GOOGLE LLC patent applications on April 4th, 2024
Patent Applications by GOOGLE LLC on April 4th, 2024
GOOGLE LLC: 39 patent applications
GOOGLE LLC has applied for patents in the areas of G06N20/00 (8), G10L15/22 (6), G06N3/08 (5), G16H50/20 (4), G10L15/30 (4)
With keywords such as: user, device, data, based, navigation, text, location, determining, network, and application in patent application abstracts.
Patent Applications by GOOGLE LLC
20240110793.PRIVATE DIRECTIONS AND NAVIGATION_simplified_abstract_(google llc)
Inventor(s): Matthew Sharifi of () for google llc
IPC Code(s): G01C21/34
Abstract: techniques for preserving privacy during turn by turn navigation sessions are provided. an example method includes receiving an indication of a precise origin location and a precise destination location via a navigation application operating on a mobile computing device. the navigation application may generate an indication of a coarse origin region including the precise origin location, and an indication of a coarse destination region including the precise destination location, and transmit the indications of the coarse origin and destination regions to an external navigation server. the navigation application may receive, from the external navigation server, a coarse navigation route from the coarse origin region to the coarse destination region, as well as navigation data associated with the coarse origin and destination regions, based on which the navigation application may generate the private navigation route for the user. the private navigation route may then be provided to the user.
Inventor(s): Bruce Bahnsen of () for google llc, Yan Mayster of () for google llc
IPC Code(s): G01C21/34, G01C21/36, G06N20/00
Abstract: a computing device may implement a method for providing an experience-focused navigation session. the method includes obtaining user data corresponding to a user of the computing device and a current location of the user. the method further includes determining a semantic mapping corresponding to the user based on one or more user preferences and a location history included in the user data, and determining a suggested experience-focused navigation session for the user based on the semantic mapping and the current location of the user. the suggested experience-focused navigation session includes an ordered list of one or more suggested points of interest. the method further includes automatically providing the suggested experience-focused navigation session to the user as an appointment on the computing device.
Inventor(s): Matthew Sharifi of () for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G06F1/3212, G01C21/36
Abstract: techniques for saving mobile device power during turn by turn navigation sessions are provided. an example method includes receiving an indication of an origin location and a destination location via a navigation application operating on a mobile computing device; generating a navigation route based on the origin location and the destination location using the navigation application, including indications of one or more maneuvers required to be performed by a user; comparing a remaining battery power level associated with the mobile computing device to a predicted processing power required for the navigation application to perform one or more functions related to the navigation route; and causing the navigation application to operate in a power-saving mode based on the comparison. operating the navigation application in the power-saving mode may include temporarily suspending at least one of the one or more functions of related to the navigation route.
Inventor(s): Maxim Tabachnyk of Munich (DE) for google llc, Yurun Shen of Mountain View CA (US) for google llc, Stoyan Stefanov Nikolov of Planegg (DE) for google llc, Stanislav Pyatykh of Unterhaching (DE) for google llc, Ksenia Korovina of Mountain View CA (US) for google llc, Evgeny Gryaznov of Mountain View CA (US) for google llc, Erik Grabljevec of Mountain View CA (US) for google llc
IPC Code(s): G06F8/33
Abstract: a method for providing autofill suggestions in a development environment includes obtaining, from a user interface executing on a user device, a user input representing source code generated within a development environment. the source code is created using a particular programming language and a programming code base. the method further includes determining, using a machine learning model, at least one autofill suggestion based on the user input, the autofill suggestion continuing the source code represented by the user input. the method further includes determining, using a rule-based semantic checker configured for the particular programming language, whether the autofill suggestion is semantically correct based on the development environment and the programming code base. the method also includes, when the autofill suggestion is semantically correct, transmitting the autofill suggestion for display on the user interface of the user device.
Inventor(s): Michael Jeffrey Procopio of Boulder CO (US) for google llc, Sarmad Hashmi of San Jose CA (US) for google llc, Rachel Goodman Moore of Kirkland WA (US) for google llc, Nicholas Eric Westbury of Seattle WA (US) for google llc, Girimurugan Natarajan of Bangalore (IN) for google llc, Francis Herrera Cortez of San Bruno CA (US) for google llc, Carlin Yuen of New Providence NJ (US) for google llc
IPC Code(s): G06F8/38, G06F3/0482, G06F8/34, H04L51/02
Abstract: a method for generation of chat applications includes receiving a deployment request requesting deployment of a no-code application generated by a user within a no-code environment to a chat application environment. the no-code application includes a trigger condition, an action response defining an action in response to the trigger condition being satisfied, and a no-code environment graphical user interface (gui) view based on the action response. the method includes, after receiving the deployment request, receiving an interaction indication indicating that the trigger condition is satisfied. in response to receiving the interaction indication, the method includes executing the action response, translating the no-code environment gui view into a chat application gui view, and transmitting the chat application gui view to a user device. the chat application gui view is configured to cause the user device to display the chat application gui view within the chat application environment.
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): G06F9/451, G06F16/33, G06F16/332, G06F40/20, G06F40/30
Abstract: methods, apparatus, systems, and computer-readable media are provided for providing context specific schema files that allow an automated assistant to broker human-to-computer dialogs between a user and an application that is separate from the automated assistant. the context specific schema file can provide the automated assistant with sufficient data to be responsive to user queries without necessarily communicating with a remote device, such as a server. multiple different context specific schema files can be made available to the automated assistant according to a context in which a user is interacting with the automated assistant. in this way, latency otherwise exhibited by the automated assistant can be mitigated by providing the automated assistant with the information needed to respond to a user without continually retrieving the information over a network.
Inventor(s): Or Igelka of Tel Mond (IL) for google llc, Leonid Vasetsky of Zikhron Yaakov (IL) for google llc
IPC Code(s): G06F9/455
Abstract: disclosure is made of methods, apparatus and system for migrating virtual machines (vms) between source and destination in a computing environment and, more specifically, to replication based migration. vms migration is controlled so as to manage transferal of data associated with one or more vms from a source location to a destination location to meet certain user definable or system constraints. dynamic control and adjustment of system parameters associated with the migration is also disclosed.
20240111572.DYNAMIC HETEROGENEOUS TASK PROCESSING_simplified_abstract_(google llc)
Inventor(s): Jamie Menjay Lin of San Diego CA (US) for google llc, Chuo-Ling Chang of Mountain View CA (US) for google llc
IPC Code(s): G06F9/48, G06F9/46
Abstract: a method including processing a stream of data in a sequence of tasks. the processing including receiving a first block of data of the stream of data, determining features associated with the first block of data, selecting, based on the features, one of a first a task to process the first block of data or a second task to process the first block of data and if the second task is selected, shift an output of the second task in time to align the output of the second task with a predicted output of the first task processing a second block of data of the stream of data.
20240111667.High Performance Memory Allocator_simplified_abstract_(google llc)
Inventor(s): Abhishek Agarwal of Santa Clara CA (US) for google llc, Srinivas Vaduvatha of San Jose CA (US) for google llc, Weiwei Jiang of Santa Clara CA (US) for google llc, Hugh McEvoy Walsh of Los Gatos CA (US) for google llc, Weihuang Wang of Los Gatos CA (US) for google llc, Jiazhen Zheng of Santa Clara CA (US) for google llc, Ajay Venkatesan of Milpitas CA (US) for google llc
IPC Code(s): G06F12/02
Abstract: aspects of the disclosure are directed to a memory allocator for assigning contiguous memory space for data packets in on-chip memory of a network interface card. the memory allocator includes a plurality of sub-allocators that correspond to a structure of entries, where each entry represents a quanta of memory allocation. the sub-allocators are organized in decreasing size in the memory allocator based on the amount of memory quanta they can allocate.
Inventor(s): Bernhard Seefeld of San Francisco CA (US) for google llc, Neal Kanodia of Mountain View CA (US) for google llc, Elizabeth M. Windram of San Francisco CA (US) for google llc
IPC Code(s): G06F16/44, G06F16/242, G06F16/248, G06F16/29, G06F16/9537
Abstract: displaying geographic search results incudes receiving, from a server system and in response to a query related to the geographic area, a plurality of search results; providing a digital map of the geographic area via a user interface; displaying the plurality of search results as visual indicators at respective geographic locations on the digital map; and providing a user interface element which, when selected by a user, causes removal from the digital map a portion of the plurality of search results that is not relevant to a certain geographic context.
20240111805.Predictively Presenting Search Capabilities_simplified_abstract_(google llc)
Inventor(s): Thomas Jenkins of London (GB) for google llc
IPC Code(s): G06F16/58, G06F3/0484, G06F16/2457, G06F16/25, G06F16/29, G06F16/9537, G06F21/62, G06N5/022, H04W4/02
Abstract: example techniques and systems may obtain one or more search types associated with a geographic location of a computing device. in one example, a technique may include determining, by a mobile computing device, a geographic location of the mobile computing device and obtaining one or more search types associated with the geographic location. responsive to obtaining the one or more search types, the technique may also include outputting, by the mobile computing device and for display, a graphical user interface comprising at least an indication of the one or more search types associated with the geographic location.
Inventor(s): Dongeek Shin of San Jose CA (US) for google llc
IPC Code(s): G06F16/9032, G06F16/9038, G06F40/30
Abstract: implementations relate to selecting a particular device, from an ecosystem of devices, to provide responses to a device-agnostic request of the user while a scenario is occurring. the user specifies a scenario and contextual features are identified from one or more devices of the ecosystem to generate scenario features indicative of the scenario occurring. the scenario features are stored with a correlation to a device that is specified by the user to handle responses while the scenario is occurring. when a subsequent device-agnostic request is received, current contextual features are identified and compared to the scenario features. based on the comparison, the specified assistant device is selected to respond to the device-agnostic request.
20240111819.Crawl Algorithm_simplified_abstract_(google llc)
Inventor(s): Linhai Qiu of Palo Alto CA (US) for google llc, Robert Istvan Busa-Fekete of Chatham NJ (US) for google llc, Julian Ulf Zimmert of Berlin (DE) for google llc, Andras Gyorgy of () for google llc, Hao Shen of Mountain View CA (US) for google llc, Hyomin Choi of Mountain View CA (US) for google llc, Sharmila Vijay of Mountain View CA (US) for google llc, Xiao Li of San Francisco CA (US) for google llc
IPC Code(s): G06F16/951
Abstract: a method for a crawl algorithm includes obtaining a plurality of web pages for a web crawler to crawl. the method also includes determining an available bandwidth for the web crawler. the method includes, for each respective web page of the plurality of web pages, determining a respective crawl value for the respective web page based on the available bandwidth and determining that the respective crawl value of the respective web page satisfies a threshold value. the method includes, in response to determining that the respective crawl value of the respective web page satisfies the threshold value, updating the respective web page in a cache memory.
20240111884.Authenticating a File System Within Untrusted Storage_simplified_abstract_(google llc)
Inventor(s): Yu-Ting Hsieh of Sunnyvale CA (US) for google llc
IPC Code(s): G06F21/62, G06F21/60
Abstract: this document includes techniques, apparatuses, and systems for authenticating a file system () within untrusted storage (). in particular, a file-system authenticator () generates a file-system root hash () corresponding to the file system () during a write operation. the file-system root hash () is uniquely determined based on contents of files within the file system () and a structure of the file system (). the file-system root hash () can be readily updated, which enables the file system to support a dynamically-changing file system (). also, the size of the file-system root hash () is independent of the size of the file system () within the untrusted storage (). as such, the size of trusted storage () used to store the file-system root hash () can be predetermined and fixed regardless of the size of the file system ().
20240111895.VERIFIABLE CONSENT FOR PRIVACY PROTECTION_simplified_abstract_(google llc)
Inventor(s): Gang Wang of Jersey City NJ (US) for google llc, Marcel M. Moti Yung of New York NY (US) for google llc
IPC Code(s): G06F21/62, H04L9/30, H04L9/32
Abstract: methods, systems, and apparatus, including a method for updating user consent in a verifiable manner. in some aspects, a method includes receiving, from a client device, a request including an attestation token. the attestation token includes a set of data that includes at least a user identifier that uniquely identifies a user of the client device, a token creation time that indicates a time at which the attestation token was created, user consent data specifying whether one or more entities that receive the attestation token are eligible to use data of the user, an action to be performed in response to the request. the attestation token also includes a digital signature of at least a portion of the set of data, including at least the user identifier and the token creation time. an integrity of the request is verified using the attestation token.
Inventor(s): Itay Laish of Timrat (IL) for google llc, Amir Reuven Feder of New York NY (US) for google llc, Fan Zhang of Cupertino CA (US) for google llc, Ayelet Benjamini of Kfar Saba (IL) for google llc
IPC Code(s): G06N3/0455, G06N3/048
Abstract: a multi-task neural network system is described. the system includes a shared neural network configured to receive as input a text span from a clinical note, and for each of one or more text segments in the text span, processing the text segment to generate a set of text segment embeddings. the system further includes a segmentation neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to determine whether the text segment is a section title or not. the system further includes a section type classification neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to classify the text segment into a section type of a plurality of section types.
Inventor(s): Hanjun Dai of San Jose CA (US) for google llc, Bo Dai of San Jose CA (US) for google llc, Mengjiao Yang of Berkeley CA (US) for google llc, Yuan Xue of Palo Alto CA (US) for google llc, Dale Eric Schuurmans of Edmonton (CA) for google llc
IPC Code(s): G06N3/08, G06N3/04
Abstract: the present disclosure is directed to generative models for datasets constrained by marginal constraints. one method includes receiving a request to generate a target dataset based on a marginal constraint for a source dataset. a first object occurs at a source frequency in the source dataset. the marginal constraint indicates a target frequency for the first object. the source dataset encodes a set of co-occurrence frequencies for a plurality of object pairs. a source generative model is accessed. the source generative model includes a first module and a second module that are trained on the source dataset. the second module is updated based on the marginal constraint. an adapted generative model is generated that includes the first module and the updated second module. the target dataset is generated based on the adapted generative model. the first object occurs at the target frequency in the target dataset. the target dataset encodes the set of co-occurrence frequencies for the plurality of object pairs.
Inventor(s): Yanqi Zhou of Sunnyvale CA (US) for google llc, Yanping Huang of Mountain View CA (US) for google llc, Yifeng Lu of Palo Alto CA (US) for google llc, Andrew M. Dai of San Francisco CA (US) for google llc, Siamak Shakeri of New York NY (US) for google llc, Zhifeng Chen of Sunnyvale CA (US) for google llc, James Laudon of Madison WI (US) for google llc, Quoc V. Le of Sunnyvale CA (US) for google llc, Da Huang of Santa Clara CA (US) for google llc, Nan Du of San Jose CA (US) for google llc, David Richard So of Brooklyn NY (US) for google llc, Daiyi Peng of Cupertino CA (US) for google llc, Yingwei Cui of Los Altos CA (US) for google llc, Jeffrey Adgate Dean of Palo Alto CA (US) for google llc, Chang Lan of Kirkland WA (US) for google llc
IPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. in one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural networks for performing the machine learning task, wherein each candidate neural network comprises a plurality of instances of a layer block composed of a plurality of layers, for each candidate neural network, selecting a respective type for each of the plurality of layers from a set of layer types that comprises, training the candidate neural network and evaluating performance scores for the trained candidate neural networks as applied to the machine learning task, and determining a final neural network for performing the machine learning task based at least on the performance scores for the candidate neural networks.
20240112059.RAPID MULTI-LEVEL QUBIT RESET_simplified_abstract_(google llc)
Inventor(s): Kevin Chenghao Miao of Goleta CA (US) for google llc, Alexander Korolkov of Riverside CA (US) for google llc, Mathew James McEwen of Santa Barabara CA (US) for google llc, Rami Barends of San Diego CA (US) for google llc
IPC Code(s): G06N10/70, G06N10/40
Abstract: methods, systems and apparatus for resetting a qubit. in one aspect, an apparatus includes a qubit, wherein the state of the qubit occupies a plurality of levels comprising two computational levels and one or more non-computational levels; a resonator that operates at a resonator frequency; control electronics that control a frequency of the qubit such that during a reset operation the qubit frequency is adjusted from a holding frequency that is lower than the resonator frequency to an idling frequency that is higher than the resonator frequency, and during the adjustment a first derivative of the qubit frequency at a first time is positive, at a second time that occurs after the first time is zero, and at a third time that occurs after the second time is positive, where the qubit frequency achieves the idling frequency at a fourth time that occurs after the third time.
20240112084.Scalable Feature Selection Via Sparse Learnable Masks_simplified_abstract_(google llc)
Inventor(s): Sercan Omer Arik of San Francisco CA (US) for google llc, Yihe Dong of New York NY (US) for google llc
IPC Code(s): G06N20/00
Abstract: aspects of the disclosure are directed to a canonical approach for feature selection referred to as sparse learnable masks (slm). slm integrates learnable sparse masks into end-to-end training. for the fundamental non-differentiability challenge of selecting a desired number of features, slm includes dual mechanisms for automatic mask scaling by achieving a desired feature sparsity and gradually tempering this sparsity for effective learning. slm further employs an objective that increases mutual information (mi) between selected features and labels in an efficient and scalable manner. empirically, slm can achieve or improve upon state-of-the-art results on several benchmark datasets, often by a significant margin, while reducing computational complexity and cost.
20240112088.Vector-Quantized Image Modeling_simplified_abstract_(google llc)
Inventor(s): Jiahui Yu of Jersey City NJ (US) for google llc, Xin Li of Santa Clara CA (US) for google llc, Han Zhang of Sunnyvale CA (US) for google llc, Vijay Vasudevan of Los Altos Hills CA (US) for google llc, Alexander Yeong-Shiuh Ku of Brooklyn NY (US) for google llc, Jason Michael Baldridge of Austin TX (US) for google llc, Yuanzhong Xu of Mountain View CA (US) for google llc, Jing Yu Koh of Austin TX (US) for google llc, Thang Minh Luong of Santa Clara CA (US) for google llc, Gunjan Baid of San Francisco CA (US) for google llc, Zirui Wang of San Francisco CA (US) for google llc, Yonghui Wu of Palo Alto CA (US) for google llc
IPC Code(s): G06N20/00
Abstract: systems and methods are provided for vector-quantized image modeling using vision transformers and improved codebook handling. in particular, the present disclosure provides a vector-quantized image modeling (vim) approach that involves pretraining a machine learning model (e.g., transformer model) to predict rasterized image tokens autoregressively. the discrete image tokens can be encoded from a learned vision-transformer-based vqgan (example implementations of which can be referred to as vit-vqgan). the present disclosure proposes multiple improvements over vanilla vqgan from architecture to codebook learning, yielding better efficiency and reconstruction fidelity. the improved vit-vqgan further improves vector-quantized image modeling tasks, including unconditional image generation, conditioned image generation (e.g., class-conditioned image generation), and unsupervised representation learning.
Inventor(s): Alok Anilkumar Sheth of Rutherford NJ (US) for google llc, Enoch Chee-Lok Lau of Brooklyn NY (US) for google llc, Brett Alexander Benowitz of Allendale NJ (US) for google llc, Dharma Muppalla of Sunnyvale CA (US) for google llc, Noah Ronald Freeman of Boston MA (US) for google llc, Eric Lo of New York NY (US) for google llc
IPC Code(s): G06Q30/02, G06F40/247
Abstract: the technology generally relates to automatically associating products and services to be advertised in response to a search query and providing sponsored advertisements for output with the search query results on a publisher's website or mobile application. an ad advertiser may create an ad campaign for products without including or identifying keywords associated with the product. upon receiving a request for an advertisement, an ad server may generate synonyms, or keywords, for the terms in the request. the ad server generated keywords may be used to identify available products that match, or are relevant to, the search query. the ad server may determine a quality of the match and, based on the quality, determine which products are most relevant to the search query. the ad server may solicit bids from the advertisers of the relevant ad campaigns. the winning ads may be returned to the publisher for output.
Inventor(s): Jonathan Blair Phillips of San Jose CA (US) for google llc
IPC Code(s): G06T5/70, G06F3/01
Abstract: this document describes techniques and devices for motion-induced blurring to reduce an appearance of a boundary separating regions of a display. sensors (e.g., cameras, microphones, biometric sensors, ambient light sensors, radar sensors, and so forth) may be placed at least partially underneath regions of a display. placing a sensor underneath a region of a display, however, often requires reduced pixel-density (e.g., relatively low resolution), which can cause scintillations of the content as it moves on the display. the techniques described herein address some undesirable effects of this reduced pixel-density by blurring content moving within regions of low resolution. furthermore, the techniques can adjust an amount of blurring based on a speed of the moving content. thus, when the display includes regions of differing resolutions, the techniques described herein can blur the moving content to reduce the appearance of a boundary separating these regions of differing resolutions.
20240112559.PRIVACY-PRESERVING RADAR-BASED FALL MONITORING_simplified_abstract_(google llc)
Inventor(s): Dongeek Shin of San Jose CA (US) for google llc, Shwetak Patel of Seattle WA (US) for google llc, Rizwan Chaudhry of Millbrae CA (US) for google llc, Chetan Bhole of Mountain View CA (US) for google llc, Vaibhav Darbari of New York NY (US) for google llc, Todd Whitehurst of Belmont CA (US) for google llc, Anupam Pathak of San Carlos CA (US) for google llc
IPC Code(s): G08B21/04, G01S13/32, G01S13/58
Abstract: various arrangements for performing fall detection are presented. a smart-home device may transmit radar waves. based on reflected radar waves, raw waveform data may be created. the raw waveform data may be processed to determine that a fall by a person has occurred. speech may then be output announcing that the fall has been detected via the speaker of the smart home device.
Inventor(s): Ye Jia of Mountain View CA (US) for google llc, Zhifeng Chen of Mountain View CA (US) for google llc, Yonghui Wu of Fremont CA (US) for google llc, Jonathan Shen of Mountain View CA (US) for google llc, Ruoming Pang of Mountain View CA (US) for google llc, Ron J. Weiss of New York NY (US) for google llc, Ignacio Lopez Moreno of Brooklyn NY (US) for google llc, Fei Ren of Mountain View CA (US) for google llc, Yu Zhang of Mountain View CA (US) for google llc, Quan Wang of Hoboken NJ (US) for google llc, Patrick An Phu Nguyen of Palo Alto CA (US) for google llc
IPC Code(s): G10L13/04, G10L17/04, G10L19/00
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech synthesis. the methods, systems, and apparatus include actions of obtaining an audio representation of speech of a target speaker, obtaining input text for which speech is to be synthesized in a voice of the target speaker, generating a speaker vector by providing the audio representation to a speaker encoder engine that is trained to distinguish speakers from one another, generating an audio representation of the input text spoken in the voice of the target speaker by providing the input text and the speaker vector to a spectrogram generation engine that is trained using voices of reference speakers to generate audio representations, and providing the audio representation of the input text spoken in the voice of the target speaker for output.
Inventor(s): Rajiv Mathews of Sunnyvale CA (US) for google llc, Dragan Zivkovic of Sunnyvale CA (US) for google llc, Khe Chai Sim of Dublin CA (US) for google llc
IPC Code(s): G10L15/19, G10L15/06, G10L15/22, G10L15/30
Abstract: on-device processor(s) of a client device may store, in on-device storage and in association with a time to live (ttl) in the on-device storage, a correction directed to asr processing of audio data. the correction may include a portion of a given speech hypothesis that was modified to an alternate speech hypothesis. further, the on-device processor(s) may cause an on-device asr model to be personalized based on the correction. moreover, and based on additional asr processing of additional audio data, the on-device processor(s) may store, in the on-device storage and in association with an additional ttl in the on-device storage, a pseudo-correction directed to the additional asr processing. accordingly, the on-device processor(s) may cause the on-device asr model to be personalized based on the pseudo-correction to prevent forgetting by the on-device asr model.
Inventor(s): Rajiv Mathews of Sunnyvale CA (US) for google llc, Rohit Prabhavalkar of Santa Clara CA (US) for google llc, Giovanni Motta of San Jose CA (US) for google llc, Mingqing Chen of Saratoga CA (US) for google llc, Lillian Zhou of Mountain View CA (US) for google llc, Dhruv Guliani of San Francisco CA (US) for google llc, Harry Zhang of Sunnyvale CA (US) for google llc, Trevor Strohman of Sunnyvale CA (US) for google llc, Françoise Beaufays of Mountain View CA (US) for google llc
IPC Code(s): G10L15/197, G10L15/06, G10L15/22, G10L15/30
Abstract: implementations described herein identify and correct automatic speech recognition (asr) misrecognitions. for example, on-device processor(s) of a client device may generate a predicted textual segment that is predicted to correspond to spoken utterance of a user of the client device, and may receive further input that modifies the predicted textual segment to an alternate textual segment. further, the on-device processor(s) may store these textual segments in on-device storage as a candidate correction pair, and transmit the candidate correction pair to a remote system. moreover, remote processor(s) of the remote system may determine that the candidate correction pair is an actual correction pair, and may cause client devices to generate updates for a global asr model for the candidate correction pair. additionally, the remote processor(s) may distribute the global asr model to the client devices and/or additional client devices.
Inventor(s): Ibrahim Badr of Zurich (CH) for google llc, Zaheed Sabur of Baar (CH) for google llc, Vladimir Vuskovic of Zollikerberg (CH) for google llc, Adrian Zumbrunnen of Zurich (CH) for google llc, Lucas Mirelmann of Zurich (CH) for google llc
IPC Code(s): G10L15/22, G06F16/903, G06N3/006, G10L15/18
Abstract: methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. in various implementations, in an existing human-to-computer dialog session between a user and an automated assistant, it may be determined that the automated assistant has responded to all natural language input received from the user. based on characteristic(s) of the user, information of potential interest to the user or action(s) of potential interest to the user may be identified. unsolicited content indicative of the information of potential interest to the user or the action(s) may be generated and incorporated by the automated assistant into the existing human-to-computer dialog session. in various implementations, the incorporating may be performed in response to the determining that the automated assistant has responded to all natural language input received from the user during the human-to-computer dialog session.
20240112804.MATCHING UNSTRUCTURED TEXT TO CLINICAL ONTOLOGIES_simplified_abstract_(google llc)
Inventor(s): Itay Laish of Timrat (IL) for google llc, Uri N. Lerner of Los Altos CA (US) for google llc, Aviel Atias of Tel Aviv (IL) for google llc, Natan Potikha of Tel Aviv (IL) for google llc, Ayelet Benjamini of Kfar Saba (IL) for google llc
IPC Code(s): G16H50/20, G06F40/166, G06F40/295, G16H10/60, G16H15/00
Abstract: a computer-implemented method for matching unstructured text to ontology entities in a clinical ontology is described. the method includes receiving one or more clinical notes associated with a patient; for each of the one or more clinical notes: extracting, using a neural network, one or more text spans from unstructured text in each clinical note, each of the one or more text spans identifying a respective input phrase in the unstructured text; for each of the one or more text spans, matching, using a text matcher, the text span with a respective output ontology entity from an ontology, the respective output ontology entity relating to a clinical condition of the patient; and outputting data defining the one or more text spans and the respective output ontology entity for each of the one or more text spans.
Inventor(s): Melissa Strader of San Jose CA (US) for google llc, William Ito of Mountain View CA (US) for google llc, Christopher Co of Saratoga CA (US) for google llc, Katherine Chou of Palo Alto CA (US) for google llc, Alvin Rajkomar of San Jose CA (US) for google llc, Rebecca Rolfe of Menlo Park CA (US) for google llc
IPC Code(s): G16H50/20, G06F16/33, G06F40/279, G10L15/00, G10L15/08, G16H10/60, G16H40/63, G16H50/70
Abstract: a computer-implemented method includes receiving, by a computing device, a particular textual description of a scene. the method also includes applying a neural network for text-to-image generation to generate an output image rendition of the scene, the neural network having been trained to cause two image renditions associated with a same textual description to attract each other and two image renditions associated with different textual descriptions to repel each other based on mutual information between a plurality of corresponding pairs, wherein the plurality of corresponding pairs comprise an image-to-image pair and a text-to-image pair. the method further includes predicting the output image rendition of the scene.
20240113893.Protecting Against DKIM Replay_simplified_abstract_(google llc)
Inventor(s): Wei-haw Chuang of Menlo Park CA (US) for google llc
IPC Code(s): H04L9/32, H04L9/08, H04L69/22
Abstract: a method for securing messages includes obtaining, at a first message server, a message for a user of a message service hosted by the first message server, the message including a header including a digital signature signed by an author of the message and a list of one or more recipients of the message. the method includes determining that a domain name system (dns) txt record associated with the message includes a delegation policy indicating that a second message server declared all intended recipients of the message. in response, the method includes determining that the digital signature by the author is valid and that the user is a declared recipient of the message. the method includes, in response to determining that the digital signature by the author is valid and the user is the declared recipient of the message, indicating the message is authentic.
20240113989.AUTOMATED NETWORK CHANGE SYSTEM_simplified_abstract_(google llc)
Inventor(s): Horia Vlad Balan of Mountain View CA (US) for google llc, Zengbin Zhang of Seattle WA (US) for google llc, Amin Vahdat of Los Altos CA (US) for google llc, Vinay Kumar Bannai of Sunnyvale CA (US) for google llc, Alexander Jinhon Lin of San Jose CA (US) for google llc, Anvesh Komuravelli of Santa Clara CA (US) for google llc, Steven Gribble of Mountain View CA (US) for google llc, Andrew DeBock Ferguson of New York NY (US) for google llc, Muhammad Mukarram Tariq of San Jose CA (US) for google llc, Joon Ong of Cupertino CA (US) for google llc, Alvaro Martinez Echevarria of Mountain View CA (US) for google llc
IPC Code(s): H04L49/15, H04L41/082, H04L41/084, H04L45/58, H04L49/25
Abstract: methods, systems, and apparatus, for automatically changing a network system. a method includes receiving a set of first intents that describe a state of a first switch fabric; receiving a set of second intents that describe a state of a second switch fabric; computing a set of network operations to perform on the first switch fabric to achieve the second switch fabric, the set of operations also defining an order in which the operations are to be executed, and the set of operations determined based on the set of first intents, the set of second intents, and migration logic that defines a ruleset for selecting the operations based on the set of first intents and the second intents; and executing the set of network operations according to the order, to apply changes to elements within the first switch fabric to achieve the state of the second switch fabric.
20240114158.Hierarchical Video Encoders_simplified_abstract_(google llc)
Inventor(s): Vihan Jain of San Francisco CA (US) for google llc, Joonseok Lee of Fremont CA (US) for google llc, Ming Zhao of Sunnyvale CA (US) for google llc, Sheide Chammas of San Francisco CA (US) for google llc, Hexiang Hu of Los Angeles CA (US) for google llc, Bowen Zhang of Los Angeles CA (US) for google llc, Fei Sha of Los Angeles CA (US) for google llc, Tze Way Eugene Ie of Los Altos CA (US) for google llc
IPC Code(s): H04N19/30, G06N20/00, H04N19/172
Abstract: a computer-implemented method for generating video representations utilizing a hierarchical video encoder includes obtaining a video, wherein the video includes a plurality of frames, processing each of the plurality of frames with a machine-learned frame-level encoder model to respectively generate a plurality of frame representations for the plurality of frames, the plurality of frame representations respective to the plurality of frames determining a plurality of segment representations representative of a plurality of video segments including one or more of the plurality of frames, the plurality of segment representations based at least in part on the plurality of frame representations, processing the plurality of segment representations with a machine-learned segment-level encoder model to generate a plurality of contextualized segment representations, determining a video representation based at least in part on the plurality of contextualized segment representations, and providing the video representation as an output.
Inventor(s): Julien Goupy of Le Mesnil-Saint-Denis (FR) for google llc, Thomas Girardier of Bourg La Reine (FR) for google llc, Nicolas Guezellot Prudhomme of Paris (FR) for google llc
IPC Code(s): H04R3/12, G10L19/16, G10L19/22, H04W72/30, H04W76/40
Abstract: various arrangements for managing a plurality of multimedia communication links in a point-to-multipoint bluetooth network established between a source device and a plurality of sink devices are presented. an initial set of values of configuration parameters respectively related to each sink device of the plurality of sink devices can be determined. an initial value of a maximum bandwidth usage parameter related to the point-to-multipoint bluetooth network can be determined. a new set of values of the configuration parameters different from the initial set of values can be determined. the new set of values may be determined to allocate bandwidth usage values between the plurality of multimedia communication links without exceeding the value of the maximum bandwidth usage parameter.
Inventor(s): Dongeek Shin of Mountain View CA (US) for google llc
IPC Code(s): H04W4/029, G01S13/87
Abstract: to provide indoor navigation directions to a user, a client device receives () a request for indoor navigation directions, and communicates () an ultra-wideband (uwb) signal with at least one anchor device in an indoor positioning system having a predetermined location within the indoor positioning system. the client device determines () a distance between the client device and the at least one anchor device based on a round trip time associated with the uwb signal, and determines () an indoor location of the client device based on (i) the distance between the client device and the at least one anchor device and (ii) the predetermined location for the at least one anchor device. additionally, the client device generates () a set of indoor navigation directions for traversing the destination location, and provides () the indoor navigation directions via a user interface of the client device.
Inventor(s): Jibing Wang of San Jose CA (US) for google llc, Erik Richard Stauffer of Sunnyvale CA (US) for google llc, Aamir Akram of San Jose CA (US) for google llc
IPC Code(s): H04W48/18, H04W40/02
Abstract: the present disclosure describes systems and methods for a user equipment wirelessly communicating with another user equipment using dual connectivity (dc) with a terrestrial base station and a satellite or high-altitude platform. the described methods and systems include a principal routing manager assessing that different subsets of data, to be transmitted from the user equipment to the other user equipment, can use different, respective qualities of service (qos) offered through different wireless-communication networks associated with the terrestrial base station and the satellite or high-altitude platform. the principal routing manager causes a routing command message to be sent to the user equipment, directing the user equipment to enter a state of dual connectivity with the terrestrial base station and the satellite or high-altitude platform and transmit the different subsets of the data in accordance with the qos offered by the different wireless-communication networks that are associated with the terrestrial base station and satellite or high-altitude platform.
Inventor(s): Chih-Hsiang Wu of Taoyuan City (TW) for google llc, Kao-Peng Chou of Taoyuan City (TW) for google llc
IPC Code(s): H04W72/30, H04W72/11
Abstract: a base station can implement a method for managing transmission of multicast and/or broadcast services (mbs) using semi-persistent scheduling (sps). the method includes: transmitting (), to a user equipment (ue), a configuration for receiving mbs data on sps radio resources; providing (), to the ue, an indication to activate receiving the mbs data in accordance with the configuration; and transmitting (), to the ue, the mbs data in accordance with the configuration.
Inventor(s): Chih-Hsiang Wu of Taoyuan City (TW) for google llc
IPC Code(s): H04W76/27, H04W76/19
Abstract: a central unit (cu) of a distributed base station a radio access network (ran) can implement a method for handling communication errors when communicating with a user equipment (ue) while a radio resource control connection between the ue and the distributed base station is not active. the method includes performing () early data communication with a ue. the method further includes determining () to stop the early data communication, and, in response to the determining, transmitting (), to the ue via a distributed unit (du) of the distributed base station, a message to instruct the ue to stop the early data communication, the message formatted in accordance with a protocol for controlling radio resources.
20240114670.Component Shielding_simplified_abstract_(google llc)
Inventor(s): Wen Shian Lin of New Taipei City (TW) for google llc, Chien Hua Hsu of New Taipei City (TW) for google llc, Shihwen Lee of New Taipei City (TW) for google llc, Bing-Feng Wang of New Taipei City (TW) for google llc, Chijer Wang of Taipei (TW) for google llc
IPC Code(s): H05K9/00
Abstract: techniques and apparatuses directed to component shielding are described in this document. a first aspect relates to a system including a printed circuit board (pcb) oriented along a first plane, a device on the pcb, and a component shield having a wall structure oriented perpendicular to the first plane and a cover structure connected to the wall structure. the system includes a housing structure oriented along a second plane that is substantially parallel to the first plane. the first and second planes define a shielded space within which the component shield and the device reside. the system further includes a shielding layer residing at least partially between the cover and housing structures. the shielding layer has an irregular cross-section along a fourth plane perpendicular to at least one of the first or second planes and a third plane. the irregular cross-section includes a protrusion that extends from the third plane.
- GOOGLE LLC
- G01C21/34
- Google llc
- G01C21/36
- G06N20/00
- G06F1/3212
- G06F8/33
- G06F8/38
- G06F3/0482
- G06F8/34
- H04L51/02
- G06F9/451
- G06F16/33
- G06F16/332
- G06F40/20
- G06F40/30
- G06F9/455
- G06F9/48
- G06F9/46
- G06F12/02
- G06F16/44
- G06F16/242
- G06F16/248
- G06F16/29
- G06F16/9537
- G06F16/58
- G06F3/0484
- G06F16/2457
- G06F16/25
- G06F21/62
- G06N5/022
- H04W4/02
- G06F16/9032
- G06F16/9038
- G06F16/951
- G06F21/60
- H04L9/30
- H04L9/32
- G06N3/0455
- G06N3/048
- G06N3/08
- G06N3/04
- G06N10/70
- G06N10/40
- G06Q30/02
- G06F40/247
- G06T5/70
- G06F3/01
- G08B21/04
- G01S13/32
- G01S13/58
- G10L13/04
- G10L17/04
- G10L19/00
- G10L15/19
- G10L15/06
- G10L15/22
- G10L15/30
- G10L15/197
- G06F16/903
- G06N3/006
- G10L15/18
- G16H50/20
- G06F40/166
- G06F40/295
- G16H10/60
- G16H15/00
- G06F40/279
- G10L15/00
- G10L15/08
- G16H40/63
- G16H50/70
- H04L9/08
- H04L69/22
- H04L49/15
- H04L41/082
- H04L41/084
- H04L45/58
- H04L49/25
- H04N19/30
- H04N19/172
- H04R3/12
- G10L19/16
- G10L19/22
- H04W72/30
- H04W76/40
- H04W4/029
- G01S13/87
- H04W48/18
- H04W40/02
- H04W72/11
- H04W76/27
- H04W76/19
- H05K9/00
