公开(公告)号：US12265560B2

公开(公告)日：2025-04-01

申请号：US18141172

申请日：2023-04-28

Applicant: GOOGLE LLC

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

IPC: G06F16/00 ,  G06F16/332 ,  G06F16/3329 ,  G06F16/3332 ,  G06F16/334 ,  G06F16/3349

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：US20250069597A1

公开(公告)日：2025-02-27

申请号：US18943544

申请日：2024-11-11

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

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：US20250069595A1

公开(公告)日：2025-02-27

申请号：US18236661

申请日：2023-08-22

Applicant: Google LLC

Inventor： Vladimir Vuskovic ,  Lukasz Bieniasz-Krzywiec ,  Jingwei Zhang ,  Ferdinand Lösch

IPC: G10L15/183 ,  G10L15/22

Abstract: Systems and methods are provided that allow for efficient and reliable execution of complex tasks using large language models (LLMs). Disclosed systems may include a runtime manager that is in communication with an LLM, and which controls the LLM's execution of the complex task. This control can be defined by a “playbook” that is provided to the LLM, and which contains a series of instructions that are to be followed by the LLM under a desired level of control by the runtime manager. The playbook can take the form of a script containing a sequence of instructions and related conditions that are written in a human-readable, natural-language format.

公开(公告)号：US20240087560A1

公开(公告)日：2024-03-14

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

CPC classification number: G10L15/1815 ,  G06F3/167 ,  G06F40/30 ,  G10L15/1822 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/226

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：US20240005125A1

公开(公告)日：2024-01-04

申请号：US18367828

申请日：2023-09-13

Applicant: GOOGLE LLC

Inventor： Yariv Adan ,  Vladimir Vuskovic ,  Behshad Behzadi

IPC: G06N3/006 ,  G06Q10/0631 ,  G10L15/22 ,  G06Q10/02 ,  G06F3/16 ,  G06F16/332

CPC classification number: G06N3/006 ,  G06Q10/063114 ,  G10L15/22 ,  G06Q10/02 ,  G06F3/167 ,  G06F16/3329 ,  G10L2015/223 ,  H04M2203/355 ,  G10L13/00

Abstract: An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; identifying, based on the utterance, a task to be performed by the computational assistant; responsive to determining, by the computational assistant, that complete performance of the task will take more than a threshold amount of time, outputting, for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs a user of the computing device that complete performance of the task will not be immediate; and performing, by the computational assistant, the task.

公开(公告)号：US11769502B2

公开(公告)日：2023-09-26

申请号：US17339114

申请日：2021-06-04

Applicant: Google LLC

Inventor： Mugurel Ionut Andreica ,  Vladimir Vuskovic ,  Joseph Lange ,  Sharon Stovezky ,  Marcin Nowak-Przygodzki

IPC: G10L15/22 ,  G06N3/08 ,  G10L15/02

CPC classification number: G10L15/22 ,  G06N3/08 ,  G10L15/02 ,  G10L2015/223

Abstract: Implementations are set forth herein for creating an order of execution for actions that were requested by a user, via a spoken utterance to an automated assistant. The order of execution for the requested actions can be based on how each requested action can, or is predicted to, affect other requested actions. In some implementations, an order of execution for a series of actions can be determined based on an output of a machine learning model, such as a model that has been trained according to supervised learning. A particular order of execution can be selected to mitigate waste of processing, memory, and network resources—at least relative to other possible orders of execution. Using interaction data that characterizes past performances of automated assistants, certain orders of execution can be adapted over time, thereby allowing the automated assistant to learn from past interactions with one or more users.

公开(公告)号：US20230259537A1

公开(公告)日：2023-08-17

申请号：US18141172

申请日：2023-04-28

Applicant: GOOGLE LLC

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

IPC: G06F16/332 ,  G06F16/33

CPC classification number: G06F16/3325 ,  G06F16/3329 ,  G06F16/3349 ,  G06F16/3344 ,  G06F16/3338

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：US20230054023A1

公开(公告)日：2023-02-23

申请号：US17982815

申请日：2022-11-08

Applicant: GOOGLE LLC

Inventor： Yariv Adan ,  Vladimir Vuskovic ,  Behshad Behzadi

IPC: G06N3/00 ,  G06Q10/06 ,  G10L15/22 ,  G06Q10/02 ,  G06F3/16 ,  G06F16/332

Abstract: An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; identifying, based on the utterance, a task to be performed by the computational assistant; responsive to determining, by the computational assistant, that complete performance of the task will take more than a threshold amount of time, outputting, for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs a user of the computing device that complete performance of the task will not be immediate; and performing, by the computational assistant, the task.

公开(公告)号：US11381409B2

公开(公告)日：2022-07-05

申请号：US16927373

申请日：2020-07-13

Applicant: Google LLC

Inventor： Vladimir Vuskovic ,  Yariv Adan

IPC: H04L12/18 ,  H04L51/02 ,  G06F40/40 ,  G06F16/00 ,  G06Q10/00 ,  H04L51/00 ,  G06Q10/06 ,  H04L65/4038 ,  H04L67/75

Abstract: Techniques are described herein for automated assistants that proactively provide content to participant(s) of multi-participant message exchange threads (e.g., group chats, audio and/or video calls in which oral messages are transcribed for analysis, etc.) based on signals such as individual participant profiles associated with participant(s). In various implementations, automated assistant(s) that may not be explicitly invoked may analyze content of a message exchange thread involving multiple human participants and/or document(s) associated with the message exchange thread. Based on the analyzing, the automated assistant(s) may identify topic(s) pertinent to the message exchange thread. Based on individual participant profiles associated with the participants, the automated assistant(s) may identify shared interest(s) of the participants. The automated assistant(s) may then select new content based both on the pertinent topic(s) and the shared interest(s) of the participants and proactively provide the new content to one or more of the participants.

公开(公告)号：US20210280180A1

公开(公告)日：2021-09-09

申请号：US16343683

申请日：2019-02-07

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 ,  G10L15/28 ,  G10L15/18

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.