AI Illustration Synthesis for Text-Based Visual Content
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for creating visual content associated with text are inefficient, as they require manual selection of illustrations, which is time-consuming and difficult to unify designs across different materials.
Innovation Solution
An electronic apparatus and method using an AI model to acquire text, determine key terms, synthesize multiple illustrations based on these terms, and output a unified image, leveraging generative adversarial networks and natural language processing to automate the illustration generation process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual selection of illustrations is used, then design quality can be controlled, but time consumption increases significantly
Solution Approach 1:
The system enables self-service by automatically generating illustrations through AI models without requiring manual selection. The electronic apparatus extracts key terms from text, generates corresponding illustrations using generative adversarial networks, and automatically synthesizes them into unified designs, allowing the system to serve itself rather than requiring human intervention for each illustration selection.
Solution Approach 2:
The patent replaces the mechanical manual selection process with an automated AI-based system. Instead of manually searching and selecting illustrations, the system uses natural language processing to extract key terms and generative adversarial networks to create illustrations automatically, substituting human manual work with automated computational processes.
2Measurement precision
If multiple illustrations are selected individually, then content accuracy improves, but design consistency deteriorates
Solution Approach 1:
The system merges multiple individually generated illustrations into a single unified illustration through synthesis. The electronic apparatus generates multiple candidate illustrations based on extracted key terms, then combines them while maintaining consistent design elements such as color schemes, styles, and visual themes, ensuring both content accuracy and design consistency in the final output.
Solution Approach 2:
The AI model performs multiple functions: it extracts key terms from text, generates illustrations for each term, and synthesizes them into a unified design. This multi-functional approach ensures that the same design principles are applied across all illustrations, maintaining consistency while accurately representing different aspects of the content.
3Productivity
If AI-based illustration generation is used, then productivity increases, but device complexity increases
Solution Approach 1:
The complex AI-based illustration generation system is segmented into distinct functional modules: a text processing module that extracts key terms, a generation module that creates illustrations using generative adversarial networks, and a synthesis module that combines illustrations into unified designs. This segmentation manages complexity by organizing functions into separate, manageable components while maintaining high productivity.
Data Source
AI summary
An artificial intelligence (AI) system using an artificial intelligence model learned according to at least one of machine learning, a neural network, or a deep-learning algorithm, and an application, and a method of controlling an electronic apparatus therefor are provided. The method includes acquiring a text based on a user input, determining a plurality of key terms from the acquired text, acquiring a plurality of first illustrations corresponding to the plurality of key terms, acquiring a second illustration by synthesizing at least two or more first illustration of the plurality of first illustrations, and outputting the acquired second illustration.