GOOGLE LLC patent applications on October 17th, 2024
Patent Applications by GOOGLE LLC on October 17th, 2024
GOOGLE LLC: 39 patent applications
GOOGLE LLC has applied for patents in the areas of H04L9/40 (4), G10L15/08 (3), G06N20/00 (3), G06V40/16 (3), G10L15/22 (3) G10L15/22 (3), G06N10/70 (2), H01L23/3732 (1), G06V40/50 (1), G09G3/32 (1)
With keywords such as: user, based, data, device, media, image, application, audio, whether, and content in patent application abstracts.
Patent Applications by GOOGLE LLC
Inventor(s): Ali BASHIR of San Mateo CA (US) for google llc, Marc BERNDL of Mountain View CA (US) for google llc, Annalisa PAWLOSKY of Mountain View CA (US) for google llc, Jun KIM of Mountain View CA (US) for google llc, Sara AHADI of Mountain View CA (US) for google llc, Alexander TRAN of Mountain View CA (US) for google llc
IPC Code(s): C12Q1/6806, C12Q1/6869
CPC Code(s): C12Q1/6806
Abstract: contemporary gene sequencing techniques, including “next. generation sequencing” techniques, can include sequencing a plurality of fragments of a target polynucleotide. however, the limitations of existing sequencing techniques means that it can be difficult and/or expensive to align the generated read fragments. methods provided herein include inserting dual polynucleotide ‘bar-codes’ into a target poly nucleotide that remain mechanically connected via a tinker.’ tire barcodes can then be ‘grown’ via. a. pool-split-pool process such that polynucleotide fragments that are linked by linkers exhibit the same complete barcode sequence that is different, from the complete barcode sequence exhibited by non-linked polynucleotide fragments. the joined fragments can then be separated and sequenced. each read sequence thus begins with a regionally-specific barcode that can be used to associate fragments from the region together, allowing for increased accuracy and reduced computational cost in aligning the read fragments and/or performing other sequencing processes on the read fragments.
Inventor(s): Thomas Deselaers of Zurich (CH) for google llc, Sandro Feuz of Zurich (CH) for google llc
IPC Code(s): G01C21/34, G01C21/36, G06N5/04, G06N20/00, H04L51/046
CPC Code(s): G01C21/3438
Abstract: a navigation service determines that a first user intends to navigate to a shared destination from a first location, at a first time, and that a second user intends to navigate to the shared destination from a second location, at a second time within a threshold interval of the first time. the navigation service notifies the first user using an electronic notification that the second user intends to navigate to the shared destination, receives from the first user an electronic request to coordinate navigation to the shared destination with the second user, and in response to receiving the electronic request, provides navigation directions to the shared destination to a device associated with the first user in view of a progress of the second user toward the shared destination.
Inventor(s): Nicholas Edward Gillian of Palo Alto CA (US) for google llc
IPC Code(s): G01S7/295, G01S13/53, G01S13/88, G06F3/01
CPC Code(s): G01S7/2955
Abstract: techniques and apparatuses are described that implement a smart-device-based radar system capable of detecting a frame-of-reference change. in particular, a radar system includes a frame-of-reference machine-learned module trained to recognize whether or not the radar system's frame of reference changes. the frame-of-reference machine-learned module analyzes complex radar data generated from at least one chirp of a reflected radar signal to analyze a relative motion of at least one object over time. by analyzing the complex radar data directly using machine learning, the radar system can operate as a motion sensor without relying on non-radar-based sensors, such as gyroscopes, inertial sensors, or accelerometers. with knowledge of whether the frame-of-reference is stationary or moving, the radar system can determine whether or not a gesture is likely to occur and, in some cases, compensate for the relative motion of the radar system itself.
20240346055. Search Suggestions Based on Native Application History_simplified_abstract_(google llc)
Inventor(s): Ulas Kirazci of Mountain View CA (US) for google llc, Othar Hansson of Sunnyvale CA (US) for google llc, Anton Hansson of London (GB) for google llc
IPC Code(s): G06F16/332
CPC Code(s): G06F16/3322
Abstract: methods, systems, and apparatus, for automatically generating search suggestions based on history data for multiple native application on a user device.
Inventor(s): Jeremy Phillips of Mountain View CA (US) for google llc, Rupak Banerjee of Mountain View CA (US) for google llc
IPC Code(s): G06F16/957, G06F16/958
CPC Code(s): G06F16/9577
Abstract: to determine whether a web resource complies with a policy for displaying an informational notice, a system obtaining a document object model (dom) representation of the web resource, the dom representation specifying a hierarchy of pages and including instructions for displaying content elements. the system traverses the dom representation of the web resource to determine whether the web resource includes the informational notice, including calculating a likelihood that a content element corresponds to the informational notice based on one or more keywords associated with the informational notice. in response to determining that the content element corresponds to the informational notice, the system determines a set of visual parameters of the content element, and determines whether the web resource is configured to display the content element according to a visibility metric. the system further generates an indication of whether the web resource contains the informational notice according to the visibility metric.
Inventor(s): Bernadette Alexia CARTER of Santa Clara CA (US) for google llc
IPC Code(s): G06F21/62, G06F21/60, H04L9/40, H04L51/212, H04L51/224, H04L51/52
CPC Code(s): G06F21/6263
Abstract: a server can receive a request from a creator of a message to share one or more rights of the creator of the message with a user referenced in the message. the server can send a notification about the one or more rights to the user referenced in the message, where the one or more rights may specify at least one of: whether the user is to receive feedback notifications of feedback related to the message, whether the user is to control visibility of feedback on the message by users, or whether the user is to control allowing feedback on the messages. the sever can then perform one or more operations related to the message based on the one or more rights accepted by the user.
Inventor(s): Zhe Dong of Zurich (CH) for google llc, Jianmo Ni of Santa Clara CA (US) for google llc, Imed Zitouni of Zug (CH) for google llc, Enrique Alfonseca of Mountain view CA (US) for google llc, Daniel Martin Bikel of Mountain View CA (US) for google llc, Chen Qu of Sunnyvale CA (US) for google llc
IPC Code(s): G06N3/0455
CPC Code(s): G06N3/0455
Abstract: aspects of the technology provide systems and methods for implementing an asymmetric dual encoder architecture. the architecture includes a token embedder layer section having a first token embedding section associated with a first input and a second token embedding section associated with a second input, and an encoder layer section having a first encoder section receiving token embeddings from the first token embedding section and a second encoder section receiving token embeddings from the second token embedding section. a shared projection layer receives encodings from both the first and second encoder sections and generates a set of projections. an embedding space is configured, based on the set of projections, to generate a question embedding and an answer embedding, in which the question and answer embeddings are used in identifying a set of candidate answers to an input answer.
Inventor(s): Alexander Krizhevsky of Mountain View CA (US) for google llc, Ilya Sutskever of San Francisco CA (US) for google llc, Geoffrey E. Hinton of Toronto (CA) for google llc
IPC Code(s): G06N3/063, G06F18/214, G06N3/04, G06N3/045, G06N3/08, G06T1/20, G06V10/44
CPC Code(s): G06N3/063
Abstract: a parallel convolutional neural network is provided. the cnn is implemented by a plurality of convolutional neural networks each on a respective processing node. each cnn has a plurality of layers. a subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. the remaining subset is not so interconnected.
20240346316. RECOMMENDING A DOCUMENT FOR A USER TO ACCESS_simplified_abstract_(google llc)
Inventor(s): Sandeep Tata of San Francisco CA (US) for google llc, Julian Gibbons of Cremorne (AU) for google llc, Divanshu Garg of Pyrmont (AU) for google llc, Alexandre Mah of Epping (AU) for google llc, Alan Green of East Maitland (AU) for google llc, Cayden Meyer of Forest Lodge (AU) for google llc, Michael Smith of Gladesville (AU) for google llc, Reuben Kan of Carlingford (AU) for google llc, Alexandrin Popescul of San Francisco CA (US) for google llc
IPC Code(s): G06N3/08, G06F16/9535, G06N3/045, G06N3/084
CPC Code(s): G06N3/08
Abstract: a user device can send, to a server, a request for a set of documents likely to be opened by a user, determine a client-suggested document to present to the user and a potential motive for the user to open the client-suggested document, receive a suggestion message from the server, the suggestion message including a set of documents likely to be opened by the user and potential motives for the user to open documents in the set of documents, and present, on a display of the user device, visual representations of the client-suggested document, the potential motive for the user to open the client-suggested document, multiple documents included in the set of documents, and the potential motives for the user to open the multiple documents in the set of documents.
20240346356. Surface Codes with Densely Packed Gauge Operators_simplified_abstract_(google llc)
Inventor(s): Nathan Cody JONES of Los Angeles CA (US) for google llc
IPC Code(s): G06N10/70
CPC Code(s): G06N10/70
Abstract: the disclosure is directed to implementing a quantum error correction code via a quantum computer that includes a set of functional qubits and a set of non-functional qubits. a set of gauge operators is formed. a set of gauge operator combinations are determined from the set of gauge operators. determining the set of gauge operator combinations may be based on a subset of functional qubits and a global sequence of each gauge operator. each gauge operator combination has a composite operator that commutes with the composite operator of each other gauge operator combination. a set of composite stabilizers may be generated. each composite stabilizer corresponds to a separate gauge operator combination. the qec code may be executed, via the qcs, based on the set of composite stabilizers.
Inventor(s): John Martinis of Santa Barbara CA (US) for google llc, Austin Greig Fowler of Reseda CA (US) for google llc, Rami Barends of San Diego CA (US) for google llc
IPC Code(s): G06N10/70, G06F15/80, G06N10/00, G06N10/20
CPC Code(s): G06N10/70
Abstract: methods, systems, and apparatus for operating a system of qubits. in one aspect, a method includes operating a first qubit from a first plurality of qubits at a first qubit frequency from a first qubit frequency region, and operating a second qubit from the first plurality of qubits at a second qubit frequency from a second first qubit frequency region, the second qubit frequency and the second first qubit frequency region being different to the first qubit frequency and the first qubit frequency region, respectively, wherein the second qubit is diagonal to the first qubit in a two-dimensional grid of qubits.
Inventor(s): Ryan Babbush of Venice CA (US) for google llc, Joonho Lee of New York NY (US) for google llc, William Huggins of Oakland CA (US) for google llc
IPC Code(s): G06N10/80
CPC Code(s): G06N10/80
Abstract: methods, systems, and apparatus for simulating a quantum system. in one aspect, a method includes performing a first quantized quantum algorithm on an initial quantum state to simulate time evolution of a fermionic system and generate a time evolved quantum state; and measuring, by the quantum computer, the time evolved quantum state to obtain one or more reduced density matrices in first quantization, the measuring including performing a classical shadows method that applies separate random clifford channels to each qubit register of multiple qubit registers that represent respective occupied orbitals in the fermionic system.
Inventor(s): Animesh Nandi of Cupertino CA (US) for google llc, Liam Charles MacDermed of Millbrae CA (US) for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: provided are systems and methods for privacy-preserving learning and analytics of a shared embedding space for data split across multiple separate data silos. a central computing system can generate a plurality of synthetic data examples having respective feature data within an aggregate feature-space that represents an aggregation of different component feature-spaces associated with the multiple separate data silos. the synthetic data examples can be used by different computing systems associated with the data silos to generate embeddings within a shared embedding space. once the embeddings have been generated in the shared embedding space, multiple different types of analytics can be performed on the shared embedding space. as one example, the multiple data silos can correspond to multiple separate entity domains and an analysis of embeddings generated in the shared embedding space can be used to facilitate identification or classification of malicious actors across the multiple separate entity domains.
Inventor(s): Alex Jacobson of Mountain View CA (US) for google llc, Nick Sabatino of Mountain View CA (US) for google llc
IPC Code(s): G06Q30/0242, G06Q30/0251
CPC Code(s): G06Q30/0242
Abstract: techniques for increasing security and privacy while requesting digital advertisements for mobile applications are provided. such techniques use a separate ad management application on the same mobile computing device as an ad-requesting application to receive an ad request and to provide an ad response that provides digital ad assets to the ad-requesting application. the ad request and the ad response may be remote procedure calls. to obtain and provide the digital ad assets of a digital advertisement, the ad management application generates an ad request message based upon the ad request (which may include augmenting the ad request), sending the ad request message to a supply-side platform (ssp) of a digital advertising network, receiving an ad response message including the digital ad assets from the ssp, and sending the ad response with the digital ad assets to the ad-requesting application for display to a user of the mobile computing device.
20240346546. EVALUATING VISUAL QUALITY OF DIGITAL CONTENT_simplified_abstract_(google llc)
Inventor(s): Catherine Shyu of Mountain View CA (US) for google llc, Luying Li of Sunnyvale CA (US) for google llc, Feng Yang of Sunnyvale CA (US) for google llc, Junjie Ke of East Palo Alto CA (US) for google llc, Xiyang Luo of San Jose CA (US) for google llc, Hao Feng of Sunnyvale CA (US) for google llc, Chao-Hung Chen of Milpitas CA (US) for google llc, Wenjing Kang of Santa Clara CA (US) for google llc, Zheng Xia of Palo Alto CA (US) for google llc, Shun-Chuan Chen of Sunnyvale CA (US) for google llc, Yicong Tian of Mountain View CA (US) for google llc, Xia Li of Sunnyvale CA (US) for google llc, Han Ke of Sunnyvale CA (US) for google llc
IPC Code(s): G06Q30/0242
CPC Code(s): G06Q30/0244
Abstract: systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. methods can include identifying content assets including one or more images that are combined to create different digital components distributed to one or more client devices. a quality of each of the one or more images is evaluated using one or more machine learning models trained to evaluate one or more visual aspects that are deemed indicative of visual quality. an aggregate quality for the content assets is determined based, at least in part, on an output of the one or more machine learning models indicating the visual quality of each of the one or more images. a graphical user interface of a first computing device is updated to present a visual indication of the aggregate quality of the content assets.
20240346631. BYSTANDER AND ATTACHED OBJECT REMOVAL_simplified_abstract_(google llc)
Inventor(s): Orly LIBA of Mountain View CA (US) for google llc, Pedro VELEZ of Mountain View CA (US) for google llc, Siyang LI of Mountain View CA (US) for google llc, Huizhong CHEN of Mountain View CA (US) for google llc, Marcel PUYAT of Mountain View CA (US) for google llc, Yanan BAO of Mountain View CA (US) for google llc
IPC Code(s): G06T5/77, G06T5/60, G06T7/11, G06T7/136, G06T7/194
CPC Code(s): G06T5/77
Abstract: a media application detects a bystander in an initial image. the media application generates a bystander box that includes the bystander, wherein all pixels for the bystander are within the bystander box. the media application generates localizer boxes that encompass the bystander and one or more objects that are attached to the bystander. the media application aggregates the bystander box and one or more of the localizer boxes to form an aggregated box. the media application applies a segmenter to the initial image, based on the aggregated box, to segment the bystander and the one or more objects from the initial image to generate a bystander mask, wherein the bystander mask includes a subset of pixels within the aggregated box. the media application generates an inpainted image that replaces all pixels within the bystander mask with pixels that match a background in the initial image.
20240346796. Multi-Angle Object Recognition_simplified_abstract_(google llc)
Inventor(s): Ibrahim Badr of New York NY (US) for google llc
IPC Code(s): G06V10/22, G06V10/10, G06V10/24, G06V10/776, G06V10/98, H04N5/265, H04N23/60, H04N23/61, H04N23/63, H04N23/661, H04N23/698
CPC Code(s): G06V10/235
Abstract: methods, systems, and apparatus for controlling smart devices are described. in one aspect a method includes capturing, by a camera on a user device, a plurality of successive images for display in an application environment of an application executing on the user device, performing an object recognition process on the images, the object recognition process including determining that a plurality of images, each depicting a particular object, are required to perform object recognition on the particular object, and in response to the determination, generating a user interface element that indicates a camera operation to be performed, the camera option capturing two or more images, determining that a user, in response to the user interface element, has caused the indicated camera operation to be performed to capture the two or more images, and in response, determining whether a particular object is positively identified from the plurality of images.
Inventor(s): Kristina BOHL of Boulder (CO) for google llc, Joe AGAJANIAN of Los Angeles CA (US) for google llc, Lily BERG of Los Angeles CA (US) for google llc, Brian POTETZ of Irvine CA (US) for google llc, Keegan MOSLEY of Los Angeles CA (US) for google llc, Shinko CHENG of Mountain View CA (US) for google llc
IPC Code(s): G06V20/40, G06F18/21, G06F18/214, G06F18/23, G06T11/60, G06V20/30, G06V40/16
CPC Code(s): G06V20/44
Abstract: a media application segments a library of media associated with a user account into episodes, wherein each episode is associated with a corresponding time period. the media application generates, using an event machine-learning model, an event signal that indicates a likelihood that an event occurred in each episode, wherein the event machine-learning model is a classifier that receives the media as input. the media application generates an event significance score for each episode. the media application determines one or more events from the episodes based on the event signal and a corresponding event significance score exceeding a threshold event significance value. the media application provides a user interface that includes corresponding media from the one or more events.
20240346824. ACTION LOCALIZATION IN VIDEOS USING LEARNED QUERIES_simplified_abstract_(google llc)
Inventor(s): Alexey Alexeevich Gritsenko of Amsterdam (NL) for google llc, Xuehan Xiong of Mountain View CA (US) for google llc, Josip Djolonga of Zurich (CH) for google llc, Mostafa Dehghani of Amsterdam (NL) for google llc, Chen Sun of San Francisco CA (US) for google llc, Mario Lucic of Adliswil (CH) for google llc, Cordelia Luise Schmid of Saint Ismier (FR) for google llc, Anurag Arnab of Grenoble (FR) for google llc
IPC Code(s): G06V20/40, G06T7/73, G06V10/62, G06V10/764, G06V10/77, G06V10/774, G06V10/776, G06V10/82
CPC Code(s): G06V20/46
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing action localization on an input video. in particular, a system maintains a set of query vectors and uses the input video and the set of query vectors to generate an action localization output for the input video. the action localization output includes, for each of one or more agents depicted in the video, data specifying, for each of one or more video frames in the video, a respective bounding box in the video frame that depicts the agent and a respective action from a set of actions that is being performed by the agent in the video frame.
Inventor(s): Samara Trilling of New York NY (US) for google llc, Tess Bianchi of New York NY (US) for google llc, Douwe Osinga of New York NY (US) for google llc, Josh Chappell of New York NY (US) for google llc, Okalo Ikhena of New York NY (US) for google llc
IPC Code(s): G06V20/52, G01C21/00, G06V20/17
CPC Code(s): G06V20/53
Abstract: methods, systems, and media for simulating movement data of pedestrians in a district are comprising receiving a district plan for a proposed district; determining a number of users that would populate the proposed district; generating a population of simulated users based on the determined number of users that would populate the proposed district; assigning, for the population of simulated users, groups of simulated users in the population of simulated users to a movement category from a plurality of movement categories; distributing, for the groups of simulated users assigned to each of the plurality of movement categories, trips having the probable walking path of the group of simulated users over time by applying a distribution function to each of the plurality of movement categories; and causing a map representation of the district to be presented.
20240346832. Detection Network Based On Embedding Distance Models_simplified_abstract_(google llc)
Inventor(s): Dongeek Shin of San Jose CA (US) for google llc
IPC Code(s): G06V20/58, G01C21/00, G06T7/70, G06V10/25, G06V10/44, G06V10/74
CPC Code(s): G06V20/586
Abstract: the present disclosure provides a space analytics system configured to determine the location of a vehicle using on-car camera snapshots to feature match against a pre-calibrated map. the system may estimate the location of a vehicle using the pre-calibrated map based on embeddings from reference images taken of the parking spot. the system may determine the location of the vehicle based on comparing reference image embeddings to real-time image embeddings and determining which comparison yields the embedding distance scores below the required threshold for a match.
20240346840. Detecting a Homoglyph in a String of Characters_simplified_abstract_(google llc)
Inventor(s): Aaron Michael Brown of Seattle WA (US) for google llc, Pranoy Kovuri of Santa Clara CA (US) for google llc, Liam Charles MacDermed of Millbrae CA (US) for google llc
IPC Code(s): G06V30/19
CPC Code(s): G06V30/19093
Abstract: a method for detecting a homoglyph in an input text includes receiving a first string of characters and deobfuscating the first string of characters to generate a second string of characters. when at least one character from the first string of characters has replaced another character in the second string of characters based on the deobfuscating, the method further includes determining a visual similarity value based on the first string of characters and the second string of characters and providing an indication whether a homoglyph is present in the first string of characters, based on the visual similarity value.
20240346851. ENROLLMENT WITH AN AUTOMATED ASSISTANT_simplified_abstract_(google llc)
Inventor(s): Diego Melendo Casado of Mountain View CA (US) for google llc, Tuan Nguyen of San Jose CA (US) for google llc, Jaclyn Konzelmann of Mountain View CA (US) for google llc, Gustavo Moura of Boulder CO (US) for google llc, Tanya Kraljic of Ridgewood NJ (US) for google llc
IPC Code(s): G06V40/50, G06V40/16, G06V40/70, G10L17/00, G10L17/04
CPC Code(s): G06V40/50
Abstract: techniques are described herein for dialog-based enrollment of individual users for single-and/or multi-modal recognition by an automated assistant, as well as determining how to respond to a particular user's request based on the particular user being enrolled and/or recognized. rather than requiring operation of a graphical user interface for individual enrollment, dialog-based enrollment enables users to enroll themselves (or others) by way of a human-to-computer dialog with the automated assistant.
Inventor(s): Aurelien Jean Francois David of San Francisco CA (US) for google llc, Patrick F. Brinkley of San Mateo CA (US) for google llc, Carlin Vieri of Menlo Park CA (US) for google llc
IPC Code(s): G09G3/32
CPC Code(s): G09G3/32
Abstract: a micro-led driver applies a low baseline power (i.e., a baseline voltage or current) to pre-charge a micro-led in a nominally-off (i.e., non-light-emitting) state in addition to applying an operating driving power to drive the micro-led in a light-emitting state. by pre-charging the micro-led prior to applying the operating driving power, the micro-led driver significantly decreases the time between application of the operating driving power and onset of emission of light from the micro-led. in some embodiments, the micro-led driver applies an operating driving power having multiple phases of current density to reduce the time between application of the operating driving power and onset of emission of light from the micro-led.
Inventor(s): Hsin Hsueh Li of New Taipei City (TW) for google llc, Chien-Hui Wen of Cupertino CA (US) for google llc
IPC Code(s): G09G5/10, G09G5/00
CPC Code(s): G09G5/10
Abstract: systems and techniques directed at dynamic power-saving mechanisms for displaying an image are disclosed. an electronic device determines an image to be displayed and an associated opr for displaying the image. based on the determined opr, the electronic device generates a bionic image. various mechanisms may be used to generate the bionic image. a display brightness value (dbv) or different blocking areas of the combined image may be used to generate the bionic image. the electronic device combines the image and the bionic image to form a combined image and presents the combined image on an emissive display. the combined image reduces a power expenditure of the emissive display that may otherwise be expended. the combined image may retain a high luminance for a focus area of the combined image while reducing the luminance for the remaining area (e.g., area outside of the focus area) of the combined image.
Inventor(s): David Qiu of Fremont CA (US) for google llc, David Rim of Mountain View CA (US) for google llc, Shaojin Ding of Mountain View CA (US) for google llc, Yanzhang He of Mountain View CA (US) for google llc
IPC Code(s): G10L15/06
CPC Code(s): G10L15/063
Abstract: a method includes obtaining a plurality of training samples, determining a minimum integer fixed-bit width representing a maximum quantization of an automatic speech recognition (asr) model, and training the asr model on the plurality of training samples using a quantity of random noise. the asr model includes a plurality of weights that each include a respective float value. the quantity of random noise is based on the minimum integer fixed-bit value. after training the asr model, the method also includes selecting a target integer fixed-bit width greater than or equal to the minimum integer fixed-bit width, and for each respective weight of the plurality of weights, quantizing the respective weight from the respective float value to a respective integer associated with a value of the selected target integer fixed-bit width. the operations also include providing the quantized trained asr model to a user device.
20240347051. Small Footprint Multi-Channel Keyword Spotting_simplified_abstract_(google llc)
Inventor(s): Jilong Wu of Mountain View CA (US) for google llc, Yiteng Huang of Mountain View CA (US) for google llc
IPC Code(s): G10L15/16, G10L15/08, G10L15/28, H04R3/00
CPC Code(s): G10L15/16
Abstract: a method to detect a hotword in a spoken utterance includes receiving a sequence of input frames characterizing streaming multi-channel audio. each channel of the streaming multi-channel audio includes respective audio features captured by a separate dedicated microphone. for each input frame, the method includes processing, using a three-dimensional (d) single value decomposition filter (svdf) input layer of a memorized neural network, the respective audio features of each channel in parallel and generating a corresponding multi-channel audio feature representation based on a concatenation of the respective audio features. the method also includes generating, using sequentially-stacked svdf layers, a probability score indicating a presence of a hotword in the audio. the method also includes determining whether the probability score satisfies a threshold and, when satisfied, initiating a wake-up process on a user device.
20240347060. CONTEXTUAL SUPPRESSION OF ASSISTANT COMMAND(S)_simplified_abstract_(google llc)
Inventor(s): Victor Carbune of Zurich (CH) for google llc, Matthew Sharifi of Kilchberg (CH) for google llc, Ondrej Skopek of Zurich (CH) for google llc, Justin Lu of Zurich (CH) for google llc, Daniel Valcarce of Zurich (CH) for google llc, Kevin Kilgour of Oetwil an der Limmat (CH) for google llc, Mohamad Hassan Rom of Zurich (CH) for google llc, Nicolo D'Ercole of Oberrieden (CH) for google llc, Michael Golikov of Merlischachen (CH) for google llc
IPC Code(s): G10L15/22, G10L15/05, G10L15/08, G10L15/18, G10L25/78
CPC Code(s): G10L15/22
Abstract: some implementations process, using warm word model(s), a stream of audio data to determine a portion of the audio data that corresponds to particular word(s) and/or phrase(s) (e.g., a warm word) associated with an assistant command, process, using an automatic speech recognition (asr) model, a preamble portion of the audio data (e.g., that precedes the warm word) and/or a postamble portion of the audio data (e.g., that follows the warm word) to generate asr output, and determine, based on processing the asr output, whether a user intended the assistant command to be performed. additional or alternative implementations can process the stream of audio data using a speaker identification (sid) model to determine whether the audio data is sufficient to identify the user that provided a spoken utterance captured in the stream of audio data, and determine if that user is authorized to cause performance of the assistant command.
Inventor(s): Arvind Neelakantan of Mountain View CA (US) for google llc, Daniel Duckworth of Salinas CA (US) for google llc, Ben Goodrich of Mountain View CA (US) for google llc, Vishaal Prasad of Mountain View CA (US) for google llc, Chinnadhurai Sankar of Montreal (CA) for google llc, Semih Yavuz of Santa Barbara CA (US) for google llc
IPC Code(s): G10L15/22, G06N5/04
CPC Code(s): G10L15/22
Abstract: training and/or utilizing a single neural network model to generate, at each of a plurality of assistant turns of a dialog session between a user and an automated assistant, a corresponding automated assistant natural language response and/or a corresponding automated assistant action. for example, at a given assistant turn of a dialog session, both a corresponding natural language response and a corresponding action can be generated jointly and based directly on output generated using the single neural network model. the corresponding response and/or corresponding action can be generated based on processing, using the neural network model, dialog history and a plurality of discrete resources. for example, the neural network model can be used to generate a response and/or action on a token-by-token basis.
Inventor(s): Tuan Nguyen of San Jose CA (US) for google llc, Gabriel Leblanc of Sunnyvale CA (US) for google llc, Qiong Huang of San Jose CA (US) for google llc, Alexey Galata of San Jose CA (US) for google llc, Tzu-Chan Chuang of San Francisco CA (US) for google llc, William A. Truong of San Jose CA (US) for google llc, Yixing Cai of San Jose CA (US) for google llc, Yuan Yuan of Redwood City CA (US) for google llc
IPC Code(s): G10L15/22, G06F3/01, G06F3/16, G06V40/10, G10L15/08, G10L15/24, G10L17/22, G10L25/78
CPC Code(s): G10L15/22
Abstract: hot word free adaptation, of function(s) of an automated assistant, responsive to determining, based on gaze measure(s) and/or active speech measure(s), that a user is engaging with the automated assistant. implementations relate to techniques for mitigating false positive occurrences of and/or false negative occurrences, of hot word free adaptation, through utilization of a permissive parameter set in some situation(s) and a restrictive parameter set in other situation(s). for example, utilizing the restrictive parameter set when it is determined that a user is engaged in conversation with additional user(s). the permissive parameter set includes permissive parameter(s) that are more permissive than counterpart(s) in the restrictive parameter set. a parameter set is utilized in determining whether condition(s) are satisfied, where those condition(s), if satisfied, indicate that the user is engaging in hot word free interaction with the automated assistant and result in adaptation of function(s) of the automated assistant
Inventor(s): Madhusudan K. Iyengar of Foster City CA (US) for google llc, Christopher Malone of Mountain View CA (US) for google llc, Woon-Seong Kwon of Santa Clara CA (US) for google llc, Emad Samadiani of Cupertino CA (US) for google llc, Melanie Beauchemin of Mountain View CA (US) for google llc, Padam Jain of San Jose CA (US) for google llc, Teckgyu Kang of Saratoga CA (US) for google llc, Yuan Li of Sunnyvale CA (US) for google llc, Connor Burgess of Alameda CA (US) for google llc, Norman Paul Jouppi of Palo Alto CA (US) for google llc, Nicholas Stevens-Yu of Palo Alto CA (US) for google llc, Yingying Wang of Sunnyvale CA (US) for google llc
IPC Code(s): H01L23/373, H01L23/00, H01L25/065, H05K3/34, H05K7/20
CPC Code(s): H01L23/3732
Abstract: a method of manufacturing a chip assembly comprises joining an in-process unit to a printed circuit board; reflowing a bonding material disposed between and electrically connecting the in-process unit with the printed circuit board, the bonding material having a first reflow temperature; and then joining a heat distribution device to the plurality of semiconductor chips using a thermal interface material (“tim”) having a second reflow temperature that is lower than the first reflow temperature. the in-process unit further comprises a substrate having an active surface, a passive surface, and contacts exposed at the active surface; an interposer electrically connected to the substrate; a plurality of semiconductor chips overlying the substrate and electrically connected to the substrate through the interposer, and a stiffener overlying the substrate and having an aperture extending therethrough, the plurality of semiconductor chips being positioned within the aperture.
20240347970. AUTO DETACHING CONNECTOR FOR ELECTRONIC DEVICES_simplified_abstract_(google llc)
Inventor(s): Chia-Hang Yeh of Campbell CA (US) for google llc, Hsing-Sheng Lin of Mountain View CA (US) for google llc
IPC Code(s): H01R13/633, H01M50/202, H01M50/24, H01M50/284, H01M50/519, H01M50/574
CPC Code(s): H01R13/633
Abstract: a connector includes a housing and a multi-layer peripheral structure disposed on the housing. the multi-layer peripheral structure is configured to enclose one or more pins and to expand in response to exposure to a liquid for disconnecting the connector from an electronic component without user intervention. the multi-layer peripheral structure may include an outer layer that may include a permeable material, a middle layer disposed within the outer layer, where the middle layer may include a material that expands when wet, and an inner layer disposed within the middle layer.
Inventor(s): Mahesh Keralapura Manjunatha of Mountain View CA (US) for google llc, Chiu Wah So of Mountain View CA (US) for google llc
IPC Code(s): H04L9/40, G06F16/23, G06F18/20, G06F21/44, G06F21/62
CPC Code(s): H04L63/0876
Abstract: at least one aspect of the present disclosure is directed to systems and methods of secure and privacy preserving device classification. a server can maintain a plurality of data records, each including an indication of a request and a known classification value. the server can train a context obfuscation model using each of the plurality of requests and known classification values. the server can train a classification model using resources and category information from a data structure in the memory of the client device. the server can transmit the context obfuscation model to a different plurality of client devices. the server can receive a request for classification including a classification vector and request metadata. the server can determine the classification of the device responsible for the request using the classification model. the server can transmit the device classification to the device responsible for the request.
Inventor(s): Matthew Berninger of Denver CO (US) for google llc, Barry Vengerik of Montclair NJ (US) for google llc
IPC Code(s): H04L9/40, G06F18/213, G06N20/00
CPC Code(s): H04L63/1416
Abstract: a computerized method for associating cyberthreat actor groups responsible for different cyberthreats is described. the method involves generating a similarity matrix based on content from received clusters of cybersecurity information. each received cluster of cybersecurity information is assumed to be associated with a cyberthreat. the similarity matrix is composed via an optimized equation combining separate similarity metrics, where each similarity metric of the plurality of similarity metrics represents a level of correlation between at least two clusters of cybersecurity information, with respect to a particular aspect of operations described in the clusters. the method further involves that, in response to queries directed to the similarity matrix, generating a listing of a subset of the clusters of cybersecurity information having a greater likelihood of being associated with cyberthreats caused by the same cyberthreat actor group.
Inventor(s): Moses Daniel Schwartz of Clayton CA (US) for google llc, Kira Ann Quan of Longmont CO (US) for google llc, Joshua Atkins of South Lake Tahoe CA (US) for google llc, Ricardo Correa of Austin TX (US) for google llc, Nathaniel Benjamin Shar of Longmont CO (US) for google llc, Sara Ann Zukowski of Longmont CO (US) for google llc, Thomas Charles Henry Lyttelton of San Francisco CA (US) for google llc, Barbara Davilla of Austin TX (US) for google llc, Vidya Gopalakrishnan of Santa Clara CA (US) for google llc, Prerit Pathak of Mountain View CA (US) for google llc, Benjamin Henry Walter of Austin TX (US) for google llc
IPC Code(s): H04L9/40
CPC Code(s): H04L63/20
Abstract: a plurality of data sets characterizing prior intrusive activities with respect to computing resources associated with one or more entities are received at a security platform. one or more rule generation policies each pertaining to at least one type of intrusive activity are received at a security platform. the one or more rule generation policies are applied to the plurality of data sets characterizing the prior intrusive activities to generate a plurality of intrusive activity detection rules. the plurality of intrusive activity detection rules are caused to be used to detect subsequent intrusive activities.
20240348875. TRANSITIONING OF CONTENT_simplified_abstract_(google llc)
Inventor(s): Robert Benea of San Jose CA (US) for google llc, Andrej Cedilnik of Oakland CA (US) for google llc
IPC Code(s): H04N21/442, G06V40/16, H04H60/33, H04H60/40, H04H60/45, H04N21/4223, H04N21/44, H04N21/4415, H04N21/45, H04N21/458, H04N21/6587, H04N21/845
CPC Code(s): H04N21/44218
Abstract: arrangements for transitioning content are presented herein. a first signal, associated with a media playback device, can be received that includes first user identification information. a first user can be identified based on the first signal. media content can be caused to be presented on the media playback device based on the identification of the first user. a second signal can be received that associated with the media playback device. a determination can be made that the first user has transitioned away from the media playback device based on the second signal. the media content may then no longer be presented by the media playback device in response to determining that the first user has transitioned away from the media playback device.
20240348930. Exposure Control for Image-Capture_simplified_abstract_(google llc)
Inventor(s): Yichang Shih of Cupertino CA (US) for google llc, Jinglun Gao of San Mateo CA (US) for google llc, Ruben Manuel Velarde of Chula Vista CA (US) for google llc, Szepo Robert Hung of Austin TX (US) for google llc
IPC Code(s): H04N23/73, H04N23/63, H04N23/71, H04N23/72, H04N23/745, H04N23/90
CPC Code(s): H04N23/73
Abstract: this document describes techniques and apparatuses for exposure control for image-capture. the techniques and apparatuses utilize sensor data to analyze a scene and, based on this analysis, determine a likelihood of exposure-related defects in captured images of the scene. based on this likelihood, the techniques determine multiple different exposure times for multiple image-capture devices. an image-merging module then combines these different images captured with different exposure times to create a single image with reduced exposure-related defects.
Inventor(s): Guohua Sun of Santa Clara CA (US) for google llc, Jae Lee of Palo Alto CA (US) for google llc
IPC Code(s): H04R1/10, G10K11/178
CPC Code(s): H04R1/1083
Abstract: a wearable device includes a feedforward microphone; a feedback microphone; a voice accelerometer; and one or more processors in communication with the feedforward microphone, the feedback microphone, and the voice accelerometer. the one or more processors may be configured to receive an occlusion effect (“oe”) profile associated with increased sound pressure level within an ear canal; determine an oe gain profile based on the oe profile; receive voice accelerometer data; adjust the oe gain profile based on the voice accelerometer data; generate an oe cancellation signal based on the oe gain profile to equalize the oe profile; receive, from the feedforward microphone, first audio content including external audio; receive, from the feedback microphone, second audio content including audio within the ear canal of a user; and adjust, based on the oe cancellation signal and the received first and second audio content, an audio output.
Inventor(s): Chih-Hsiang Wu of Taoyuan City (TW) for google llc
IPC Code(s): H04W72/543, H04W72/11, H04W72/30
CPC Code(s): H04W72/543
Abstract: methods for managing packet transmissions, which may be implemented in a node of a radio access network, are provided. one such method includes receiving, from an upstream node, a packet via a downlink tunnel, selecting, based on one or more properties of the downlink tunnel, a semi-persistent scheduling radio resource for transmitting the packet to one or more ues, and transmitting the packet via a radio interface to the one or more ues using the semi-persistent scheduling radio resource. another method includes receiving, from an upstream node, a packet associated with a quality-of-service (qos) flow, selecting, based on the qos flow, a semi-persistent scheduling radio resource for transmitting the packet to one or more ues, and transmitting the packet via a radio interface to the one or more ues using the semi-persistent scheduling radio resource.
- GOOGLE LLC
- C12Q1/6806
- C12Q1/6869
- CPC C12Q1/6806
- Google llc
- G01C21/34
- G01C21/36
- G06N5/04
- G06N20/00
- H04L51/046
- CPC G01C21/3438
- G01S7/295
- G01S13/53
- G01S13/88
- G06F3/01
- CPC G01S7/2955
- G06F16/332
- CPC G06F16/3322
- G06F16/957
- G06F16/958
- CPC G06F16/9577
- G06F21/62
- G06F21/60
- H04L9/40
- H04L51/212
- H04L51/224
- H04L51/52
- CPC G06F21/6263
- G06N3/0455
- CPC G06N3/0455
- G06N3/063
- G06F18/214
- G06N3/04
- G06N3/045
- G06N3/08
- G06T1/20
- G06V10/44
- CPC G06N3/063
- G06F16/9535
- G06N3/084
- CPC G06N3/08
- G06N10/70
- CPC G06N10/70
- G06F15/80
- G06N10/00
- G06N10/20
- G06N10/80
- CPC G06N10/80
- CPC G06N20/00
- G06Q30/0242
- G06Q30/0251
- CPC G06Q30/0242
- CPC G06Q30/0244
- G06T5/77
- G06T5/60
- G06T7/11
- G06T7/136
- G06T7/194
- CPC G06T5/77
- G06V10/22
- G06V10/10
- G06V10/24
- G06V10/776
- G06V10/98
- H04N5/265
- H04N23/60
- H04N23/61
- H04N23/63
- H04N23/661
- H04N23/698
- CPC G06V10/235
- G06V20/40
- G06F18/21
- G06F18/23
- G06T11/60
- G06V20/30
- G06V40/16
- CPC G06V20/44
- G06T7/73
- G06V10/62
- G06V10/764
- G06V10/77
- G06V10/774
- G06V10/82
- CPC G06V20/46
- G06V20/52
- G01C21/00
- G06V20/17
- CPC G06V20/53
- G06V20/58
- G06T7/70
- G06V10/25
- G06V10/74
- CPC G06V20/586
- G06V30/19
- CPC G06V30/19093
- G06V40/50
- G06V40/70
- G10L17/00
- G10L17/04
- CPC G06V40/50
- G09G3/32
- CPC G09G3/32
- G09G5/10
- G09G5/00
- CPC G09G5/10
- G10L15/06
- CPC G10L15/063
- G10L15/16
- G10L15/08
- G10L15/28
- H04R3/00
- CPC G10L15/16
- G10L15/22
- G10L15/05
- G10L15/18
- G10L25/78
- CPC G10L15/22
- G06F3/16
- G06V40/10
- G10L15/24
- G10L17/22
- H01L23/373
- H01L23/00
- H01L25/065
- H05K3/34
- H05K7/20
- CPC H01L23/3732
- H01R13/633
- H01M50/202
- H01M50/24
- H01M50/284
- H01M50/519
- H01M50/574
- CPC H01R13/633
- G06F16/23
- G06F18/20
- G06F21/44
- CPC H04L63/0876
- G06F18/213
- CPC H04L63/1416
- CPC H04L63/20
- H04N21/442
- H04H60/33
- H04H60/40
- H04H60/45
- H04N21/4223
- H04N21/44
- H04N21/4415
- H04N21/45
- H04N21/458
- H04N21/6587
- H04N21/845
- CPC H04N21/44218
- H04N23/73
- H04N23/71
- H04N23/72
- H04N23/745
- H04N23/90
- CPC H04N23/73
- H04R1/10
- G10K11/178
- CPC H04R1/1083
- H04W72/543
- H04W72/11
- H04W72/30
- CPC H04W72/543
