AI Multimodal Design Content Personalization for Accessibility

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing AI-based personalized bulk design content creation systems fail to accommodate individual recipient consumption needs and preferences, such as physical disabilities, language barriers, and cognitive barriers, limiting the personalization of design content items.

Innovation Solution

A system utilizing a large multimodal model (LMM) transforms design content items in bulk based on recipient-specific consumption needs and preferences, including physical and cognitive disabilities, language barriers, and content preferences, automating the personalization process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If existing AI-based systems share the same design content item with different recipients, then distribution efficiency is improved, but personalization capability deteriorates

Engineering Contradiction:

Improvedistribution efficiencyVSAvoidpersonalization capability

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system segments the personalization process by separating content transformation from distribution. It divides recipients into groups based on consumption needs and preferences, then applies specific transformations to each group before distribution, enabling both efficiency and personalization

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-defining content consumption needs and preferences for different recipient groups. Transformation prompts are pre-configured for each group, so when distribution occurs, the personalized content is already prepared, maintaining efficiency while achieving personalization

Inventive Principle:

Principle #10Preliminary action

2Adaptability or versatility

If manual transformation prompts are used for each recipient, then personalization capability is improved, but time consumption deteriorates

Engineering Contradiction:

Improvepersonalization capabilityVSAvoidtime consumption

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system creates transformation prompt templates that can be copied and applied to multiple recipients with similar consumption needs. Instead of manually creating unique prompts for each recipient, standardized templates are reused across groups, dramatically reducing time consumption while maintaining personalization

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system changes parameters by automatically adjusting transformation prompts based on recipient group characteristics. Rather than manual prompt creation, the system dynamically modifies prompt parameters (such as content format, language style, accessibility features) according to pre-defined recipient preferences, eliminating manual time investment

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If design content items are not transformed for different consumption formats, then system complexity is reduced, but accessibility deteriorates

Engineering Contradiction:

ImproveaccessibilityVSAvoidsystem complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system achieves universality by creating a multi-functional transformation engine that handles various content formats (audio, video, text, images) through a single unified platform. This engine can transform design content items into multiple consumption formats automatically, improving accessibility without requiring separate systems for each format

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces an intermediary transformation layer between content creation and distribution. This intermediary automatically converts design content items into appropriate formats based on recipient preferences, shielding users from complexity while ensuring accessibility for diverse consumption needs

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12430388B1AI-based personalized bulk design content creation

Publication Date: 2025.09.30 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A data processing system implements receiving, from a sender device, a request to personalize and distribute a design content item based on content consumption needs and/or preferences of recipients, wherein the content consumption needs and/or preferences include a data type; constructing a prompt by appending the design content item and the content consumption needs and/or preferences to an instruction string, the instruction string including instructions to a generative model to transform per recipient the design content item into a personalized content item based at least one of a content consumption need or a content consumption preference of a respective recipient; providing as an input the prompt to the generative model and receiving as an output the personalized content item from the generative model; providing the personalized content item to a recipient device; and causing a user interface of the recipient device to render the personalized content item.