Google patents shrinking search queries for satellite connections
This filing describes a method where a device checks if a user's search request is too large to send over a satellite link within a set time. If it is too big, the device uses machine learning to shrink or change the data before sending it, along with context clues, so the server can still understand the request. The device then displays the text answer it receives back through the satellite connection.
In the filing’s own words
An example computing device connected with an accessible non-terrestrial network receives data indicative of a user input and determines whether an amount of the data exceeds a maximum amount of data that can be transmitted via the connection within a predetermined time frame. Responsive to determining the amount of the data exceeds the maximum amount of data, the computing device generates modified data by applying transformations to the data indicative of the user input. Responsive to determining an amount of the modified data does not exceed the maximum amount of data, the computing device transmits, to a computing system via the connection, the modified data and a prompt including context information for the computing device. The computing device receives, from the computing system, output generated by the computing system based on the modified data and the prompt. The computing device generates, for display, a user interface including the output.
What exactly they claim (claim 1)
1. A method comprising: establishing, by a computing device, a connection with at least one accessible non-terrestrial network; receiving, by the computing device, data indicative of at least one user input; determining, by the computing device, whether an amount of the data exceeds a maximum amount of data that can be transmitted via the connection within a predetermined time frame; responsive to determining the amount of the data exceeds the maximum amount of data, generating, by the computing device, modified data by applying one or more transformations to the data indicative of the at least one user input; responsive to determining an amount of the modified data does not exceed the maximum amount of data, transmitting, by the computing device, and to a computing system via the connection, the modified data and a prompt, wherein the prompt is indicative of context information for the computing device; receiving, by the computing device, and via the connection, at least one text output generated by the computing system based on the modified data and the prompt; and generating, by the computing device, and for display by a user interface device included in the computing device, the at least one text output.
Facts
- Company
- Google (Google LLC)
- Official title
- USING MACHINE LEARNING MODELS FOR INFORMATION RETRIEVAL DURING NON-TERRESTRIAL NETWORK COMMUNICATION
- Publication number
- US20260259914A1
- Application number
- 19530897
- Filed
- Feb 5, 2026
- Published
- Sep 3, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G06F 16/335 Physics & computingMore from Google in Networks & wireless
- Google patents way for phones to send data without waking up fully Sep 8, 2026
- Google patents faster data handoff for phones in standby mode Sep 15, 2026
- Google patents video calls that change quality settings mid-conversation Sep 29, 2026
- Google patents video coding that trims extra detail to fit bandwidth limits Sep 29, 2026
- Google patents method for phones to sync with satellite signals Sep 29, 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.