IP Library Granted Patent US 12,500,856
Granted Patent B2
US 12,500,856 · App. 17/944,712 · Granted Dec 16, 2025

Automated assistants with conference capabilities

Inventors: Marcin Nowak-Przygodzki (Bäch, CH); Jan Lamecki (Zurich, CH); Behshad Behzadi (Freienbach, CH)
Assignee: GOOGLE LLC
H04L51/02G06Q10/1093G10L15/1815G10L15/22H04L12/1822H04L12/1831H04M3/4936H04M3/527G10L2015/223G10L15/26G10L15/30H04M2201/40H04M2203/5009H04M2203/5027
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 12,500,856
App. No.
17/944,712
Granted
Dec 16, 2025
Kind
B2
Abstract

Techniques are described related to enabling automated assistants to enter into a “conference mode” in which they can “participate” in meetings between multiple human participants and perform various functions described herein. In various implementations, an automated assistant implemented at least in part on conference computing device(s) may be set to a conference mode in which the automated assistant performs speech-to-text processing on multiple distinct spoken utterances, provided by multiple meeting participants, without requiring explicit invocation prior to each utterance. The automated assistant may perform semantic processing on first text generated from the speech-to-text processing of one or more of the spoken utterances, and generate, based on the semantic processing, data that is pertinent to the first text. The data may be output to the participants at conference computing device(s). The automated assistant may later determine that the meeting has concluded, and may be set to a non-conference mode.

Claims (43)

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

during a first conference dialog session between multiple participants, setting an automated assistant implemented at least in part on one or more conference computing devices to a conference mode in which the automated assistant performs semantic processing on multiple distinct spoken utterances without requiring explicit invocation of the automated assistant prior to each of the multiple distinct spoken utterances;

detecting, by the automated assistant based on the semantic processing of the multiple distinct utterances, one or more topics discussed by one or more of the multiple participants during the first conference dialog session;

storing one or more of the topics discussed by one or more of the multiple participants during the first conference dialog session for use during one or more subsequent conference dialog sessions, wherein the first conference dialog session and the one or more subsequent conference dialog sessions are distinct from one other;

subsequent to the storing, transitioning the automated assistant out of the conference mode;

determining that a second conference dialog session, in which the automated assistant is transitioned back into the conference mode, subsequent to the first conference dialog session is a follow up conference dialog session to the first conference dialog session, wherein the determining comprises analyzing one or more electronic calendar entries associated with the first and second conference dialog sessions to detect whether there is an overlap between the multiple participants of the first conference dialog session and at least one participant in the second conference dialog session that occurs subsequent to the first conference dialog session;

in response to detecting an overlap between the multiple participants of the first conference dialog session and at least one participant of the second conference dialog session, carrying over content of the first conference dialog session to the second conference dialog session, wherein the carrying over includes, and during the second conference dialog session that occurs subsequent to the first conference dialog session, retrieving one or more of the stored topics; and

generating, by the automated assistant, data indicative of the one or more retrieved topics; and

outputting, by the automated assistant at one or more of the conference computing devices, the data indicative of the one or more retrieved topics.

2 . The method of claim 1 , wherein the determining is based on titles assigned to the first and second conference dialog sessions.

3 . The method of claim 1 , wherein the determining is based on one or more documents associated with the first and second conference dialog sessions.

4 . The method of claim 3 , further comprising generating an initial dialog context for the second conference dialog session based on one or more of the documents.

5 . The method of claim 1 , wherein the one or more of the topics discussed by one or more of the multiple participants comprise a plurality of action items, and the method further comprises:

determining that a given action item of the plurality of action items was addressed during a time interval between the first and second conference dialog sessions; and

refraining from including the given action item in the data indicative of the one or more retrieved topics.

6 . The method of claim 1 , wherein the one or more of the topics discussed by one or more of the multiple participants comprise a plurality of action items, and the method further comprises, in response to a determination that a given action item of the plurality of action items was not addressed during the first conference dialog session or during a time interval between the first and second conference dialog sessions, including the given action item in the data indicative of the one or more retrieved topics.

7 . A non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a processor, cause the processor to:

during a first conference dialog session between multiple participants, set an automated assistant implemented at least in part on one or more conference computing devices to a conference mode in which the automated assistant performs semantic processing on multiple distinct spoken utterances without requiring explicit invocation of the automated assistant prior to each of the multiple distinct spoken utterances;

detect, by the automated assistant based on the semantic processing of the multiple distinct utterances, one or more topics discussed by one or more of the multiple participants during the first conference dialog session;

store one or more of the topics discussed by one or more of the multiple participants during the first conference dialog session for use during one or more subsequent conference dialog sessions, wherein the first conference dialog session and the one or more subsequent conference dialog sessions are distinct from one other;

subsequent to the storing, transitioning the automated assistant out of the conference mode;

determine that a second conference dialog session, in which the automated assistant is transitioned back into the conference mode, subsequent to the first conference dialog session is a follow up conference dialog session to the first conference dialog session, wherein the instructions to determine comprise instructions to analyze one or more electronic calendar entries associated with the first and second conference dialog sessions to detect whether there is an overlap between the multiple participants of the first conference dialog session and at least one participant in the second conference dialog session that occurs subsequent to the first conference dialog session;

in response to detecting an overlap between the multiple participants of the first conference dialog session and at least one participant of the second conference dialog session, carry over content of the first conference dialog session to the second conference dialog session, wherein the instructions to carry over comprise instructions to, during the second conference dialog session that occurs subsequent to the first conference dialog session, retrieve one or more of the stored topics; and

generate, by the automated assistant, data indicative of the one or more retrieved topics; and

output, by the automated assistant at one or more of the conference computing devices, the data indicative of the one or more retrieved topics.

8 . The non-transitory computer-readable medium of claim 7 , wherein the determination that the second conference dialog session is related to the first conference dialog session is based on titles assigned to the first and second conference dialog sessions.

9 . The non-transitory computer-readable medium of claim 7 , wherein the determination that the second conference dialog session is related to the first conference dialog session is based on one or more documents associated with the first and second conference dialog sessions.

10 . A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions, cause the one or more processors to:

during a first conference dialog session between multiple participants, set an automated assistant implemented at least in part on one or more conference computing devices to a conference mode in which the automated assistant performs semantic processing on multiple distinct spoken utterances without requiring explicit invocation of the automated assistant prior to each of the multiple distinct spoken utterances;

detect, by the automated assistant based on the semantic processing of the multiple distinct utterances, one or more topics discussed by one or more of the multiple participants during the first conference dialog session;

store one or more of the topics discussed by one or more of the multiple participants during the first conference dialog session for use during one or more subsequent conference dialog sessions, wherein the first conference dialog session and the one or more subsequent conference dialog sessions are distinct from one other;

subsequent to the storing, transition the automated assistant out of the conference mode;

determine that a second conference dialog session, in which the automated assistant is transitioned back into the conference mode, subsequent to the first conference dialog session is a follow up conference dialog session to the first conference dialog session, wherein the instructions to determine comprise instructions to analyze one or more electronic calendar entries associated with the first and second conference dialog sessions to detect whether there is an overlap between the multiple participants of the first conference dialog session and at least one participant in the second conference dialog session that occurs subsequent to the first conference dialog session;

in response to detecting an overlap between the multiple participants of the first conference dialog session and at least one participant of the second conference dialog session, carry over content of the first conference dialog session to the second conference dialog session, wherein the instructions to carry over comprise instructions to, during the second conference dialog session that occurs subsequent to the first conference dialog session, retrieve one or more of the stored topics; and

generate, by the automated assistant, data indicative of the one or more retrieved topics; and

output, by the automated assistant at one or more of the conference computing devices, the data indicative of the one or more retrieved topics.

11 . The system of claim 10 , wherein the determination that the second conference dialog session is related to the first conference dialog session is based on titles assigned to the first and second conference dialog sessions.

12 . The system of claim 10 , wherein the determination that the second conference dialog session is related to the first conference dialog session is based on one or more documents associated with the first and second conference dialog sessions.

13 . The system of claim 12 , further comprising instructions to generate an initial dialog context for the second conference dialog session based on one or more of the documents.

14 . The system of claim 10 , wherein the one or more of the topics discussed by one or more of the multiple participants comprise a plurality of action items, and the system further comprises instructions to:

determine that a given action item of the plurality of action items was addressed during a time interval between the first and second conference dialog sessions; and

refrain from including the given action item in the data indicative of the one or more retrieved topics.

15 . The system of claim 10 , wherein the one or more of the topics discussed by one or more of the multiple participants comprise a plurality of action items, and the system further comprises instructions to, in response to a determination that a given action item of the plurality of action items was not addressed during the first conference dialog session or during a time interval between the first and second conference dialog sessions, include the given action item in the data indicative of the one or more retrieved topics.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 15, 2022
From: NOWAK-PRZYGODZKI, MARCIN; LAMECKI, JAN; BEHZADI, BEHSHAD
To: GOOGLE LLC
Reel/Frame 061107/0648 →
Continuity (4)
Continuation 16832637 · Mar 27, 2020
Continuation 15833454 · Dec 6, 2017
Provisional Application 62580982 · Nov 2, 2017
Related Publication 20230013581A1 · Jan 19, 2023
References Cited (78)
US 7603413B1 · Herold et al. · 2009 [cited by applicant]
US 9420227B1 · Shires et al. · 2016 [cited by applicant]
US 9734208B1 · Goldstein · 2017 [cited by examiner]
US 10176167B2 · Evermann · 2019 [cited by applicant]
US 10176808B1 · Lovitt et al. · 2019 [cited by applicant]
US 10339925B1 · Rastrow et al. · 2019 [cited by applicant]
US 10645035B2 · Nowak-przygodzki et al. · 2020 [cited by applicant]
US 10891947B1 · Le Chevalier · 2021 [cited by examiner]
US 20020103647A1 · Houplain · 2002 [cited by applicant]
US 20040145652A1 · Yamauchi et al. · 2004 [cited by applicant]
US 20130144603A1 · Lord 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 20140082100A1 · Sammon et al. · 2014 [cited by applicant]
US 20140164953A1 · Lynch et al. · 2014 [cited by applicant]
US 20140218372A1 · Missig et al. · 2014 [cited by applicant]
US 20140330562A1 · Gabara · 2014 [cited by applicant]
US 20150149177A1 · Kalns et al. · 2015 [cited by applicant]
US 20150181020A1 · Fitzsimmons · 2015 [cited by applicant]
US 20160294964A1 · Brune et al. · 2016 [cited by applicant]
US 20170092264A1 · Hakkani-Tur · 2017 [cited by examiner]
US 20180091648A1 · Hughes · 2018 [cited by applicant]
US 20180267774A1 · Williams et al. · 2018 [cited by applicant]
US 20180366118A1 · Lovitt · 2018 [cited by examiner]
US 20190074987A1 · Wiener · 2019 [cited by examiner]
US 20200236069A1 · Nowak-przygodzki et al. · 2020 [cited by applicant]
CN 102436812 · 2012 [cited by applicant]
CN 102572372 · 2012 [cited by applicant]
CN 105447578 · 2016 [cited by applicant]
CN 106471570 · 2017 [cited by applicant]
CN 106486116 · 2017 [cited by applicant]
CN 107210045 · 2017 [cited by applicant]
JP H0749695 · 1995 [cited by applicant]
JP 2006330170 · 2006 [cited by applicant]
JP 2007293454 · 2007 [cited by applicant]
JP 2010113610 · 2010 [cited by applicant]
JP 2014229075 · 2014 [cited by applicant]
JP 2015156099 · 2015 [cited by applicant]
JP 2017016566 · 2017 [cited by applicant]
JP 2017123027 · 2017 [cited by applicant]
JP 2017537361 · 2017 [cited by applicant]
KR 20100109499 · 2010 [cited by applicant]
KR 20100109520 · 2010 [cited by applicant]
KR 20110109977 · 2011 [cited by applicant]
KR 20120137434 · 2012 [cited by applicant]
KR 20140016154 · 2014 [cited by applicant]
KR 20160019435 · 2016 [cited by applicant]
KR 20160135346 · 2016 [cited by applicant]
KR 20170070094 · 2017 [cited by applicant]
WO 2014071152 · 2014 [cited by applicant]
WO 2017078792 · 2017 [cited by applicant]
WO 2018173252 · 2018 [cited by applicant]
G. Tur et al., “The CALO Meeting Assistant System,” in IEEE Transactions on Audio, Speech, and Language Processing, vol. 18, No. 6, pp. 1601-1611, Aug. 2010, doi: 10.1109/TASL.2009.2038810 (Year: 2010). [cited by examiner]
Japanese Patent Office; Notice of Reasons for Rejection issued in Application No. 2022-026648; 12 pages; dated Mar. 6, 2023. [cited by applicant]
Japanese Patent Office; Notice of Reasons for Rejection issued in Application No. 2022-026648; 13 pages; dated Aug. 14, 2023. [cited by applicant]
Intellectual Property India; Hearing Notice issued in Application No. 201927051000; 2 pages; dated Dec. 26, 2023. [cited by applicant]
China National Intellectual Property Administration; Notification of First Office Action issued in Application No. 202011124441.4, 15 pages; dated Dec. 5, 2023. [cited by applicant]
European Patent Office, Brief Communication issued in Application No. 19206958.1; 1 page; dated Feb. 16, 2024. [cited by applicant]
China National Intellectual Property Administration; Notice of Grant issue in Application No. 202011124441.4; 4 pages; dated Mar. 4, 2024. [cited by applicant]
European Patent Office; Intention to Grant issued in Application No. 19206958.1; 48 page; dated Mar. 14, 2024. [cited by applicant]
European Patent Office; Brief Communication issued in Application No. 19206958.1; 11 page; dated Feb. 29, 2024. [cited by applicant]
European Patent Office, Communication issue in application No. 24188660.5; 7 pages; dated Aug. 29, 2024. [cited by applicant]
Raux, A. ; Flexible Turn-Taking for Spoken Dialog System—PhD Thesis; 151 pages; dated Dec. 2008. [cited by applicant]
Galley et al.; Discourse Segmentation of Multi-Party Conversation; In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics; pp. 562-569; Sapporo, Japan; Association for Computational L… [cited by applicant]
Korean Patent Office; Notice of Office Action issued in Application No. KR10-2021-7038325; 6 pages; dated Feb. 28, 2022. [cited by applicant]
Tur et al.; The CALO Meeting Assistant System; in IEEE Transactions on Audio, Speech, and Language Processing; vol. 18, No. 6; pp. 1601-1611; doi: 10.1109/TASL.2009.2038810; dated Aug. 2010. [cited by applicant]
Japanese Patent Office; Notice of Allowance issued for Application No. 2020-169048 dated Jan. 24, 2022. [cited by applicant]
European Patent Office; Communication pursuant to Article 94(3) EPC issue in application No. 19206958.1; 7 pages; dated Oct. 26, 2021. [cited by applicant]
Korean Patent Office; Notice of Allowance issued in Application No. 10-2019-7038862; 4 pages; dated Aug. 27, 2021. [cited by applicant]
Intellectual Property India; Examination Report issued in Application No. 201927051000; 5 pages; dated Apr. 15, 2021. [cited by applicant]
Korean Patent Office; Notice of Office Action issued in Application No. 10-2019-7038862; 8 pages; dated Feb. 23, 2021. [cited by applicant]
Japan Patent Office: Notice of Allowance issued for Application No. 2019-568368 dated Sep. 7, 2020. [cited by applicant]
China National Intellectual Property Administration: Notice of Grant issued for Application No. 201880039481.3 dated Sep. 3, 2020. [cited by applicant]
China National Intellectual Property Administration; Notification of First Office Action issue in Application No. 201880039481.3; 10 pages; dated May 20, 2020. [cited by applicant]
European Patent Office—International Searching Authority; Notification of Transmittal of the International Search Report and the Written Opinion of PCT Serial No. PCT/US2018/058155; dated Feb. 12, 2019. [cited by applicant]
Prakken, Henry; “Formalizing Robert's Rules of Order. An Experiment in Automating Mediation of Group Decision Making”; GMD—German National Research Center for Information Technology, Germany (accessible at http://www.cs… [cited by applicant]
European Patent Office; Extended European Search report for EP19206958.1 9 pages; dated Jan. 29, 2020. [cited by applicant]
European Patent Office; Summons to attend oral proceedings issue in Application No. 19206958.1; 7 pages; dated Aug. 10, 2023. [cited by applicant]