Adaptive Electronic Content Personalization via Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing electronic content, such as e-books and articles, remain static and unadaptable, failing to accommodate individual readers' varying comprehension levels, interests, and needs, leading to frustration and disengagement.

Innovation Solution

A computer-implemented method and system that utilizes a machine-learning model to generate and adapt electronic content in real-time based on user inputs and consumption data, tailoring the content to a specific consumption level and displaying personalized text and visuals on electronic devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If static and pre-set text and visuals are used in electronic content, then the content can be consistently published across all platforms, but the content becomes difficult for readers with varying comprehension levels to understand, leading to frustration and disengagement

Engineering Contradiction:

Improveadaptability to reader comprehension levelsVSAvoidsystem complexity for content generation

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic content generation where the machine learning model creates personalized text and visuals in real-time based on reader characteristics. The system transitions from static pre-set content to dynamic adaptive content that changes according to individual reader needs, comprehension levels, and preferences, thereby resolving the contradiction between adaptability and system complexity

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes multiple parameters including text complexity, visual style, content length, and presentation format based on reader profiles. By adjusting these parameters dynamically according to reader characteristics, the system achieves high adaptability while managing complexity through parameterized control of content generation

Inventive Principle:

Principle #35Parameter changes

2Ease of operation

If a machine-learning model generates personalized content in real-time, then reader engagement and understanding are enhanced, but the computational resources and processing time required increase

Engineering Contradiction:

Improvereader engagement and understandingVSAvoidcomputational energy consumption

Core Design Contradiction:

Ease of operationVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by pre-processing source material into structured representations and pre-analyzing reader profiles before content generation. This preparation work is done in advance to reduce the computational burden during real-time personalized content creation, thereby improving reader engagement while managing energy consumption

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The machine learning model creates simplified copies or variations of the source material tailored to different reader levels. Instead of processing the entire source material from scratch for each reader, the system generates appropriate copies with adjusted complexity, reducing computational energy while maintaining personalized engagement

Inventive Principle:

Principle #26Copying

3Adaptability or versatility

If the content is customized to individual consumption levels, then accessibility is improved, but the time required to generate and deliver personalized content increases

Engineering Contradiction:

Improvecustomization to consumption levelVSAvoidcontent generation and delivery time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent replaces manual or mechanical content creation processes with an automated machine learning system. The ML model automatically generates personalized content based on reader profiles without requiring human intervention for each customization, thereby achieving high adaptability to individual consumption levels while minimizing time loss through automated processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250036433A1Methods and systems for adaptive and personalized text and visuals of electronic content

Publication Date: 2025.01.30 EDIFY TECHNOLOGIES INC

AI summary

Systems and methods are disclosed for generation, adaptive configuration, and personalized display of text and visuals on electronic devices. The multi-level adaptive system may determine and present a configuration of text and visuals that is customized for a specific user's capacity, interests, and needs when that user takes any physical action to reveal more material in a digital work displayed on an electronic device. An embodiment of the invention adapts an electronic presentation in real-time so that the graphics, language (words, sentences, paragraphs etc.), and overall structure of the work becomes dynamic and responsive to the context of individual users, rather than operating as a static object. In one particular example, delivering personalized text and visuals on electronic devices may entail three technology system components: a machine-learning or artificial intelligence (AI) platform; a display program, and a computing device comprising a display.