Virtual Object Engagement Scoring With Multi-Source Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems fail to accurately assess the efficacy of virtual objects in promoting user engagement with real-world entities in extended-reality environments, lacking a comprehensive method to validate engagement scores.

Innovation Solution

A system utilizing machine learning models to generate engagement scores based on user movement parameters and information access requests, incorporating a virtual object engagement model and a real-world entity engagement model to validate the efficacy of virtual objects in encouraging real-world interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If engagement scores are generated using only movement parameters from tracking devices, then the assessment of user engagement is simplified, but the accuracy and validity of the engagement scores are insufficient

Engineering Contradiction:

Improveengagement assessment systemVSAvoidengagement score accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines multiple data sources including movement parameters from tracking devices, information access requests, and machine learning model outputs to generate comprehensive engagement scores. This merging of diverse data streams resolves the contradiction by maintaining system simplicity while improving measurement accuracy through multi-factor analysis.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces machine learning models as intermediary components that process raw movement parameters and information access requests to generate validated engagement scores. These intermediary models bridge the gap between simple data collection and accurate engagement measurement, resolving the contradiction between system simplicity and measurement precision.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of manufacture

If a single engagement score model is used, then the system is easier to implement, but the validation of user interest in real-world entities is insufficient

Engineering Contradiction:

Improvesystem implementationVSAvoidengagement score validation

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent segments the engagement assessment into multiple specialized machine learning models: one model processes movement parameters to generate first engagement scores, while another model processes information access requests to generate second engagement scores. This segmentation enables validation by comparing results from different models, improving reliability while maintaining ease of implementation through modular architecture.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements feedback mechanisms where engagement scores from different models are compared and validated against each other. The system uses feedback from information access requests to validate and refine movement-based engagement scores, ensuring reliable assessment of user interest in real-world entities while maintaining a straightforward implementation structure.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If comprehensive data collection including information access requests is implemented, then the accuracy of engagement assessment improves, but the device complexity increases

Engineering Contradiction:

Improveengagement assessment accuracyVSAvoiddata collection system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a multi-functional system where the same tracking devices and data collection infrastructure serve multiple purposes: collecting movement parameters for engagement scoring, capturing information access requests for validation, and providing data for multiple machine learning models. This universality improves measurement precision through comprehensive data collection while minimizing device complexity by reusing existing components across multiple functions.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250272701A1Generating engagement scores using machine learning models for users interacting with virtual objects

Publication Date: 2025.08.28 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Provided are a computer program product, system, and method for generating engagement scores using machine learning models for users interacting with virtual objects. Movement parameters are received from tracking devices from a user in a real-world while the user is interacting with a virtual object in the extended-reality environment. The movement parameters are processed to determine a first engagement score indicating user interest in the real-world entity represented by the virtual object. A determination is made of on user information access requests with respect to the real-world entity. The information on the user information access requests is inputted to an engagement machine learning model to output a second engagement score indicating user interest in the real-world entity. The first engagement score and the second engagement score are outputted to provide information on an efficacy of the virtual object in promoting interest in the real-world entity.