-
公开(公告)号:US11232792B2
公开(公告)日:2022-01-25
申请号:US16829323
申请日:2020-03-25
Applicant: Google LLC
Inventor: Ibrahim Badr , Zaheed Sabur , Vladimir Vuskovic , Adrian Zumbrunnen , Lucas Mirelmann
IPC: G10L15/22 , G06F16/903 , G10L15/18 , G06N3/00
Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, in an existing human-to-computer dialog session between a user and an automated assistant, it may be determined that the automated assistant has responded to all natural language input received from the user. Based on characteristic(s) of the user, information of potential interest to the user or action(s) of potential interest to the user may be identified. Unsolicited content indicative of the information of potential interest to the user or the action(s) may be generated and incorporated by the automated assistant into the existing human-to-computer dialog session. In various implementations, the incorporating may be performed in response to the determining that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.
-
公开(公告)号:US11222637B2
公开(公告)日:2022-01-11
申请号:US16613705
申请日:2019-05-31
Applicant: Google LLC
Inventor: Lucas Mirelmann , Zaheed Sabur , Bohdan Vlasyuk , Marie Patriarche Bledowski , Sergey Nazarov , Denis Burakov , Behshad Behzadi , Michael Golikov , Steve Cheng , Daniel Cotting , Mario Bertschler
Abstract: Implementations herein relate to pre-caching data, corresponding to predicted interactions between a user and an automated assistant, using data characterizing previous interactions between the user and the automated assistant. An interaction can be predicted based on details of a current interaction between the user and an automated assistant. One or more predicted interactions can be initialized, and/or any corresponding data pre-cached, prior to the user commanding the automated assistant in furtherance of the predicted interaction. Interaction predictions can be generated using a user-parameterized machine learning model, which can be used when processing input(s) that characterize a recent user interaction with the automated assistant. Should the user command the automated assistant in a way that is aligned with a pre-cached, predicted interaction, the automated assistant will exhibit instant fulfillment of the command, thereby eliminating any latency that the user would have otherwise experienced interacting with the automated assistant.
-
公开(公告)号:US11102309B2
公开(公告)日:2021-08-24
申请号:US16860706
申请日:2020-04-28
Applicant: Google LLC
Inventor: Zaheed Sabur , Andrea Terwisscha van Scheltinga , Mikhail Reutov , Lucas Mirelmann
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for pairing a speech-enabled device with a display device. A determination may be made to pair a speech-enabled device with a display device of a particular type. A set of display devices that are associated with the speech-enabled device may be identified in response to determining to pair the speech-enabled device with the display device of the particular type. An instruction may be provided to each of the display devices. The instruction may cause the display device to determine (i) whether the display device is of the particular type and (ii) whether the display device and the speech-enabled device both share a local area network and display on the display device an indication regarding pairing with the speech-enabled device.
-
公开(公告)号:US10929416B2
公开(公告)日:2021-02-23
申请号:US16806682
申请日:2020-03-02
Applicant: Google LLC
Inventor: Tilke Mary Judd , Zaheed Sabur , Eduardo Jodas Samper , Alexandru Ovidiu Dovlecel , Ardan Arac
IPC: G06F16/248 , G06F16/951 , G06F16/2457
Abstract: Implementations include actions of obtaining a set of entities based on one or more terms of a query, obtaining one or more entities associated with each live event of a plurality of live events, identifying a live event that is responsive to the query based on comparing at least one entity in the set of entities to one or more entities associated with each live event of a plurality of live events, determining that an event search result corresponding to the live event is to be displayed in search results, and in response: providing the event search result for display, the event search result including information associated with the live event, the information including an indicator of an occurrence of the live event.
-
公开(公告)号:US10791078B2
公开(公告)日:2020-09-29
申请号:US15953266
申请日:2018-04-13
Applicant: Google LLC
Inventor: Fredrik Bergenlid , Vladyslav Lysychkin , Denis Burakov , Behshad Behzadi , Andrea Terwisscha van Scheltinga , Quentin Lascombes de Laroussilhe , Mikhail Golikov , Koa Metter , Ibrahim Badr , Zaheed Sabur
IPC: H04L12/58 , G06F16/44 , H04N21/4788 , H04N21/439 , H04N7/15 , G10L15/22 , G10L25/63 , G10L15/16 , G10L15/00
Abstract: Implementations relate to providing information items for display during a communication session. In some implementations, a computer-implemented method includes receiving, during a communication session between a first computing device and a second computing device, first media content from the communication session. The method further includes determining a first information item for display in the communication session based at least in part on the first media content. The method further includes sending a first command to at least one of the first computing device and the second computing device to display the first information item.
-
公开(公告)号:US10560761B2
公开(公告)日:2020-02-11
申请号:US16017718
申请日:2018-06-25
Applicant: GOOGLE LLC
Inventor: Andrea Terwisscha van Scheltinga , Zaheed Sabur , Michael Reutov , Pratik Gilda
Abstract: A first computing device may receive an indication of user input that is at least a part of a conversation between a user and a first assistant executing at the first computing device. The first assistant and/or an assistant executing at a digital assistant system may determine whether to handoff the conversation from the first assistant executing at the first computing device to a second assistant executing at a second computing device. In response to determining to handoff the conversation to the second assistant executing at the second computing device, the first assistant and/or the assistant executing at the digital assistant system may send to the second computing device a request to handoff the conversation which includes at least an indication of the conversation.
-
公开(公告)号:US20190230056A1
公开(公告)日:2019-07-25
申请号:US16369680
申请日:2019-03-29
Applicant: Google LLC
Inventor: Tilke Judd , Yariv Adan , Zaheed Sabur , Behshad Behzadi , Lucas Mirelmann , Jan Lamecki , Dhruv Bakshi
IPC: H04L12/58 , G06F16/93 , H04W4/12 , H04W4/02 , H04L29/08 , G06F3/0482 , G06F16/955 , G06Q10/10 , G06F17/24 , G06F17/22
Abstract: Methods, apparatus, systems, and computer-readable media are provided for incorporating application links into message exchange threads. One or more cues emanating from a message exchange thread involving two or more message exchange clients may be detected. The one or more cues may trigger incorporation, into the message exchange thread, of a selectable link to a distinct application. At least one candidate application that is installed on a given client computing device operated by a message exchange thread participant may be identified. The candidate application may be associated with content of the message exchange thread. A selectable link may be incorporated into a transcript of the message exchange thread displayed in a graphical user interface of a message exchange client operating on the given client computing device. The selectable link may be operable by the participant to expose to the participant an interface associated with a respective candidate application.
-
公开(公告)号:US20190036856A1
公开(公告)日:2019-01-31
申请号:US15953266
申请日:2018-04-13
Applicant: Google LLC
Inventor: Fredrik Bergenlid , Vladyslav Lysychkin , Denis Burakov , Behshad Behzadi , Andrea Terwisscha van Scheltinga , Quentin Lascombes de Laroussilhe , Mikhail Golikov , Koa Metter , Ibrahim Badr , Zaheed Sabur
CPC classification number: H04L51/10 , G06F16/44 , G10L15/005 , G10L15/16 , G10L15/22 , G10L25/63 , G10L2015/223 , H04N7/15 , H04N21/4394 , H04N21/4788
Abstract: Implementations relate to providing information items for display during a communication session. In some implementations, a computer-implemented method includes receiving, during a communication session between a first computing device and a second computing device, first media content from the communication session. The method further includes determining a first information item for display in the communication session based at least in part on the first media content. The method further includes sending a first command to at least one of the first computing device and the second computing device to display the first information item.
-
-
-
-
-
-
-