IP Library Granted Patent US 12,632,665
Granted Patent B2
US 12,632,665 · App. 18/738,974 · Granted May 19, 2026

Context-based natural language processing

Inventors: Ilya Gennadyevich Gelfenbeyn (Sunnyvale, CA); Artem Goncharuk (Mountain View, CA); Pavel Aleksandrovich Sirotin (Sunnyvale, CA)
Assignee: GOOGLE LLC
G06F40/35G06F40/279G10L15/22G10L15/26G10L2015/228
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 12,632,665
App. No.
18/738,974
Granted
May 19, 2026
Kind
B2
Abstract

A method for context-based natural language processing is disclosed herein. The method comprises maintaining a plurality of dialog system rules, receiving a user request from a Dialog System Interface, receiving one or more attributes associated with the user request from the Dialog System Interface or a user device, and identifying a type of context associated with the user request based on the user request and the one or more attributes. A context label is assigned to the user request associated with the type of context. Based on the context label and the user request, a particular dialog system rule is selected from the plurality of dialog system rules. A response to the user request is generated by applying the dialog system rule to at least a part of the user request.

Claims (37)

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

determining user request text for a user request that is based on input provided by a user during a current user session via a dialog system interface, wherein the dialog system interface is integrated into one or more applications of a client device;

determining a current conversational context for the current user session, wherein determining the current conversational context is based on a given application being active on the client device, wherein the given application that is active on the client device is one of the one or more applications into which the dialog system interface is integrated, and wherein the current conversational context includes content associated specifically with the given application;

generating, based on both the user request text and the current conversational context, including the content associated specifically with the given application, a computer-implementable instruction that is responsive to the user request, wherein the computer-implementable instruction comprises an actionable command for the given application that is active on the client device; and

causing the client device to implement the computer-implementable instruction responsive to the user request, wherein causing the client device to implement the computer-implementable instruction comprises causing execution of the actionable command for the given application that is active on the client device.

2 . The method of claim 1 , wherein the content associated specifically with the given application includes terms, keywords, and/or phrases associated specifically with the given application.

3 . The method of claim 2 , wherein the terms, keywords, and/or phrases associated specifically with the given application are established by a developer of the given application.

4 . The method of claim 2 , wherein the content associated specifically with the given application includes variables and/or expressions associated specifically with the given application.

5 . The method of claim 4 , wherein the variables and/or expressions associated specifically with the given application are established by a developer of the given application.

6 . The method of claim 1 , wherein the content associated specifically with the given application includes variables and/or expressions associated specifically with the given application.

7 . The method of claim 1 , wherein the input provided by the user is speech input.

8 . The method of claim 7 , wherein determining the user request text for the user request comprises:

performing speech recognition on the speech input provided by the user; and

converting the speech input to the user request text.

9 . A system, comprising:

one or more computers each including at least one processor and a memory storing processor-executable code, one or more of the computers configured to:

determine user request text for a user request that is based on input provided by a user during a current user session via a dialog system interface, wherein the dialog system interface is integrated into one or more applications of a client device;

determine a current conversational context for the current user session, wherein determining the current conversational context is based on a given application being active on the client device, wherein the given application that is active on the client device is one of the one or more applications into which the dialog system interface is integrated, and wherein the current conversational context includes content associated specifically with the given application;

generate, based on both the user request text and the current conversational context, including the content associated specifically with the given application, a response to the user request; and

cause the response to be rendered at the client device responsive to the user request.

10 . The system of claim 9 , wherein the content associated specifically with the given application includes terms, keywords, and/or phrases associated specifically with the given application.

11 . The system of claim 10 , wherein the terms, keywords, and/or phrases associated specifically with the given application are established by a developer of the given application.

12 . The system of claim 10 , wherein the content associated specifically with the given application includes variables and/or expressions associated specifically with the given application.

13 . The system of claim 12 , wherein the variables and/or expressions associated specifically with the given application are established by a developer of the given application.

14 . The system of claim 9 , wherein the content associated specifically with the given application includes variables and/or expressions associated specifically with the given application.

15 . The system of claim 9 , wherein the input provided by the user is speech input.

16 . The system of claim 15 , wherein in determining the user request text for the user request, one or more of the computers are further configured to:

perform speech recognition on the speech input provided by the user; and

convert the speech input to the user request text.

17 . A non-transitory processor-readable medium having instructions stored thereon, which when executed by one or more processors, cause one or more of the processors to:

determine user request text for a user request that is based on input provided by a user during a current user session via a dialog system interface, wherein the dialog system interface is integrated into one or more applications of a client device;

determine a current conversational context for the current user session, wherein determining the current conversational context is based on a given application being active on the client device, wherein the given application that is active on the client device is one of the one or more applications into which the dialog system interface is integrated, and wherein the current conversational context includes content associated specifically with the given application;

generate, based on both the user request text and the current conversational context, including the content associated specifically with the given application, a computer-implementable instruction that is responsive to the user request, wherein the computer-implementable instruction comprises an actionable command for the given application that is active on the client device; and

cause the client device to implement the computer-implementable instruction responsive to the user request, wherein in causing the client device to implement the computer-implementable instruction, one or more of the processors are to cause execution of the actionable command for the given application that is active on the client device.

18 . The non-transitory processor-readable medium of claim 17 , wherein the content associated specifically with the given application includes terms, keywords, and/or phrases associated specifically with the given application.

19 . The non-transitory processor-readable medium of claim 18 , wherein the terms, keywords, and/or phrases associated specifically with the given application are established by a developer of the given application.

20 . The non-transitory processor-readable medium of claim 18 , wherein the content associated specifically with the given application includes variables and/or expressions associated specifically with the given application.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 26, 2024
From: GELFENBEYN, ILYA GENNADYEVICH; GONCHARUK, ARTEM; SIROTIN, PAVEL ALEKSANDROVICH
To: SPEAKTOIT, INC.
Reel/Frame 068402/0453 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 26, 2024
From: SPEAKTOIT, INC.
To: GOOGLE INC.
Reel/Frame 068402/0485 →
CHANGE OF NAME Recorded Aug 26, 2024
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 068789/0973 →
Continuity (5)
Continuation 17582881 · Jan 24, 2022
Continuation 16686257 · Nov 18, 2019
Continuation 15063757 · Mar 8, 2016
Provisional Application 62129877 · Mar 8, 2015
Related Publication 20240330599A1 · Oct 3, 2024
References Cited (49)
US 6044347A · Abella et al. · 2000 [cited by applicant]
US 6144938A · Surace et al. · 2000 [cited by applicant]
US 6567805B1 · Johnson et al. · 2003 [cited by applicant]
US 6907546B1 · Haswell et al. · 2005 [cited by applicant]
US 7085723B2 · Ross · 2006 [cited by examiner]
US 7729916B2 · Coffman · 2010 [cited by examiner]
US 8082153B2 · Coffman · 2011 [cited by examiner]
US 8812316B1 · Chen · 2014 [cited by examiner]
US 8903716B2 · Chen et al. · 2014 [cited by applicant]
US 8942986B2 · Cheyer et al. · 2015 [cited by applicant]
US 9043205B2 · Mengibar et al. · 2015 [cited by applicant]
US 9805718B2 · Ayan et al. · 2017 [cited by applicant]
US 9852136B2 · Venkataraman · 2017 [cited by applicant]
US 9892723B2 · Korbecki · 2018 [cited by examiner]
US 10241752B2 · Lemay et al. · 2019 [cited by applicant]
US 10482184B2 · Gelfenbeyn et al. · 2019 [cited by applicant]
US 11232265B2 · Gelfenbeyn et al. · 2022 [cited by applicant]
US 20030028498A1 · Hayes-Roth · 2003 [cited by applicant]
US 20030171925A1 · Werner · 2003 [cited by applicant]
US 20040006483A1 · Sasaki et al. · 2004 [cited by applicant]
US 20040193421A1 · Blass · 2004 [cited by applicant]
US 20050033582A1 · Gadd et al. · 2005 [cited by applicant]
US 20050080628A1 · Kuperstein · 2005 [cited by applicant]
US 20060217978A1 · Mitby et al. · 2006 [cited by applicant]
US 20070198272A1 · Horioka et al. · 2007 [cited by applicant]
US 20120016678A1 · Gruber et al. · 2012 [cited by applicant]
US 20120022872A1 · Gruber et al. · 2012 [cited by applicant]
US 20120265528A1 · Gruber et al. · 2012 [cited by applicant]
US 20130080173A1 · Talwar et al. · 2013 [cited by applicant]
US 20130275164A1 · Gruber et al. · 2013 [cited by applicant]
US 20130275875A1 · Gruber et al. · 2013 [cited by applicant]
US 20130275899A1 · Schubert et al. · 2013 [cited by applicant]
US 20130346077A1 · Mengibar et al. · 2013 [cited by applicant]
US 20140074483A1 · van Os · 2014 [cited by applicant]
US 20140156277A1 · Fujii et al. · 2014 [cited by applicant]
US 20140180697A1 · Torok et al. · 2014 [cited by applicant]
US 20140195252A1 · Gruber et al. · 2014 [cited by applicant]
US 20140223011A1 · Smith et al. · 2014 [cited by applicant]
US 20140278444A1 · Larson et al. · 2014 [cited by applicant]
US 20140316764A1 · Ayan et al. · 2014 [cited by applicant]
US 20140365209A1 · Evermann · 2014 [cited by applicant]
US 20140365216A1 · Gruber et al. · 2014 [cited by applicant]
US 20150206533A1 · Jin et al. · 2015 [cited by applicant]
US 20150379989A1 · Balasubramanian et al. · 2015 [cited by applicant]
US 20160179801A1 · Venkataraman et al. · 2016 [cited by applicant]
US 20160259775A1 · Gelfenbeyn et al. · 2016 [cited by applicant]
US 20160365209A1 · Blackmon et al. · 2016 [cited by applicant]
US 20200081976A1 · Gelfenbeyn et al. · 2020 [cited by applicant]
US 20220147712A1 · Gelfenbeyn et al. · 2022 [cited by applicant]