Transmedia Recommender Engine for Content Organization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for managing and consuming transmedia content struggle to effectively identify and surface relevant content items and user-generated content, particularly on lower-power devices, and fail to provide real-time visualization and personalized recommendations.

Innovation Solution

An apparatus and method that utilizes a transmedia content linking engine and recommender engine to organize and surface transmedia content items and subsets based on user interactions, preferences, and time-ordered links, allowing users to create and consume linked content subsets and identify relevant content and users.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If users access and organize large amounts of transmedia content items manually, then content organization capability is improved, but user time and effort increase significantly

Engineering Contradiction:

Improvecontent organization efficiencyVSAvoiduser time for content curation

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system implements feedback loops where user interactions with content (views, likes, shares, time spent) are continuously monitored and fed back into the recommendation engine. This feedback mechanism enables the system to learn from user behavior patterns and automatically adjust content recommendations, eliminating the need for manual content organization while improving content discovery efficiency.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The recommendation engine operates autonomously to curate and organize content for users without requiring manual intervention. The system self-adjusts by processing user interaction data and automatically generating personalized content feeds, allowing users to consume relevant content without spending time on manual curation or organization tasks.

Inventive Principle:

Principle #25Self-service

2Ease of operation

If the system processes and visualizes large datasets of transmedia content in real-time, then user engagement is improved, but computational power requirements increase

Engineering Contradiction:

Improvereal-time content visualizationVSAvoidcomputational energy consumption

Core Design Contradiction:

Ease of operationVSUse of energy by moving object

Solution Approach 1:

The system segments the large transmedia content dataset into smaller, manageable subsets based on user preferences, content types, and relevance scores. By processing and visualizing content in segmented batches rather than as a monolithic dataset, the system reduces computational memory requirements and energy consumption while maintaining real-time visualization capabilities for personalized user experiences.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of processing and visualizing the entire transmedia content dataset in real-time, the system performs partial processing by focusing only on the most relevant content subsets for each user based on their profile and interaction history. This selective processing approach significantly reduces computational energy requirements while still providing effective real-time content recommendations and visualization.

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If the system provides personalized content recommendations based on user behavior analysis, then content relevance is improved, but system complexity increases

Engineering Contradiction:

Improvecontent recommendation accuracyVSAvoiduser modeling system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The user modeling system implements a universal framework that handles multiple analysis functions (behavior pattern recognition, preference extraction, content scoring) through a unified set of algorithms and data structures. This multi-functional approach achieves high recommendation accuracy without proportionally increasing system complexity, as the same core infrastructure supports diverse analytical tasks.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system achieves precise content recommendations by dynamically adjusting analysis parameters such as weighting factors for different user behaviors, time decay rates for past interactions, and relevance thresholds based on content characteristics. These parameter changes allow the system to fine-tune recommendation accuracy without adding fundamental architectural complexity, leveraging configurable parameters rather than complex structural modifications.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS10375200B2Recommender engine and user model for transmedia content data

Publication Date: 2019.08.06 DISNEY ENTERPRISES INC

AI summary

A recommender engine is configured to access memory and surface transmedia content items; and/or linked transmedia content subsets; and/or one or more identifications of identified users; and/or content items of the plurality of transmedia content items associated with at least one identified user. The surfaced items are presented for selection by the given user via the transmedia content linking engine as one or more user-selected transmedia content items.