公开(公告)号：US20250168892A1

公开(公告)日：2025-05-22

申请号：US18839598

申请日：2023-02-22

Applicant: GOOGLE LLC

Inventor： Chih-Hsiang Wu

IPC: H04W74/0833 ,  H04W74/00

Abstract: A user equipment (UE) 102 receives, from a radio access network (RAN) 105, a configuration for uplink transmission to the RAN 105 when a radio connection between the UE 102 and a radio access network (RAN) 105 is suspended (e.g., event 602); detects, at a first time when the radio connection is suspended, that a message for transmitting to the RAN 105 is available (e.g., event 604); and refrains, at the first time in response to determining that an uplink (UE) resource corresponding to the configuration is not available until a second time subsequent to the first time, from transmitting the message to the RAN 105 (e.g., event 608).

公开(公告)号：US20250168430A1

公开(公告)日：2025-05-22

申请号：US18944571

申请日：2024-11-12

Applicant: Google LLC

Inventor： Jing Lu ,  Fei Dong ,  Ravi Viswanathan

IPC: H04N21/25 ,  H04N21/266 ,  H04N21/488

Abstract: A method includes identifying a channel associated with a user of a content sharing platform. An indication of one or more channel related features associated with the channel is provided as input to an artificial intelligence (AI) model. The AI model is trained to predict a number of new users to obtain at least one content access level for the channel within a predetermined time of an effective date of the at least one content access level for the channel. One or more outputs of the AI model is obtained. The one or more obtained outputs comprise a predicted number of new users to obtain at least one content access level for the channel within a predetermined time of an effective date of the at least one content access level for the channel. A recommendation is provided for presentation on a client device of the user.

公开(公告)号：US20250167988A1

公开(公告)日：2025-05-22

申请号：US18960831

申请日：2024-11-26

Applicant: Google LLC

Inventor： Gang Wang ,  Ardian Poernomo ,  Marcel M. Moti Yung

IPC: H04L9/08 ,  G06F21/62 ,  G06Q10/10 ,  G06Q30/0241 ,  H04L9/06

Abstract: This disclosure relates to protecting the security of information in content selection and distribution. In one aspect, a method includes receiving, from a client device and by a first computing system of multi-party computation (MPC) systems, a digital component request including first secret shares of data identifying user groups that include a user of the client device as a member. The first computing system transmits a contextual digital component request to a content platform. The first computing system receives, from the content platform, selection data for multiple digital components. The selection data includes first vector data defining a contextual-based vector of values selected based in part on the set of contextual signals. The first computing system obtains, for each digital component, second vector data defining a user group-based vector of values selected based in part on a respective user group corresponding to the digital component.

公开(公告)号：US20250167310A1

公开(公告)日：2025-05-22

申请号：US19033274

申请日：2025-01-21

Applicant: Google LLC

Inventor： Jianmin Zhang ,  Mingfeng Xue ,  Chi Kin Benjamin Leung ,  Ramesh C. Bhardwaj ,  Sheba Devan

IPC: H01M10/0587 ,  H01M10/0525 ,  H01M50/497 ,  H01M50/531

Abstract: The present document describes a low-emission cylindrical-winding battery design. The battery design is a rolled and stacked battery, with two or more winding rolls of cathode and anode layers separated by insulation layers, the winding rolls also being separated by a distance with the distance, in some embodiments, filled with a dielectric material. A first winding roll of first stacked anode and cathode layers and a second winding roll of second stacked anode and cathode layers are wound in a direction around a central axis of the battery. The first winding roll of first stacked anode and cathode layers follows a first stacking order with the anode and cathode layers alternating. The second winding roll of second stacked anode and cathode layers follows a second stacking order with the anode and cathode layers alternating opposite to the first stacking order. The alternating stacking orders cause the battery to produce a reduced H-field when compared with a battery having non-alternating stacking orders.

公开(公告)号：US20250166628A1

公开(公告)日：2025-05-22

申请号：US19035299

申请日：2025-01-23

Applicant: Google LLC

Inventor： Victor Carbune ,  Matthew Sharifi

IPC: G10L15/22 ,  G06F16/9032 ,  G10L15/26 ,  G10L25/78

Abstract: A method includes instructing an always-on first processor to operate in a follow-on query detection mode, and while the always-on first processor operates in the follow-on query detection mode: receiving follow-on audio data captured by the assistant-enabled device; determining, using a voice activity detection (VAD) model executing on the always-on first processor, whether or not the VAD model detects voice activity in the follow-on audio data; performing, using a speaker identification (SID) model executing on the always-on first processor, speaker verification on the follow-on audio data to determine whether the follow-on audio data includes an utterance spoken by the same user. The method also includes initiating a wake-up process on a second processor to determine whether the utterance includes a follow-on query.

公开(公告)号：US20250166619A1

公开(公告)日：2025-05-22

申请号：US19029556

申请日：2025-01-17

Applicant: GOOGLE LLC

Inventor： David Roy Schairer ,  Di Lin ,  Lucas Palmer

IPC: G10L15/18 ,  G10L15/22 ,  G10L15/30

Abstract: Various implementations relate to techniques, for controlling smart devices, that are low latency and/or that provide computational efficiencies (client and/or server) and/or network efficiencies. Those implementations relate to generating and/or utilizing cache entries, of a cache that is stored locally at an assistant client device, in control of various smart devices (e.g., smart lights, smart thermostats, smart plugs, smart appliances, smart routers, etc.). Each of the cache entries includes a mapping of text to one or more corresponding semantic representations.

公开(公告)号：US20250166614A1

公开(公告)日：2025-05-22

申请号：US19034304

申请日：2025-01-22

Applicant: Google LLC

Inventor： Andrew Rosenberg ,  Bhuvana Ramabhadran ,  Zhehuai Chen ,  Yuan Wang ,  Yu Zhang ,  Jesse Emond

IPC: G10L15/06 ,  G06N3/0464 ,  G06N3/09

Abstract: A method includes receiving audio data corresponding to an utterance and generating a pair of positive audio data examples. Here, each positive audio data example includes a respective augmented copy of the received audio data. For each respective positive audio data example, the method includes generating a respective sequence of encoder outputs and projecting the respective sequence of encoder outputs for the positive data example into a contrastive loss space. The method also includes determining a L2 distance between each corresponding encoder output in the projected sequences of encoder outputs for the positive audio data examples and determining a per-utterance consistency loss by averaging the L2 distances. The method also includes generating corresponding speech recognition results for each respective positive audio data example. The method also includes updating parameters of the speech recognition model based on a respective supervised loss term and the per-utterance consistency loss.

公开(公告)号：US20250166337A1

公开(公告)日：2025-05-22

申请号：US19029798

申请日：2025-01-17

Applicant: Google LLC

Inventor： Brian Mulford ,  Nathan Frey ,  Alexandros Panagopoulos ,  Yinquan Hao ,  Yuan Zhang

IPC: G06V10/25 ,  G06F3/04845 ,  G06T3/10 ,  G06T7/11 ,  G06T11/20 ,  G06V20/05

Abstract: Described herein are systems and methods of converting media dimensions. A device may identify a set of frames from a video in a first orientation as belonging to a scene. The device may receive a selected coordinate on a frame of the set of frames for the scene. The device may identify a first region within the frame including a first feature corresponding to the selected coordinate and a second region within the frame including a second feature. The device may generate a first score for the first feature and a second score for the second feature. The first score may be greater than the second score based on the first feature corresponding to the selected coordinate. The device may crop the frame to include the first region and the second region within a predetermined display area comprising a subset of regions of the frame in a second orientation.

公开(公告)号：US20250166135A1

公开(公告)日：2025-05-22

申请号：US18951203

申请日：2024-11-18

Applicant: Google LLC

Inventor： Yu-Chuan Su ,  Hsin-Ping Huang ,  Ming-Hsuan Yang ,  Deqing Sun ,  Lu Jiang ,  Yukun Zhu ,  Xuhui Jia

IPC: G06T5/60 ,  G06T7/00 ,  G06T7/246 ,  G06T11/20 ,  G06T11/60

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controllable video generation. One of the methods includes receiving a text prompt that specifies an object; receiving a control input that comprises an image that depicts a particular instance of the object; generating a video that comprises a respective video frame at each of a plurality of time steps in the video and that depicts the particular instance of the object. Generating the video includes, at each of the plurality of time steps: obtaining a text prompt embedding; obtaining a control input embedding; and generating the respective video frame at the time step using a video generation neural network while the video generation neural network is conditioned on the text prompt embedding and on the control input embedding.

公开(公告)号：US20250165728A1

公开(公告)日：2025-05-22

申请号：US18862092

申请日：2023-05-10

Applicant: GOOGLE LLC

Inventor： Ruofei Du ,  Alex Olwal ,  Vikas Bahirwani ,  Boris Smus ,  Christopher Ross

IPC: G06F40/58

Abstract: Described techniques may be utilized to process transcribed text of a transcription stream using a summarization ML model to obtain a summary stream. In this way, a live conversation or other live speech may be provided to a user in real-time, using a display of a head-mounted device (HMD) or other suitable device. A user interface may be provided with a toggle or other stream selector for selecting either or both of the transcription stream or the summary stream at a given point in time. Actionable items may be identified within either or both of the transcription stream or the summary stream, and a scroll bar or other action selector may be provided in the user interface to execute corresponding actions.