If you interact with Assistant by voice, our speech recognition technology converts your request to text. Next, Assistant analyzes the text, in combination with useful information such as recent requests or the type of device you are using, to identify possible interpretations.
For example, if you say "Hey Google, stop," you might want to stop one of two timers that are running, music that’s playing, or a routine that’s running. You might also want to see search results for “Stop,” or something else entirely.
To weigh the options, Assistant compiles a list of the different interpretations of your request and how it would respond to each one. The next step is to rank these options to find the best way to fulfill your request.