US 12,469,485 B2
Expediting interaction with a digital assistant by predicting user responses
Vipul Agarwal, Bellevue, WA (US); Rahul Kumar Jha, Redmond, WA (US); Soumya Batra, Bellevue, WA (US); Karthik Tangirala, Redmond, WA (US); Mohammad Makarechian, Seattle, WA (US); and Imed Zitouni, Bellevue, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 9, 2023, as Appl. No. 18/483,320.
Application 18/483,320 is a continuation of application No. 17/103,098, filed on Nov. 24, 2020, granted, now 11,823,661.
Application 17/103,098 is a continuation of application No. 16/212,662, filed on Dec. 6, 2018, granted, now 10,878,805, issued on Dec. 29, 2020.
Prior Publication US 2024/0038220 A1, Feb. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/07 (2013.01); G06F 3/16 (2006.01); G06F 16/3349 (2025.01); G10L 15/22 (2006.01)
CPC G10L 15/07 (2013.01) [G06F 16/3349 (2019.01); G10L 15/22 (2013.01); G06F 3/16 (2013.01); G10L 2015/223 (2013.01); G10L 2015/225 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor; and
a memory coupled to the processor and storing instructions that, when executed by the processor, perform operations, comprising:
receiving a system prompt generated by a digital assistant in response to an input provided through an input device operated by a user, where the system prompt includes a request for additional information associated with the input;
generating, by a machine learning model, a predicted response corresponding to the system prompt based at least in part on a set of contextual features associated with a circumstance in which the system prompt was generated, the predicted response indicating a predicted user response to the system prompt
providing to the digital assistant the predicted response without providing the system prompt to the input device for interaction with by the user;
causing the digital assistant to perform a dialogue action based at least in part on a confidence level associated with the predicted response, where the digital assistant performs the dialogue action as if the predicted user response was provided in response to the system prompt without obtaining the additional information from associated with the input from the user.