Driver Pattern Deviation Analysis for Personalized Training

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current driver monitoring systems fail to effectively analyze and provide feedback on driver pattern deviations in a user-friendly manner, often leading to inadequate training and potential safety issues due to lack of personalized and stress-free assessment methods.

Innovation Solution

A computer-implemented method and system that collects data from multiple vehicles, determines baselines for driving actions, identifies deviations from these baselines, and generates user interfaces to display problem actions, allowing drivers to review and practice improvements in a stress-free environment using camera and sensor data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If driver monitoring systems send alerts or assign scores based on driving data, then safety monitoring capability is improved, but driver anxiety and stress increase

Engineering Contradiction:

Improvesafety monitoring capabilityVSAvoiddriver anxiety and stress

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

Instead of providing immediate alerts during driving that cause stress, the system records driving data and provides feedback after the driving event. The interface displays problem actions and baselines in a relaxed, non-time-critical environment, inverting the traditional real-time alert approach into a post-drive analysis approach that maintains safety monitoring while eliminating driver anxiety.

Inventive Principle:

Principle #13The other way round (Inversion)

2Adaptability or versatility

If detailed driving data analysis is performed to identify pattern deviations, then training personalization is improved, but system complexity increases

Engineering Contradiction:

Improvetraining personalizationVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system extracts only the essential elements needed for personalized training: problem actions (deviations from baseline) and baseline comparisons. By focusing on these key extracted elements rather than analyzing all raw driving data, the system achieves high personalization while maintaining manageable complexity in the feedback interface.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system creates simplified representations of driving behavior through baseline models and problem action identifications. These copied and standardized data structures enable personalized training analysis without requiring complex processing of raw, unstructured driving data, thus reducing system complexity while maintaining adaptability.

Inventive Principle:

Principle #26Copying

3Productivity

If real-time feedback is provided during driving, then immediate correction capability is improved, but driver distraction and stress increase

Engineering Contradiction:

Improveimmediate correction capabilityVSAvoiddriver distraction and stress

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary data collection and baseline establishment during driving, but delays the feedback delivery until after the driving event. This preliminary action approach allows the system to prepare personalized training content in advance while avoiding real-time feedback that would distract or stress the driver during operation.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10957215B2Analyzing driver pattern deviations for training

Publication Date: 2021.03.23 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Approaches for analyzing driver pattern deviations and reproducing the pattern deviations in a user interface or a driving simulator are provided. A computer-implemented method includes: collecting, by a server, data from plural vehicles; determining, by the server, a baseline for a driving action based on the data from the plural vehicles; identifying, by the server, a problem action for a driver based on the baseline; and generating, by the server, an interface to display the problem action.