Google patents system that picks best AI model for your device
Google describes a method where a device checks conditions like battery life or network speed to decide where to run an AI task. It calculates a "capability score" for both a local model on the phone and a remote server model, then sends the data to whichever option is currently better suited for the job.
In the filing’s own words
A method includes obtaining input data using a client device, and determining a plurality of attribute values, where the attribute values are associated with processing the input data using a client-side machine learning model and a server-side machine learning model. The method also includes determining, for each respective machine learning model of the client-side machine learning model and the server-side machine learning model, a corresponding capability value based on the plurality of attribute values. The corresponding capability value may represent a capability of the respective machine learning model for processing the input data under conditions represented by the plurality of attribute values. The method further includes selecting, from the client-side machine learning model and the server-side machine learning model and based on the corresponding capability values thereof, a preferred machine learning model for processing the input data, and providing the input data to the preferred machine learning model.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: obtaining input data using a client device; determining a plurality of attribute values, wherein the plurality of attribute values is associated with processing the input data using (i) a client-side machine learning model executable on the client device and (ii) a server-side machine learning model executable on a server device that is communicatively connected to the client device; determining, for each respective machine learning model of the client-side machine learning model and the server-side machine learning model, a corresponding capability value based on the plurality of attribute values, wherein the corresponding capability value represents a capability of the respective machine learning model for processing the input data under conditions represented by the plurality of attribute values; selecting, from the client-side machine learning model and the server-side machine learning model and based on the corresponding capability values thereof, a preferred machine learning model for processing the input data; and providing the input data to the preferred machine learning model.
Facts
- Company
- Google (Google LLC)
- Official title
- Dynamic Runtime Scoring and Selection of Machine Learning Models
- Publication number
- US20260267773A1
- Application number
- 19071692
- Filed
- Mar 5, 2025
- Published
- Sep 10, 2026
- Inventors
- 2
- Claims
- 20
Classified under
G06F 11/3612 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.