-
公开(公告)号:US11470022B2
公开(公告)日:2022-10-11
申请号:US16832637
申请日:2020-03-27
Applicant: Google LLC
Inventor: Marcin Nowak-Przygodzki , Jan Lamecki , Behshad Behzadi
IPC: H04L51/02 , H04L12/18 , G10L15/18 , G10L15/22 , G06Q10/10 , H04M3/493 , G10L15/26 , H04M3/527 , G10L15/30
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.
-
2.
公开(公告)号:US10601755B2
公开(公告)日:2020-03-24
申请号:US16170652
申请日:2018-10-25
Applicant: GOOGLE LLC
Inventor: Tilke Judd , Yariv Adan , Zaheed Sabur , Behshad Behzadi , Lucas Mirelmann , Jan Lamecki , Dhruv Bakshi
Abstract: Methods, apparatus, systems, and computer-readable media are provided for: operating an instance of a personal assistant module to serve a user while the user operates the client computing device, wherein the instance of the personal assistant module has access to a persistent record of a message exchange thread between the user and instance(s) of the personal assistant module; detecting cue(s) emanating from the persistent message exchange thread; identifying candidate application(s) that are installed on a client computing device operated by the user, wherein the candidate application(s) are associated with content of the message exchange thread; and incorporating, into a transcript of the message exchange thread that is displayed in a graphical user interface rendered on the client computing device, selectable link (operable by the user to cause the client computing device to expose to the user an interface associated with a respective candidate application.
-
公开(公告)号:US20190132265A1
公开(公告)日:2019-05-02
申请号:US15833454
申请日:2017-12-06
Applicant: Google LLC
Inventor: Marcin Nowak-Przygodzki , Jan Lamecki , Behshad Behzadi
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.
-
公开(公告)号:US20230013581A1
公开(公告)日:2023-01-19
申请号:US17944712
申请日:2022-09-14
Applicant: GOOGLE LLC
Inventor: Marcin Nowak-Przygodzki , Jan Lamecki , Behshad Behzadi
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.
-
公开(公告)号:US20220108696A1
公开(公告)日:2022-04-07
申请号:US17552887
申请日:2021-12-16
Applicant: Google LLC
Inventor: Andrea Terwisscha van Scheltinga , Nicolo D'Ercole , Zaheed Sabur , Bibo Xu , Megan Knight , Alvin Abdagic , Jan Lamecki , Bo Zhang
Abstract: Determining whether, upon cessation of a second automated assistant session that interrupted and supplanted a prior first automated assistant session: (1) to automatically resume the prior first automated assistant session, or (2) to transition to an alternative automated assistant state in which the prior first session is not automatically resumed. Implementations further relate to selectively causing, based on the determining and upon cessation of the second automated assistant session, either the automatic resumption of the prior first automated assistant session that was interrupted, or the transition to the state in which the first session is not automatically resumed.
-
公开(公告)号:US20200236069A1
公开(公告)日:2020-07-23
申请号:US16832637
申请日:2020-03-27
Applicant: Google LLC
Inventor: Marcin Nowak-Przygodzki , Jan Lamecki , Behshad Behzadi
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.
-
公开(公告)号:US20250157470A1
公开(公告)日:2025-05-15
申请号:US19025587
申请日:2025-01-16
Applicant: GOOGLE LLC
Inventor: Andrea Terwisscha van Scheltinga , Nicolo D'Ercole , Zaheed Sabur , Bibo Xu , Megan Knight , Alvin Abdagic , Jan Lamecki , Bo Zhang
Abstract: Determining whether, upon cessation of a second automated assistant session that interrupted and supplanted a prior first automated assistant session: (1) to automatically resume the prior first automated assistant session, or (2) to transition to an alternative automated assistant state in which the prior first session is not automatically resumed. Implementations further relate to selectively causing, based on the determining and upon cessation of the second automated assistant session, either the automatic resumption of the prior first automated assistant session that was interrupted, or the transition to the state in which the first session is not automatically resumed.
-
公开(公告)号:US12243526B2
公开(公告)日:2025-03-04
申请号:US18238898
申请日:2023-08-28
Applicant: GOOGLE LLC
Inventor: Andrea Terwisscha van Scheltinga , Nicolo D'Ercole , Zaheed Sabur , Bibo Xu , Megan Knight , Alvin Abdagic , Jan Lamecki , Bo Zhang
Abstract: Determining whether, upon cessation of a second automated assistant session that interrupted and supplanted a prior first automated assistant session: (1) to automatically resume the prior first automated assistant session, or (2) to transition to an alternative automated assistant state in which the prior first session is not automatically resumed. Implementations further relate to selectively causing, based on the determining and upon cessation of the second automated assistant session, either the automatic resumption of the prior first automated assistant session that was interrupted, or the transition to the state in which the first session is not automatically resumed.
-
公开(公告)号:US11830491B2
公开(公告)日:2023-11-28
申请号:US17552887
申请日:2021-12-16
Applicant: Google LLC
Inventor: Andrea Terwisscha van Scheltinga , Nicolo D'Ercole , Zaheed Sabur , Bibo Xu , Megan Knight , Alvin Abdagic , Jan Lamecki , Bo Zhang
CPC classification number: G10L15/22 , G06F3/167 , G10L15/083 , G10L2015/223
Abstract: Determining whether, upon cessation of a second automated assistant session that interrupted and supplanted a prior first automated assistant session: (1) to automatically resume the prior first automated assistant session, or (2) to transition to an alternative automated assistant state in which the prior first session is not automatically resumed. Implementations further relate to selectively causing, based on the determining and upon cessation of the second automated assistant session, either the automatic resumption of the prior first automated assistant session that was interrupted, or the transition to the state in which the first session is not automatically resumed.
-
公开(公告)号:US11741961B2
公开(公告)日:2023-08-29
申请号:US17552887
申请日:2021-12-16
Applicant: Google LLC
Inventor: Andrea Terwisscha van Scheltinga , Nicolo D'Ercole , Zaheed Sabur , Bibo Xu , Megan Knight , Alvin Abdagic , Jan Lamecki , Bo Zhang
CPC classification number: G10L15/22 , G06F3/167 , G10L15/083 , G10L2015/223
Abstract: Determining whether, upon cessation of a second automated assistant session that interrupted and supplanted a prior first automated assistant session: (1) to automatically resume the prior first automated assistant session, or (2) to transition to an alternative automated assistant state in which the prior first session is not automatically resumed. Implementations further relate to selectively causing, based on the determining and upon cessation of the second automated assistant session, either the automatic resumption of the prior first automated assistant session that was interrupted, or the transition to the state in which the first session is not automatically resumed.
-
-
-
-
-
-
-
-
-