Google LLC patent applications on June 27th, 2024
Patent Applications by Google LLC on June 27th, 2024
Google LLC: 45 patent applications
Google LLC has applied for patents in the areas of G06N3/045 (4), G06N3/08 (4), G06N3/04 (3), G06F9/38 (3), G06F3/01 (3) G06N3/08 (3), A63B71/0622 (1), G06Q30/0243 (1), G06Q30/0255 (1), G06T5/50 (1)
With keywords such as: device, input, user, image, based, data, output, network, session, and include in patent application abstracts.
Patent Applications by Google LLC
Inventor(s): Fernando Pantoja of San Francisco CA (US) for google llc
IPC Code(s): A63B71/06, A63B24/00, G04G21/02, G04G99/00, G06F3/01, G06F3/0481, G06F3/04842, G16H40/67
CPC Code(s): A63B71/0622
Abstract: a computing device includes a display device, one or more sensors to obtain biometric information of a user associated with the computing device, and one or more processors to execute instructions stored in one or more memories to: determine whether the user completes one or more biometric goals based on the biometric information, and receive data associated with a first user interface screen and data associated with one or more first biometric achievement user interface screens. each of the first biometric achievement user interface screens include one or more first user interface elements from the first user interface screen and are associated with biometric goals. the first user interface screen forms at least part of a home screen, and in response to the user completing a first biometric goal, a corresponding first biometric achievement user interface screen associated with completion of the first biometric goal is provided.
20240207729.GAME CONTROLLER MOBILE BRIDGE_simplified_abstract_(google llc)
Inventor(s): John Thomas McDole of Sunnyvale CA (US) for google llc, Matt Joseph of San Francisco CA (US) for google llc
IPC Code(s): A63F13/352, A63F13/23, A63F13/355, A63F13/92
CPC Code(s): A63F13/352
Abstract: a bridge device communicatively coupled to an input device generates a device pair request associated with a client gaming session and transmits the device pair request to a device discovery engine operating on one or more servers. based on the device pair request, the device discovery engine identifies one or more servers running a gaming application supporting the client gaming session. the device discovery engine then generates a linking code identifying and allowing access to the servers. in response to receiving the linking code. the bridge device establishes a connection between one or more input devices communicatively connected to the bridge device and the identified servers running the gaming application. the bridge device maintains the connection for at least a portion of the client gaming session such that data representing interactions received at the input devices is provided to the servers for use as inputs to the gaming application.
Inventor(s): Leon Bayliss of Redwood City CA (US) for google llc, Philip George Nichols Lamoureux of San Francisco CA (US) for google llc
IPC Code(s): A63F13/5255, A63F13/211, A63F13/26, A63F13/355
CPC Code(s): A63F13/5255
Abstract: gaming content for a game session is provided to a first client device associated with a user, the game session operating in a first mode of operation. an indication is received that the game session on the first client device has initiated a second mode of operation. based on the initiation of the second mode, the game session operating in the second mode is initiated on a second client device associated with the user. an interface element is presented in the game session on the first client device to facilitate a connection with the second client device, which may then be used to control aspects of operations in the second mode.
Inventor(s): Annalisa Marie Pawlosky of Mountain View CA (US) for google llc, Zachary Cutts of San Francisco CA (US) for google llc, Shirley Jing Shao of Sunnyvale CA (US) for google llc, Michelle Therese Hoerner Dimon of Woodside CA (US) for google llc, Marc Berndl of Mountain View CA (US) for google llc, Alexander Julian Tran of Alameda CA (US) for google llc, Diana Terri Wu of Menlo Park CA (US) for google llc
IPC Code(s): C12N15/115
CPC Code(s): C12N15/115
Abstract: this disclosure describes methods and compositions for protein and peptide sequencing.
Inventor(s): Matthew Sharifi of Mountain View CA (US) for google llc
IPC Code(s): G01C21/36, G10L15/22
CPC Code(s): G01C21/3608
Abstract: a computing device may implement a method for determining places and routes through natural conversation. the method may include receiving, from a user, a speech input including a search query to initiate a navigation session; and generating a set of navigation search results responsive to the search query. the set of navigation search results include a plurality of destinations or a plurality of routes corresponding to one or more destinations. the method further includes providing an audio request to the user for refining the set of navigation search results, and in response to the audio request, receiving, from the user, a subsequent speech input including a refined search query. the method further includes providing one or more refined navigation search results responsive to the refined search query including a subset of the plurality of destinations or the plurality of routes.
Inventor(s): Matthew Sharifi of Mountain View CA (US) for google llc
IPC Code(s): G01C21/36
CPC Code(s): G01C21/3641
Abstract: a computing device may implement a method for creating and providing reminders during navigation sessions. the method may include initiating a navigation session for providing a set of navigation instructions to a user from a starting location to a destination location along a route, and receiving, from a user during the navigation session, an input including a request to create a reminder. the method may further include analyzing the input to determine: (i) a content of the reminder, and (ii) a trigger condition for providing the reminder, the trigger condition including a trigger location on the route, and storing the reminder, including the content and the trigger condition. the method may also include, detecting, during a subsequent navigation session, the trigger condition, and, in response to detecting the trigger condition, providing the reminder.
20240210524.Radar-Based Input Controls_simplified_abstract_(google llc)
Inventor(s): Aditya Shailesh Ghadiali of San Jose CA (US) for google llc
IPC Code(s): G01S7/41, G01S13/00, G06F3/01
CPC Code(s): G01S7/415
Abstract: this document describes systems and techniques directed at radar-based input controls for electronic devices. in aspects, an electronic device includes a radar input control system that can perform presence detection, as well as distinguish between touch input, gesture input, and/or potential docking devices. in implementations, the electronic device includes a plurality of radar reception antennas and at least one transmit channel that feeds a plurality of radar transmission antennas. one or more radar reception antennas of the plurality of radar reception antennas may correspond to a discrete input location on a surface of the electronic device. in this way, the electronic device can be implemented without mechanical switches or a touchscreen interface and still receive user input.
20240211003.FOLDING PORTABLE DISPLAY DEVICE_simplified_abstract_(google llc)
Inventor(s): Michael J. Lombardi of Chicago IL (US) for google llc, Joe Allore of Chicago IL (US) for google llc
IPC Code(s): G06F1/16
CPC Code(s): G06F1/1681
Abstract: an example a folding device includes a first assembly; a second assembly; a continuous display comprising a primary flexible segment; a hinge assembly rotatably connected to the first assembly about a first axis and rotatably connected to the second assembly about a second axis, wherein, when the folding device is fully opened about the hinge assembly, an inner surface of the first assembly is substantially coplanar with an inner surface of the second assembly; a first collapsible support platform attached to the first assembly and configured to articulate against a first edge of the hinge assembly to support the primary flexible segment when the folding device is fully opened; and a second collapsible support platform attached to the second assembly and configured to articulate against a second edge of the hinge assembly to support at least the primary flexible segment when the folding device is fully opened.
20240211010.TRUE LOAD DISCONNECT RESET OF COMPUTING DEVICES_simplified_abstract_(google llc)
Inventor(s): Nathan Connell of Chicago IL (US) for google llc, Juha Joonas Oikarinen of Los Gatos CA (US) for google llc, Badhri Jagan Sridharan of Fremont CA (US) for google llc
IPC Code(s): G06F1/26
CPC Code(s): G06F1/26
Abstract: an example method includes, responsive to determining that a button of a mobile computing device has been pressed for longer than a first amount of time, resetting a power management integrated circuit (pmic); responsive to determining that the button of the mobile computing device has been pressed for longer than a second amount of time that is longer than the first amount of time, electrically disconnecting, at a first time, power sources from the mobile computing device; and electrically reconnecting, at a second time that is after the first time, the power sources to the mobile computing device.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G06F3/04842, G06F3/01, G06F3/0481, G06F3/16, G10L15/22
CPC Code(s): G06F3/04842
Abstract: implementations set forth herein relate to an automated assistant that can perform operations to revert various applications to prior states that the applications may have arrived at via certain user inputs. the user can provide a spoken utterance such as, “undo,” in order to cause the automated assistant to identify a particular application that the user may want to affect with the “undo” command. when the particular application is identified, the automated assistant can identify one or more operations recently performed using the particular application. in some implementations, the automated assistant can provide the user with a variety of undo options in response to an “undo” command. for instance, the automated assistant can prompt the user to select one of a first cluster of operations and/or a second cluster of operations to be undone, and each cluster can refer to different operations.
Inventor(s): Kensen Shi of Palo Alto CA (US) for google llc, Rishabh Singh of San Jose CA (US) for google llc, David J. Bieber of New York NY (US) for google llc
IPC Code(s): G06F8/36, G06F16/24, G06N5/04, G06N20/00
CPC Code(s): G06F8/36
Abstract: the present disclosure provides systems and methods for synthesizing computer-readable code based on the receipt of input and output examples. a computing system in accordance with the disclosure can be configured to receive a given input and output, access and library of operations, and perform a search of a library of operations (e.g., transpose, slice, norm, etc.) that can be applied to the input. by applying the operations to the input and tracking the results, the computing system may identify an expression comprising one or a combination of operations that when applied to the input generates the output. in this manner, implementations of the disclosure may be used to identify one or more solutions that a user having access to the library of operations may use to generate the output from the input.
Inventor(s): Ilya Gennadyevich Gelfenbeyn of Sunnyvale CA (US) for google llc, Artem Goncharuk of Mountain View CA (US) for google llc, Pavel Aleksandrovich Sirotin of Sunnyvale CA (US) for google llc
IPC Code(s): G06F8/65, G06F8/61, G06F9/445, G06Q20/12, G10L15/22, H04L9/40, H04M3/42, H04M3/537, H04M7/00
CPC Code(s): G06F8/65
Abstract: a method for enhancing dialog systems is disclosed herein. the method comprises maintaining an online marketplace that may include a plurality of dialog system extension elements. each of the plurality of dialog system extension elements may include at least one of a dialog system plugin, a dialog system add-on, a dialog system update, and a dialog system upgrade. the method may further include receiving a selection of one of the plurality of dialog system extension elements from a software developer. the software developer may be associated with a dialog system. the method may continue with associating the one of the plurality of dialog system extension elements with the dialog system of the software developer.
20240211264.Cooperative Instruction Prefetch on Multicore System_simplified_abstract_(google llc)
Inventor(s): Rahul Nagarajan of San Jose CA (US) for google llc, Christopher Leary of Sunnyvale CA (US) for google llc, Thejasvi Magudilu Vijayaraj of Santa Clara CA (US) for google llc, Thomas James Norrie of San Jose CA (US) for google llc
IPC Code(s): G06F9/38
CPC Code(s): G06F9/3802
Abstract: aspects of the disclosure are directed to methods, systems, and apparatuses using an instruction prefetch pipeline architecture that provides good performance without the complexity of a full cache coherent solution deployed in conventional cpus. the architecture can include components which can be used to construct an instruction prefetch pipeline, including instruction memory (timem), instruction buffer (ibuf), a prefetch unit, and an instruction router.
20240211269.Sparse SIMD Cross-lane Processing Unit_simplified_abstract_(google llc)
Inventor(s): Rahul Nagarajan of San Jose CA (US) for google llc, Suvinay Subramanian of Sunnyvale CA (US) for google llc, Arpith Chacko Jacob of Los Altos CA (US) for google llc
IPC Code(s): G06F9/38, G06F9/30
CPC Code(s): G06F9/3887
Abstract: aspects of the disclosure are directed to a cross-lane processing unit (xpu) for performing data-dependent operations across multiple data processing lanes of a processor. rather than implementing operation-specific circuits for each data-dependent operation, the xpu can be configured to perform different operations in response to input signals configuring individual operations performed by processing cells and crossbars arranged as a stacked network in the xpu. each processing cell can receive and process data across multiple data processing lanes. aspects of the disclosure include configuring the xpu to use a vector sort network to perform a duplicate count eliminating the need to configure the xpu separately for sorting and duplicate counting.
20240211356.RESTORATION OF A COMPUTING SESSION_simplified_abstract_(google llc)
Inventor(s): Xin Wang of Belmont CA (US) for google llc, Shihui Song of Lafayette CO (US) for google llc, Aga Wronska of Mountain View CA (US) for google llc
IPC Code(s): G06F11/14, G06F8/61, G06F9/451, G09G5/14, H04L67/306
CPC Code(s): G06F11/1469
Abstract: according to an aspect, a method of restoring a computing session includes receiving, over a network, session data from a server computer, where the session data includes information about at least one session item that is active during a computing session of a first computing device. the at least one session item includes at least one of a web application or a native application. the method includes restoring the at least one session item of the computing session on a second computing device based on the session data, where the at least one session item is arranged on a user interface of the second computing device according to a display arrangement that corresponds to a display arrangement of the at least one session item on a user interface of the first computing device.
20240211412.Selective Memory Duplication Control_simplified_abstract_(google llc)
Inventor(s): Jonathan Charles Masters of Boston MA (US) for google llc
IPC Code(s): G06F12/14, G06F11/14
CPC Code(s): G06F12/1408
Abstract: generally disclosed herein is an approach for securing data. the approach may include encountering a pointer to a first memory location and determining, based on the pointer, that the first memory location is storing sensitive data. the approach may further include automatically copying the sensitive data to a secure memory location in response to determining that the first memory location is storing sensitive data.
20240211413.Streaming Transfers and Ordering Model_simplified_abstract_(google llc)
Inventor(s): Rahul Nagarajan of San Jose CA (US) for google llc, Arpith Chacko Jacob of Los Altos CA (US) for google llc, Suvinay Subramanian of Sunnyvale CA (US) for google llc, Hema Hariharan of Cupertino CA (US) for google llc
IPC Code(s): G06F13/16, G06F9/35, G06F9/38, G06F9/52
CPC Code(s): G06F13/161
Abstract: generally disclosed herein is a hardware/software interface for asynchronous data movement between an off-core memory and a core-local memory, referred to as “stream transfers”, and a stream ordering model. the stream transfers allow software to more efficiently express common data-movement patterns, specifically ones seen in sparse workloads. direct stream instructions that belong to a stream are processed in-order. for indirect stream instructions, offset elements in an offset list are processed in order. a sync flag is updated to indicate monotonic incremental progress for the stream.
20240211458.Efficient Embedding Table Storage and Lookup_simplified_abstract_(google llc)
Inventor(s): Gaurav Menghani of Santa Clara CA (US) for google llc
IPC Code(s): G06F16/22, G06F16/174, G06F16/215, G06F16/33, G06F30/27, G06N3/04, G06N3/08, H03M7/30
CPC Code(s): G06F16/2282
Abstract: the present disclosure provides systems, methods, and computer program products for providing efficient embedding table storage and lookup in machine-learning models. a computer-implemented method may include obtaining an embedding table comprising a plurality of embeddings respectively associated with a corresponding index of the embedding table, compressing each particular embedding of the embedding table individually allowing each respective embedding of the embedding table to be decompressed independent of any other embedding in the embedding table, packing the embedding table comprising individually compressed embeddings with a machine-learning model, receiving an input to use for locating an embedding in the embedding table, determining a lookup value based on the input to search indexes of the embedding table, locating the embedding based on searching the indexes of the embedding table for the determined lookup value, and decompressing the located embedding independent of any other embedding in the embedding table.
20240211481.Distance Based Search Ranking Demotion_simplified_abstract_(google llc)
Inventor(s): Neha Arora of San Carlos CA (US) for google llc
IPC Code(s): G06F16/2457, G06F16/248, G06F16/29, G06F16/9535, G06F16/9537, H04L101/69
CPC Code(s): G06F16/24578
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing local search results. in one aspect, a method determines a first local document in a set of local documents for search results is eligible for a demotion operation. the determination is based at least in part on a proximity measure based on the location of the user device and a location specified for the first local document. in response to the determination, for each other local documents in the set of local documents, a proximity measure location of the user device and the location specified for the other local document is determined. the first local document is demoted in its ranking when at least one of the proximity measures indicates a respective other local document has a specified location that is within a threshold distance of the location of the user device.
Inventor(s): Senthil Kumar Hariramasamy of Los Altos CA (US) for google llc, Omar Frazer Restom of San Francisco CA (US) for google llc, Abhinav Gaiha of Mountain View CA (US) for google llc, Bhavika Goyal of San Francisco CA (US) for google llc, Rushil Grover of San Jose CA (US) for google llc
IPC Code(s): G06F16/955, G06V10/776
CPC Code(s): G06F16/9558
Abstract: techniques for presenting a search result with an improved user interface. a computer system can receive, from a user device, a request for a content item. additionally, the system can select, based on the request, a first content item from a plurality of content items. the first content item can be associated with an organization image and an organization name of an organization. moreover, the system can process, using one or more machine-learned model, the organization image to determine whether the organization image is acceptable to be presented in the search result. subsequently, the system can transmit, to the user device, the first content item and the organization image to be presented in the search result.
20240211534.PERMUTING IN A MATRIX-VECTOR PROCESSOR_simplified_abstract_(google llc)
Inventor(s): Dong Hyuk Woo of San Jose CA (US) for google llc, Gregory Michael Thorson of Waunakee WI (US) for google llc, Andrew Everett Phelps of Middleton WI (US) for google llc, Olivier Temam of Antony (FR) for google llc, Jonathan Ross of Mountain View CA (US) for google llc, Christopher Aaron Clark of Madison WI (US) for google llc
IPC Code(s): G06F17/16, G06F7/76, G06F9/30, G06N3/063, G06N3/084
CPC Code(s): G06F17/16
Abstract: a circuit comprises an input register configured to receive an input vector of elements, a control register configured to receive a control vector of elements, wherein each element of the control vector corresponds to a respective element of the input vector, and wherein each element specifies a permutation of a corresponding element of the input vector, and a permute execution circuit configured to generate an output vector of elements corresponding to a permutation of the input vector. generating each element of the output vector comprises accessing, at the input register, a particular element of the input vector, accessing, at the control register, a particular element of the control vector corresponding to the particular element of the input vector, and outputting the particular element of the input vector as an element at a particular position of the output vector that is selected based on the particular element of the control vector.
Inventor(s): Abhirut Gupta of Bangalore (IN) for google llc, Aravindan Raghuveer of Chennai (IN) for google llc, Abhay Sharma of Bangalore (IN) for google llc, Nitin Raut of Mountain View CA (US) for google llc, Manish Kumar of Bangalore (IN) for google llc
IPC Code(s): G06F40/284, G06F40/232, G06F40/242, G10L13/08, G10L15/02, G10L15/06, G10L15/187
CPC Code(s): G06F40/284
Abstract: systems and methods for generating phonetic spelling variations of a given word based on locale-specific pronunciations. a phoneme-letter density model may be configured to identify a phoneme sequence corresponding to an input word, and to identify all character sequences that may correspond to an input phoneme sequence and their respective probabilities. the phoneme-phoneme error model may be configured to identify locale-specific alternative phoneme sequences that may correspond to a given phoneme sequence, and their respective probabilities. using these two models, a processing system may be configured to generate, for a given input word, a list of alternative character sequences that may correspond to the input word based on locale-specific pronunciations, and/or a probability distribution representing how likely each alternative character sequence is to correspond to the input word.
Inventor(s): Noam M. Shazeer of Palo Alto CA (US) for google llc, Lukasz Mieczyslaw Kaiser of San Francisco CA (US) for google llc, Etienne Pot of Palo Alto CA (US) for google llc, Mohammad Saleh of Santa Clara CA (US) for google llc, Ben David Goodrich of San Francisco CA (US) for google llc, Peter J. Liu of Santa Clara CA (US) for google llc, Ryan Sepassi of Beverly Hills CA (US) for google llc
IPC Code(s): G06N3/08, G06N3/045
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. one of the methods includes, at each of a plurality of generation time steps: generating a combined sequence for the generation time step that includes the input sequence followed by the output tokens that have already been generated as of the generation time step; processing the combined sequence using a self-attention decoder neural network to generate a time step output that defines a score distribution over a set of possible output tokens; and selecting, using the time step output, an output token from the set of possible output tokens as the next output token in the output sequence.
Inventor(s): Noam M. Shazeer of Palo Alto CA (US) for google llc, Lukasz Mieczyslaw Kaiser of San Francisco CA (US) for google llc, Etienne Pot of Palo Alto CA (US) for google llc, Mohammad Saleh of Santa Clara CA (US) for google llc, Ben David Goodrich of San Francisco CA (US) for google llc, Peter J. Liu of Santa Clara CA (US) for google llc, Ryan Sepassi of Beverly Hills CA (US) for google llc
IPC Code(s): G06N3/08, G06N3/045
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. one of the methods includes, at each of a plurality of generation time steps: generating a combined sequence for the generation time step that includes the input sequence followed by the output tokens that have already been generated as of the generation time step; processing the combined sequence using a self-attention decoder neural network to generate a time step output that defines a score distribution over a set of possible output tokens; and selecting, using the time step output, an output token from the set of possible output tokens as the next output token in the output sequence.
20240211759.USING EMBEDDING FUNCTIONS WITH A DEEP NETWORK_simplified_abstract_(google llc)
Inventor(s): Gregory S. Corrado of San Francisco CA (US) for google llc, Kai Chen of San Bruno CA (US) for google llc, Jeffrey A. Dean of Palo Alto CA (US) for google llc, Gary R. Holt of Murrysville PA (US) for google llc, Julian P. Grady of Pittsburgh PA (US) for google llc, Sharat Chikkerur of Pittsburgh PA (US) for google llc, David W. Sculley, II of Pittsburgh PA (US) for google llc
IPC Code(s): G06N3/08, G06F7/483, G06F17/16, G06N3/04, G06N3/045, G06N3/084
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for using embedded function with a deep network. one of the methods includes receiving an input comprising a plurality of features, wherein each of the features is of a different feature type; processing each of the features using a respective embedding function to generate one or more numeric values, wherein each of the embedding functions operates independently of each other embedding function, and wherein each of the embedding functions is used for features of a respective feature type; processing the numeric values using a deep network to generate a first alternative representation of the input, wherein the deep network is a machine learning model composed of a plurality of levels of non-linear operations; and processing the first alternative representation of the input using a logistic regression classifier to predict a label for the input.
20240211764.COMPOUND MODEL SCALING FOR NEURAL NETWORKS_simplified_abstract_(google llc)
Inventor(s): Mingxing Tan of Newark CA (US) for google llc, Quoc V. Le of Sunnyvale CA (US) for google llc
IPC Code(s): G06N3/082, G06N3/04
CPC Code(s): G06N3/082
Abstract: a method for determining a final architecture for a neural network to perform a particular machine learning task is described. the method includes receiving a baseline architecture for the neural network, wherein the baseline architecture has a network width dimension, a network depth dimension, and a resolution dimension; receiving data defining a compound coefficient that controls extra computational resources used for scaling the baseline architecture; performing a search to determine a baseline width, depth and resolution coefficient that specify how to assign the extra computational resources to the network width, depth and resolution dimensions of the baseline architecture, respectively; determining a width, depth and resolution coefficient based on the baseline width, depth, and resolution coefficient and the compound coefficient; and generating the final architecture that scales the network width, network depth, and resolution dimensions of the baseline architecture based on the corresponding width, depth, and resolution coefficients.
Inventor(s): Deepa Thiruppathiraju of Fremont CA (US) for google llc, Vidya Visweswaran Iyer of Cupertino CA (US) for google llc, Sagar Subodh Shah of Redmond WA (US) for google llc, Pallavi Naresh Dhruva of San Carlos CA (US) for google llc, Shuichi Koga of Mountain View CA (US) for google llc
IPC Code(s): G06Q30/0242
CPC Code(s): G06Q30/0243
Abstract: methods, systems, and apparatus include computer program encoded on a computer-readable storage medium for conducting an experiment for a campaign. a subset of current campaign parameters from a third party can be received, by a computing system, to be a set of test variables, where the set of test variables correspond to a proposed modification of a current campaign that is applied to a treatment campaign. the current campaign can be monitored for changes to the current campaign parameters. based on a determination that the current campaign parameter that has been modified by the third party is outside the set of test variables, the modification to the current campaign parameter can be reproduced and propagated to the treatment campaign. an action to take can be determined based on the modified current campaign parameter causing a change to at least one of the set of test variables.
Inventor(s): Michael Kleber of Newton MA (US) for google llc, Gang Wang of Frederick MD (US) for google llc, Daniel Ramage of Seattle WA (US) for google llc, Charlie Harrison of Mountain View CA (US) for google llc, Josh Karlin of Mountain View CA (US) for google llc, Moti Yung of New York NY (US) for google llc
IPC Code(s): G06Q30/0251, G06F16/951, H04L9/08, H04L9/32
CPC Code(s): G06Q30/0255
Abstract: the present disclosure provides systems and methods for content quasi-personalization or anonymized content retrieval via aggregated browsing history of a large plurality of devices, such as millions or billions of devices. a sparse matrix may be constructed from the aggregated browsing history, and dimensionally reduced, reducing entropy and providing anonymity for individual devices. relevant content may be selected via quasi-personalized clusters representing similar browsing histories, without exposing individual device details to content providers.
Inventor(s): Chloe LeGendre of Culver City CA (US) for google llc, Paul Debevec of Culver City CA (US) for google llc, Sean Ryan Francesco Fanello of San Francisco CA (US) for google llc, Rohit Kumar Pandey of Mountain View CA (US) for google llc, Sergio Orts Escolano of San Francisco CA (US) for google llc, Christian Haene of Berkeley CA (US) for google llc, Sofien Bouaziz of Los Gatos CA (US) for google llc
IPC Code(s): G06T5/50, G06T7/194, G06V10/56, G06V10/60, H04N5/272
CPC Code(s): G06T5/50
Abstract: apparatus and methods related to applying lighting models to images are provided. an example method includes receiving, via a computing device, an image comprising a subject. the method further includes relighting, via a neural network, a foreground of the image to maintain a consistent lighting of the foreground with a target illumination. the relighting is based on a per-pixel light representation indicative of a surface geometry of the foreground. the light representation includes a specular component, and a diffuse component, of surface reflection. the method additionally includes predicting, via the neural network, an output image comprising the subject in the relit foreground. one or more neural networks can be trained to perform one or more of the aforementioned aspects.
Inventor(s): Ruofei Du of San Francisco CA (US) for google llc, David Li of Gaithersburg MD (US) for google llc, Danhang Tang of West Hollywood CA (US) for google llc, Yinda Zhang of Palo Alto CA (US) for google llc
IPC Code(s): G06T7/55, G06T5/77, G06T7/181, G06T15/00, G06T17/20
CPC Code(s): G06T7/55
Abstract: a method including predicting a stereo depth associated with a first panoramic image and a second panoramic image, the first panoramic image and the second panoramic image being captured with a time interlude between the capture of the first panoramic image and the second panoramic image, generating a first mesh representation based on the first panoramic image and a stereo depth corresponding to the first panoramic image, generating a second mesh representation based on the second panoramic image and a stereo depth corresponding to the second panoramic image, and synthesizing a third panoramic image based on fusing the first mesh representation with the second mesh representation.
20240212246.IMAGE MANIPULATION BY TEXT INSTRUCTION_simplified_abstract_(google llc)
Inventor(s): Tianhao Zhang of Sunnyvale CA (US) for google llc, Weilong Yang of Freemont CA (US) for google llc, Honglak Lee of Ann Arbor MI (US) for google llc, Hung-Yu Tseng of Merced CA (US) for google llc, Irfan Aziz Essa of Atlanta GA (US) for google llc, Lu Jiang of Mountain View CA (US) for google llc
IPC Code(s): G06T11/60, G06N3/045, G06N3/088, G06T3/02, G06T3/40, G06T9/00
CPC Code(s): G06T11/60
Abstract: a method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. the neural network includes an image encoder, an image decoder, and an instruction attention network. the method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.
Inventor(s): Yinda Zhang of Daly City CA (US) for google llc, Feitong Tan of Beijing (CN) for google llc, Danhang Tang of West Hollywood CA (US) for google llc, Mingsong Dou of Cupertino CA (US) for google llc, Kaiwen Guo of Zurich (CH) for google llc, Sean Ryan Francesco Fanello of San Francisco CA (US) for google llc, Sofien Bouaziz of Los Gatos CA (US) for google llc, Cem Keskin of San Francisco CA (US) for google llc, Ruofei Du of San Francisco CA (US) for google llc, Rohit Kumar Pandey of Mountain View CA (US) for google llc, Deqing Sun of Cambridge MA (US) for google llc
IPC Code(s): G06V10/771, G06T7/70, G06T17/00, G06V10/44, G06V10/75
CPC Code(s): G06V10/771
Abstract: systems and methods for training models to predict dense correspondences across images such as human images. a model may be trained using synthetic training data created from one or more 3d computer models of a subject. in addition, one or more geodesic distances derived from the surfaces of one or more of the 3d models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.
20240212347.MEMORY-GUIDED VIDEO OBJECT DETECTION_simplified_abstract_(google llc)
Inventor(s): Dmitry Kalenichenko of Los Angeles CA (US) for google llc, Menglong Zhu of Playa Vista CA (US) for google llc, Marie Charisse White of Mountain View CA (US) for google llc, Mason Liu of Acton MA (US) for google llc, Yinxiao Li of Sunnyvale CA (US) for google llc
IPC Code(s): G06V20/40, G06V10/70, G06V10/774, G06V10/776, G06V10/80, G06V10/82, G06V10/94
CPC Code(s): G06V20/40
Abstract: systems and methods for detecting objects in a video are provided. a method can include inputting a video comprising a plurality of frames into an interleaved object detection model comprising a plurality of feature extractor networks and a shared memory layer. for each of one or more frames, the operations can include selecting one of the plurality of feature extractor networks to analyze the one or more frames, analyzing the one or more frames by the selected feature extractor network to determine one or more features of the one or more frames, determining an updated set of features based at least in part on the one or more features and one or more previously extracted features extracted from a previous frame stored in the shared memory layer, and detecting an object in the one or more frames based at least in part on the updated set of features.
Inventor(s): Dan Vanderkam of Brooklyn NY (US) for google llc, Douwe Osinga of New York NY (US) for google llc, Violet Whitney of Long Island City NY (US) for google llc, Kabir Soorya of Long Island City NY (US) for google llc, Jack Amadeo of Brooklyn NY (US) for google llc, Difei Chen of New York NY (US) for google llc, Brian Ho of New York NY (US) for google llc, Okalo Ikhena of New York NY (US) for google llc, Amanda Meurer of Brooklyn NY (US) for google llc, Samara Trilling of New York NY (US) for google llc
IPC Code(s): G08G1/01
CPC Code(s): G08G1/0112
Abstract: methods, systems, and media for generating and evaluating street grids comprising: receiving street grid information corresponding to a plurality of locations, wherein the street grid information corresponding to a location is associated with vehicular traffic information; training a pedestrian comfort model using the street grid information and the vehicular traffic information, wherein an output of the pedestrian comfort model is a predicted pedestrian comfort score that is based on traffic congestion from the vehicular traffic information;
Inventor(s): Dan Vanderkam of Brooklyn NY (US) for google llc, Douwe Osinga of New York NY (US) for google llc, Violet Whitney of Long Island City NY (US) for google llc, Kabir Soorya of Long Island City NY (US) for google llc, Jack Amadeo of Brooklyn NY (US) for google llc, Difei Chen of New York NY (US) for google llc, Brian Ho of New York NY (US) for google llc, Okalo Ikhena of New York NY (US) for google llc, Amanda Meurer of Brooklyn NY (US) for google llc, Samara Trilling of New York NY (US) for google llc
IPC Code(s): G08G1/01
CPC Code(s): G08G1/0112
Abstract: receiving a plurality of potential street grids; evaluating each potential street grid in the plurality of potential street grids using the trained pedestrian comfort model, wherein the trained pedestrian comfort model generates predicted pedestrian comfort scores for portions of each potential street grid; and generating an augmented map of each potential street grid that presents the predicted pedestrian comfort scores for each portion of each potential street grid.
20240213215.Asic Package With Photonics And Vertical Power Delivery_simplified_abstract_(google llc)
Inventor(s): Woon-Seong Kwon of Santa clara CA (US) for google llc, Nam Hoon Kim of San Jose CA (US) for google llc, Teckgyu Kang of Saratoga CA (US) for google llc, Ryohei Urata of San Carlos CA (US) for google llc
IPC Code(s): H01L25/065, G02B6/42, H01L23/31, H01L23/367, H01L23/498, H01L23/538, H01L25/04, H01L25/075, H01L25/16, H01L31/12, H10K39/00
CPC Code(s): H01L25/0652
Abstract: the technology relates to an integrated circuit (ic) package. the ic package may include a substrate. an ic die may be mounted to the substrate. one or more photonic modules may be attached to the substrate and one or more serializer/deserializer (serdes) interfaces may connect the ic die to the one or more photonic modules. the ic die may be an application specific integrated circuit (asic) die and the one or more photonic modules may include a photonic integrated circuit (pic) and fiber array. the one or more photonic modules may be mounted to one or more additional substrates which may be attached to the substrate via one or more sockets.
Inventor(s): Gang Wang of Frederick MD (US) for google llc, Marcel M. Moti Yung of New York NY (US) for google llc
IPC Code(s): H04L9/32, H04L9/08, H04L9/14
CPC Code(s): H04L9/3257
Abstract: methods, systems, and apparatus, including a method for determining network measurements. in some aspects, a method includes receiving, by a first aggregation server and from each of multiple client devices, encrypted impression data. a second aggregation server receives, from each of at least a portion of the multiple client devices, encrypted conversion data. the first aggregation server and the second aggregation server perform a multi-party computation process to decrypt the encrypted impression data and the encrypted conversion data. each portion of decrypted impression data and each portion of decrypted conversion data is sent to a respective reporting system.
Inventor(s): Gang Wang of Frederick MD (US) for google llc, Yue Wang of Los Altos CA (US) for google llc, Chin-Yet Lin of San Jose CA (US) for google llc
IPC Code(s): H04L9/40, G06F21/62
CPC Code(s): H04L63/104
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting and providing digital contents to a client device are described. the system receives a request including a user membership probabilistic data structure encoding user membership information, and constructs, based on the user membership probabilistic data structure, a query for identifying candidate digital components that are eligible for distribution to users. the system obtains the set of candidate digital components by querying one or more digital component databases using the constructed query, selects, from the candidate digital components, one or more digital components, and provides the one or more digital components to the client device for presentation to the user.
20240214438.ANCHORS FOR LIVE STREAMS_simplified_abstract_(google llc)
Inventor(s): Justin Lewis of Marina del Rey CA (US) for google llc, Scott Davies of Santa Monica CA (US) for google llc
IPC Code(s): H04L65/612, H04L65/60, H04L67/01, H04L67/60, H04N21/2187, H04N21/234, H04N21/262, H04N21/845
CPC Code(s): H04L65/612
Abstract: an application on a viewer client device receives a user input to access a live stream, sends a request to access the live stream, presents information allowing a user to indicate a first anchor of a plurality of anchors of the live stream, the first anchor corresponding to a timestamp for starting a portion of the live stream, receives user input identifying the live stream and user input indicating the first anchor of the live stream, and displays the live stream beginning at the timestamp corresponding to the first anchor of the live stream.
Inventor(s): Yeping Su of Cupertino CA (US) for google llc, Balu Adsumilli of San Francisco CA (US) for google llc
IPC Code(s): H04L65/80, H04L65/75, H04L67/61, H04N7/01, H04N21/442
CPC Code(s): H04L65/80
Abstract: a method is provided that may include receiving, at a server, an indication of a first video to be presented on a user device, determining, at the server based on video features of the first video, a group of predicted viewership scores for each format from a group of available formats for the first video, selecting, at the server, a first format for the first video based on the group of predicted viewership scores for the first video, causing the first video to be presented on the user device, identifying a quality of a network connection between the user device and the server that hosts the first video during the presentation of the first video on the user device, receiving an indication of a second video to be presented on the user device, identifying a change in the quality of the network connection between the user device and the server, determining whether a format of the second video is to be changed from the first format to a second format based at least in part on the change in the quality of the network connection between the user device and the server, and in response to determining that the format of the second video is not to be changed from the first format to the second format, causing the second video to be presented by the user device.
20240214542.TECHNIQUES TO CAPTURE AND EDIT DYNAMIC DEPTH IMAGES_simplified_abstract_(google llc)
Inventor(s): Mira Leung of Seattle WA (US) for google llc, Steve Perry of Mountain View CA (US) for google llc, Fares Alhassen of Redwood Shores CA (US) for google llc, Abe Stephens of San Mateo CA (US) for google llc, Neal Wadhwa of Mountain View CA (US) for google llc
IPC Code(s): H04N13/271, G06T7/55
CPC Code(s): H04N13/271
Abstract: implementations described herein relate to a computer-implemented method that includes capturing image data using one or more cameras, wherein the image data includes a primary image and associated depth values. the method further includes encoding the image data in an image format. the encoded image data includes the primary image encoded in the image format and image metadata that includes a device element that includes a profile element indicative of an image type and a first camera element, wherein the first camera element includes an image element and a depth map based on the depth values. the method further includes, after the encoding, storing the image data in a file container based on the image format. the method further includes causing the primary image to be displayed.
Inventor(s): In Suk Chong of Mountain View CA (US) for google llc, Jeremy Christopher Dorfman of Burlington MA (US) for google llc, Aki Kuusela of Palo Alto CA (US) for google llc
IPC Code(s): H04N19/172, H04N19/105, H04N19/154
CPC Code(s): H04N19/172
Abstract: a media item to be provided to users of a platform is identified. the media item includes multiple frames. metrics for the frames of the media item are obtained. a frame type associated with each of the frames is determined based on the metrics. the media item is determined, based on the frame type associated with each frames, to be encoded using two or more of a hardware encoder, a software encoder, or a hybrid encoder. the frames of the media item are encoded using the two or more of the hardware encoder, the software encoder, or the hybrid encoder in accordance with the determination.
20240214607.MAPPING-AWARE CODING TOOLS FOR 360 DEGREE VIDEOS_simplified_abstract_(google llc)
Inventor(s): Bohan Li of Santa Clara CA (US) for google llc, Ching-Han Chiang of San Jose CA (US) for google llc, Jingning Han of Santa Clara CA (US) for google llc, Yao Yao of Baltimore MD (US) for google llc
IPC Code(s): H04N19/597, H04N19/139, H04N19/167, H04N19/176, H04N19/182, H04N19/52, H04N19/57, H04N19/583, H04N19/80
CPC Code(s): H04N19/597
Abstract: mapping-aware coding tools for 360 degree videos adapt conventional video coding tools for 360 degree video data using parameters related to a spherical projection of the 360 degree video data. the mapping-aware coding tools perform motion vector mapping techniques, adaptive motion search pattern techniques, adaptive interpolation filter selection techniques, and adaptive block partitioning techniques. motion vector mapping includes calculating a motion vector for a pixel of a current block by mapping the location of the pixel within a two-dimensional plane (e.g., video frame) onto a sphere and mapping a predicted location of the pixel on the sphere determined based on rotation parameters back onto the plane. adaptive motion searching, adaptive interpolation filter selection, and adaptive block partitioning operate according to density distortion based on locations along the sphere. these mapping-aware coding tools contemplate changes to video information by the mapping of 360 degree video data into a conventional video format.
Inventor(s): Saleh Altayyar of Modesto CA (US) for google llc, Sourav Basu of Fremont CA (US) for google llc
IPC Code(s): H04N21/258, H04N21/254, H04N21/262, H04N21/2668
CPC Code(s): H04N21/25891
Abstract: this application is directed to presenting a unified user interface on a network-connected television device. the unified user interface displays media content recommendations selected and organized based on knowledge of a user (e.g., search queries, search results, watch history, purchase history, physical activities). the unified user interface also includes a focus area for displaying a series of media content items (e.g., an advertisement) sequentially according to a temporal order for the purposes of promoting a media content item, product, event or service. in some implementations, playback of a media content item presented on the unified user interface relies on a collaborative implementation of a corresponding media player application and a media content casting application, particularly when the play involves a restricted mode. the content casting application is enabled to play the media content item at the restrict mode when the media player application does not operate in the restricted mode.
20240214647.MIDROLL BREAKS FEEDBACK SYSTEM_simplified_abstract_(google llc)
Inventor(s): Yun Shi of Sunnyvale CA (US) for google llc, Jianfeng Yang of Mountain View CA (US) for google llc, Ramesh Sarukkai of Los Gatos CA (US) for google llc, Zindziswa Lara McCormick of Mountain View CA (US) for google llc
IPC Code(s): H04N21/81, H04N21/234, H04N21/24, H04N21/45, H04N21/475
CPC Code(s): H04N21/812
Abstract: a computer-implemented method for optimizing the placement of previously selected breaks in a media item is provided herein. embodiments of the method include steps of identifying a break in a media item, the break being associated with a first break point at a first time during playback of the media item. the method may also include steps of dynamically adjusting the placement of the breaks within the media item based on the performance of the media item.
20240214774.Altitude Enhanced Geofence_simplified_abstract_(google llc)
Inventor(s): Andrew Larsen Axley of Bend OR (US) for google llc, Erin Rebecca Griffiths of Santa Clara CA (US) for google llc
IPC Code(s): H04W4/021, H04W4/38, H04W24/08, H04W64/00
CPC Code(s): H04W4/021
Abstract: this document describes systems and techniques directed at an altitude enhanced geofence. in aspects, a geofence manager maintains a three-dimensional virtual boundary for a geographic area associated with a user. the geofence manager determines a spatial positioning of a portable electronic device associated with the user relative to the virtual boundary. based on a determination that the portable electronic device is within a horizontal boundary of the virtual boundary, the geofence manager monitors a barometric pressure surrounding the portable electronic device using information from at least one sensor associated with the portable electronic device. the geofence manager can determine an altitude of the portable electronic device based on the monitored pressure and initiate one or more functions if the altitude indicates the portable electronic device is within a vertical boundary of the virtual boundary. through such techniques, the geofence manager can increase the accuracy and reliability of geofencing systems.
- Google LLC
- A63B71/06
- A63B24/00
- G04G21/02
- G04G99/00
- G06F3/01
- G06F3/0481
- G06F3/04842
- G16H40/67
- CPC A63B71/0622
- Google llc
- A63F13/352
- A63F13/23
- A63F13/355
- A63F13/92
- CPC A63F13/352
- A63F13/5255
- A63F13/211
- A63F13/26
- CPC A63F13/5255
- C12N15/115
- CPC C12N15/115
- G01C21/36
- G10L15/22
- CPC G01C21/3608
- CPC G01C21/3641
- G01S7/41
- G01S13/00
- CPC G01S7/415
- G06F1/16
- CPC G06F1/1681
- G06F1/26
- CPC G06F1/26
- G06F3/16
- CPC G06F3/04842
- G06F8/36
- G06F16/24
- G06N5/04
- G06N20/00
- CPC G06F8/36
- G06F8/65
- G06F8/61
- G06F9/445
- G06Q20/12
- H04L9/40
- H04M3/42
- H04M3/537
- H04M7/00
- CPC G06F8/65
- G06F9/38
- CPC G06F9/3802
- G06F9/30
- CPC G06F9/3887
- G06F11/14
- G06F9/451
- G09G5/14
- H04L67/306
- CPC G06F11/1469
- G06F12/14
- CPC G06F12/1408
- G06F13/16
- G06F9/35
- G06F9/52
- CPC G06F13/161
- G06F16/22
- G06F16/174
- G06F16/215
- G06F16/33
- G06F30/27
- G06N3/04
- G06N3/08
- H03M7/30
- CPC G06F16/2282
- G06F16/2457
- G06F16/248
- G06F16/29
- G06F16/9535
- G06F16/9537
- H04L101/69
- CPC G06F16/24578
- G06F16/955
- G06V10/776
- CPC G06F16/9558
- G06F17/16
- G06F7/76
- G06N3/063
- G06N3/084
- CPC G06F17/16
- G06F40/284
- G06F40/232
- G06F40/242
- G10L13/08
- G10L15/02
- G10L15/06
- G10L15/187
- CPC G06F40/284
- G06N3/045
- CPC G06N3/08
- G06F7/483
- G06N3/082
- CPC G06N3/082
- G06Q30/0242
- CPC G06Q30/0243
- G06Q30/0251
- G06F16/951
- H04L9/08
- H04L9/32
- CPC G06Q30/0255
- G06T5/50
- G06T7/194
- G06V10/56
- G06V10/60
- H04N5/272
- CPC G06T5/50
- G06T7/55
- G06T5/77
- G06T7/181
- G06T15/00
- G06T17/20
- CPC G06T7/55
- G06T11/60
- G06N3/088
- G06T3/02
- G06T3/40
- G06T9/00
- CPC G06T11/60
- G06V10/771
- G06T7/70
- G06T17/00
- G06V10/44
- G06V10/75
- CPC G06V10/771
- G06V20/40
- G06V10/70
- G06V10/774
- G06V10/80
- G06V10/82
- G06V10/94
- CPC G06V20/40
- G08G1/01
- CPC G08G1/0112
- H01L25/065
- G02B6/42
- H01L23/31
- H01L23/367
- H01L23/498
- H01L23/538
- H01L25/04
- H01L25/075
- H01L25/16
- H01L31/12
- H10K39/00
- CPC H01L25/0652
- H04L9/14
- CPC H04L9/3257
- G06F21/62
- CPC H04L63/104
- H04L65/612
- H04L65/60
- H04L67/01
- H04L67/60
- H04N21/2187
- H04N21/234
- H04N21/262
- H04N21/845
- CPC H04L65/612
- H04L65/80
- H04L65/75
- H04L67/61
- H04N7/01
- H04N21/442
- CPC H04L65/80
- H04N13/271
- CPC H04N13/271
- H04N19/172
- H04N19/105
- H04N19/154
- CPC H04N19/172
- H04N19/597
- H04N19/139
- H04N19/167
- H04N19/176
- H04N19/182
- H04N19/52
- H04N19/57
- H04N19/583
- H04N19/80
- CPC H04N19/597
- H04N21/258
- H04N21/254
- H04N21/2668
- CPC H04N21/25891
- H04N21/81
- H04N21/24
- H04N21/45
- H04N21/475
- CPC H04N21/812
- H04W4/021
- H04W4/38
- H04W24/08
- H04W64/00
- CPC H04W4/021
