Dynamic Campaign Optimization for AR Virtual Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for campaign optimization in augmented reality applications lack the ability to dynamically generate and customize experience content datasets based on real-time user interactions and analytics, leading to suboptimal user engagement and experience personalization.
Innovation Solution
A server-based system that processes analytics data from user interactions with virtual objects to generate and modify experience content datasets, incorporating pose estimation, duration, orientation, and interaction data, which are then used to enhance or modify virtual object models and features in real-time, allowing for personalized and interactive experiences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If experience content datasets are statically generated without real-time analytics processing, then system complexity is reduced, but user engagement and personalization are compromised
Solution Approach 1:
The system continuously processes analytics data from user interactions with virtual objects and uses this feedback to dynamically generate and modify experience content datasets. The feedback loop includes collecting interaction data, analyzing user behavior patterns, and adjusting virtual object properties in real-time to optimize engagement.
Solution Approach 2:
The experience content dataset transitions from a static structure to a dynamic one that automatically adapts based on real-time analytics. The system dynamically generates virtual object models and modifies their properties (such as appearance, behavior, or functionality) based on processed user interaction data, enabling continuous optimization without manual intervention.
2Adaptability or versatility
If real-time analytics processing is implemented to personalize experiences, then user engagement improves, but processing time and computational resources increase
Solution Approach 1:
The system pre-processes and stores user interaction data in structured formats that enable rapid analytics processing. Historical data is organized in advance to facilitate quick pattern recognition and virtual object generation, reducing real-time computational burden while maintaining personalization capabilities.
Solution Approach 2:
The system changes processing parameters dynamically based on data volume and complexity. When user interaction data exceeds certain thresholds, the system adjusts analytics processing intensity, selects relevant features for virtual object generation, and modifies simulation parameters to balance personalization accuracy with processing speed.
3Adaptability or versatility
If virtual object models are continuously modified based on analytics, then experience relevance increases, but data processing complexity increases
Solution Approach 1:
The virtual object model is divided into modular components that can be independently modified based on analytics insights. The system segments the object into base properties, variable properties, and interactive elements, allowing targeted modifications without regenerating the entire model, thus reducing processing complexity.
Solution Approach 2:
The system applies different modification strategies to different parts of the virtual object model based on local analytics data. Rather than uniformly modifying all object properties, the system identifies specific regions or features that users interact with most and applies targeted adjustments to those areas, optimizing relevance while minimizing processing overhead.
Data Source
AI summary
A server for campaign optimization is described. The server generates analytics data from users interactions with a first virtual object displayed on a plurality of devices and user interactions with a first set of user interactive features of the first virtual object from a first content dataset. The server generates and provides a second content dataset to a device based on the analytics data. The second content dataset. The device recognizes an identifier from the second content dataset and displays, in the device, the second virtual object and the second set of user interactive features of the second virtual object in response to identifying the identifier.