Automated Data Visualization and Infographics Using LLMs and Diffusion Models

ChangeBridge: Patent Apps - AI & Computing (G06N)

Published April 2nd, 2026

Detected April 3rd, 2026

Summary

Microsoft Technology Licensing filed USPTO Patent Application US20260094325A1 for automated generation of data visualizations and infographics using large language models and diffusion models. The system generates candidate analytics from raw data, creates visualization code scaffolds, and produces programmatic outputs including infographics via diffusion models. Application No. 19412362 was filed December 8, 2025.

View original document View source feed page

What changed

Microsoft Technology Licensing has been granted a US patent (US20260094325A1) for systems and methods that automatically generate data visualizations and infographics using large language models and diffusion models. The invention processes raw data into summary data, generates candidate analytics reflecting user intent through prompts, creates visualization code scaffolds according to specifications, and produces infographics via diffusion models. CPC classifications include G06T 11/26, G06F 40/40, and G06N 20/00.

This is a patent publication notice with no regulatory compliance requirements. Technology companies developing AI-driven data visualization tools should review the disclosed methods for competitive intelligence and potential licensing considerations. No filing deadlines, penalties, or required actions apply to this document.

Source document (simplified)

← USPTO Patent Applications

AUTOMATED GENERATION OF DATA VISUALIZATIONS AND INFOGRAPHICS USING LARGE LANGUAGE MODELS AND DIFFUSION MODELS

Application US20260094325A1 Kind: A1 Apr 02, 2026

Assignee

Microsoft Technology Licensing, LLC

Inventors

Victor Chukwuma DIBIA

Abstract

Systems and methods are provided for generating visualization data associated with raw data using a machine learning model. For example, the machine learning model may automatically generate a set of candidate analytics and/or a scenario for visualizing the raw data based on summary data. Given the summary data and answers to prompts for visualizing data, the generated candidate analytics may reflect a context of the raw data as intended by the user. A visualization code scaffold according to a visualization specification may be used to generate programmatic output that corresponds to the candidate analytics, which may thus be used to generate a visualization accordingly. In some examples, an infographic may further be generated based on the visualization and a prompt using a diffusion model.