GOOGLE LLC patent applications on July 25th, 2024
Patent Applications by GOOGLE LLC on July 25th, 2024
GOOGLE LLC: 43 patent applications
GOOGLE LLC has applied for patents in the areas of G10L15/22 (5), G06N3/08 (3), G06F16/2457 (3), G06N20/00 (3), G06F40/40 (2) G10L15/22 (3), G06N20/00 (2), G10L21/0364 (1), G06T7/50 (1), G06T11/60 (1)
With keywords such as: data, device, user, input, based, image, computing, media, network, and interface in patent application abstracts.
Patent Applications by GOOGLE LLC
20240248315. BATTERY WAVEGUIDE FOR AUGMENTED REALITY DISPLAY_simplified_abstract_(google llc)
Inventor(s): Chen-Cheng Lee of Hsinchu County (TW) for google llc, Pin-Ci Liao of Taichung City (TW) for google llc
IPC Code(s): G02B27/01, F21V8/00
CPC Code(s): G02B27/0176
Abstract: an eyewear display system incorporates a substantially transparent battery into a lens portion of the eyewear display system to serve as a waveguide substrate. the substantially transparent battery waveguide receives display light from a micro-display and transmits the display light from a proximal end of the waveguide to a distal end of the waveguide while also supplying power to the micro-display. either a transflective mirror or a diffraction structure is disposed on the surface of the substantially transparent battery to couple light into and out of the substantially transparent battery (i.e., to serve as the incoupler and outcoupler).
20240248458. On-Robot Data Collection_simplified_abstract_(google llc)
Inventor(s): Sarah Najmark of Paris (FR) for google llc, Ammar Husain of Palo Alto CA (US) for google llc
IPC Code(s): G05B19/4155, B25J9/16, B25J13/00, G05D1/648, G05D105/80
CPC Code(s): G05B19/4155
Abstract: systems and methods are provided for improved generation and selection of robot sensor data for manual annotation and/or use in training machine learning models used to operate robots. an on-robot controller can operate to determine a cross-modal inconsistency, that a temporally proximate target task was failed, and/or that a confidence in a model output indicate that particular sensor data should be transmitted to a remote system for human annotation and/or use in updating the machine learning model(s) of the robot. embedding vector(s) representing such selected sensor data (e.g., representing common aspects across a population of sets of sensor data) could also be determined and transmitted to the robot. the robot could then determine embeddings for sensor data and, if the embeddings are similar enough to the transmitted embedding(s), the sensor data could be transmitted to the remote system for annotation and/or model updating.
Inventor(s): Nicholas Gillett of San Francisco CA (US) for google llc, Bengt Brummer of San Francisco CA (US) for google llc, Eugene Fox of San Francisco CA (US) for google llc, Carl Cepress of Sunnyvale CA (US) for google llc, Maj Isabelle Olsson of Sunnyvale CA (US) for google llc, Nicholas Sanders of Saratoga CA (US) for google llc, Jose Madrid of Mountain View CA (US) for google llc
IPC Code(s): G06F1/16, H01F7/02
CPC Code(s): G06F1/1632
Abstract: various arrangements of an electronic device case are presented herein. the case can include a housing shaped to allow an electronic device to be removably installed within the housing. the case can include magnets, the magnets being arranged to magnetically couple with magnets of a dock. the case can include a kickstand assembly attached with the housing. a kickstand body of the kickstand assembly can be extended for propping up the electronic device case when the electronic device case is not docked with the dock. the kickstand body can be collapsed for when the electronic device case is magnetically docked with the dock.
20240248538. HAPTIC INTERFACE FOR COMPUTING DEVICES_simplified_abstract_(google llc)
Inventor(s): Claire Tauziet of Redwood City CA (US) for google llc, Kejia Shao of Mountain View CA (US) for google llc
IPC Code(s): G06F3/01, G06F3/0354, G06F3/0483, G06F3/04842, G06F3/04845, G06F3/04847, G06F3/0485, G06F3/0488
CPC Code(s): G06F3/016
Abstract: the technology involves providing haptic feedback to a user of a computing device. for instance, user input associated with a program of the computing device is received by a user interface module of the computing device. one or more processors of the computing device determine a kind of interaction corresponding to the user input. the one or more processors identify whether the kind of interaction is associated with one or more haptic feedback effects of a curated suite of haptic effects. upon identifying that the kind of interaction is associated with one or more haptic feedback effect, the one or more processors select a particular haptic feedback effect from the curated suite of haptic effects. and the one or more processors are able to cause a haptic feedback module of the computing device to provide the particular haptic feedback effect for sensation by the user.
Inventor(s): Mark David Scott of Kirkland WA (US) for google llc, Mark Alan Foltz of Seattle WA (US) for google llc, John Affaki of San Jose CA (US) for google llc, Majd Bakar of San Jose CA (US) for google llc, Francis Tsui of Mountain View CA (US) for google llc, Jennifer Shien-Ming Chen of Mountain View CA (US) for google llc
IPC Code(s): G06F3/0484, H04N21/41, H04N21/422
CPC Code(s): G06F3/0484
Abstract: a system enables universal remote media control across multiple platforms, devices, and users. a protocol allows a cast controller to have access to media operations and a state(s) associated with media content. the system receives commands from a cast controller, provides the commands to a media player, loads new media content into the media player, based on the commands, and receives state notifications from the media player. another cast controller can receive the state notifications from the media player and control the media player based on the media operations and state(s) associated with media content.
Inventor(s): Michael Uy of Mountain View CA (US) for google llc, William Levi Frohn of Kenmore WA (US) for google llc
IPC Code(s): G06F3/04886, G06F3/023, G06F3/0481, G06F3/0484
CPC Code(s): G06F3/04886
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enhancing user interaction with an interface are described. in one aspect, a method includes displaying a keyboard layer of a user interface that includes a keyboard having at least one user interface element configured to receive a user input. an initial input at a given user interface element is detected. in response to detecting the initial interaction, a first portion of a symbol layer of the user interface is revealed while maintaining display of the keyboard layer of the user interface. a subsequent input at the given user interface element is detected. in response to detecting the subsequent input, a larger portion of the symbol layer of the user interface is revealed while maintaining a position of the first portion of the symbol layer that was previously revealed in response to detecting the initial input.
Inventor(s): Vinoth Kumar Deivasigamani of San Diego CA (US) for google llc
IPC Code(s): G06F8/65, G06F9/4401, G06F21/57
CPC Code(s): G06F8/66
Abstract: this document describes techniques and apparatuses for memory patching with associative and directly mapped patch data. in some aspects, a processor requests boot code stored at an address of a first region of an address map of a boot rom. a boot rom controller can determine, based on the address, that an associative record in a programmable memory includes address information matching the address. the controller returns patch data of the associative record. this patch data includes another address to a second region of the address map. the processor requests other data of the other address, which is directly mapped to other records of the programmable memory that do not include address information related to the address map. based on an offset between the start address of the second region and the other address from which data is requested, the other data can be fetched from the directly mapped record.
20240248798. QUANTUM ERROR CORRECTION_simplified_abstract_(google llc)
Inventor(s): Austin Greig Fowler of Reseda CA (US) for google llc
IPC Code(s): G06F11/10, G06N10/00
CPC Code(s): G06F11/1076
Abstract: methods, systems and apparatus for quantum error correction. a layered representation of error propagation through quantum error detection circuits is constructed. the layered representation includes multiple line circuit layers that each represent a probability of local detection events in a quantum computing system associated with potential error processes in an execution of a quantum algorithm. to construct the layered representation, potential detection events associated with each potential error process occurring at quantum gates in the quantum circuit are determined. lines are associated with each potential error process, the lines each connecting a potential detection event associated with the potential error process to another potential detection event associated with the same potential error process or a boundary of the quantum circuit. similar lines are merged and used to construct unique line circuit layers. the layered representation is transmitted to the quantum computing system prior to execution of the quantum algorithm.
20240248811. AUTOMATED BACKUP AND RESTORE OF A DISK GROUP_simplified_abstract_(google llc)
Inventor(s): Xiangdong Zhang of Wellesley MA (US) for google llc, Satya Sri Kanth Palaparthi of Waltham MA (US) for google llc, Sachindra Kumar of Framingham MA (US) for google llc, Uday Tekade of Westford MA (US) for google llc, Madhav Mutalik of Southborough MA (US) for google llc, Suresh Bezawada of Hyderabad (IN) for google llc
IPC Code(s): G06F11/14
CPC Code(s): G06F11/1466
Abstract: restoring a clustered database having a plurality of nodes each having database from a failed storage device by receiving a request to restore a backup image of a failed shared storage device associated with the clustered database to a time; performing a preflight check including at least one checklist process; terminating the restore when any checklist process fails; when each checklist process succeeds completing the restore by creating at least one flashcopy associated with the backup image, mapping to each of the plurality of nodes an associated portion of the at least one flashcopy, mounting the at least one flashcopy to the node as a diskgroup, and switching the clustered database to run from the diskgroup.
20240248825. CONTRIBUTION INCREMENTALITY MACHINE LEARNING MODELS_simplified_abstract_(google llc)
Inventor(s): Xinlong Bao of Los Altos CA (US) for google llc, Ali Nasiri Amini of Redwood City CA (US) for google llc, Jing Wang of Mountain View CA (US) for google llc, Mert Dikmen of Belmont CA (US) for google llc, Amy Richardson of Santa Cruz CA (US) for google llc, Dinah Shender of Mountain View CA (US) for google llc, Junji Takagi of Sunnyvale CA (US) for google llc, Sen Li of Mountain View CA (US) for google llc, Ruoyi Jiang of Sunnyvale CA (US) for google llc, Yang Jiao of San Mateo CA (US) for google llc, Yang Zhang of Sunnyvale CA (US) for google llc, Zhuo Zhang of Santa Clara CA (US) for google llc
IPC Code(s): G06F11/34, G06N20/00
CPC Code(s): G06F11/3433
Abstract: methods, systems, and computer programs encoded on a computer storage medium, for training and using machine learning models are disclosed. methods include creating a model that represents relationships between user attributes, content exposures, and performance levels for a target action using organic exposure data specifying one or more organic exposures experienced by a particular user over a specified time prior to performance of a target action by the particular user and third party exposure data specifying third party exposures of a specified type of digital component to the particular user over the specified time period. using the model, an incremental performance level attributable to each of the third party exposures at an action time when the target action was performed by the particular user is determined. transmission criteria for at least some digital components to which the particular user was exposed are modified based on the incremental performance.
20240248927. QUERY RESPONSE USING MEDIA CONSUMPTION HISTORY_simplified_abstract_(google llc)
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc
IPC Code(s): G06F16/487, G06F16/245, G06F16/2455, G06F16/2457, G06F16/432, G06F16/435, G06F16/48, G06F16/683, G06F16/783, G06F16/9535, G06F16/955, G06Q30/02, G06Q30/0601
CPC Code(s): G06F16/487
Abstract: methods, systems, and apparatus for receiving a natural language query of a user, and environmental data, identifying a media item based on the environmental data, determining an entity type based on the natural language query, selecting an entity associated with the media item that matches the entity type, selecting, from a media consumption database that identifies media items that have been indicated as consumed by the user, one or more media items that have been indicated as consumed by the user and that are associated with the selected entity, and providing a response to the query based on selecting the one or more media items that have been indicated as consumed by the user and that are associated with the selected entity.
20240248928. PERSONALIZED CONTENT SHARING_simplified_abstract_(google llc)
Inventor(s): Justin Lewis of Marina del Rey CA (US) for google llc, Ruxandra Georgiana Davies of Santa Monica CA (US) for google llc
IPC Code(s): G06F16/738, G06F16/2457, G06F16/48
CPC Code(s): G06F16/738
Abstract: a method for providing personalized content sharing is disclosed. the method includes: presenting, by a user device of a user, a user interface (ui) including content and a ui element allowing the user to share the content with other users; upon a selection of the ui element by the user in the ui, transmitting, to a server, a request to share the content with other users; identifying a selected subset of contacts of the user, wherein contacts in the subset of contacts are selected from a plurality of contacts of the user based on at least one of (i) an affinity of the user with each contact of the subset of contacts, or (ii) interactions of the user with content of each contact of the subset of contacts; presenting, to the user, the subset of contacts of the user comprising a first contact of the plurality of contacts of the user and not including a second contact of the plurality of contacts of the user; and allowing the user to share the content with the first contact of the plurality of contacts.
20240248938. UNIFIED MESSAGE SEARCH_simplified_abstract_(google llc)
Inventor(s): Vinh Quoc Ly of Sunnyvale CA (US) for google llc, Ahmet Onur Tekdas of Santa Clara CA (US) for google llc, Timo Mertens of Millbrae CA (US) for google llc, Okan Kolak of Sunnyvale CA (US) for google llc, Charles Randell Sievert of San Jose CA (US) for google llc, Christine Nguyen of Santa Clara CA (US) for google llc, Jin Lu of Redwood City CA (US) for google llc
IPC Code(s): G06F16/951, G06F16/904, G06Q10/00, G06Q10/107, H04M1/27, H04M1/7243, H04W4/14
CPC Code(s): G06F16/951
Abstract: the disclosed embodiments include computerized methods, systems, and devices, including computer programs encoded on a computer storage medium, for generating terms of a search query based on a user's spoken utterances, identifying multiple cross-platform messages based on the generated terms, and to generating, via a presentation device, a single interface that enables the user to interact with identified messages. based on a spoken utterance, the disclosed embodiments may determine user-specified search terms and/or criteria, and based on the user-specified search terms and/or criteria, may obtain cross-platform message data that corresponds to the search query. the communications device may generate one or more interface elements that describe corresponding ones of the cross-platform messages, which may be presented within a unified graphical user interface or voice-user interface by a communications device.
20240248940. INDICATING LOCATION STATUS_simplified_abstract_(google llc)
Inventor(s): Daisuke Ikeda of Sunnyvale CA (US) for google llc, Ryoichi Imaizumi of Tokyo (JP) for google llc, Kaleigh S. Smith of New York NY (US) for google llc, Keiji Maekawa of Tokyo (JP) for google llc
IPC Code(s): G06F16/9535, G06F16/2457, G06F16/248, G06F16/29, G06F16/9537, G06F16/9538
CPC Code(s): G06F16/9535
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for indicating location status. a computing device can receive a query from a user device, a current time, and a location for the user device. the computing device identifies results responsive to the query, including one or more business results that are each associated with a business location and operating hours. the computing device can select a subset of the business results as open results based on the operating hours of the business results, the current time, and travel times from the device location to the respective business locations. data can be provided for a search engine results page that designates the subset of the business results as open results.
Inventor(s): Anna Darling Goldie of San Francisco CA (US) for google llc, Azalia Mirhoseini of Mountain View CA (US) for google llc, Ebrahim Songhori of San Jose CA (US) for google llc, Wenjie Jiang of Mountain View CA (US) for google llc, Shen Wang of Sunnyvale CA (US) for google llc, Roger David Carpenter of San Francisco CA (US) for google llc, Young-Joon Lee of San Jose CA (US) for google llc, Mustafa Nazim Yazgan of Cupertino CA (US) for google llc, Chian-min Richard Ho of Palo Alto CA (US) for google llc, Quoc V. Le of Sunnyvale CA (US) for google llc, James Laudon of Madison WI (US) for google llc, Jeffrey Adgate Dean of Palo Alto CA (US) for google llc, Kavya Srinivasa Setty of Sunnyvale CA (US) for google llc, Omkar Pathak of Mountain View CA (US) for google llc
IPC Code(s): G06F30/392, G06F30/398, G06N3/08
CPC Code(s): G06F30/392
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a computer chip placement. one of the methods includes obtaining netlist data for a computer chip; and generating a computer chip placement, comprising placing a respective macro node at each time step in a sequence comprising a plurality of time steps, the placing comprising, for each time step: generating an input representation for the time step; processing the input representation using a node placement neural network having a plurality of network parameters, wherein the node placement neural network is configured to process the input representation in accordance with current values of the network parameters to generate a score distribution over a plurality of positions on the surface of the computer chip; and assigning the macro node to be placed at the time step to a position from the plurality of positions using the score distribution.
20240249066. Adaptive Structured User Interface_simplified_abstract_(google llc)
Inventor(s): Timothy Edward Jaeger of Bloomfield NJ (US) for google llc, Catherine Goings Lin of Irvine CA (US) for google llc, Bert Bräutigam of San Francisco CA (US) for google llc
IPC Code(s): G06F40/106, G06F3/14, G06F40/166
CPC Code(s): G06F40/106
Abstract: systems and method for the structure, configuration, or arrangement of the input fields in a user interface. for example, a computer-implemented method includes displaying a structured input interface configured with a plurality of input fields. the structured input interface can be configured for rendering in a graphical user interface. a first input field can correspond to an initial notification element in the graphical user interface for rendering in association with the first input field. the method includes receiving user data. the method includes determining, based on the user data, an updated notification element for rendering in association with the first input field. the method includes updating the structured input interface comprising the first input field and the updated notification element.
Inventor(s): Ruoxi Sun of Santa Clara CA (US) for google llc, Xingchen Wan of Oxford (GB) for google llc, Hanjun Dai of San Jose CA (US) for google llc, Sercan Omer Arik of San Francisco CA (US) for google llc, Tomas Pfister of Redwood Shores CA (US) for google llc
IPC Code(s): G06F40/40, G06F16/33
CPC Code(s): G06F40/40
Abstract: aspects of the disclosure are directed to automatically selecting examples in a prompt for an llm to demonstrate how to perform tasks. aspects of the disclosure can select and build a set of examples from llm zero-shot outputs via predetermined criteria that can combine consistency, diversity, and repetition. in the zero-shot setting for three different llms, using only llm predictions, aspects of the disclosure can improve performance up to 15% compared to zero-shot baselines and can match or exceed few-shot base-lines for a range of reasoning tasks.
Inventor(s): Pararth Shah of Sunnyvale CA (US) for google llc, Dilek Hakkani-Tur of Los Altos CA (US) for google llc, Juliana Kew of San Francisco CA (US) for google llc, Marek Fiser of Mountain View CA (US) for google llc, Aleksandra Faust of Palo Alto CA (US) for google llc
IPC Code(s): G06N3/008, B25J9/16, B25J13/08, G05B13/02, G06F18/21, G06N3/044, G06T7/593, G06V20/10, G06V30/262, G10L15/16, G10L15/18, G10L15/22, G10L25/78
CPC Code(s): G06N3/008
Abstract: implementations relate to using deep reinforcement learning to train a model that can be utilized, at each of a plurality of time steps, to determine a corresponding robotic action for completing a robotic task. implementations additionally or alternatively relate to utilization of such a model in controlling a robot. the robotic action determined at a given time step utilizing such a model can be based on: current sensor data associated with the robot for the given time step, and free-form natural language input provided by a user. the free-form natural language input can direct the robot to accomplish a particular task, optionally with reference to one or more intermediary steps for accomplishing the particular task. for example, the free-form natural language input can direct the robot to navigate to a particular landmark, with reference to one or more intermediary landmarks to be encountered in navigating to the particular landmark.
20240249138. IMAGE CLASSIFICATION USING BATCH NORMALIZATION LAYERS_simplified_abstract_(google llc)
Inventor(s): Sergey Ioffe of Mountain View CA (US) for google llc, Corinna Cortes of New York NY (US) for google llc
IPC Code(s): G06N3/08, G06F18/10, G06F18/2415, G06N3/04, G06N3/084, G06V10/70, G06V10/82
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images or features of images using an image classification system that includes a batch normalization layer. one of the systems includes a convolutional neural network configured to receive an input comprising an image or image features of the image and to generate a network output that includes respective scores for each object category in a set of object categories, the score for each object category representing a likelihood that that the image contains an image of an object belonging to the category, and the convolutional neural network comprising: a plurality of neural network layers, the plurality of neural network layers comprising a first convolutional neural network layer and a second neural network layer; and a batch normalization layer between the first convolutional neural network layer and the second neural network layer.
Inventor(s): Sercan Omer Arik of San Francisco CA (US) for google llc, Si-An Chen of Taipei City (TW) for google llc, Nathanael Christian Yoder of San Francisco CA (US) for google llc, Chun-Liang Li of Santa Clara CA (US) for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: the present disclosure provides an architecture for time series forecasting. the architecture is based on multi-layer perceptrons (mlps), which involve stacking linear models with non-linearities between them. in this architecture, the time-domain mlps and feature-domain mlps are used to perform both time-domain and feature-domain operations in a sequential manner, alternating between them. in some examples, auxiliary data is used as input, in addition to historical data. the auxiliary data can include known future data points, as well as static information that does not vary with time. the alternation of time-domain and feature-domain operations using linear models allows the architecture to learn temporal patterns while leveraging cross-variate information to generate more accurate time series forecasts.
Inventor(s): Jared Alexander Lichtarge of Brooklyn NY (US) for google llc, Rajiv Mathews of Sunnyvale CA (US) for google llc, Rohan Anil of Lafayette CA (US) for google llc, Ehsan Amid of Mountain View CA (US) for google llc, Shankar Kumar of New York NY (US) for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: generally, the present disclosure is directed to enhanced federated learning (fl) that employs a set of clients with varying amounts of computational resources (e.g., system memory, storage, and processing bandwidth). to overcome limitations of conventional fl methods that employ a set of clients with varying amounts of computational resources, the embodiments run multi-directional knowledge distillation between the server models produced by each federated averaging (fedavg) pool, using unlabeled server data as the distillation dataset. by co-distilling the two (or more) models frequently over the course of fedavg rounds, information is shared between the pools without sharing model parameters. this leads to increased performance and faster convergence (in fewer federated rounds).
Inventor(s): Jinsung Yoon of San Jose CA (US) for google llc, Jiefeng Chen of Mountain View CA (US) for google llc, Sayna Ebrahimi of Los Altos Hills CA (US) for google llc, Sercan Omer Arik of San Francisco CA (US) for google llc
IPC Code(s): G06N20/20
CPC Code(s): G06N20/20
Abstract: a method includes obtaining a set of unlabeled test data samples and, for each respective initial training step, determining a first average output for each unlabeled test data sample using a deep ensemble. for each round of a plurality of rounds, the method includes selecting a subset of unlabeled test data samples based on the determined first average outputs, labeling each respective unlabeled in the subset of unlabeled test data samples, fine-tuning the deep ensemble model using the subset of labeled test data samples, and determining a second average output for each unlabeled test data sample using the fine-tuned deep ensemble model. the method also includes generating, using the set of unlabeled test data samples and the determined second average outputs, a pseudo-labeled set of training data samples. the method also includes training the deep ensemble model using the pseudo-labeled set of training data samples.
Inventor(s): Michael Yang Liu of Santa Clara CA (US) for google llc, Richard A. Maher of Newport Beach CA (US) for google llc, Edward Chou of Eastvale CA (US) for google llc, Srirama Koneru of Redwood City CA (US) for google llc, Batool Nadeem Husain of Bothell WA (US) for google llc, Cheolmin Kim of San Francisco CA (US) for google llc
IPC Code(s): G06Q30/0203, G06Q30/0201
CPC Code(s): G06Q30/0203
Abstract: an aspect of the disclosed technology is a scalable method to derive drivers of change for composite metrics (e.g., cost metrics and ratio metrics) in a time series data set. the disclosed technology comprises an automated mechanism that enables identification and deciphering of one or more drivers, e.g., the largest contributors, or a composite metric change in a scalable manner.
Inventor(s): Varun Jampani of Rockland MA (US) for google llc, Huiwen Chang of Mountain View CA (US) for google llc, Kyle Sargent of Cambridge MA (US) for google llc, Abhishek Kar of Sunnyvale CA (US) for google llc, Richard Tucker of New York City NY (US) for google llc, Dominik Kaeser of New York City NY (US) for google llc, Brian L. Curless of Seattle WA (US) for google llc, David Salesin of Sausalito CA (US) for google llc, William T. Freeman of Acton MA (US) for google llc, Michael Krainin of Arlington MA (US) for google llc, Ce Liu of Belmont MA (US) for google llc
IPC Code(s): G06T7/50, G06T5/60, G06T5/77
CPC Code(s): G06T7/50
Abstract: a method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. the method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. the method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. the method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3d) representation of the image and a second 3d representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3d representation based on the foreground visibility map.
Inventor(s): Chitwan Saharia of Toronto (CA) for google llc, William Chan of Toronto (CA) for google llc, Mohammad Norouzi of Richmond Hill (CA) for google llc, Saurabh Saxena of Mississauga (CA) for google llc, Yi Li of Oakville (CA) for google llc, Jay Ha Whang of Austin TX (US) for google llc, David James Fleet of Toronto (CA) for google llc, Jonathan Ho of New York NY (US) for google llc
IPC Code(s): G06T11/60, G06F40/284, G06F40/40, G06N3/08, G06T3/4053, G06T5/70
CPC Code(s): G06T11/60
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating images. in one aspect, a method includes: receiving an input text prompt including a sequence of text tokens in a natural language; processing the input text prompt using a text encoder neural network to generate a set of contextual embeddings of the input text prompt; and processing the contextual embeddings through a sequence of generative neural networks to generate a final output image that depicts a scene that is described by the input text prompt.
Inventor(s): Idris Syed Aleem of Kitchener (CA) for google llc, Mayank Bhargava of Kitchener (CA) for google llc
IPC Code(s): G06T19/00, G02C13/00, G06T7/50, G06T7/60, G06T7/73
CPC Code(s): G06T19/00
Abstract: a system and method of predicting fit of a wearable device from image data obtained by a computing device together with position and orientation of the computing device is provided. the system and method may include capturing a series of frames of image data, and detecting one or more fixed features in the series of frames of image data. position and orientation data associated with the capture of the image data is combined with the position data related to the one or more fixed features, to extract depth data from the series of frames of image data. a three-dimensional model of is generated based on the extracted depth data. the three-dimensional model is processed by a simulator and/or a machine learning model to predict fit of the wearable device for the user.
Inventor(s): Brian Mulford of Palos Verdes CA (US) for google llc, Nathan Frey of Venice CA (US) for google llc, Alexandros Panagopoulos of Leonia NJ (US) for google llc, Yinquan Hao of Lake Grove NY (US) for google llc, Yuan Zhang of Torrance CA (US) for google llc
IPC Code(s): G06V10/25, G06F3/04845, G06T3/10, G06T7/11, G06T11/20, G06V20/05
CPC Code(s): G06V10/25
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.
Inventor(s): Forrester H. Cole of Cambridge MA (US) for google llc, Andrew Zisserman of Oxford (GB) for google llc, Tali Dekel of Arlington MA (US) for google llc, William Tafel Freeman of Acton MA (US) for google llc, Erika Lu of Lexington MA (US) for google llc, Michael Rubinstein of Natick MA (US) for google llc
IPC Code(s): G06V20/40, G06T7/194, G06T7/246, G06T7/73, G06V10/26, G06V10/776, G06V10/82
CPC Code(s): G06V20/46
Abstract: the present disclosure provides systems and methods for identifying and extracting object-related effects in videos. given an ordinary video and a rough segmentation mask overtime of one or more subjects of interest, example systems proposed herein can estimate an omnimatte for each subject—an alpha matte and color image that includes the subject along with all its related time-varying scene elements. example implementations of the proposed models can be trained only on the input video in a self-supervised manner, without any manual labels, and are generic. for example, the models can produce omnimattes automatically for arbitrary objects and a variety of effects.
Inventor(s): Thomas Deselaers of Zurich (CH) for google llc, Sandro Feuz of Zurich (CH) for google llc
IPC Code(s): G10L15/22, G06F3/16, G06F9/54, G10L15/06
CPC Code(s): G10L15/22
Abstract: implementations relate to an automated assistant that is capable of interacting with non-assistant applications that do not have functionality explicitly provided for interfacing with certain automated assistants. application data, such as annotation data and/or gui data, associated with a non-assistant application, can be processed to map such data into an embedding space. an assistant input command can then be processed and mapped to the same embedding space, and a distance from the assistant input command embedding and the non-assistant application data embedding can be determined. when the distance between the assistant input command embedding and the non-assistant application data embedding satisfies threshold(s), the automated assistant can generate instruction(s), for the non-assistant application, that correspond to the non-assistant application data. for instance, the instruction(s) can simulate user input(s) that cause the non-assistant application to perform one or more operations characterized by, or otherwise associated with, the non-assistant application data.
Inventor(s): Dongeek Shin of San Jose CA (US) for google llc
IPC Code(s): G10L15/22, G06F1/16, G10L15/08
CPC Code(s): G10L15/22
Abstract: implementations relate to an automated assistant that can bypass invocation phrase detection when an estimation of device-to-device distance satisfies a distance threshold. the estimation of distance can be performed for a set of devices, such as a computerized watch and a cellular phone, and/or any other combination of devices. the devices can communicate ultrasonic signals between each other, and the estimated distance can be determined based on when the ultrasonic signals are sent and/or received by each respective device. when an estimated distance satisfies the distance threshold, the automated assistant can operate as if the user is holding onto their cellular phone while wearing their computerized watch. this scenario can indicate that the user may be intending to hold their device to interact with the automated assistant and, based on this indication, the automated assistant can temporarily bypass invocation phrase detection (e.g., invoke the automated assistant).
Inventor(s): David Roy Schairer of San Jose CA (US) for google llc, Sumer Mohammed of New York NY (US) for google llc, Mark Spates, IV of San Francisco CA (US) for google llc, Prem Kumar of Saratoga CA (US) for google llc, Chi Yeung Jonathan Ng of San Francisco CA (US) for google llc, Di Zhu of Sunnyvale CA (US) for google llc, Steven Clark of San Leandro CA (US) for google llc
IPC Code(s): G10L15/22, G06F3/16, G10L15/08, G10L15/30, G16Y40/10, G16Y40/35, H04L12/28, H04W4/70
CPC Code(s): G10L15/22
Abstract: remote automated assistant component(s) generate client device notification(s) based on a received iot state change notification that indicates a change in at least one state associated with at least one iot device. the generated client device notification(s) can each indicate the change in state associated with the at least one iot device, and can optionally indicate the at least one iot device. further, the remote automated assistant component(s) can identify candidate assistant client devices that are associated with the at least one iot device, and determine whether each of the one or more of the candidate assistant client device(s) should render a corresponding client device notification. the remote automated assistant component(s) can then transmit a corresponding command to each of the assistant client device(s) it determines should render a corresponding client device notification, where each transmitted command causes the corresponding assistant client device to render the corresponding client device notification.
20240249741. Guided Speech Enhancement Network_simplified_abstract_(google llc)
Inventor(s): George Chiachi Sung of San Diego CA (US) for google llc, Yang Yang of San Diego CA (US) for google llc, Shao-Fu Shih of Mountain View CA (US) for google llc, Hakan Erdogan of Lexington MA (US) for google llc, Jamie Menjay Lin of San Diego CA (US) for google llc
IPC Code(s): G10L21/0232, G10L15/06, G10L15/16, G10L15/22, G10L21/0308, G10L25/18
CPC Code(s): G10L21/0232
Abstract: a method includes receiving, as input, reference audio data representing a reference audio signal captured by an audio input device. the method also includes receiving, as input, from a beamformer, spatially-filtered audio data representing an output of the beamformer, the beamformer configured to spatially filter, based on additional audio data captured by one or more additional audio input devices, the reference audio data to attenuate one or more interfering signals in the spatially-filtered audio data. the method processes, using a trained guided speech-enhancement network, the reference audio data and the spatially-filtered audio data to generate, as output, enhanced audio data, the guided speech-enhancement network processing the reference audio data and the spatially-filtered audio data to further attenuate, in the enhanced audio data, the one or more interfering signals attenuated by the beamformer.
20240249743. Enhancing Audio Content of a Captured Sense_simplified_abstract_(google llc)
Inventor(s): Snehitha Singaraju of Hyderabad, Telangana (IN) for google llc
IPC Code(s): G10L21/0364, G06V10/70, G06V20/40, G06V20/50, G10L21/034, G10L25/57
CPC Code(s): G10L21/0364
Abstract: this document describes systems and methods for enhancing dynamically audio content of a captured scene (). as part of the described systems and methods, an electronic device () may include a content-enhancement manager module () that directs the electronic device () to perform operations to enhance the audio content. operations may include determining a context () surrounding the capture of the scene, determining an audio focus point () within the scene, or determining an intent of a user directing the electronic device () to capture the scene (). based on one or more of these determinations, the electronic device () may use a variety of techniques to enhance the audio content associated with the captured scene so as to present the captured scene () with relevant audio content.
20240250082. Integrated Circuit Package For High Bandwidth Memory_simplified_abstract_(google llc)
Inventor(s): Nam Hoon Kim of San Jose CA (US) for google llc, Woon Seong Kwon of Santa Clara CA (US) for google llc, Teckgyu Kang of Saratoga CA (US) for google llc, Yujeong Shim of Cupertino CA (US) for google llc
IPC Code(s): H01L25/18, H01L23/498, H01L25/00, H01L25/065
CPC Code(s): H01L25/18
Abstract: an integrated circuit package including a substrate configured to receive one or more high-bandwidth memory (hbm) stacks on the substrate, an interposer positioned on the substrate and configured to receive a logic die on the interposer, a plurality of interposer channels formed in the interposer and connecting the logic die to the one or more hbm stacks, and a plurality of substrate traces formed in the substrate and configured to interface the plurality of interposer channels to the one or more hbm stacks.
20240250841. Hierarchical Framework of Contexts for the Smart Home_simplified_abstract_(google llc)
Inventor(s): Daniele Midi of San Francisco CA (US) for google llc, Chrisoula Kapelonis of San Jose CA (US) for google llc, Husain Bengali of Redmond WA (US) for google llc, Andrew Larsen Axley of Bend OR (US) for google llc, Marci Meingast of San Francisco CA (US) for google llc, Lindsay Jane Graves of San Carlos CA (US) for google llc, Jacob Antony Arnold of Boulder CO (US) for google llc
IPC Code(s): H04L12/28
CPC Code(s): H04L12/2807
Abstract: techniques and devices for a hierarchical framework of contexts for the smart home are described for managing modes in a smart home system by an electronic device. the electronic device receives a first input of a model for a second operational mode of a smart home system and receives a second input of the model for the second operational mode of the smart home system. based on the first input and the second input, the electronic device determines an effective time interval for the second operational mode that is effective to cause the smart home system to transition from a first operational mode to the second operational mode during the effective time interval.
Inventor(s): Amitabha Roy of Kitchener (CA) for google llc, Nasrin Baratalipour of Kitchener (CA) for google llc, Vinit Jogani of Kitchener (CA) for google llc, Pushkarini Agharkar of Kitchener (CA) for google llc
IPC Code(s): H04L9/40, G06N3/0464
CPC Code(s): H04L63/14
Abstract: a method and system for classifying assets by features of individual entities and relations of the individual entities to the assets using a neural network is disclosed herein. the method comprises aggregating, at each of a plurality of aggregator nodes, data regarding features of each node in each distant neighborhood of a multiplicity of distant neighborhoods; updating, at each of the plurality of aggregator nodes, a state of the aggregator node by assigning a weight to each of the features of the corresponding distant neighborhood; updating, at the seed node, a state of the seed node by performing convolutional analysis of each node in a local neighborhood surrounding the seed node; and determining a label of the seed node based on the state of the seed node.
Inventor(s): Christopher Glyer of Arlington VA (US) for google llc, Seth Jesse Summersett of Hathway Pines CA (US) for google llc
IPC Code(s): H04L9/40, H04L43/12
CPC Code(s): H04L63/1416
Abstract: a comprehensive cybersecurity platform includes a cybersecurity intelligence hub, a cybersecurity sensor and one or more endpoints communicatively coupled to the cybersecurity sensor, where the platform allows for efficient scaling, analysis, and detection of malware and/or malicious activity. an endpoint includes a local data store and an agent that monitors for one or more types of events being performed on the endpoint, and performs deduplication within the local data store to identify “distinct” events. the agent provides the collected metadata of distinct events to the cybersecurity sensor which also performs deduplication within a local data store. the cybersecurity sensor sends all distinct events and/or file objects to a cybersecurity intelligence hub for analysis. the cybersecurity intelligence hub is coupled to a data management and analytics engine (dmae) that analyzes the event and/or object using multiple services to render a verdict (e.g., benign or malicious) and issues an alert.
Inventor(s): Gia Datuashvili of Cupertino CA (US) for google llc, Alexander Kesselman of Sunnyvale CA (US) for google llc, Alexandre Drobychev of San Jose CA (US) for google llc
IPC Code(s): H04L67/1095, G06F16/174, G06F16/178, G06F16/182, G06F16/23, G06F16/2455, G06F16/27
CPC Code(s): H04L67/1095
Abstract: a method is performed by a device of a group of devices in a distributed data replication system. the method includes storing an index of objects in the distributed data replication system, the index being replicated while the objects are stored locally by the plurality of devices in the distributed data replication system. the method also includes conducting a scan of at least a portion of the index and identifying a redundant replica(s) of the at least one of the objects based on the scan of the index. the method further includes de-duplicating the redundant replica(s), and updating the index to reflect the status of the redundant replica.
20240251129. SUGGESTING MEDIA CONTENT TO ACCOMPANY A JOURNEY_simplified_abstract_(google llc)
Inventor(s): Matthew Sharifi of Mountain View CA (US) for google llc
IPC Code(s): H04N21/45, G01C21/36, H04N21/414, H04N21/482
CPC Code(s): H04N21/4524
Abstract: to provide media content tailored to a user's route, a computing device receives a request for navigation directions to a destination location, and obtains a set of navigation directions for traveling on a route to the destination location. the computing device also obtains candidate media content items to play during the route, and selects one or more of the candidate media content items to play during the route based on characteristics of the candidate media content items and characteristics of the route. then the computing device provides the set of navigation directions and an indication of the selected one or more media content items to a user for presentation during the route. the selected one or more media content items are automatically presented upon receiving a selection by the user to initiate a navigation session for traveling along the route in accordance with the set of navigation directions.
Inventor(s): Lawrence Chia-Yu Huang of Santa Clara CA (US) for google llc, Carsten Hinz of Munich (DE) for google llc, Chorong Hwang Johnston of Mountain View CA (US) for google llc, Mike Ma of San Jose CA (US) for google llc, Isaac William Reynolds of Longmont UT (US) for google llc
IPC Code(s): H04N23/698, H04N23/60, H04N23/63
CPC Code(s): H04N23/698
Abstract: this document describes apparatuses and techniques enabling a scale down capture preview for a panorama capture user interface. this scale down preview enables users to more-easily and more-accurately capture images for a panorama.
20240251350. ULTRA-WIDEBAND POWER USAGE OPTIMIZATION_simplified_abstract_(google llc)
Inventor(s): Sharath Ananth of Cupertino CA (US) for google llc
IPC Code(s): H04W52/02
CPC Code(s): H04W52/0225
Abstract: a computing device may determine, via ultra-wideband ranging, that the computing device is proximate to a second computing device paired with the computing device. the computing device may determine that the second computing device is abie to perform ultra-wideband ranging with a particular set of one or more devices. the computing device may, in response to determining that the computing device is proximate to the second computing device and that the second computing device is able to perform ultra-wideband ranging with the particular set of one or more devices, set an ultra-wideband component of the computing device to a power-saving mode.
Inventor(s): Ihab A. Ali of Cupertino CA (US) for google llc, Frédéric Heckmann of Taipei City (TW) for google llc
IPC Code(s): H05K1/02, H05K7/20, H05K9/00
CPC Code(s): H05K1/0203
Abstract: this document describes a thermal-control system () that may be integrated into a mesh network device () and associated mesh network devices. the thermal-control system (), which may include a heat sink (), multiple heat spreaders (), and a heat shield (), is such that heat () originating from ic devices populating a printed circuit board () of the mesh network device () may be transferred to a housing component () of the mesh network device () for external dissipation to maintain a desired thermal profile of the mesh network device ().
- GOOGLE LLC
- G02B27/01
- F21V8/00
- CPC G02B27/0176
- Google llc
- G05B19/4155
- B25J9/16
- B25J13/00
- G05D1/648
- G05D105/80
- CPC G05B19/4155
- G06F1/16
- H01F7/02
- CPC G06F1/1632
- G06F3/01
- G06F3/0354
- G06F3/0483
- G06F3/04842
- G06F3/04845
- G06F3/04847
- G06F3/0485
- G06F3/0488
- CPC G06F3/016
- G06F3/0484
- H04N21/41
- H04N21/422
- CPC G06F3/0484
- G06F3/04886
- G06F3/023
- G06F3/0481
- CPC G06F3/04886
- G06F8/65
- G06F9/4401
- G06F21/57
- CPC G06F8/66
- G06F11/10
- G06N10/00
- CPC G06F11/1076
- G06F11/14
- CPC G06F11/1466
- G06F11/34
- G06N20/00
- CPC G06F11/3433
- G06F16/487
- G06F16/245
- G06F16/2455
- G06F16/2457
- G06F16/432
- G06F16/435
- G06F16/48
- G06F16/683
- G06F16/783
- G06F16/9535
- G06F16/955
- G06Q30/02
- G06Q30/0601
- CPC G06F16/487
- G06F16/738
- CPC G06F16/738
- G06F16/951
- G06F16/904
- G06Q10/00
- G06Q10/107
- H04M1/27
- H04M1/7243
- H04W4/14
- CPC G06F16/951
- G06F16/248
- G06F16/29
- G06F16/9537
- G06F16/9538
- CPC G06F16/9535
- G06F30/392
- G06F30/398
- G06N3/08
- CPC G06F30/392
- G06F40/106
- G06F3/14
- G06F40/166
- CPC G06F40/106
- G06F40/40
- G06F16/33
- CPC G06F40/40
- G06N3/008
- B25J13/08
- G05B13/02
- G06F18/21
- G06N3/044
- G06T7/593
- G06V20/10
- G06V30/262
- G10L15/16
- G10L15/18
- G10L15/22
- G10L25/78
- CPC G06N3/008
- G06F18/10
- G06F18/2415
- G06N3/04
- G06N3/084
- G06V10/70
- G06V10/82
- CPC G06N3/08
- CPC G06N20/00
- G06N20/20
- CPC G06N20/20
- G06Q30/0203
- G06Q30/0201
- CPC G06Q30/0203
- G06T7/50
- G06T5/60
- G06T5/77
- CPC G06T7/50
- G06T11/60
- G06F40/284
- G06T3/4053
- G06T5/70
- CPC G06T11/60
- G06T19/00
- G02C13/00
- G06T7/60
- G06T7/73
- CPC G06T19/00
- G06V10/25
- G06T3/10
- G06T7/11
- G06T11/20
- G06V20/05
- CPC G06V10/25
- G06V20/40
- G06T7/194
- G06T7/246
- G06V10/26
- G06V10/776
- CPC G06V20/46
- G06F3/16
- G06F9/54
- G10L15/06
- CPC G10L15/22
- G10L15/08
- G10L15/30
- G16Y40/10
- G16Y40/35
- H04L12/28
- H04W4/70
- G10L21/0232
- G10L21/0308
- G10L25/18
- CPC G10L21/0232
- G10L21/0364
- G06V20/50
- G10L21/034
- G10L25/57
- CPC G10L21/0364
- H01L25/18
- H01L23/498
- H01L25/00
- H01L25/065
- CPC H01L25/18
- CPC H04L12/2807
- H04L9/40
- G06N3/0464
- CPC H04L63/14
- H04L43/12
- CPC H04L63/1416
- H04L67/1095
- G06F16/174
- G06F16/178
- G06F16/182
- G06F16/23
- G06F16/27
- CPC H04L67/1095
- H04N21/45
- G01C21/36
- H04N21/414
- H04N21/482
- CPC H04N21/4524
- H04N23/698
- H04N23/60
- H04N23/63
- CPC H04N23/698
- H04W52/02
- CPC H04W52/0225
- H05K1/02
- H05K7/20
- H05K9/00
- CPC H05K1/0203
