US 12,252,136 B2
Warning method and apparatus for driving risk, computing device and storage medium
Chen Hou, Guangdong (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Guangdong (CN)
Filed on Oct. 18, 2022, as Appl. No. 17/968,341.
Application 17/968,341 is a continuation in part of application No. PCT/CN2021/114418, filed on Aug. 25, 2021.
Claims priority of application No. 202011105843.X (CN), filed on Oct. 15, 2020.
Prior Publication US 2023/0048112 A1, Feb. 16, 2023
Int. Cl. B60W 40/09 (2012.01); B60W 50/14 (2020.01); G06V 20/59 (2022.01)
CPC B60W 40/09 (2013.01) [B60W 50/14 (2013.01); G06V 20/597 (2022.01); B60W 2050/146 (2013.01); B60W 2420/403 (2013.01); B60W 2556/10 (2020.02)] 16 Claims
OG exemplary drawing
 
1. A warning method for a driving risk, performed by a computing device having a display function, the method comprising:
obtaining driving behavior data, which are related to preset driving behaviors of a driver, in a first time period, and obtaining a correspondence between a quantity of occurrences of preset driving behaviors of one or more drivers and a quantity of actual occurrences of preset scenarios to the one or more drivers while driving;
predicting, based on a quantity of actual occurrences of the preset driving behaviors of the driver, indicated in the driving behavior data of the driver, and the correspondence, a target quantity of times the driver is predicted to encounter one or more preset scenarios in the first time period;
generating warning information based on the target quantity of times; and
providing, using the display function, the warning information to the driver,
wherein the obtaining the driving behavior data comprises:
obtaining a driver image collected by a first in-vehicle camera in the first time period;
by using a pre-trained image recognition model that is trained to recognize facial features that are related to states of face parts and behavioral features that are related to movements of body parts, recognizing a quantity of actual occurrences of different types of preset driving behaviors in the driver image based on types of the preset driving behaviors; and
obtaining the driving behavior data based on the recognized quantity of the actual occurrences,
wherein the generating warning information based on the target quantity of times comprises:
determining warning probabilities respectively corresponding to different preset scenarios based on the target quantity of times; and
determining at least one preset scenario for warning based on the warning probabilities, and generating the warning information based on the at least one preset scenario for warning, and
wherein, when two or more preset scenarios for warning are determined, the providing the warning information comprises displaying the two or more preset scenarios in a form of a list in which each of the two or more preset scenarios is shown in association with a corresponding predicted target quantity of times, the list being arranged in a manner such that a preset scenario having a higher warning probability is preferentially displayed in the list than a preset scenario having a lower warning probability.