IP Library Granted Patent US 11,373,083
Granted Patent B2
US 11,373,083 · App. 16/658,608 · Granted Jun 28, 2022

Query having multiple response portions

Inventors: Roderick Echols (Chapel Hill, NC); Ryan Charles Knudson (Durham, NC); Jonathan Gaither Knox (Morrisville, NC); Russell Speight VanBlon (Raleigh, NC)
Assignee: Lenovo (Singapore) Pte. Ltd.
G06N3/004G06F16/9038G06F40/30G06N20/00
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 11,373,083
App. No.
16/658,608
Granted
Jun 28, 2022
Kind
B2
Abstract

One embodiment provides a method, including: receiving, at a digital assistant of an information handling device, a query from a user comprising at least two response portions; determining responses for the at least two response portions, wherein the determining comprises separately processing each of the at least two response portions; and providing a response to the user comprising the responses. Other aspects are described and claimed.

Claims (18)

1. A method, comprising: receiving, at a digital assistant of an information handling device, a query from a user comprising at least two response portions; identifying, from the query, for each of the at least two response portions, a starting point for a path of research for the digital assistant, each of the paths of research being associated with an explicit processor thread; determining, from the at least two paths of research, responses for the at least two response portions, wherein the determining comprises separately processing each of the at least two response portions using the explicit processor thread corresponding to the response portion; and providing a response to the user comprising the responses, wherein the providing the response comprises providing a fluid response incorporating the responses for the at least two response portions, wherein the fluid response is generated utilizing natural language and machine learning techniques.

2. The method of claim 1 , wherein the separately processing comprises separating the at least two response portions and sending each of the response portions to one of a plurality of processing unit threads.

3. The method of claim 1 , wherein the query comprises a multi-part query and wherein each of the at least one response portions corresponds to a part of the multi-part query.

4. The method of claim 1 , wherein the providing the response comprises providing a single response comprising information that satisfies the at least two response portions.

5. The method of claim 1 , comprising providing an indication to a user after the responses are determined.

6. The method of claim 5 , wherein the indication is selected from the group consisting of: an audible indication, a visual indication, and a haptic indication.

7. The method of claim 5 , wherein the providing an indication comprises providing an indication as a response is determined for each of the at least two response portions.

8. The method of claim 7 , wherein the indication is different for each of the at least two response portions.

9. The method of claim 1 , wherein the providing is responsive to determining a response for all of the at least two response portions.

10. An information handling device, comprising: a processor; a memory device that stores instructions executable by the processor to: receive, at a digital assistant of an information handling device, a query from a user comprising at least two response portions; identify, from the query, for each of the at least two response portions, a starting point for a path of research for the digital assistant, each of the paths of research being associated with an explicit processor thread; determine, from the at least two paths of research, responses for the at least two response portions, wherein the determining comprises separately processing each of the at least two response portions using the explicit processor thread corresponding to the response portion; and provide a response to the user comprising the responses, wherein the providing the response comprises providing a fluid response incorporating the responses for the at least two response portions, wherein the fluid response is generated utilizing natural language and machine learning techniques.

11. The information handling device of claim 10 , wherein the separately processing comprises separating the at least two response portions and sending each of the response portions to one of a plurality of processing unit threads.

12. The information handling device of claim 10 , wherein the query comprises a multi-part query and wherein each of the at least one response portions corresponds to a part of the multi-part query.

13. The information handling device of claim 10 , wherein the instructions executable by the processor to provide the response comprise instructions executable by the processor to provide a single response comprising information that satisfies the at least two response portions.

14. The information handling device of claim 10 , comprising instructions executable by the processor to provide an indication to a user after the responses are determined.

15. The information handling device of claim 14 , wherein the instructions executable by the processor to provide an indication comprise instructions executable by the processor to provide an indication as a response is determined for each of the at least two response portions.

16. The information handling device of claim 15 , wherein the indication is different for each of the at least two response portions.

17. The information handling device of claim 10 , wherein the instructions executable by the processor to provide is responsive to determining a response for all of the at least two response portions.

18. A product, comprising: a storage device that stores code, the code being executable by a processor and comprising: code that receives, at a digital assistant of an information handling device, a query from a user comprising at least two response portions; code that identifies, from the query, for each of the at least two response portions, a starting point for a path of research for the digital assistant, each of the paths of research being associated with an explicit processor thread; code that determines, from the at least two paths of research, responses for the at least two response portions, wherein the determining comprises separately processing each of the at least two response portions using the explicit processor thread corresponding to the response portion; and code that provides a response to the user comprising the responses, wherein the providing the response comprises providing a fluid response incorporating the responses for the at least two response portions, wherein the fluid response is generated utilizing natural language and machine learning techniques.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 20, 2025
From: LENOVO PC INTERNATIONAL LIMITED
To: LENOVO SWITZERLAND INTERNATIONAL GMBH
Reel/Frame 070269/0092 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 19, 2025
From: LENOVO (SINGAPORE) PTE LTD.
To: LENOVO PC INTERNATIONAL LIMITED
Reel/Frame 070266/0821 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 9, 2022
From: ECHOLS, RODERICK; KNUDSON, RYAN CHARLES; KNOX, JONATHAN GAITHER; VANBLON, RUSSELL SPEIGHT
To: LENOVO (SINGAPORE) PTE. LTD.
Reel/Frame 059911/0691 →
Continuity (1)
Related Publication 20210117754A1 · Apr 22, 2021