Mixed Reality Object Placement Using Viewability and Reward Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mixed reality systems inadequately assign virtual objects in a user's field of view, favoring easy-to-view positions over relevance, leading to irrelevant virtual objects receiving high interaction scores and relevant objects receiving low scores.
Innovation Solution
A system that calculates viewability and reward scores for virtual objects based on ease of viewing, interaction frequency, and relevance, using machine learning to optimize placement in a user's field of view, considering both viewability and interaction metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If virtual objects are assigned based on ease of viewability (distance and viewing angle), then positions closer to the user and with better viewing angles receive higher scores, but relevant virtual objects may be overlooked in favor of easily viewable positions
Solution Approach 1:
The patent introduces a multi-parameter scoring system that combines viewability parameters (distance, viewing angle) with interaction parameters (interaction frequency, easiness score) to determine virtual object placement. This changes the single-parameter approach to a multi-parameter approach, allowing the system to balance ease of viewing with object relevance through weighted combination of multiple factors.
Solution Approach 2:
The system uses historical interaction data to calculate reward scores and easiness scores for virtual objects, creating a feedback loop where past user interactions inform future placement decisions. This feedback mechanism ensures that relevant objects that users have previously interacted with are more likely to be placed in favorable positions, correcting the bias toward purely viewability-based assignment.
2Measurement precision
If virtual objects are assigned based on interaction frequency and reward scores, then relevant objects receive higher scores, but they may be placed in less viewable positions
Solution Approach 1:
The patent combines multiple parameters including viewability metrics (distance, viewing angle) and interaction metrics (reward score, easiness score) into a unified placement score. This parameter combination ensures that objects with high relevance don't necessarily occupy the most viewable positions, but rather positions that optimize the balance between visibility and relevance based on the composite scoring system.
3Ease of operation
If the system prioritizes viewability metrics (distance and viewing angle), then virtual objects are easily viewable, but irrelevant objects receive high placement scores
Solution Approach 1:
The system incorporates feedback from historical interaction data to calculate reward scores that reflect the relevance and importance of virtual objects. This feedback mechanism ensures that placement decisions are informed by actual user behavior patterns, preventing irrelevant objects from receiving high placement scores solely based on viewability metrics.
Solution Approach 2:
The patent transitions from a single viewability-based parameter to a multi-parameter system that includes interaction frequency, reward scores, and easiness scores. This parameter expansion allows the system to filter out irrelevant objects even in highly viewable positions by requiring them to also meet relevance thresholds.
4Measurement precision
If the system uses complex scoring mechanisms (viewability scores, reward scores, easiness scores), then relevant objects are placed accurately, but the system complexity increases
Solution Approach 1:
The patent creates a universal scoring framework where viewability scores, reward scores, and easiness scores all serve the single function of determining optimal virtual object placement. This multi-functional approach allows different types of metrics to be combined through a unified mathematical model, reducing the need for separate complex systems for each scoring type.
Data Source
AI summary
Provided are a computer program product, system, and method for determining an assignment of virtual objects to positions in a user field of view to render in a mixed reality display. A reward score for a virtual object is calculated based on an easiness score indicating an easiness to view the virtual object in previous interactions with the virtual object and frequency of interactions with the virtual object. The reward scores and the viewability scores for the positions are inputted into a virtual object placement program to output an assignment of the virtual objects to the positions. The assignment of the virtual objects to the positions are transmitted to the mixed reality display to cause the mixed reality display to render the virtual objects at the positions in the field of view of the user indicated in the assignment.