Automotive Data Quality Marker Generation via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The automotive industry lacks a standardized method for evaluating the quality of automotive data signals from various sources, such as Telematics, Body Control, ADAS, Diagnostics, and In-Vehicle Infotainment, which hinders data collection, handling, and analysis, and prevents derivation of useful insights due to the absence of a quantitative mechanism for assessing data quality and frequency.
Innovation Solution
A system and method utilizing a machine learning engine to extract attributes from automotive data packets, calculate an Automotive Data Quality Marker (ADQM), and classify data into pre-defined categories, incorporating distributed source systems, storage systems, and a data quality module to determine the quality of numeric and image data sets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data collection is performed from multiple automotive data sources without standardization, then the quantity of data signals increases, but the quality and consistency of data deteriorates
Solution Approach 1:
The patent introduces a quality marker system that transforms raw automotive data into standardized quality-assessed data products. By changing the parameter of data representation from raw signals to quality-marked data with associated metadata, the system maintains data quantity while ensuring quality through automated assessment algorithms that evaluate data against predefined quality criteria.
Solution Approach 2:
The patent employs an intermediary quality assessment layer between data collection and data consumption. This intermediary system automatically evaluates data quality markers, assesses data reliability, and provides standardized quality information to consumers, thereby resolving the contradiction between collecting diverse data sources and maintaining data quality without requiring manual intervention.
2Measurement precision
If manual methods are used for data quality assessment, then measurement precision of data quality can be maintained, but productivity and automation level deteriorates
Solution Approach 1:
The patent implements a self-service automated quality assessment system where data products automatically generate and attach quality markers to themselves. The system uses automated algorithms to assess data quality, generate quality reports, and provide quality information to consumers without human intervention, thereby achieving both high precision through systematic assessment criteria and high productivity through automation.
Solution Approach 2:
The patent replaces manual mechanical quality assessment processes with automated computational systems. Instead of human experts manually evaluating data quality, the system uses automated algorithms, machine learning models, and computational assessment frameworks to evaluate data quality markers, thereby maintaining measurement precision while dramatically improving productivity and enabling scaling.
3Adaptability or versatility
If comprehensive data collection is performed across all automotive systems, then the coverage of data signals increases, but the complexity of data handling increases
Solution Approach 1:
The patent segments the complex automotive data ecosystem into distinct modular components: data sources, data products, quality markers, assessment algorithms, and consumer applications. Each component operates independently with well-defined interfaces, allowing comprehensive data collection across multiple automotive systems while managing complexity through modular architecture and standardized data product formats.
Data Source
AI summary
The present invention provides a robust and effective solution to an entity or an organization for creating and standardizing an Automotive Data Quality Marker (ADQM) to determine/evaluate/predict the quality of automotive data such as Telematics, Body Control, ADAS, Diagnostics, Dashcams, and In-Vehicle Infotainment but not limited to the like generated by the vehicle (i.e., data source) using a machine learning (ML) engine associated with a processing unit. The machine learning engine comprises an amalgamation of machine learning algorithms to determine ADQM for a particular dataset. Data pertaining to vehicles is huge and repetitive. Re-training of the model for improved accuracy is a requirement as automotive data can be augmented with additional signals and data received and stored as trip objects on a regular basis.