AR Object Replacement Using Location-Based Preference Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current AR viewing systems fail to predictably automate and adjust AR viewing environments based on changes in user preferences and location, leading to irrelevant objects being displayed, which reduces user engagement and missed commercial opportunities.
Innovation Solution
An AI-enabled system that creates location clusters based on user data, classifies object interest levels, and selectively replaces irrelevant objects with more relevant ones using AR devices, allowing for personalized and context-aware AR experiences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If AR viewing systems display all observable objects in the environment, then the completeness of information is improved, but the relevance to user preferences and location context deteriorates
Solution Approach 1:
The system applies different quality filters to different objects based on their relevance to the user's current location cluster and preferences. High-priority objects matching user interests are displayed in full detail, while low-priority objects are replaced or obscured, creating local quality variations in the AR overlay that optimize both information completeness and preference relevance.
Solution Approach 2:
The system performs preliminary classification of objects into priority levels before the AR viewing experience begins. By pre-processing environmental objects and categorizing them based on location cluster relevance and user preferences, the system prepares the filtered object set in advance, enabling real-time AR display to focus only on high-priority relevant objects without missing important information.
2Adaptability or versatility
If AR viewing systems replace objects based on user preferences, then the relevance to user preferences is improved, but the system complexity increases
Solution Approach 1:
The system introduces an intermediary AI classifier component that mediates between the raw environmental objects and the AR display. This intermediary layer automatically categorizes objects into priority levels based on location cluster analysis and user preferences, handling the complex decision-making logic centrally rather than requiring complex processing at each AR display node, thus managing system complexity while maintaining high adaptability.
Solution Approach 2:
The system changes the parameter of object visibility from a binary state to a multi-level priority state. By adjusting the visibility parameter based on object priority classification and user preference matching, the system achieves adaptive relevance without requiring complex real-time processing, as the priority parameters are pre-determined through location cluster analysis.
3Productivity
If AR viewing systems display location-specific relevant objects, then the user engagement is improved, but the loss of irrelevant information increases
Solution Approach 1:
The system extracts and removes low-priority irrelevant objects from the AR display view, replacing them with virtual objects that are relevant to user preferences. By taking out only the unnecessary information rather than filtering everything, the system maintains user engagement through preference-relevant content while minimizing information loss, as the extraction process is selective and preserves high-priority objects.
4Adaptability or versatility
If AR viewing systems use AI to classify and prioritize objects, then the adaptability to user preferences is improved, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary AI classification of objects into priority levels before the AR viewing session begins. By pre-processing and categorizing environmental objects based on location cluster relevance and user preferences in advance, the system reduces real-time processing requirements, enabling fast AR object replacement decisions without sacrificing adaptability to user preferences.
Solution Approach 2:
The system segments the object classification process into distinct priority levels (high, medium, low) based on location cluster analysis. This segmentation allows the AI to process objects in hierarchical batches rather than uniformly, reducing overall processing time by focusing computational resources first on high-priority objects that most impact user engagement and preference relevance.
Data Source
AI summary
An approached is disclosed that selectively replaces physical objects with virtual objects viewable in augmented reality. Selective replacement is based on user location and corresponding preferences mapped to location clusters. AI systems learn user preferences for location clusters and derive object preferences for users depending on location. Preferences and priorities for objects within each location cluster are derived using location data, purchase histories, IoT data, social media, communication data and other data sources. AI systems implement algorithms to predict levels of engagement between users and objects of a particular location cluster and as objects around the user are predicted to be uninteresting to the user, uninteresting objects may be replaced within AR environments using AR image overlay techniques with new objects having an interest rating above a threshold level. Replacement objects are purchasable through the AR interface, whereby users select objects to purchase and initiate delivery.