Driving Risk Warning Using Behavior-Based Scenario Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving risk warning systems based on computer vision technologies have low warning accuracy due to ineffective human-computer interaction, failing to alert drivers to potential dangers caused by their current driving behaviors in real-time.
Innovation Solution
A method and apparatus that predict the likelihood of dangerous scenarios by analyzing driver behavior data, using a computing device to obtain and correlate the frequency of dangerous driving behaviors with actual scenario occurrences, generating targeted warning information to improve driver awareness of potential risks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional camera-based driving behavior monitoring is used, then the system can collect driving behavior data, but the warning accuracy is low and driver attention is not obtained
Solution Approach 1:
The system implements a feedback mechanism by predicting the quantity of times dangerous scenarios will occur based on current driving behaviors, and using this prediction to generate targeted warning information. This closed-loop feedback improves warning accuracy by directly connecting observed behaviors to predicted consequences, making warnings more reliable and attention-grabbing for drivers.
Solution Approach 2:
The system performs preliminary action by predicting future dangerous scenarios before they actually occur. By analyzing current driving behaviors and using pre-established correspondence data, the system forecasts potential dangers and issues warnings in advance, allowing drivers to correct behaviors before accidents happen, thereby improving both accuracy and driver response.
2Ease of operation
If general driving behavior monitoring is implemented, then the system can provide basic warnings, but it fails to achieve effective human-computer interaction
Solution Approach 1:
The system applies local quality by customizing warning information based on specific driving behaviors and their predicted consequences. Instead of generic warnings, the system tailors alerts to the particular dangerous behavior detected and its likely outcomes, making the interaction more relevant and effective for the specific driving context, thereby reducing information loss and improving driver engagement.
3Adaptability or versatility
If the system warns about all possible dangerous scenarios, then comprehensive coverage is achieved, but warning accuracy decreases due to false alarms
Solution Approach 1:
The system applies partial action by selectively warning about dangerous scenarios based on predicted occurrence quantities. Instead of alerting about all possible dangers equally, the system focuses warnings on scenarios with higher predicted frequencies and greater severity, optimizing the balance between comprehensive coverage and accurate, meaningful alerts that maintain driver attention without excessive false alarms.
Data Source
AI summary
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.