Microsoft patents system for updating AI models on your devices
Microsoft describes a system where a central server trains an AI model and sends it to user devices like phones or computers. These devices run the model locally on their own data and send performance feedback back to the server, which then updates the model to improve its accuracy.
In the filing’s own words
A server computing device generates training data based upon an identifier for a device, a timestamp, and a label received from a developer computing device. The server computing device trains a computer-implemented machine learning (ML) model based upon the training data. The server computing device also generates client configuration data for the ML model that specifies transformations that are to be applied to values in order to generate input values for the ML model. The server computing device deploys ML assets to client computing devices, the ML assets comprising the ML model and the client configuration data. The client computing devices execute the ML model using input values derived via transformations of (local) values produced by the client computing devices and transmit telemetry data to the server computing device. The server computing device updates the ML assets based upon the telemetry data.
What exactly they claim (claim 1)
1. A client computing device, comprising: a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform a set of operations comprising: receiving an application programming interface (API) call from a target application; locating machine learning (ML) assets based on the API call, the ML assets comprising an ML model and client configuration data; acquiring a value for a feature specified by the client configuration data; performing a transformation specified by the client configuration data on the value to generate an input value; providing the input value as input to the ML model; receiving, from the ML model, a prediction based upon the input value; and returning the prediction to the target application.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- COMPUTING SYSTEM FOR TRAINING, DEPLOYING, EXECUTING, AND UPDATING MACHINE LEARNING MODELS
- Publication number
- US20260330322A1
- Application number
- 19718705
- Filed
- Jun 24, 2026
- Published
- Oct 22, 2026
- Inventors
- 10
- Claims
- 20
Classified under
G06N 20/00 Physics & computingG06F 8/65 Physics & computingG06F 18/10 Physics & computingG06F 8/60 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 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.