Google patents method to train AI models for customizing user interfaces
This patent describes a two-step process for training machine learning models that decide which content to show users. It uses one model to calculate how likely a user is to interact with a specific element, then uses those scores to train a second model that selects the best content for a real-time interface.
In the filing’s own words
Example embodiments of the present disclosure provide for an example method. The example method includes obtaining session data descriptive of a plurality of user sessions, the plurality of user sessions respectively including an interaction with an input element rendered at a user device and a request for a resource associated with the input element. The example method includes obtaining, using a first machine-learned model, a plurality of weights associated with the plurality of user sessions by, for a respective user session of the plurality of user sessions: inputting, to the first machine-learned model, data descriptive of one or more characteristics of the respective user session; and obtaining, from the first machine-learned model, a respective weight of the plurality of weights, the respective weight indicative of an incremental probability of the request conditioned on rendering of the input element. The example method includes updating, based on the plurality of weights, a second machine-learned model to optimize candidate proposals for participation in a real-time content selection process for populating a user interface with one or more selected input elements.
What exactly they claim (claim 1)
1. A computer-implemented method, comprising: obtaining session data descriptive of a plurality of user sessions, the plurality of user sessions respectively comprising an interaction with an input element rendered at a user device and a request for a resource associated with the input element; obtaining, using a first machine-learned model, a plurality of weights associated with the plurality of user sessions by, for a respective user session of the plurality of user sessions: inputting, to the first machine-learned model, data descriptive of one or more characteristics of the respective user session; and obtaining, from the first machine-learned model, a respective weight of the plurality of weights, the respective weight indicative of an incremental probability of the request for a resource conditioned on rendering of the input element; determining the incremental probability of the request conditioned on rendering of the input element is below a threshold incremental probability; and updating, based on the plurality of weights, a second machine-learned model to optimize candidate proposals for participation in a real-time content selection process for populating a user interface with one or more selected input elements, wherein updating the second machine-learned model comprises: training the second machine-learned model using the respective weight to adjust future candidate proposals; and de-prioritizing, based on the incremental probability being below the threshold incremental probability, candidate proposals for participation in the real-time content selection process for populating the user interface with the input element.
Facts
- Company
- Google (Google LLC)
- Official title
- Training pipeline for training machine-learned user interface customization models
- Patent number
- US12761930B2
- Application number
- 18260645
- Filed
- Jun 14, 2023
- Granted
- Oct 13, 2026
- Inventors
- 6
- Claims
- 18
Classified under
G06F 9/451 Physics & computingG06N 20/00 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.