Distributed Vehicle Data Model for Secure PII Transmission
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle data analysis systems face challenges in securely transmitting personally-identifiable information (PII) across jurisdictions, violating privacy laws and risking unauthorized access, while needing to aggregate data for vehicle action decision-making.
Innovation Solution
A distributed model is implemented, where local output models are generated to modify PII, allowing only authorized nodes to reconstruct the data, enabling secure transmission and processing across geographic locations without exposing sensitive information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If vehicle data is transmitted to a central location for aggregation and analysis, then data-driven models can be produced to assist vehicle actions, but personally-identifiable information may be exposed violating privacy laws
Solution Approach 1:
The patent extracts personally-identifiable information from vehicle data before transmission to central locations. Local systems identify and remove PII elements such as facial recognition data, license plate numbers, and personal identifiers, retaining only anonymized vehicle operational data for aggregation and model training.
Solution Approach 2:
The patent introduces local processing systems as intermediary components between data collection and central aggregation. These local systems act as mediators that preprocess data, removing PII before transmission, thereby enabling centralized analysis while protecting individual privacy through the intermediary filtering layer.
2Loss of information
If all vehicle data is transmitted to central locations, then comprehensive analysis can be performed, but data security and unauthorized access risks increase
Solution Approach 1:
The patent segments the data processing architecture into local and central components. Local systems perform initial processing and filtering, transmitting only essential anonymized data to central locations. This segmentation reduces the volume of transmitted data and minimizes exposure to security risks while maintaining analytical capability.
Solution Approach 2:
The patent applies preliminary data processing and filtering at local systems before transmission. Data is prepared, anonymized, and validated locally, ensuring that only clean, necessary information is transmitted to central locations, thereby reducing security vulnerabilities and transmission overhead.
3Object-affected harmful factors
If PII is removed from vehicle data, then privacy protection is improved, but data utility for analysis may be reduced
Solution Approach 1:
The patent applies different processing qualities to different data elements. Personally-identifiable information is completely removed or anonymized, while vehicle operational data retains full detail and precision. This local quality differentiation ensures privacy protection for sensitive elements while maintaining data utility for analytical purposes.
Solution Approach 2:
The patent transforms PII parameters into anonymized forms that preserve statistical properties without enabling identification. For example, exact locations are transformed into geographic zones, exact timestamps into time intervals, and personal identifiers into anonymized codes, maintaining data utility while protecting privacy.
Data Source
AI summary
The present disclosure relates to techniques to implement a vehicle action using a distributed model distributed across the vehicle and a remote node. A local portion of the distributed model at the vehicle may generate a local output model based on vehicle event data collected at the vehicle. The local output model may be sent from the vehicle at a first location to the remote node at a second location. The remote node may generate a remote output model based on the local output model using the remote portion of the distributed model. The vehicle action may be determined based on inspecting a reconstructed version of the vehicle event data included in the remote output model. The determined vehicle action may be implemented at the vehicle. The distributed model may facilitate the transmission of vehicle event data across multiple locations while securing the transmission of personally-identifiable information.