Digital Content Excerpt Identification via Interaction Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of digital content, such as eBooks, videos, and songs, seek enhanced consumption experiences as the volume of digital works and devices increases, but existing technologies lack effective methods to highlight key excerpts and relate them across different digital works.
Innovation Solution
A device and method for displaying digital content that ranks and presents key excerpts based on user interactions and reviews, allowing navigation through a timeline and related excerpts across multiple digital works, including those from different books or media types, using a scrollable card format and emphasizing relevant entities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If key excerpts are identified and displayed across multiple digital works, then user engagement and content discovery are improved, but device complexity and information processing requirements increase
Solution Approach 1:
The system segments digital works into discrete key excerpts that can be independently identified, ranked, and displayed. Each excerpt is treated as a separate unit that can be extracted from its source context and presented in a standardized format across different works, reducing the complexity of processing entire works at once.
Solution Approach 2:
The patent introduces an intermediary ranking system that mediates between raw digital content and user presentation. This intermediary layer processes and ranks excerpts based on multiple criteria (user interactions, review references, entity relationships), creating a manageable intermediate representation that simplifies cross-work content discovery.
2Measurement precision
If excerpts are ranked based on multiple criteria (interactions, reviews, entities), then content relevance is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-identifying and pre-ranking key excerpts during content ingestion or periodic updates. User interactions and review references are accumulated and processed in advance, so that when users access content, the ranking is already established, reducing real-time processing requirements.
Solution Approach 2:
The ranking system incorporates feedback loops where user interactions (views, shares, quotes) and review references continuously refine excerpt rankings. This feedback mechanism allows the system to learn from user behavior and automatically adjust rankings without requiring manual intervention or extensive re-processing of all content.
3Productivity
If related excerpts from different books are identified and displayed, then user exploration and engagement are enhanced, but information processing complexity increases
Solution Approach 1:
The system applies universal entity recognition and relationship identification across multiple digital works regardless of source. The same excerpt identification and ranking processes work uniformly across different books and content types, enabling cross-work discovery without requiring work-specific customization or complex source-tracking mechanisms.
Data Source
AI summary
Described herein are techniques for identifying and displaying key excerpts of a digital work and related key excerpts of other digital works. Key excerpts are identified by evaluating (a) the number of interactions by human readers within each of the key excerpts and (b) the number of reviews that reference each of the key excerpts. Related excerpts from other books can be identified by comparing the key excerpts of the other books. Excerpts can be displayed by subject, and links are provided to move from one subject to another.