Warning method and apparatus for driving risk, computing device and storage medium

Patent metadata

Field	Value
Publication number	US-12252136-B2
Application number	US-202217968341-A
Country	US
Kind code	B2
Filing date	Oct 18, 2022
Priority date	Oct 15, 2020
Publication date	Mar 18, 2025
Grant date	Mar 18, 2025

Abstract

Embodiments of the disclosure provide a warning method and an apparatus for a driving risk, a computing device and a storage medium. In an embodiment, driving behavior data of a driver in a first time period is obtained, and a correspondence between a quantity of occurrences of preset driving behaviors of one or more drivers and a quantity of an actual occurrence of preset scenarios to the one or more drivers while driving is obtained. 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, it is predicted a target quantity of times the driver is predicted to encounter one or more preset scenarios in the first time period, and warning information is generated based on the target quantity of times.

First claim

What is claimed is:

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.

2. The method according to claim 1 , wherein the obtaining the correspondence comprises:
obtaining historical driving behavior data and historical preset scenario data of the driver in a historical time period;
determining a behavior historical quantity of times of different preset driving behaviors of the driver in the historical time period based on the historical driving behavior data of the driver;
determining a scenario historical quantity of times of different preset scenarios encountered by the driver in the historical time period based on the historical preset scenario data of the driver; and
obtaining the correspondence based on the behavior historical quantity of times and the scenario historical quantity of times.

3. The method according to claim 1 , wherein the warning information comprises the target quantity of times.

4. The method according to claim 1 , wherein the obtaining the driving behavior data further comprises:
obtaining the driving behavior data of the driver in the first time period from a second in-vehicle camera, the second in-vehicle camera being configured to collect a driver image, and generating the driving behavior data by performing preset driving behavior recognition on the collected driver image based on types of the preset driving behaviors.

5. The method according to claim 1 , wherein the method further comprises:
obtaining preset scenario data of a vehicle where the driver is in a second time period; and
predicting a prediction quantity of times of preset driving behaviors of the driver in the second time period based on a quantity of occurrences of preset scenarios involved in the preset scenario data and the correspondence.

6. A computing device, comprising: a memory and a processor;
the memory being configured to store a computer program; and
the processor being configured to execute the computer program to implement the warning method for a driving risk according to claim 1 .

7. A warning apparatus for a driving risk, comprising:
at least one memory configured to store program code; and
at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
first obtaining code configured to cause the at least one processor to obtain driving behavior data of a driver in a first time period, and obtain 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;
first prediction code configured to cause the at least one processor to predict, 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 code configured to cause the at least one processor to generate warning information based on the target quantity of times; and
providing code configured to cause the at least one processor to provide, using a display function, the warning information to the driver,
wherein the first obtaining code is configured to cause the at least one processor to:
obtain 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, recognize 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
obtain the driving behavior data based on the recognized quantity of the actual occurrences,
wherein the generating code is configured to cause the at least one processor to:
determine warning probabilities respectively corresponding to different preset scenarios based on the target quantity of times; and
determine at least one preset scenario for warning based on the warning probabilities, and generate 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 code is configured to cause the at least one processor to display the two or more preset scenarios in a form of a list in which each of the two or more preset scenarios is associated 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.

8. The apparatus according to claim 7 , wherein the first obtaining code comprises:
first obtaining sub-code configured to cause the at least one processor to obtain historical driving behavior data and historical preset scenario data of the driver in a historical time period;
first determining sub-code configured to cause the at least one processor to determine a behavior historical quantity of times of different preset driving behaviors of the driver in the historical time period based on the historical driving behavior data of the driver;
second d

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Hou Chen

Classifications

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• B60W2050/146

  Display means · CPC title

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title

• G06V20/597 Primary

  Recognising the driver's state or behaviour, e.g. attention or drowsiness · CPC title

• B60W2556/10

  Historical data · CPC title