Knowledge Graph Occupant Profiling for Cross-Vehicle Personalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Driver Information Acquisition Systems (DIAS) are limited to a particular driver and vehicle, lacking a method for generating a portable digital occupant profile for seamless transitions to other autonomous vehicles with varying features, and there is a need for methods that can concatenate multiple occupant profiles for actionable insights.
Innovation Solution
A method involving occupant data collection, generation of a knowledge graph using automotive ontology, and querying to create an occupant profile, which is communicated to a target vehicle for compatible feature configuration, and optionally recommending upgrades or coaching based on feature comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If current DIAS collects driver information for vehicle configuration, then driver experience is improved, but the system is limited to a particular driver and vehicle lacking portability
Solution Approach 1:
The patent creates a digital twin or virtual replica of the driver's preferences, behaviors, and vehicle settings as a portable data structure. This digital profile can be transferred between different physical vehicles, allowing the driver experience to be replicated without being tied to a specific vehicle's hardware.
Solution Approach 2:
The system designs a universal driver profile format that can be applied across multiple vehicle types and models. The knowledge graph structure and data schema are engineered to be vehicle-agnostic, enabling the same driver profile to function in different vehicle contexts while maintaining personalization.
2Adaptability or versatility
If a portable digital occupant profile is generated, then seamless transitions between vehicles are enabled, but system complexity increases due to knowledge graph generation and data processing
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary layer between raw driver data and vehicle configuration systems. This structured representation acts as a mediator that transforms complex, vehicle-specific configuration data into a universal, portable format that can be easily transferred and applied across different vehicles.
Solution Approach 2:
The system divides the driver profile into modular components including demographic data, preferences, behaviors, and vehicle-specific settings. This segmentation allows the profile to be constructed from standardized data blocks that can be independently processed and reassembled in different vehicle contexts, reducing overall system complexity.
3Productivity
If multiple occupant profiles are concatenated for actionable insights, then business value is improved, but data processing and machine learning requirements increase
Solution Approach 1:
The patent merges multiple individual driver profiles into a unified knowledge graph structure that preserves both individual and aggregate information. This consolidation enables the system to process multiple profiles simultaneously while maintaining the ability to generate actionable insights through machine learning algorithms that operate on the integrated data structure.
Data Source
AI summary
A method of occupant profiling for seamless experience and actionable insights. The method includes receiving occupant data about an occupant of a host vehicle, generating a knowledge graph based on the occupant data using automotive ontology, querying the knowledge graph to generate an occupant profile comprising the wants and the needs of the occupant of the host vehicle, communicating the occupant profile to a target vehicle, comparing features of a target vehicle to features of the host vehicle to determine a compatible feature, and configuring the at least one compatible feature of the target vehicle based on the occupant profile. The compatible feature is a vehicle feature present in both the target vehicle and the host vehicle. The occupant data includes meta-data about the occupant of the host vehicle, customer-facing features of the host vehicle, and interaction data between the occupant and the customer-facing features of the host vehicle.