Machine Learning Models for Online Engagement Stage Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for measuring user experience in interactive computing environments are limited to high-level information and fail to consider detailed user interactions, making it difficult to accurately customize the environment for enhanced user engagement.

Innovation Solution

Applying machine learning models to interaction data to identify user engagement stages and critical events, allowing for modifications to user interfaces to improve user engagement by promoting transitions to higher engagement levels.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machine learning models are applied to detailed interaction data, then measurement precision of user experience is improved, but device complexity increases

Engineering Contradiction:

Improveuser experience measurement precisionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces machine learning models as intermediary components that process detailed interaction data and transform it into meaningful user experience metrics. These models act as mediators between raw interaction data and the customization system, enabling precise measurement without requiring the entire system to directly handle complex data processing.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system employs self-service mechanisms where the machine learning models automatically analyze interaction data and generate user experience measurements without requiring manual intervention. The models continuously learn from interaction patterns and autonomously provide insights for customization, reducing operational complexity while maintaining high measurement precision.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If user interfaces are modified based on detailed interaction analysis, then adaptability to user needs is improved, but device complexity increases

Engineering Contradiction:

Improveinterface adaptabilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies local quality by modifying specific portions of user interfaces based on detailed interaction analysis rather than changing entire interfaces. The system identifies particular interface elements that require adaptation and applies targeted modifications to those specific components, maintaining overall system simplicity while achieving high adaptability where needed.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system implements dynamic interface adaptation where interface characteristics change in real-time based on ongoing interaction analysis. The machine learning models continuously monitor user behavior and dynamically adjust interface properties such as layout, content presentation, and interaction patterns, enabling high adaptability without requiring complex manual reconfiguration.

Inventive Principle:

Principle #15Dynamics

3Device complexity

If high-level information only is used for measuring user experience, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:

Improvesystem complexityVSAvoiduser experience measurement precision

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional mechanical or rule-based measurement systems with machine learning models that can process and interpret detailed interaction data. Instead of using simple counting metrics or predefined rules, the system employs intelligent algorithms that automatically extract meaningful patterns from complex interaction sequences, achieving high measurement precision without proportionally increasing system complexity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11775412B2Machine learning models applied to interaction data for facilitating modifications to online environments

Publication Date: 2023.10.03 ADOBE INC

AI summary

In some embodiments, a computing system identifies a current engagement stage of a user with an online platform by applying a stage prediction model based on interaction data associated with the user. The interaction data describe actions performed by the user with respect to the online platform and context data associated with each of the actions. The computing system further identifies one or more critical events for promoting the user to transition from one engagement stage to a higher engagement stage based on the interaction data associated with the user. The computing system can make the identified current engagement stage of the user or the identified critical event to be accessible by the online platform so that user interfaces presented on the online platform can be modified to improve a likelihood of the user to transit from the current stage to a higher engagement stage.