# US 2026/0094325 A1 · Automated generation of data visualizations and infographics using large language models and diffusion models

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0094325 A1
- Document ID: US20260094325A1
- Status: Published application
- Kind: A1
- Application number: 19/412,362
- Filed: 2025-12-08
- Published: 2026-04-02
- Earliest claimed: 2022-12-01
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Victor Chukwuma DIBIA
- Web page: https://patentgrep.com/patent/US20260094325A1

## CPC

- G06F 16/26: Visual data mining; Browsing structured data
- G06T 11/26: Drawing of charts or graphs
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06N 3/08: Learning methods
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## 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.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A system, comprising
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the system to perform a set of operations, the set of operations comprising:
obtaining a natural language description of a visualization for raw data;
generating, using a machine learning model and based on the natural language description, visualization programmatic code for rendering at least a part of the raw data as the described visualization; and
processing the visualization programmatic code to generate the visualization for display to a user.

### Claim 22 (depends on 21)

The system of claim 21, wherein the natural language description is received from a computing device of the user.

### Claim 23 (depends on 21)

The system of claim 21, wherein the visualization programmatic code renders summary data according to the at least a part of the raw data.

### Claim 24 (depends on 23)

The system of claim 23, wherein the summary data comprises a compacted representation of the set of raw data.

### Claim 25 (depends on 23)

The system of claim 23, wherein the natural language description comprises an indication of the summary data to generate based on the raw data.

### Claim 26 (depends on 21)

The system of claim 21, wherein the generated visualization programmatic code specifies one or more graphics libraries to import during execution of the visualization programmatic code.

### Claim 27 (depends on 21)

The system of claim 21, wherein the machine learning model is a multimodal generative machine learning model for processing both natural language and programmatic code.

### Claim 28

A method, comprising:
obtaining, from a user of a computing device, a natural language description of a visualization for raw data;
generating, using a machine learning model and based on the natural language description, visualization programmatic code for rendering at least a part of the raw data as the described visualization, wherein the generated visualization programmatic code includes a programmatic instruction to import a graphics library during execution of the visualization programmatic code; and
executing the visualization programmatic code to render the visualization for display to the user.

### Claim 29 (depends on 28)

The method of claim 28, wherein the visualization programmatic code renders summary data according to the at least a part of the raw data.

### Claim 30 (depends on 29)

The method of claim 29, wherein the summary data comprises a compacted representation of the set of raw data.

### Claim 31 (depends on 29)

The method of claim 29, wherein the natural language description comprises an indication of the summary data to generate based on the raw data.

### Claim 32 (depends on 28)

The method of claim 28, wherein the natural language description further comprises an indication of the raw data to be visualized.

### Claim 33 (depends on 28)

The method of claim 28, wherein the machine learning model is a multimodal generative machine learning model for processing both natural language and programmatic code.

### Claim 34

A method, comprising:
obtaining a natural language description of a visualization for raw data;
generating, using a machine learning model and based on the natural language description, visualization programmatic code for rendering at least a part of the raw data as the described visualization; and
processing the visualization programmatic code to generate the visualization for display to a user.

### Claim 35 (depends on 34)

The method of claim 34, wherein the natural language description is received from a computing device of the user.

### Claim 36 (depends on 34)

The method of claim 34, wherein the visualization programmatic code renders summary data according to the at least a part of the raw data.

### Claim 37 (depends on 36)

The method of claim 36, wherein the summary data comprises a compacted representation of the set of raw data.

### Claim 38 (depends on 36)

The method of claim 36, wherein the natural language description comprises an indication of the summary data to generate based on the raw data.

### Claim 39 (depends on 34)

The method of claim 34, wherein the generated visualization programmatic code specifies one or more graphics libraries to import during execution of the visualization programmatic code.

### Claim 40 (depends on 34)

The method of claim 34, wherein the machine learning model is a multimodal generative machine learning model for processing both natural language and programmatic code.
