Google patents tool to expand ad audiences using machine learning
This filing describes a feature for advertisers that suggests new groups of users to target with ads. It uses machine learning to predict if adding these new users will increase ad performance, and only suggests them if the predicted improvement meets a set threshold.
In the filing’s own words
A method is disclosed for providing a UI indicating characteristics of a baseline audience segment defining a first group of users designated to receive advertising content, receiving a user selection initiating an audience expansion feature, and in response to the user selection, identifying, based on the first group, an expanded audience segment comprising a second group of users not currently designated to receive the advertising content, estimating content related metrics for the second group, predicting, using a machine learning model and based on the estimated content related metrics for the second group, a performance metric lift representing an expected increase in user actions for the advertising content upon adding the expanded audience segment, responsive to the predicted performance metric lift satisfying a threshold condition, modifying campaign targeting parameters to include at least a subset of the expanded audience segment, and causing display of an indication of the expanded audience segment and a representation of the predicted performance metric lift.
What exactly they claim (claim 1)
1. A method comprising: providing, for display to a content provider, a user interface (UI) indicating one or more characteristics of a baseline audience segment defining a first group of users designated to receive advertising content within a digital media platform; receiving a user selection initiating an audience expansion feature associated with the baseline audience segment; and in response to the user selection: identifying, based on the first group of users, an expanded audience segment comprising a second group of users not currently designated to receive the advertising content; estimating content related metrics for the second group of users not currently designated to receive the advertising content; predicting, using a machine learning model and based on the estimated content related metrics for the second group of users, a performance metric lift representing an expected increase in user actions relative to the advertising content upon adding the expanded audience segment to the baseline audience segment; responsive to the predicted performance metric lift satisfying a threshold condition, modifying campaign targeting parameters to include at least a subset of the expanded audience segment; and causing display of an indication of the expanded audience segment and a representation of the predicted performance metric lift.
Facts
- Company
- Google (Google LLC)
- Official title
- METHOD FOR IDENTIFYING NEW AUDIENCES FOR CONTENT OF A CONTENT PROVIDER
- Publication number
- US20260303921A1
- Application number
- 19701646
- Filed
- Jun 8, 2026
- Published
- Oct 1, 2026
- Inventors
- 5
- Claims
- 20
Classified under
H04N 21/4788 Electricity & electronicsG06Q 10/40 Physics & computingG06Q 30/0202 Physics & computingG06Q 30/0251 Physics & computingH04H 60/66 Electricity & electronicsMore 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.