IP Library Granted Patent US 11,823,661
Granted Patent B2
US 11,823,661 · App. 17/103,098 · Granted Nov 21, 2023

Expediting interaction with a digital assistant by predicting user responses

Inventors: Vipul Agarwal (Bellevue, WA); Rahul Kumar Jha (Redmond, WA); Soumya Batra (Bellevue, WA); Karthik Tangirala (Redmond, WA); Mohammad Makarechian (Seattle, WA); Imed Zitouni (Bellevue, WA)
Assignee: Microsoft Technology Licensing, LLC
G10L15/07G06F16/3349G10L15/22G06F3/16G10L2015/223G10L2015/225
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,823,661
App. No.
17/103,098
Granted
Nov 21, 2023
Kind
B2
Abstract

A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.

Claims (49)

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 natural language system prompt generated by a digital assistant;

generating a predicted response that comprises a prediction of how an individual will respond to the system prompt, the predicted response being generated based, at least in part, on at least one of:

a first contextual information associated with the system prompt;

a previously-generated system prompt;

a second contextual information describing a circumstance in which the previously-generated system prompt was issued; and

a previously-encountered response to the previously-generated system prompt;

selecting a dialogue action from a plurality of dialogue actions based, at least in part, on a confidence level associated with the predicted response, wherein the dialogue action expedites an interaction between the individual and the digital assistant by automatically providing the dialog action as a proxy response to the system prompt and by not providing the system prompt; and

causing the selected dialog action to be performed.

2. The system of claim 1 , further comprising instructions for selecting the dialogue action when the confidence level associated with the predicted response is above a threshold value.

3. The system of claim 1 , further comprising instructing the digital assistant to provide the system prompt to the individual.

4. The system of claim 1 , wherein the second contextual information includes a received query that caused generation of the previously-generated system prompt.

5. The system of claim 1 , wherein the second contextual information includes a time at which a query was received that caused generation of the previously-generated system prompt.

6. The system of claim 1 , wherein the second contextual information includes a location at which a query was received that caused generation of the previously-generated system prompt.

7. The system of claim 1 , further comprising instructions for providing a confirmation prompt to the individual, the confirmation prompt being based, at least in part, on providing the predicted response as the proxy response to the system prompt.

8. A method, comprising:

receiving a natural language system prompt generated by a digital assistant;

generating a predicted response that comprises a prediction of how an individual will respond to the system prompt, the predicted response being generated based, at least in part, on at least one of:

a previously-generated system prompt;

contextual information associated with the system prompt or the previously-generated system prompt; and

a previously-encountered response to the previously-generated system prompt;

selecting a dialogue action from a plurality of dialogue actions based, at least in part, on a confidence level associated with the predicted response, wherein the dialogue action expedites an interaction between the individual and the digital assistant by automatically providing the dialog action as a proxy response to the system prompt and by not providing the system prompt

and

and

performing the selected dialog action.

9. The method of claim 8 , further comprising selecting the dialogue action when a confidence level associated with the predicted response is above a threshold value.

10. The method of claim 8 , further comprising instructing the digital assistant to provide the system prompt to the individual.

11. The method of claim 8 , wherein the contextual information includes a received query that caused generation of the previously-generated system prompt.

12. The method of claim 8 , wherein the contextual information includes a time at which a query was received that caused generation of the previously-generated system prompt.

13. The method of claim 8 , wherein the contextual information includes a location at which a query was received that caused generation of the previously-generated system prompt.

14. The method of claim 8 , further comprising providing a confirmation prompt to the individual, the confirmation prompt being further based on providing the predicted response as the proxy response to the system prompt.

15. A method, comprising:

receiving a natural language system prompt generated by a digital assistant;

generating a predicted response including a prediction of how an individual will respond to the system prompt, the predicted response being generated based, at least in part, on a record entry in a data store, the record entry comprising one or more of:

a previously-generated system prompt;

contextual information associated with the system prompt or the previously-generated system prompt; and

a previously-encountered response to the previously-generated system prompt;

selecting a dialogue action from a plurality of dialogue actions based, at least in part, on a confidence level associated with the predicted response, wherein the dialogue action expedites an interaction between the individual and the digital assistant by automatically providing the dialog action as a proxy response to the system prompt and by not providing the system prompt; and

performing the selected dialog action.

16. The method of claim 15 , wherein the selected dialog action from the plurality of dialogue actions comprises one of:

providing the predicted response to the digital assistant as the proxy response to the system prompt;

instructing the digital assistant to provide the system prompt to the individual; and

providing a confirmation prompt to the individual, the confirmation prompt being based, at least in part, on the predicted response.

17. The method of claim 16 , further comprising providing the confirmation prompt to the individual, the confirmation prompt being further based on providing the predicted response as the proxy response to the system prompt.

18. The method of claim 15 , wherein the contextual information includes a time at which a query was received that caused generation of the previously-generated system prompt.

19. The method of claim 15 , wherein the contextual information includes a location at which a query was received that caused generation of the previously-generated system prompt.

20. The method of claim 15 , wherein the contextual information includes a received query that caused generation of the previously-generated system prompt.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 24, 2020
From: AGARWAL, VIPUL; JHA, RAHUL KUMAR; BATRA, SOUMYA; TANGIRALA, KARTHIK; MAKARECHIAN, MOHAMMAD; ZITOUNI, IMED
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 054459/0433 →
Continuity (2)
Continuation 16212662 · Dec 6, 2018
Related Publication 20210082403A1 · Mar 18, 2021
Cited By (1)
US 12,469,485