Microsoft patents translation that uses sensor data for context
Microsoft has been granted a patent for a machine translation system that combines text with data from sensors to improve accuracy. The system takes a user's text request and adds instructions based on real-time sensor data, such as location or device state, before sending it to a neural network model. This allows the translation to reflect the specific situation in which the text was created.
In the filing’s own words
A method for utilizing contextual data in generating machine translations. The method includes receiving a translation request including an initial prompt received via a user interface. The initial prompt includes a first language passage and a translation instruction. The initial prompt also includes a context data signal received via a context data source. The method further includes generating a context instruction based on the context data signal and generating a modified prompt including the initial prompt and the context instruction. The method further includes sending the modified prompt to a neural machine translation (NMT) model to process the modified prompt and receiving a second language translation passage as a response to the modified prompt. The second translation language passage being a second language translation of the first language passage translated according to the translation instruction and the context instruction.
What exactly they claim (claim 1)
1. A system, comprising: a processor; and a memory including instructions executable by the processor to: receive a translation request including: an initial prompt received via a user interface and including a first language passage and a translation instruction defining a desired translation for the first language passage, and a context data signal received via a context data source coupled to a device associated with the user interface and corresponding to a context of the initial prompt, wherein the context data source comprises a sensing device used to form the initial prompt, and wherein the context data signal comprises sensor output obtained at a time the initial prompt is received; generate a context instruction based on the context data signal; generate a modified prompt including the initial prompt and the context instruction that embeds the context instruction for a neural machine translation (NMT) model; send the modified prompt to the NMT model to process the modified prompt; and receive a second language translation passage as a response to the modified prompt, the second language translation passage being a second language translation of the first language passage translated according to the translation instruction and the context instruction.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Machine translation systems utilizing context data
- Patent number
- US12730985B2
- Application number
- 18786368
- Filed
- Jul 26, 2024
- Granted
- Sep 8, 2026
- Inventors
- 8
- Claims
- 20
Classified under
G06F 40/58 Physics & computingG06F 16/353 Physics & computingG06N 3/0895 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.