IP Library Granted Patent US 10,956,425
Granted Patent B2
US 10,956,425 · App. 16/216,521 · Granted Mar 23, 2021

User attribute resolution of unresolved terms of action queries

Inventors: Vikram Aggarwal (Palo Alto, CA); Alice Lee (Menlo Park, CA)
Assignee: GOOGLE LLC
G06F16/24575G06F16/29G06F16/335G06F16/9535G06F16/9537
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 10,956,425
App. No.
16/216,521
Granted
Mar 23, 2021
Kind
B2
Abstract

User attribute data associated with a user may be used to resolve unresolved entities in connection with the performance of computer-based actions, e.g., actions resulting from action queries generated based at least in part on content being accessed on a computing device.

Claims (62)

1. A method implemented by one or more processors, the method comprising:

receiving a voice input provided at a computing device by a user of the computing device;

in response to receiving the voice input, identifying at least one action term for an action query, wherein the at least one action term is mapped to at least one entity term and at least one computer-based action in one or more databases;

identifying content displayed by the computing device most recently relative to receiving the voice input, wherein the content displayed by the computing device most recently relative to receiving the voice input is content displayed in response to an interaction between the computing device and the user initiated previous to receiving the voice input at the computing device;

processing the identified content displayed by the computing device most recently relative to receiving the voice input to resolve the at least one entity term for the action query;

in response to determining, based on the processing, that the at least one entity term remains unresolved:

determining a current location of the computing device based on location information generated by the computing device, and

resolving the at least one entity term, for the action query, using the determined current location of the computing device; and

subsequent to resolving the at least one entity term for the action query:

generating interactive content based on processing the action query including the resolved at least one entity term of the action query, wherein the interactive content includes a graphical element that, when selected via further user input received at the computing device, causes performance, by a computer application installed on the computing device, of the computer-based action for the resolved at least one entity term;

providing, in response to receiving the voice input, the interactive content for display at the computing device; and

initiating performance of the computer-based action in response to a user selection of the graphical element when the interactive content is displayed at the computing device, wherein initiating performance of the computer-based action comprises causing the computer application installed on the computing device to automatically perform the computer-based action for the resolved at least one entity term.

2. The method of claim 1 , wherein causing the computer application to automatically perform the computer-based action comprises:

interfacing with an API of the computer application based on a parse of the action query.

3. The method of claim 1 , wherein identifying the at least one action term for the action query comprises:

identifying the at least one action term based on determining that the computer-based action is performable via one or more applications installed on the computing device.

4. The method of claim 1 , wherein determining, based on the processing, that the at least one entity term remains unresolved comprises:

determining that an entity in the identified content is subject to multiple interpretations.

5. The method of claim 4 , wherein causing the computer application to automatically perform the computer-based action comprises:

interfacing with an API of the computer application based on a parse of the action query.

6. The method of claim 1 , wherein determining, based on the processing, that the at least one entity term remains unresolved comprises:

determining an inability to determine a species for a genus determined in the identified content.

7. The method of claim 1 , wherein identifying the at least one action term for the action query in response to receiving the voice input is based at least in part on the identified content.

8. The method of claim 1 , wherein resolving the at least one entity term further comprises using user attribute data stored in the computing device.

9. A system, comprising:

memory storing instructions;

one or more processors, operable to execute the instructions stored in the memory, wherein the instructions comprise instructions to:

receive a voice input provided at a computing device by a user of the computing device;

in response to receiving the voice input, identify at least one action term for an action query, wherein the at least one action term is mapped to at least one entity term and at least one computer-based action in one or more databases;

identify content displayed by the computing device most recently relative to receiving the voice input, wherein the content displayed by the computing device most recently relative to receiving the voice input is content displayed in response to an interaction between the computing device and the user initiated previous to receiving the voice input at the computing device;

processing the identified content displayed by the computing device most recently relative to receiving the voice input to resolve the at least one entity term for the action query;

in response to determining, based on the processing, that the at least one entity term remains unresolved:

determine a current location of the computing device based on location information generated by the computing device, and

resolve the at least one entity term, for the action query, using the determined current location of the computing device; and

subsequent to resolving the at least one entity term for the action query:

generate interactive content based on processing the action query including the resolved at least one entity term of the action query, wherein the interactive content includes a graphical element that, when selected via further user input received at the computing device, causes performance, by a computer application installed on the computing device, of the computer-based action for the resolved at least one entity term;

provide, in response to receiving the voice input, the interactive content for display at the computing device; and

initiate performance of the computer-based action in response to a user selection of the graphical element when the interactive content is displayed at the computing device, wherein initiating performance of the computer-based action comprises causing the computer application installed on the computing device to automatically perform the computer-based action for the resolved at least one entity term.

10. The system of claim 9 , wherein the instructions to cause the computer application to automatically perform the computer-based action comprise instructions to:

interface with an API of the computer application based on a parse of the action query.

11. The system of claim 9 , wherein the instructions to identify the at least one action term for the action query comprise instructions to:

identify the at least one action term based on determining that the computer-based action is performable via one or more applications installed on the computing device.

12. The system of claim 9 , wherein the instructions to determine, based on the processing, that the at least one entity term remains unresolved comprise instructions to:

determine that an entity in the identified content is subject to multiple interpretations.

13. The system of claim 12 , wherein the instructions to cause the computer application to automatically perform the computer-based action comprise instructions to:

interface with an API of the computer application based on a parse of the action query.

14. The system of claim 9 , wherein the instructions to determine, based on the processing, that the at least one entity term remains unresolved comprise instructions to:

determine an inability to determine a species for a genus determined in the identified content.

15. The system of claim 9 , wherein identifying the at least one action term for the action query in response to receiving the voice input based at least in part on the identified content.

16. The system of claim 9 , wherein resolving the at least one entity term further is further based on user attribute data stored in the computing device.

17. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to:

receive a voice input provided at a computing device by a user of the computing device;

in response to receiving the voice input, identify at least one action term for an action query, wherein the at least one action term is mapped to at least one entity term and at least one computer-based action in one or more databases;

identify content displayed by the computing device most recently relative to receiving the voice input, wherein the content displayed by the computing device most recently relative to receiving the voice input is content displayed in response to an interaction between the computing device and the user initiated previous to receiving the voice input at the computing device;

processing the identified content displayed by the computing device most recently relative to receiving the voice input to resolve the at least one entity term for the action query;

in response to determining, based on the processing, that the at least one entity term remains unresolved:

determine a current location of the computing device based on location information generated by the computing device, and

resolve the at least one entity term, for the action query, using the determined current location of the computing device; and

subsequent to resolving the at least one entity term for the action query:

generate interactive content based on processing the action query including the resolved at least one entity term of the action query, wherein the interactive content includes a graphical element that, when selected via further user input received at the computing device, causes performance, by a computer application installed on the computing device, of the computer-based action for the resolved at least one entity term;

provide, in response to receiving the voice input, the interactive content for display at the computing device; and

initiate performance of the computer-based action in response to a user selection of the graphical element when the interactive content is displayed at the computing device, wherein initiating performance of the computer-based action comprises causing the computer application installed on the computing device to automatically perform the computer-based action for the resolved at least one entity term.

Assignments (2)
CHANGE OF NAME Recorded May 16, 2019
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 050395/0119 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 16, 2019
From: AGGARWAL, VIKRAM; LEE, ALICE
To: GOOGLE INC.
Reel/Frame 049202/0045 →
Continuity (2)
Continuation 15204236 · Jul 7, 2016
Related Publication 20190114296A1 · Apr 18, 2019
Cited By (1)
US 12,461,924