GOOGLE LLC patent applications on February 20th, 2025
Patent Applications by GOOGLE LLC on February 20th, 2025
GOOGLE LLC: 37 patent applications
GOOGLE LLC has applied for patents in the areas of G10L15/22 (5), G06N3/08 (4), G10L15/06 (4), G06N3/045 (4), G10L15/26 (4) G06N3/08 (2), G10L15/063 (2), B25J9/1605 (1), G11B27/031 (1), G10L13/04 (1)
With keywords such as: user, data, based, computing, include, training, device, digital, object, and image in patent application abstracts.
Patent Applications by GOOGLE LLC
20250058460. SIMULATING MULTIPLE ROBOTS IN VIRTUAL ENVIRONMENTS_simplified_abstract_(google llc)
Inventor(s): Matthew Bennice of San Jose CA (US) for google llc, Paul Bechard of Ogdensburg NY (US) for google llc
IPC Code(s): B25J9/16, B25J9/00
CPC Code(s): B25J9/1605
Abstract: implementations are provided for operably coupling multiple robot controllers to a single virtual environment, e.g., to generate training examples for training machine learning model(s). in various implementations, a virtual environment may be simulated that includes an interactive object and a plurality of robot avatars that are controlled independently and contemporaneously by a corresponding plurality of robot controllers that are external from the virtual environment. sensor data generated from a perspective of each robot avatar of the plurality of robot avatars may be provided to a corresponding robot controller. joint commands that cause actuation of one or more joints of each robot avatar may be received from the corresponding robot controller. joint(s) of each robot avatar may be actuated pursuant to corresponding joint commands. the actuating may cause two or more of the robot avatars to act upon the interactive object in the virtual environment.
Inventor(s): Soeren Pirk of Palo Alto CA (US) for google llc, Seyed Mohammad Khansari Zadeh of San Carlos CA (US) for google llc, Karol Hausman of San Francisco CA (US) for google llc, Alexander Toshev of San Francisco CA (US) for google llc
IPC Code(s): B25J9/16, G06N3/045, G06V10/147, G06V10/44, G06V10/82, G06V20/10, G06V20/13, G06V20/17
CPC Code(s): B25J9/1697
Abstract: training and/or using a machine learning model for performing robotic tasks is disclosed herein. in many implementations, an environment-conditioned action sequence prediction model is used to determine a set of actions as well as a corresponding particular order for the actions for the robot to perform to complete the task. in many implementations, each action in the set of actions has a corresponding action network used to control the robot in performing the action.
Inventor(s): King Hei Leung of Palo Alto CA (US) for google llc
IPC Code(s): G01M7/02
CPC Code(s): G01M7/02
Abstract: the technology is generally directed to determining fatigue damages to an electronic component or a hardware system caused by the transport or movement of the electronic component or hardware system. the electronic components may be, for example, data center hardware components. the electronic components are susceptible to fatigue damage resulting from thermal, shock and vibration events. the thermal, shock, and vibration events may occur, for example, during transport or movement of the electronic components. to fully characterize fatigue, the acceleration and stress cycles may be tracked, which correlate with natural phenomena in the global supply chain and data center environment.
Inventor(s): Arash Sadr of Belmont CA (US) for google llc
IPC Code(s): G06F3/14, G06F1/16, G06F3/04842, H04M1/02
CPC Code(s): G06F3/1454
Abstract: techniques involve triggering a divided screen mode for a computing environment in response to an indication that a display aspect of the computing environment has changed. in a first portion of the divided screen mode, an interface for a main application is displayed; in a second portion of the divided screen mode, an interface for a companion application is displayed. in some implementations, prior to the interface for the companion application being displayed, an icon representing the companion application is displayed in the second portion; the user may point to, or click on, the icon to launch the companion application.
Inventor(s): Joseph Lange of Zurich (CH) for google llc, Asier Aguirre of Adliswil (CH) for google llc, Olivier Siegenthaler of Zurich (CH) for google llc, Michal Pryt of Zurich (CH) for google llc
IPC Code(s): G06F3/16, G06T7/70, G06V20/00, G10L15/26
CPC Code(s): G06F3/167
Abstract: implementations are described herein for analyzing existing graphical user interfaces (“guis”) to facilitate automatic interaction with those guis, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those guis. for example, in various implementations, a user intent to interact with a particular gui may be determined based at least in part on a free-form natural language input. based on the user intent, a target visual cue to be located in the gui may be identified, and object recognition processing may be performed on a screenshot of the gui to determine a location of a detected instance of the target visual cue in the screenshot. based on the location of the detected instance of the target visual cue, an interactive element of the gui may be identified and automatically populate with data determined from the user intent.
Inventor(s): Christopher Johnson of Mukilteo WA (US) for google llc
IPC Code(s): G06F11/36
CPC Code(s): G06F11/3612
Abstract: aspects of the technology provide a software testing framework that can significantly reduce hardware resources needed to validate code modules. this may include employing a hardware emulator capable of instrumenting binaries to produce a trace of operations performed by a given program. the trace of operations performed by the given program may be mapped to representative profiles of operations benchmarked on a hardware system corresponding to the hardware emulated by the hardware emulator. the representative profile may contain sets of representative operations previously performed on the hardware. the mapping may allow for estimates on performance metrics of the given program (e.g., efficacy and/or speed) when run on the hardware. such estimates may allow for the identification of operations that cause the given program to run inefficiently or slowly on the hardware.
20250061117. Cross-List Learning to Rank_simplified_abstract_(google llc)
Inventor(s): Gil Shamir of Sewickley PA (US) for google llc
IPC Code(s): G06F16/2457
CPC Code(s): G06F16/24578
Abstract: provided are systems and methods that perform learning to rank using training data for two or more different training lists. specifically, a training dataset can include a number of training examples. each training example can include a query and a plurality of items that are potentially responsive to the query. the ranking model can be trained using pairs of items taken from two different training examples.
20250061123. CLOUD INFERENCE SYSTEM_simplified_abstract_(google llc)
Inventor(s): Emanuel Taropa of San Jose CA (US) for google llc
IPC Code(s): G06F16/248, G06F16/22, G06F16/2455, G06F16/2458, G06F16/28
CPC Code(s): G06F16/248
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for storing and accessing data in a cloud system. one of the methods includes receiving an identification of log data that records occurrences of events; receiving a specification of a plurality of different event types to be indexed; indexing the log data according to the specification and group identifiers; receiving a query specifying a reference parameter and requesting one or more predicted events; searching the indexed groups to identify a plurality of groups having events associated with the reference parameter; computing one or more predicted events, from the identified plurality of groups, that are most likely to co-occur in the indexed groups with events associated with the reference parameter; and providing the computed one or more predicted events.
20250061137. FILE SEARCH_simplified_abstract_(google llc)
Inventor(s): Krystal Rose Higgins of Balgowlah (AU) for google llc, Benjamin Thomas Hartney of Palm Beach (AU) for google llc, Simon Walter Hangl of Munich (DE) for google llc, Ameet Jani of Campbell CA (US) for google llc, Mirco Franz of Voehringen (DE) for google llc, Admir Hadžic of Bodenkirchen (DE) for google llc, Andrey Rayskiy of Munich (DE) for google llc
IPC Code(s): G06F16/332, G06F16/338, G06F16/35, G06F16/383
CPC Code(s): G06F16/3323
Abstract: a method may receive a query. a method may obtain a representation of the query, the representation approximating content of the query. a method may determine a set of files accessible by an operating system that are relevant to the query by comparing the representation of the query with representations of files stored in an index, the files in the set of files having representations meeting a similarity threshold with the representation of the query. a method may cause a display of a response to the query, the response identifying the files in the set of files as relevant to the query.
Inventor(s): Benedict Junjie Liang of Singapore (SG) for google llc, Ahmad Nizam Anuar of Iskandar Puteri (MY) for google llc, Sumeet Kale of Singapore (SG) for google llc, Ching-Fei Yang of Singapore (SG) for google llc, Dian Zhang of Beijing (CN) for google llc, Kiat Chuan Tan of Singapore (SG) for google llc
IPC Code(s): G06F16/435, G06F16/48, H04N21/2187
CPC Code(s): G06F16/435
Abstract: the present disclosure provides computer-implemented methods, systems, and devices for generating media content pages for live events at scale. a computing system accesses media data associated with a live event. the computing system customizes media data for one or more user groups. the computing system selects one or more page templates from a plurality of page templates based, at least in part on the customized media data. the computing system generates one or more content pages based on the customized media data and the one or more page templates. the computing system provides the one or more content pages to one or more user computing devices.
20250061146. IMAGE QUERY PROCESSING USING LARGE LANGUAGE MODELS_simplified_abstract_(google llc)
Inventor(s): Olivier Siegenthaler of Zurich (CH) for google llc, Ágoston Weisz of Zurich (CH) for google llc, Boris Bluntschli of Zurich (CH) for google llc, Dan Banica of Zurich (CH) for google llc, Kaan Ege Özgün of Zurich (CH) for google llc, Daniel Mogoreanu of Zurich (CH) for google llc, Filip Sladek of Zurich (CH) for google llc
IPC Code(s): G06F16/532, G06F40/40, G06V10/80, G06V20/50
CPC Code(s): G06F16/532
Abstract: implementations utilize an llm to respond to queries comprising image data, such as multimodal queries that include both text and image data. a natural language processing system is extended such that when an image is provided, the natural language processing system invokes one or more auxiliary image processing models (e.g., visual query) and/or image search engines. the results, of invoking such model(s) and/or search engine(s), are collected into structured data signals related to the image. these signals form part of the conversation context and are used to extend the text prompt that is sent to the llm. this allows the llm to take the context into account when being used to process the user query, thereby enabling generation of an llm reply that addresses relevant feature(s) of the image.
Inventor(s): Ibrahim Badr of Zurich (CH) for google llc, Yariv Adan of Cham (CH) for google llc, Hugo Santos of Zurich (CH) for google llc, Shikha Kapoor of Sunnyvale CA (US) for google llc, Karthik Nagaraj of Dublin CA (US) for google llc, Glenn Wilson of Mountain View CA (US) for google llc, Arwa Rangwala of Santa Clara CA (US) for google llc, Leo Deegan of Mountain View CA (US) for google llc, Peter Krogh of Nevada City CA (US) for google llc
IPC Code(s): G06F40/40, G06F3/16, G06F9/46, G06F9/54, G06F16/33, G06F16/332, G06F16/9537, G10L15/18, G10L15/22, G10L15/26, G10L21/06
CPC Code(s): G06F40/40
Abstract: methods, apparatus, and computer readable media are described herein for allowing a first user to interface with an automated assistant to assign tasks to additional user(s), and/or for causing notification(s) of the assigned task to be rendered to the additional user(s) via corresponding automated assistant interface(s). in various implementations, one or more criteria can be utilized in selecting a group of client device(s), linked to the additional user, via which to provide the notification(s) for the task assigned to the additional user. also, in various implementations condition(s) for providing the notification(s) for the task can be determined, and the notification(s) provided based on determining satisfaction of the condition(s).
Inventor(s): Krishna Shankar of Los Altos CA (US) for google llc, Nicolas Hudson of San Mateo CA (US) for google llc, Alexander Toshev of San Francisco CA (US) for google llc
IPC Code(s): G06N3/008, B25J9/16, G06F18/40, G06N3/04, G06N3/08, G06N3/084, G06V10/778, G06V10/82
CPC Code(s): G06N3/008
Abstract: methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. the local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.
Inventor(s): Matthias Heiler of Zug (CH) for google llc, Sylvanus Garnet Bent, III of Palo Alto CA (US) for google llc, Mehmet Levent Koc of Redwood City CA (US) for google llc, Snehal Sunilkumar Motarwar of Bengaluru (IN) for google llc, Aravindan Raghuveer of Bangalore (IN) for google llc, Saachi Grover of Bangalore (IN) for google llc, Nidhi Gupta of Bangalore (IN) for google llc, Preksha Nema of Vijaynagar (IN) for google llc, Durga Deepthi Singh Sharma of Bangalore (IN) for google llc, Abhinav Khandelwal of Bengaluru (IN) for google llc
IPC Code(s): G06N3/0475
CPC Code(s): G06N3/0475
Abstract: example aspects of the present disclosure provide an example method. in some implementations, the example method can include receiving request data indicating a request for content. in some implementations, the example method can include determining a request context associated with the request data, wherein the request context is based on account data for a user device associated with the request. in some implementations, the example method can include determining, based on the request and the request context, a data object from a knowledge graph, wherein the data object comprises a subject and one or more attributes for the subject. in some implementations, the example method can include generating, using a machine-learned content generation model, content descriptive of the subject, the content generated based on the request, the request context, and the data object.
20250061328. PERFORMING CLASSIFICATION USING POST-HOC AUGMENTATION_simplified_abstract_(google llc)
Inventor(s): Mariano Ruben Schain of Tel Aviv (IL) for google llc, Elad Eban of Sunnyvale CA (US) for google llc
IPC Code(s): G06N3/08, G06N3/0455
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing network inputs by applying augmentations to internal representations of the network inputs.
20250061333. Parameter-Efficient Multi-Task and Transfer Learning_simplified_abstract_(google llc)
Inventor(s): Mark Sandler of Mountain View CA (US) for google llc, Andrew Gerald Howard of Culver City CA (US) for google llc, Andrey Zhmoginov of Mountain View CA (US) for google llc, Pramod Kaushik Mudrakarta of Chicago IL (US) for google llc
IPC Code(s): G06N3/08, G06N3/045, G10L15/16
CPC Code(s): G06N3/08
Abstract: the present disclosure provides systems and methods that enable parameter-efficient transfer learning, multi-task learning, and/or other forms of model re-purposing such as model personalization or domain adaptation. in particular, as one example, a computing system can obtain a machine-learned model that has been previously trained on a first training dataset to perform a first task. the machine-learned model can include a first set of learnable parameters. the computing system can modify the machine-learned model to include a model patch, where the model patch includes a second set of learnable parameters. the computing system can train the machine-learned model on a second training dataset to perform a second task that is different from the first task, which may include learning new values for the second set of learnable parameters included in the model patch while keeping at least some (e.g., all) of the first set of parameters fixed.
Inventor(s): Daniel Sank of Goleta CA (US) for google llc, Evan Robert Jeffrey of Santa Barbara CA (US) for google llc
IPC Code(s): G06N10/40
CPC Code(s): G06N10/40
Abstract: this disclosure is directed to a quantum computing system (qcs) that includes a cryogenic sub-system, a signal-generating element, a first signal-splitting element, a first transmission path, a second transmission path, a third transmission path, and a quantum device. a first environment is located outside the cryogenic sub-system and a second environment is associated with the cryogenic sub-system. the signal-generating element generates a first signal. the first signal-splitting element is positioned within the second environment. the quantum device is positioned within the cryogenic sub-system. the first transmission path transmits the first signal from the signal-generating element to the first signal-splitting element. the first signal-splitting element subdivides the first signal into a second signal and a third signal. the third transmission transmits the third signal from the first signal-splitting element to the first environment. the second transmission path transmits the second signal from the first signal-splitting element to the quantum device.
20250061370. Latency-Reduced Quantum Error Detection Graph Decoding_simplified_abstract_(google llc)
Inventor(s): Noah John Shutty of Santa Monica CA (US) for google llc, Austin Fowler of Los Angeles CA (US) for google llc
IPC Code(s): G06N10/70
CPC Code(s): G06N10/70
Abstract: systems and methods for error detection in a quantum computing system are provided. in one example, the method includes obtaining a multidimensional quantum error detection graph. the multidimensional quantum error detection graph represents one or more quantum error detection measurements across a time period. the method includes determining a partitioning scheme and a fusing scheme for the multidimensional quantum error detection graph based at least in part on a decoding latency and a fusing latency. the method includes partitioning the multidimensional quantum error detection graph into a plurality of blocks based at least in part on the partitioning scheme. the method includes decoding each of the plurality of blocks. the method includes fusing the plurality of blocks into a decoded detection graph based at least in part on the fusing scheme. the method includes operating a quantum computing system based at least in part on the decoded detection graph.
20250061490. Integrating User Declarations in Ads Personalization_simplified_abstract_(google llc)
Inventor(s): Elena Erbiceanu-Tener of Los Gatos CA (US) for google llc, Tianyi Pan of Cupertino CA (US) for google llc, Derek Dunfield of New York NY (US) for google llc, Khannan Sundar of Mountain View CA (US) for google llc, Benjamin Max Ewing of Seattle WA (US) for google llc, Mayank Krishna Kedia of San Francisco CA (US) for google llc, Fang Han of Livermore CA (US) for google llc, Dhruv Sagar of New York NY (US) for google llc
IPC Code(s): G06Q30/0251, G06Q30/0241
CPC Code(s): G06Q30/0255
Abstract: the technology is generally directed to personalizing digital components for users based on a merged preference profile. the merged preference profile may be generated based on declared and inferred preferences of the users. the declared and inferred preferences may be preferences related to brands, topics, types of products, etc. the merged preference profile may be used to personalize the digital components output to the user. for example, when identifying digital components to be selected, at least some of the digital components may be selected based on the merged preference profile of the user. at least a portion of the selected digital components may be digital components with a subject matching the preferences of the user, thereby improving the digital components output to the user.
Inventor(s): Chitwan Saharia of Toronto (CA) for google llc, Jonathan Ho of Berkeley CA (US) for google llc, William Chan of Toronto (CA) for google llc, Tim Salimans of Utrecht (NL) for google llc, David Fleet of Toronto (CA) for google llc, Mohammad Norouzi of Toronto (CA) for google llc
IPC Code(s): G06T5/70, G06N3/045, G06N3/08, G06T3/4007, G06T5/50
CPC Code(s): G06T5/70
Abstract: a method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. the method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward gaussian diffusion process that adds gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse markov chain associated with the forward gaussian diffusion process. the method additionally includes outputting the trained neural network.
20250061608. AUTO-REGRESSIVE VIDEO GENERATION NEURAL NETWORKS_simplified_abstract_(google llc)
Inventor(s): Oscar Carl Tackstrom of Stockholm (SE) for google llc, Jakob D. Uszkoreit of Berlin (DE) for google llc, Dirk Weissenborn of Berlin (DE) for google llc
IPC Code(s): G06T9/00, G06N3/045
CPC Code(s): G06T9/002
Abstract: a method for generating a video is described. the method includes: generating an initial output video including multiple frames, each of the frames having multiple channels; identifying a partitioning of the initial output video into a set of channel slices that are indexed according to a particular slice order, each channel slice being a down sampling of a channel stack from a set of channel stacks; initializing, for each channel stack in the set of channel stacks, a set of fully-generated channel slices; repeatedly processing, using an encoder and a decoder, a current output video to generate a next fully-generated channel slice to be added to the current set of fully-generated channel slices; generating, for each channel index, a respective fully-generated channel stack using the respective fully generated channel slices; and generating a fully-generated output video using the fully-generated channel stacks.
20250061628. SIMULATING LIGHT REFLECTING OFF AN OBJECT_simplified_abstract_(google llc)
Inventor(s): Dongeek Shin of Mountain View CA (US) for google llc
IPC Code(s): G06T11/60, G06F3/14, G06T7/40, G06V10/764, G06V10/82, G06V20/70
CPC Code(s): G06T11/60
Abstract: a computing device is described that includes one or more processors, an image sensor that captures an image at a location of the computing device, and at least one module. the at least one module is operable by the one or more processors to capture, by the image sensor of the computing device, an image frame, determine, based on the image frame, one or more characteristics of light produced by one or more light sources, apply a light source image, generated with the one or more characteristics of light associated with the one or more light sources, to an image of an object, to generate an adjusted image to simulate effects of the one or more light sources on the object; and output, for display by the computing device, the adjusted image.
Inventor(s): Mark Bowers of Brooklyn NY (US) for google llc, Brian F. Allen of San Francisco CA (US) for google llc, Nida Zada of San Jose CA (US) for google llc, Julie Anne Seguin of Mountain View CA (US) for google llc
IPC Code(s): G10L13/04, G06V40/10, G10L13/10
CPC Code(s): G10L13/04
Abstract: generating synthesized speech audio data on behalf of a given user in a conversation. the synthesized speech audio data includes synthesized speech that incorporates textual segment(s). the textual segment(s) can include recognized text that results from processing spoken input, of the given user, using a speech recognition model and/or can include a selection of a rendered suggestion that conveys the textual segment(s). some implementations dynamically determine one or more prosodic properties for use in speech synthesis of the textual segment, and generate the synthesized speech with the one or more determined prosodic properties. the prosodic properties can be determined based on the textual segment(s) used in speech synthesis, textual segment(s) corresponding to recent spoken input of additional participant(s), attribute(s) of relationship(s) between the given user and additional participant(s) in the conversation, and/or feature(s) of a current location for the conversation.
20250061889. Lattice Speech Corrections_simplified_abstract_(google llc)
Inventor(s): Ágoston Weisz of Pfaeffikon (CH) for google llc, Leonid Velikovich of New York NY (US) for google llc
IPC Code(s): G10L15/06, G10L15/22, G10L15/26, G10L15/30
CPC Code(s): G10L15/063
Abstract: a method includes receiving audio data corresponding to a query spoken and processing the audio data to generate multiple candidate hypotheses each represented by a respective sequence of hypothesized terms. for each candidate hypothesis, the method includes determining whether the sequence of hypothesized terms includes a source phrase from a list of phrase correction pairs. each phrase correction pair includes a corresponding source phrase that was misrecognized and a corresponding target phrase replacing the source phrase. when the respective sequence of hypothesized terms includes the source phrase, the method includes generating a corresponding additional candidate hypothesis that replaces the source phrase. the method also includes ranking the multiple candidate hypotheses and each corresponding additional candidate hypothesis generated and generating a transcription of the query spoken by the user by selecting the highest ranking one of the multiple candidate hypotheses and each additional candidate hypothesis.
20250061890. EXAMPLE-BASED VOICE BOT DEVELOPMENT TECHNIQUES_simplified_abstract_(google llc)
Inventor(s): Asaf Aharoni of Ramat Hasharon (IL) for google llc, Yaniv Leviathan of New York NY (US) for google llc, Eyal Segalis of Tel Aviv (IL) for google llc, Gal Elidan of Modiin (IL) for google llc, Sasha Goldshtein of Tel Aviv (IL) for google llc, Tomer Amiaz of Tel Aviv (IL) for google llc, Deborah Cohen of Tel Aviv (IL) for google llc
IPC Code(s): G10L15/06, G10L15/22, G10L15/30, H04L67/133, H04L67/53, H04M3/51
CPC Code(s): G10L15/063
Abstract: implementations are directed to providing a voice bot development platform that enables a third-party developer to train a voice bot based on training instance(s). the training instance(s) can each include training input and training output. the training input can include a portion of a corresponding conversation and a prior context of the corresponding conversation. the training output can include a corresponding ground truth response to the portion of the corresponding conversation. subsequent to training, the voice bot can be deployed for conducting conversations on behalf of a third-party. in some implementations, the voice bot is further trained based on a corresponding feature emphasis input that attentions the voice bot to a particular feature of the portion of the corresponding conversation. in some additional or alternative implementations, the voice bot is further trained to interact with third-party system(s) via remote procedure calls (rpcs).
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G10L15/08, G06F3/16, G06V20/64, G10L15/06, G10L15/18, G10L15/22, G10L15/26
CPC Code(s): G10L15/083
Abstract: generating audio tracks is provided. the system selects a digital component object having a visual output format. the system determines to convert the digital component object into an audio output format. the system generates text for the digital component object. the system selects, based on context of the digital component object, a digital voice to render the text. the system constructs a baseline audio track of the digital component object with the text rendered by the digital voice. the system generates, based on the digital component object, non-spoken audio cues. the system combines the non-spoken audio cues with the baseline audio form of the digital component object to generate an audio track of the digital component object. the system provides the audio track of the digital component object to the computing device for output via a speaker of the computing device.
Inventor(s): Glen Shires of Danville CA (US) for google llc
IPC Code(s): G10L15/24, G06F21/32, G10L15/18, G10L15/20, G10L15/22
CPC Code(s): G10L15/24
Abstract: implementations can determine whether to activate non-audible silent speech recognition for using non-audible speech commands to an automated assistant. this can include detecting non-audible silent speech data based on one or more non-audible sensors, and, optionally, detecting temporally corresponding audible data based on one or more audible sensors. recognized text based can then be generated based on processing the non-audible silent speech data and then one or more actions can be performed or one or more fulfillments initiated based on the non-audible silent speech data.
20250061917. LANGUAGE-MODEL SUPPORTED SPEECH EMOTION RECOGNITION_simplified_abstract_(google llc)
Inventor(s): Josh Belanich of Brooklyn NY (US) for google llc, Taesik Gong of Seo-gu (KR) for google llc, Krishna Somandepalli of New York NY (US) for google llc, Brian Eoff of Lexington MA (US) for google llc, Brendan Wesley Jou of New York NY (US) for google llc, Arsha Nagrani of Cambridge MA (US) for google llc
IPC Code(s): G10L25/63, G10L15/06
CPC Code(s): G10L25/63
Abstract: the technology relates to enhancing speech emotion recognition models with methods that enable the use of unlabeled data by inferring weak emotion labels. this is done by pre-trained large language models through weakly-supervised learning. for inferring weak labels constrained to a taxonomy, a textual entailment approach selects an emotion label with the highest entailment score for a speech transcript extracted via automatic speech recognition. the system may employ a method that generates, by one or more processors, a text transcript for a snippet of input speech, and then applies the text transcript to a pre-trained language model. the system can generate, using the pre-trained language model according to an engineered prompt and a predetermined taxonomy, a textual entailment from the text transcript. based on this, the system may generate, by the one or more processors using the textual entailment, a predicted emotion corresponding to the input speech.
20250061922. GENERATING VIDEOS_simplified_abstract_(google llc)
Inventor(s): Nathan James Frey of Venice CA (US) for google llc, Zheng Sun of Sunnyvale CA (US) for google llc
IPC Code(s): G11B27/031, G06T7/20, G06V20/40
CPC Code(s): G11B27/031
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating videos. in one aspect, a method comprises: receiving: (i) an input video comprising a sequence of video frames, and (ii) data indicating a target object type; processing the input video to generate tracking data that identifies and tracks visual locations of one or more instances of target objects of the target object type in the input video; generating a plurality of sub-videos based on the input video and the tracking data, including: for each sub-video, generating a respective sequence of sub-video frames that are each extracted from a respective video frame of the input video to include a respective instance of a given target object from among the identified target objects of the target object type; and generating an output video that comprises the plurality of sub-videos.
20250062808. Adaptive Phase-Changing Device Power-Saving Operations_simplified_abstract_(google llc)
Inventor(s): Jibing Wang of San Jose CA (US) for google llc, Erik Richard Stauffer of Sunnyvale CA (US) for google llc
IPC Code(s): H04B7/06, H04B7/026, H04B7/04, H04B7/0456, H04W52/02, H04W76/28
CPC Code(s): H04B7/0617
Abstract: techniques and apparatuses are described for adaptive phase-changing device power-saving operations. in aspects, a base station determines to transition an adaptive phase-changing device (apd) into an enabled apd-ps mode and determines an apd-ps configuration for the apd that specifies a framework for operating in the enabled apd-ps mode. the base station then directs the apd to operate in the enabled apd-ps mode by communicating the apd-ps configuration to the apd and transmits or receives wireless signals using a surface of the apd and based on the apd-ps configuration.
Inventor(s): Wei-haw Chuang of Mountain View CA (US) for google llc
IPC Code(s): H04L9/32, H04L51/214, H04L51/234, H04L51/48
CPC Code(s): H04L9/3247
Abstract: a method for securing messages includes obtaining, at a message server, a message for a user of a message service hosted by the message server. the message includes a header and the header includes 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 whether the digital signature by the author is valid and determining, using the list of one or more recipients, whether the user is a declared recipient of the message. when the digital signature by the author is valid and the user is the declared recipient of the message, the method includes delivering the message to a user device of the user. when the digital signature by the author is valid and the user is not the declared recipient of the message, the method includes alerting the user.
Inventor(s): Gaurav Menghani of Santa Clara CA (US) for google llc, Ariel Fuxman of Redwood City CA (US) for google llc
IPC Code(s): H04L9/40, H04L41/16
CPC Code(s): H04L63/1433
Abstract: an example method can include obtaining, by a computing system, a first dataset including first reference inputs and first reference outputs. the example method can include training, by the computing system, a first machine-learned model using the first dataset. the example method can include obtaining, by the computing system, a second dataset including a plurality of second reference inputs, the plurality of second reference inputs obtained from a data corpus based on a distribution of second reference inputs in the second dataset. the example method can include processing, by the computing system and using the first machine-learned model, the plurality of second reference inputs to generate a plurality of second reference outputs corresponding to the plurality of second reference inputs. the example method can include training, by the computing system, a second machine-learned model using the plurality of second reference outputs and the plurality of second reference inputs.
Inventor(s): Kevin Jonathan Jeyakumar of Seattle WA (US) for google llc, Juan Carlos Angustia Garcia of Philadelphia PA (US) for google llc, Antoinette Garlit Salom of Honolulu (HI) for google llc, Shannon Ona Wei Sum Juzenas of Bothell WA (US) for google llc, Jared O'Connor of Issaquah WA (US) for google llc, Alia Walid Awni of Seattle WA (US) for google llc, Wonsuk Jung of Seattle WA (US) for google llc, Drexel Alexander Feeling of Durham NC (US) for google llc, Patrick J. Neill of Sammamish WA (US) for google llc, Kimberly Ha of Seattle WA (US) for google llc, Gregory Cannon of Seattle WA (US) for google llc, Yelena Zukin of Foster City CA (US) for google llc, Zong Ye Yang of Pasadena CA (US) for google llc, Pablo Federico Majernik of Sammamish WA (US) for google llc
IPC Code(s): H04N7/15, G06T7/20
CPC Code(s): H04N7/157
Abstract: a method for adjusting the user interface for a video conferencing application is provided. the method includes receiving an indication of a motion of a first client device of a first participant of a plurality of participants of a virtual meeting. the method further includes determining, based on the indication of the motion of the first client device of the first participant, a set of interface adjustments for a virtual meeting user interface to be presented on the first client device of the first participant. the method further includes causing the virtual meeting user interface presented on the first client device of the first participant to reflect the set of user interface adjustments during the virtual meeting.
Inventor(s): James McGregor Scanlan of San Francisco CA (US) for google llc
IPC Code(s): H04R29/00, G01N27/22, H04R3/04
CPC Code(s): H04R29/004
Abstract: provided is a system for correcting the audio received by an audio sensor that has been distorted by the presence of water in a port associated with the audio sensor. more specifically. wearable computing devices can include audio sensors that can detect audio signals in the vicinity of the wearable computing devices. to enable the audio sensors to capture audio signal data more accurately, the wearable computing device can include a port (e.g., a microphone or “mic” port) that connects the audio sensor to the exterior of the wearable computing device. however, in some circumstances, the port can become partially or totally filled with water. for example, when a user is swimming while wearing the wearable computing device, the wearable computing device may be submerged and the port can become filled with water.
20250063453. FAST 5G BEAM SWITCHING BY EARLY MEASUREMENT REPORTING_simplified_abstract_(google llc)
Inventor(s): Edison Chen of Taipei (TW) for google llc, Yuan Ho of Hsinchu City (TW) for google llc, Poying Chuang of Taipei (TW) for google llc
IPC Code(s): H04W36/30, H04B7/06, H04W24/10, H04W36/06
CPC Code(s): H04W36/305
Abstract: a user equipment (ue) in a wireless communication network determines that a radio link failure (rlf) has previously occurred within a threshold distance from a current location of the ue. responsive to determining that the rlf has previously occurred, the ue determines an expected beam to be encountered and that is associated with the rlf. the ue generates a first beam measurement report for the expected beam. the beam measurement report includes an adjusted power measurement for the expected beam indicating that the expected beam is an optimal beam compared to at least one neighboring beam. the ue transmits the first beam measurement report to the cellular network.
Inventor(s): Ching- Jung Hsieh of Taipei City (TW) for google llc, Chih-Hsiang Wu of Taoyuan City (TW) for google llc
IPC Code(s): H04W36/36, H04W36/00
CPC Code(s): H04W36/362
Abstract: a method and system for managing candidate cell configuration for a user equipment (ue) initially in communication with at least a first node is disclosed herein. the method is implemented in a second node and comprises receiving, by the second node and from the first node, a request for connectivity with the second node, the request including at least a procedure indicator; and transmitting, by the second node to the first node and depending on the procedure indicator, one of a list of two or more conditional configurations or a single conditional configuration, the list of two or more conditional configurations or the single conditional configuration to be used by the ue.
20250063526. OFFLOADING NETWORK COMMUNICATIONS TO A SHARED MODEM_simplified_abstract_(google llc)
Inventor(s): Jayachandran Chinnakkannu of Santa Clara CA (US) for google llc, Hui Wang of Buffalo Grove (CA) for google llc
IPC Code(s): H04W60/04, H04W8/20, H04W12/06, H04W12/40, H04W88/18
CPC Code(s): H04W60/04
Abstract: shared modems discrete from user equipment (ue) or other user devices are configured to facilitate the reception and transmission of network messages between ue and a cellular network. the shared modems are connected to consistent power sources and are configured to communicatively couple to ue or other user devices using one or more communication protocols and communicatively couple to one or more cells of a cellular network using one or more cellular network protocols. once coupled to the ue or other user devices and the cellular network, the shared modems allow network messages to be transmitted and received between the ue or other user devices and the cellular network.
- GOOGLE LLC
- B25J9/16
- B25J9/00
- CPC B25J9/1605
- Google llc
- G06N3/045
- G06V10/147
- G06V10/44
- G06V10/82
- G06V20/10
- G06V20/13
- G06V20/17
- CPC B25J9/1697
- G01M7/02
- CPC G01M7/02
- G06F3/14
- G06F1/16
- G06F3/04842
- H04M1/02
- CPC G06F3/1454
- G06F3/16
- G06T7/70
- G06V20/00
- G10L15/26
- CPC G06F3/167
- G06F11/36
- CPC G06F11/3612
- G06F16/2457
- CPC G06F16/24578
- G06F16/248
- G06F16/22
- G06F16/2455
- G06F16/2458
- G06F16/28
- CPC G06F16/248
- G06F16/332
- G06F16/338
- G06F16/35
- G06F16/383
- CPC G06F16/3323
- G06F16/435
- G06F16/48
- H04N21/2187
- CPC G06F16/435
- G06F16/532
- G06F40/40
- G06V10/80
- G06V20/50
- CPC G06F16/532
- G06F9/46
- G06F9/54
- G06F16/33
- G06F16/9537
- G10L15/18
- G10L15/22
- G10L21/06
- CPC G06F40/40
- G06N3/008
- G06F18/40
- G06N3/04
- G06N3/08
- G06N3/084
- G06V10/778
- CPC G06N3/008
- G06N3/0475
- CPC G06N3/0475
- G06N3/0455
- CPC G06N3/08
- G10L15/16
- G06N10/40
- CPC G06N10/40
- G06N10/70
- CPC G06N10/70
- G06Q30/0251
- G06Q30/0241
- CPC G06Q30/0255
- G06T5/70
- G06T3/4007
- G06T5/50
- CPC G06T5/70
- G06T9/00
- CPC G06T9/002
- G06T11/60
- G06T7/40
- G06V10/764
- G06V20/70
- CPC G06T11/60
- G10L13/04
- G06V40/10
- G10L13/10
- CPC G10L13/04
- G10L15/06
- G10L15/30
- CPC G10L15/063
- H04L67/133
- H04L67/53
- H04M3/51
- G10L15/08
- G06V20/64
- CPC G10L15/083
- G10L15/24
- G06F21/32
- G10L15/20
- CPC G10L15/24
- G10L25/63
- CPC G10L25/63
- G11B27/031
- G06T7/20
- G06V20/40
- CPC G11B27/031
- H04B7/06
- H04B7/026
- H04B7/04
- H04B7/0456
- H04W52/02
- H04W76/28
- CPC H04B7/0617
- H04L9/32
- H04L51/214
- H04L51/234
- H04L51/48
- CPC H04L9/3247
- H04L9/40
- H04L41/16
- CPC H04L63/1433
- H04N7/15
- CPC H04N7/157
- H04R29/00
- G01N27/22
- H04R3/04
- CPC H04R29/004
- H04W36/30
- H04W24/10
- H04W36/06
- CPC H04W36/305
- H04W36/36
- H04W36/00
- CPC H04W36/362
- H04W60/04
- H04W8/20
- H04W12/06
- H04W12/40
- H04W88/18
- CPC H04W60/04