Samsung patents voice system that chains multiple commands together
This filing describes a method for electronic devices to understand complex voice requests that contain multiple actions. The system checks if these actions can be done in a specific order and then executes them one after another, displaying the results on the screen.
In the filing’s own words
A system, apparatus, and method for processing a natural language, and a computer readable recording medium are provided. The system includes a user device configured to receive a compound or complex sentence and a natural language processing apparatus configured to generate a plurality of control commands for the user device based on whether operations intended by a user are sequentially performable in the compound or complex sentence received from the user device.
What exactly they claim (claim 1)
1. An electronic apparatus comprising: a display; a communicator; a voice input receiver; and a processor configured to: receive a user voice input corresponding to performing of a function of the electronic apparatus through the voice input receiver, receive, through the communicator, a data corresponding to sequentially performable functions obtained by a natural language model from a server, perform voice recognition on the user voice input based on the data corresponding to the sequentially performable functions, the user voice input including a first voice command corresponding to a first function and a second voice command corresponding to a second function, based on the first function being able to be performed according to the data, control to output a result of performing the first function corresponding to the user voice input on the display, and based on the first function and the second function being able to be sequentially performed according to the data, control to output the result of performing the second function after performing the first function on the display differently according to whether the second function is performable after performing the first function.
Facts
- Company
- Samsung (SAMSUNG ELECTRONICS CO., LTD.)
- Official title
- System, apparatus, and method for processing natural language, and non-transitory computer readable recording medium
- Patent number
- US12749483B2
- Application number
- 18362510
- Filed
- Jul 31, 2023
- Granted
- Sep 29, 2026
- Inventors
- 2
- Claims
- 21
Classified under
G10L 15/22 Physics & computingG06F 40/20 Physics & computingG10L 2015/223 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 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.