公开(公告)号：US20240330361A1

公开(公告)日：2024-10-03

申请号：US18741082

申请日：2024-06-12

Applicant: Google LLC

Inventor： Zhen Li ,  Yi-Ting Chen ,  Yaxi Gao ,  Da-Cheng Juan ,  Aleksei Timofeev ,  Chun-Ta Lu ,  Futang Peng ,  Sujith Ravi ,  Andrew Tomkins ,  Thomas J. Duerig

IPC: G06F16/55 ,  G06F16/538 ,  G06F16/9538 ,  G06F18/214 ,  G06F18/22 ,  G06F18/40 ,  G06N3/042 ,  G06N3/044 ,  G06N3/084

CPC classification number: G06F16/55 ,  G06F16/538 ,  G06F16/9538 ,  G06F18/2148 ,  G06F18/22 ,  G06F18/41 ,  G06N3/042 ,  G06N3/044 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.

公开(公告)号：US20240231862A1

公开(公告)日：2024-07-11

申请号：US18615767

申请日：2024-03-25

Applicant: GOOGLE LLC

Inventor： Robin Dua ,  Andrew Tomkins ,  Sujith Ravi

IPC: G06F9/451 ,  G06F3/0481 ,  G06F40/20 ,  G06F40/30 ,  G06N20/00 ,  H04L67/60

CPC classification number: G06F9/453 ,  G06F3/0481 ,  G06F40/20 ,  G06F40/30 ,  G06N20/00 ,  H04L67/60

Abstract: Facilitating user device and/or agent device actions during a communication session. An interactive communications system provides outputs that are tailored to enhance the functionality of the communication session, reduce the number of dialog “turns” of the communications session and/or the number of user inputs to devices involved in the session, and/or otherwise mitigate consumption of resources during the communication session. In various implementations, the communication session involves user device(s) of a user, agent device(s) of an agent, and the interactive system. The interactive communications system can analyze various communications from the user device(s) and/or agent device(s) during a communication session in which the user directs various communications to the agent, and in which the agent optionally directs various communications to the user. The interactive communications system provides action performance element(s) and/or other output(s) that are each specific to a corresponding current intent and corresponding current action of the communication session.

公开(公告)号：US11941420B2

公开(公告)日：2024-03-26

申请号：US17687316

申请日：2022-03-04

Applicant: Google LLC

Inventor： Robin Dua ,  Andrew Tomkins ,  Sujith Ravi

IPC: G06F9/451 ,  G06F3/0481 ,  G06F40/20 ,  G06F40/30 ,  G06N20/00 ,  H04L67/60

CPC classification number: G06F9/453 ,  G06F3/0481 ,  G06F40/20 ,  G06F40/30 ,  G06N20/00 ,  H04L67/60

Abstract: Implementations are directed to facilitating user device and/or agent device actions during a communication session. An interactive communications system provides outputs, as outlined below, that are tailored to enhance the functionality of the communication session, reduce the number of dialog “turns” of the communications session and/or the number of user inputs to devices involved in the session, and/or otherwise mitigate consumption of network and/or hardware resources during the communication session. In various implementations, the communication session involves user device(s) of a user, agent device(s) of an agent, and the interactive communications system. The interactive communications system can analyze various communications from the user device(s) and/or agent device(s) during a communication session in which the user (via the user device(s)) directs various communications to the agent, and in which the agent (via the agent device(s)) optionally directs various communications to the user. The interactive communications system provides action performance element(s) and/or other output(s) that are each specific to a corresponding current intent and corresponding current action of the communication session.

公开(公告)号：US20230205813A1

公开(公告)日：2023-06-29

申请号：US18171511

申请日：2023-02-20

Applicant: Google LLC

Inventor： Zhen Li ,  Yi-Ting Chen ,  Yaxi Gao ,  Da-Cheng Juan ,  Aleksei Timofeev ,  Chun-Ta Lu ,  Futang Peng ,  Sujith Ravi ,  Andrew Tomkins ,  Thomas J. Duerig

IPC: G06F16/55 ,  G06F16/538 ,  G06F16/9538 ,  G06N3/084 ,  G06F18/22 ,  G06F18/40 ,  G06F18/214 ,  G06N3/042 ,  G06N3/044

CPC classification number: G06F16/55 ,  G06F16/538 ,  G06F16/9538 ,  G06N3/084 ,  G06F18/22 ,  G06F18/41 ,  G06F18/2148 ,  G06N3/042 ,  G06N3/044

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.

公开(公告)号：US20230048218A1

公开(公告)日：2023-02-16

申请号：US17878631

申请日：2022-08-01

Applicant: Google LLC

Inventor： Sujith Ravi ,  Zornitsa Kozareva

IPC: G06F40/30 ,  G06N3/08 ,  G06N3/04 ,  G06F40/253

Abstract: The present disclosure provides projection neural networks and example applications thereof. In particular, the present disclosure provides a number of different architectures for projection neural networks, including two example architectures which can be referred to as: Self-Governing Neural Networks (SGNNs) and Projection Sequence Networks (ProSeqoNets). Each projection neural network can include one or more projection layers that project an input into a different space. For example, each projection layer can use a set of projection functions to project the input into a bit-space, thereby greatly reducing the dimensionality of the input and enabling computation with lower resource usage. As such, the projection neural networks provided herein are highly useful for on-device inference in resource-constrained devices. For example, the provided SGNN and ProSeqoNet architectures are particularly beneficial for on-device inference such as, for example, solving natural language understanding tasks on-device.

公开(公告)号：US11526680B2

公开(公告)日：2022-12-13

申请号：US16790917

申请日：2020-02-14

Applicant: Google LLC

Inventor： Sujith Ravi ,  Zornitsa Kozareva ,  Chinnadhurai Sankar

IPC: G06F40/56 ,  G06N20/00 ,  H04L67/04 ,  G06K9/62 ,  G06N3/04

Abstract: Systems and methods are provided to pre-train projection networks for use as transferable natural language representation generators. In particular, example pre-training schemes described herein enable learning of transferable deep neural projection representations over randomized locality sensitive hashing (LSH) projections, thereby surmounting the need to store any embedding matrices because the projections can be dynamically computed at inference time.

公开(公告)号：US20220383036A1

公开(公告)日：2022-12-01

申请号：US17764015

申请日：2020-09-25

Applicant: Google LLC

Inventor： Azade Nazi ,  Azalia Mirhoseini ,  Anna Darling Goldie ,  Sujith Ravi ,  William Hang

IPC: G06K9/62 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a clustering neural network. One of the methods includes obtaining unlabeled training data; and training the clustering neural network on the unlabeled training data to determine trained values of the clustering parameters by minimizing a normalized cuts loss function that includes a first term that measures an expected normalized cuts of clustering nodes in a graph representing the data set into the plurality of clusters according to clustering outputs generated by the clustering neural network.

公开(公告)号：US20220374719A1

公开(公告)日：2022-11-24

申请号：US17861930

申请日：2022-07-11

Applicant: Google LLC

Inventor： Sujith Ravi ,  Gaurav Menghani ,  Prabhu Kaliamoorthi ,  Yicheng Fan

IPC: G06N3/08 ,  G06F8/76 ,  G06F9/54 ,  G06K9/62

Abstract: The present disclosure provides an application development platform and associated software development kits (“SDKs”) that provide comprehensive services for generation, deployment, and management of machine-learned models used by computer applications such as, for example, mobile applications executed by a mobile computing device. In particular, the application development platform and SDKs can provide or otherwise leverage a unified, cross-platform application programming interface (“API”) that enables access to all of the different machine learning services needed for full machine learning functionality within the application. In such fashion, developers can have access to a single SDK for all machine learning services.

公开(公告)号：US20220292261A1

公开(公告)日：2022-09-15

申请号：US17582206

申请日：2022-01-24

Applicant: Google LLC

Inventor： Dana Movshovitz-Attias ,  John Patrick McGregor, JR. ,  Gaurav Nemade ,  Sujith Ravi ,  Jeongwoo Ko ,  Dora Demszky

IPC: G06F40/289 ,  G06F40/30 ,  G06N20/00

Abstract: The technology relates to methods for detecting and classifying emotions in textual communication, and using this information to suggest graphical indicia such as emoji, stickers or GIFs to a user. Two main types of models are fully supervised models and few-shot models. In addition to fully supervised and few-shot models, other types of models focusing on the back-end (server) side or client (on-device) side may also be employed. Server-side models are larger-scale models that can enable higher degrees of accuracy, such as for use cases where models can be hosted on cloud servers where computational and storage resources are relatively abundant. On-device models are smaller-scale models, which enable use on resource-constrained devices such as mobile phones, smart watches or other wearables (e.g., head mounted displays), in-home devices, embedded devices, etc.

公开(公告)号：US11269666B2

公开(公告)日：2022-03-08

申请号：US16621769

申请日：2018-08-22

Applicant: Google LLC

Inventor： Robin Dua ,  Andrew Tomkins ,  Sujith Ravi

IPC: G06F3/0481 ,  G06F9/451 ,  G06N20/00 ,  G06F40/30 ,  H04L67/60 ,  G06F40/20

Abstract: Implementations are directed to facilitating user device and/or agent device actions during a communication session. An interactive communications system provides outputs, as outlined below, that are tailored to enhance the functionality of the communication session, reduce the number of dialog “turns” of the communications session and/or the number of user inputs to devices involved in the session, and/or otherwise mitigate consumption of network and/or hardware resources during the communication session. In various implementations, the communication session involves user device(s) of a user, agent device(s) of an agent, and the interactive communications system. The interactive communications system can analyze various communications from the user device(s) and/or agent device(s) during a communication session in which the user (via the user device(s)) directs various communications to the agent, and in which the agent (via the agent device(s)) optionally directs various communications to the user. The interactive communications system provides action performance element(s) and/or other output(s) that are each specific to a corresponding current intent and corresponding current action of the communication session.