,  H04L12/26 ,  G06N99/00

CPC classification number: H04L41/145 ,  G06N20/00 ,  H04L41/16 ,  H04L43/062 ,  H04L43/065 ,  H04L63/1408 ,  H04L67/12 ,  H04W4/80 ,  H04W84/18

Abstract: A method is described. The method includes receiving an event monitoring model generated by a machine learning engine. The event monitoring model is configured to classify network device behavior based on observed events. The method also includes monitoring events in a network based on the event monitoring model. Machine learning features are extracted from network traffic generated by one or more network devices. The method further includes determining a network device classification of the monitored events based on the event monitoring model. The method additionally includes sending the observed events and the network device classification to the machine learning engine to update the event monitoring model.