Trip Data Prediction Using Travel Condition Mediation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in interpreting and managing telematics data due to inconsistencies, which affects the accuracy of trip data prediction and analysis.
Innovation Solution
A computer-implemented method and system for predicting trip data by obtaining and analyzing sets of telematics data and travel conditions, using weighted data sets based on condition matching and temporal proximity to estimate telematics data for target vehicular trips.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If telematics data is collected and analyzed to determine driving behavior, then insurance-related monitoring and safety analysis are improved, but data inconsistency and interpretation difficulty increase
Solution Approach 1:
The patent introduces travel conditions as an intermediary factor that mediates between raw telematics data and driving behavior analysis. By incorporating travel conditions (weather, road conditions, traffic) as a mediating variable, the system can filter and interpret inconsistent telematics data more accurately, resolving the contradiction between monitoring reliability and interpretation complexity.
Solution Approach 2:
The patent changes the parameters used for analysis by introducing travel conditions as additional variables. Instead of analyzing telematics data in isolation, the system modifies the analysis parameters to include environmental and contextual factors, which helps resolve data inconsistency and improves the reliability of driving behavior determination.
2Measurement precision
If more telematics data is collected to improve prediction accuracy, then trip data prediction improves, but data collection complexity and processing requirements increase
Solution Approach 1:
The patent segments the data collection process into two distinct components: telematics data (from vehicle sensors) and travel conditions data (from external sources). This segmentation allows the system to collect and process data more efficiently by targeting specific data types from appropriate sources, improving prediction accuracy without proportionally increasing overall system complexity.
Solution Approach 2:
The system uses a unified data processing framework that handles both telematics data and travel conditions data through the same analysis pipeline. This multi-functional approach allows the system to incorporate diverse data sources without requiring separate processing mechanisms, thereby improving prediction accuracy while controlling processing complexity.
3Measurement precision
If travel conditions are considered in data analysis, then prediction accuracy improves, but the scope of data analysis and computational requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-processing and structuring travel conditions data before integrating it with telematics data. By preparing travel conditions data in advance (organizing, normalizing, and structuring it), the system reduces the computational burden during the main analysis phase, thereby improving interpretation accuracy without proportionally decreasing processing efficiency.
Data Source
AI summary
A computer-implemented method includes obtaining a first set of trip data associated with a first set of vehicular trips operated by a vehicle operator during a first time period. The first set of trip data includes a first set of telematics data and a first set of travel conditions. The method also includes determining a second set of travel conditions associated with a target vehicular trip. The method further includes predicting a second set of telematics data associated with the target vehicular trip. The method further includes determining a set of vehicle operation behaviors based at least in part on the second set of telematics data, as predicted. Other embodiments are disclosed.