Google patents personalized ads using AI-generated images
Google describes a system that combines user personalization data with merchant assets to create custom advertising content. It uses a text-based AI model to generate specific terms, which are then fed into an image-based AI model to produce unique pictures for a content item. The final image is displayed on the user's device as part of a graphical interface.
In the filing’s own words
Techniques for presenting a content item using text-to-image machine-learned models are presented. For example, a system can obtain user personalization data associated with a user and merchant assets data of a merchant. Additionally, the system can process the user personalization data and the merchant assets data with a text generation model to generate one or more model-generated terms. Moreover, the system can process the one or more model-generated terms with an image generation model to generate one or more model-generated images. Furthermore, the system can determine a content item based on the one or more model-generated images. Subsequently, the system can present, on a display of a user device of the user, a graphical user interface having the content item.
What exactly they claim (claim 1)
1. A computing system, the system comprising: one or more processors; and a memory storing instructions that when executed by the one or more processors cause the system to perform operations comprising: obtaining user personalization data associated with a user; obtaining asset data; processing the user personalization data and the asset data with a text generation model to generate one or more model-generated terms; processing the one or more model-generated terms with an image generation model to generate one or more model-generated images; and causing a presentation, on a display of a user device of the user, of a graphical user interface based on the one or more model-generated images.
Facts
- Company
- Google (Google LLC)
- Official title
- User-Specific Content Generation Using Text-To-Image Machine-Learned Models
- Publication number
- US20260278018A1
- Application number
- 19667374
- Filed
- May 4, 2026
- Published
- Sep 17, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06F 16/9535 Physics & computingG06F 3/04845 Physics & computingG06F 16/9538 Physics & computingG06T 11/00 Physics & computingG06T 2200/24 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.