Semantic Content Grouping for Digital Layouts

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Digital content often presents images and text separately, leading to a disjointed user experience due to unnecessary page breaks and requiring users to swipe or flip through pages to understand complex information, which can be frustrating and discourage users from engaging with digital content.

Innovation Solution

The use of supervised and unsupervised machine learning techniques to detect semantic information in digital content, such as image-caption relationships, allowing for the tagging and rendering of relevant images and text together on the same page, improving user experience by presenting semantic groupings optimally.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If digital content is rendered on separate pages based on device dimensions, then the content can be displayed to fit the screen, but the content appears disjointed and requires users to swipe or turn pages frequently to understand related information

Engineering Contradiction:
Improveuser experienceVSAvoidcontent coherence
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent segments digital content into semantic groups using machine learning to identify relationships between entities (images, text, tables, captions). Related entities are grouped together and rendered on the same page, eliminating unnecessary page breaks while maintaining content coherence and reducing the need for users to swipe or turn pages frequently

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces semantic relationships as an additional dimension for organizing content beyond traditional page layouts. By detecting semantic groupings through machine learning and rendering related entities together regardless of their original positional separation, the system preserves content coherence while adapting to device screen dimensions

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Device complexity

If images and text are rendered separately on different pages, then the layout can be simplified, but users must flip through pages to understand the relationship between images and their captions

Engineering Contradiction:
Improvelayout complexityVSAvoidtime to understand content
Core Design Contradiction:
Device complexityVSLoss of time

Solution Approach 1:

The patent merges related digital content entities (images with captions, tables with text, headings with chapter content) into semantic groups that are rendered together on the same page. This combining approach maintains simplified layouts while eliminating the need for users to flip through multiple pages to understand content relationships, thereby reducing time to understand content

Inventive Principle:
Principle #5Merging (Combining)

3Adaptability or versatility

If page breaks are inserted to fit device dimensions, then the content can be displayed properly on different devices, but the formatting appears choppy or disjointed

Engineering Contradiction:
Improvedevice compatibilityVSAvoidcontent formatting
Core Design Contradiction:
Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The patent dynamically adjusts content rendering by detecting semantic relationships and adapting page break placement accordingly. The system maintains content formatting stability by keeping semantically related entities together on the same page while still adapting to different device dimensions, eliminating choppy or disjointed formatting caused by arbitrary page breaks

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS12159021B1Semantic detection and rendering in digital content
Publication Date: 2024.12.03 AMAZON TECH INC
  • US12159021B1 patent drawing
  • US12159021B1 patent drawing
  • US12159021B1 patent drawing

AI summary

Systems and methods for determining semantic relationships in digital content are provided. Digital content may be processed to detect and extract one or more entities present in at least a subset of the digital content. The entities may include at least one image and at least one body of text. One or more aspects of the entities may be analyzed to filter out a subset of the entities based on a determined importance of the entities to the subset of the digital content. An anchor entity may be determined from one or more remaining entities after the filtering. Relationships between the one or more remaining entities and the anchor entity may be determined, and a presentation pattern for presenting the related entities may be determined. The presentation pattern may be stored to a repository and used as training data to detect future relationships within digital content.