公开(公告)号：US20220157309A1

公开(公告)日：2022-05-19

申请号：US17588451

申请日：2022-01-31

Applicant: GOOGLE LLC

Inventor： Gleb Skobeltsyn ,  Olga Kapralova ,  Konstantin Shagin ,  Vladimir Vuskovic ,  Yufei Zhao ,  Bradley Nelson ,  Alessio Macrì ,  Abraham Lee

IPC: G10L15/22 ,  G06F3/16 ,  G10L15/18 ,  G10L15/28

Abstract: Implementations described herein relate to providing suggestions, via a display modality, for completing a spoken utterance for an automated assistant, in order to reduce a frequency and/or a length of time that the user will participate in a current and/or subsequent dialog session with the automated assistant. A user request can be compiled from content of an ongoing spoken utterance and content of any selected suggestion elements. When a currently compiled portion of the user request (from content of a selected suggestion(s) and an incomplete spoken utterance) is capable of being performed via the automated assistant, any actions corresponding to the currently compiled portion of the user request can be performed via the automated assistant. Furthermore, any further content resulting from performance of the actions, along with any discernible context, can be used for providing further suggestions.

公开(公告)号：US20190246045A1

公开(公告)日：2019-08-08

申请号：US16259946

申请日：2019-01-28

Applicant: Google LLC

Inventor： Vladimir Vuskovic ,  Dhruv Bakshi ,  Amaury Forgeot d'Arc ,  Christoph Poropatits

IPC: H04N5/262 ,  G06F16/48 ,  H04N21/435 ,  H04N21/854 ,  H04N21/84 ,  H04N21/81 ,  H04N21/2743 ,  H04N21/44 ,  H04N21/431 ,  H04N21/2668 ,  H04N21/2343 ,  H04N21/234 ,  G11B27/031 ,  G06K9/62 ,  G06K9/00 ,  H04N21/258 ,  H04N21/475 ,  H04N21/4722 ,  H04N7/12

CPC classification number: H04N5/262 ,  G06F16/48 ,  G06K9/00718 ,  G06K9/6256 ,  G11B27/031 ,  H04N7/12 ,  H04N21/23424 ,  H04N21/23439 ,  H04N21/25825 ,  H04N21/2668 ,  H04N21/2743 ,  H04N21/4312 ,  H04N21/4355 ,  H04N21/44016 ,  H04N21/4722 ,  H04N21/4756 ,  H04N21/812 ,  H04N21/8126 ,  H04N21/84 ,  H04N21/85403

Abstract: Systems and methods for optimizing videos are disclosed. A method of the present disclosure includes providing a user interface (UI) that presents a plurality of metrics for analysis of a plurality of videos of an entity, and receiving, via the UI, a user selection of a subset of metrics of the plurality of metrics. The method also includes in response to the user selection of the subset of metrics, processing a video of the plurality of videos using a machine learning algorithm or a plurality of rules to determine one or more optimizations for the video, the one or more optimizations reflecting the subset of metrics to improve viewership statistics of the video. The method further includes modifying the video to produce a modified version of the video that implements the one or more optimizations, and causing the modified version of the video to be presented to viewers to demonstrate results of the one or more optimizations.

公开(公告)号：US20190095523A1

公开(公告)日：2019-03-28

申请号：US16135205

申请日：2018-09-19

Applicant: Google LLC

Inventor： Vladimir Vuskovic ,  Joseph Lange ,  Behshad Behzadi ,  Marcin M. Nowak-Przygodzki

IPC: G06F17/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating subqueries from a query. In one aspect, a method includes obtaining a query, generating a set of two subqueries from the query, where the set includes a first subquery and a second subquery, determining a quality score for the set of two subqueries, determining whether the quality score for the set of two subqueries satisfies a quality threshold, and in response to determining that the quality score for the set of two subqueries satisfies the quality threshold, providing a first response to the first subquery that is responsive to a first operation that receives the first subquery as input and providing a second response to the second subquery that is responsive to a second operation that receives the second subquery as input.

公开(公告)号：US20250157469A1

公开(公告)日：2025-05-15

申请号：US19025036

申请日：2025-01-16

Applicant: GOOGLE LLC

Inventor： Ibrahim Badr ,  Zaheed Sabur ,  Vladimir Vuskovic ,  Adrian Zumbrunnen ,  Lucas Mirelmann

IPC: G10L15/22 ,  G06F16/903 ,  G06N3/006 ,  G10L15/18

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：US12154557B2

公开(公告)日：2024-11-26

申请号：US18511517

申请日：2023-11-16

Applicant: GOOGLE LLC

Inventor： Gleb Skobeltsyn ,  Mihaly Kozsevnyikov ,  Vladimir Vuskovic

IPC: G10L15/18 ,  G06F3/16 ,  G06F40/30 ,  G10L15/22

Abstract: The systems and methods of the present disclosure generally relate to a data processing system that can identify and surface alternative requests when presented with ambiguous, unclear, or other requests to which a data processing system may not be able to respond. The data processing system can improve the efficiency of network transmissions to reduce network bandwidth usage and processor utilization by selecting alternative requests that are responsive to the intent of the original request.

公开(公告)号：US11915692B2

公开(公告)日：2024-02-27

申请号：US17211488

申请日：2021-03-24

Applicant: Google LLC

Inventor： James Kuczmarski ,  Vibhor Jain ,  Amarnag Subramanya ,  Nimesh Ranjan ,  Melvin Jose Johnson Premkumar ,  Vladimir Vuskovic ,  Luna Dai ,  Daisuke Ikeda ,  Nihal Sandeep Balani ,  Jinna Lei ,  Mengmeng Niu

IPC: G06F40/00 ,  G10L15/183 ,  G10L15/00 ,  G10L15/22 ,  G06F16/33 ,  G06N20/00 ,  G06F16/332 ,  G06F40/47 ,  G06F40/58 ,  H04L51/02 ,  G06F18/22

CPC classification number: G10L15/183 ,  G06F16/3329 ,  G06F16/3337 ,  G06F18/22 ,  G06F40/47 ,  G06F40/58 ,  G06N20/00 ,  G10L15/005 ,  G10L15/22 ,  H04L51/02

Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.

公开(公告)号：US11869506B2

公开(公告)日：2024-01-09

申请号：US17587478

申请日：2022-01-28

Applicant: Google LLC

Inventor： Michael Fink ,  Vladimir Vuskovic ,  Shimon Or Salant ,  Deborah Cohen ,  Asaf Revach ,  David Kogan ,  Andrew Callahan ,  Richard Borovoy ,  Andrew Richardson ,  Eran Ofek ,  Idan Szpektor ,  Jonathan Berant ,  Yossi Matias

IPC: G06F40/35 ,  G06N3/0475 ,  G10L15/22 ,  G06F40/284 ,  G06N3/08 ,  G10L15/06 ,  G10L15/18 ,  G10L15/20

CPC classification number: G10L15/22 ,  G06F40/284 ,  G06N3/08 ,  G10L15/063 ,  G10L15/1815 ,  G10L15/20 ,  G10L2015/223

Abstract: Generating expanded responses that guide continuance of a human-to computer dialog that is facilitated by a client device and that is between at least one user and an automated assistant. The expanded responses are generated by the automated assistant in response to user interface input provided by the user via the client device, and are caused to be rendered to the user via the client device, as a response, by the automated assistant, to the user interface input of the user. An expanded response is generated based on at least one entity of interest determined based on the user interface input, and is generated to incorporate content related to one or more additional entities that are related to the entity of interest, but that are not explicitly referenced by the user interface input.

公开(公告)号：US11354521B2

公开(公告)日：2022-06-07

申请号：US16792572

申请日：2020-02-17

Applicant: Google LLC

Inventor： James Kuczmarski ,  Vibhor Jain ,  Amarnag Subramanya ,  Nimesh Ranjan ,  Melvin Jose Johnson Premkumar ,  Vladimir Vuskovic ,  Luna Dai ,  Daisuke Ikeda ,  Nihal Sandeep Balani ,  Jinna Lei ,  Mengmeng Niu ,  Hongjie Chai ,  Wangqing Yuan

IPC: G06F40/00 ,  G06F40/58 ,  G06F40/47 ,  G06F16/33 ,  G06K9/62 ,  H04L51/02 ,  G06N20/00 ,  G06F16/332

Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.

公开(公告)号：US20220130386A1

公开(公告)日：2022-04-28

申请号：US17572293

申请日：2022-01-10

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：US11282510B2

公开(公告)日：2022-03-22

申请号：US16829786

申请日：2020-03-25

Applicant: Google LLC

Inventor： Gleb Skobeltsyn ,  Mihaly Kozsevnyikov ,  Vladimir Vuskovic

IPC: G10L15/18 ,  G06F3/16 ,  G10L15/22 ,  G06F40/30

Abstract: The systems and methods of the present disclosure generally relate to a data processing system that can identify and surface alternative requests when presented with ambiguous, unclear, or other requests to which a data processing system may not be able to respond. The data processing system can improve the efficiency of network transmissions to reduce network bandwidth usage and processor utilization by selecting alternative requests that are responsive to the intent of the original request.