GOOGLE LLC patent applications on April 11th, 2024
Patent Applications by GOOGLE LLC on April 11th, 2024
GOOGLE LLC: 44 patent applications
GOOGLE LLC has applied for patents in the areas of G10L15/22 (8), G06N20/00 (6), G06N3/08 (6), G06Q30/02 (4), G06F16/245 (4)
With keywords such as: data, user, assistant, client, content, query, application, device, computing, and example in patent application abstracts.
Patent Applications by GOOGLE LLC
Inventor(s): Dongeek Shin of Mountain View CA (US) for google llc
IPC Code(s): G01S5/02
Abstract: to determine locations of ultra-wideband (uwb) anchor devices in an indoor positioning system, the indoor positioning system obtains distance measurements between each pair of n uwb anchor devices in the indoor positioning system. each distance measurement is determined based on a round trip time of a uwb signal communicated between the pair of uwb anchor devices. the indoor positioning system also determines a location of each of the uwb anchor devices within the indoor positioning system using the distance measurements, and reconstructs an absolute network topology of the uwb anchor devices using the determined locations of the uwb anchor devices. the absolute network topology is used to determine a location of a client device within the indoor positioning system.
Inventor(s): Jamie Elizabeth Kowalski of Oakland CA (US) for google llc, Shreyas Potnis of Kitchener (CA) for google llc, Rhys Anderson of Kitchener (CA) for google llc, Kirill Afanasev of Waterloo (CA) for google llc, Eliezer Glik of San Diego CA (US) for google llc, Timothy Paul Bodiya of Shanghai (CN) for google llc, Victor Isbrucker of Fenelon Falls (CA) for google llc
IPC Code(s): F21V8/00, G02B27/01
Abstract: a waveguide including first and second sections has a first molded optic material forming a portion of the geometry of one or more bragg gratings disposed on one surface of the first section of the waveguide. similarly, a second molded optic material forming another portion of the geometry of one or more bragg gratings is disposed on one surface of the second section of the waveguide. further, a photopolymer material is deposited on the first molded optic material. as the first and second sections are coupled, a waveguide is formed with a layer of photopolymer material disposed in the waveguide with the layer of photopolymer material having a geometry defined by the first and second molded optic materials. bragg grating holograms are then recorded in the layer of photopolymer material, resulting in a waveguide with a plurality of bragg gratings.
Inventor(s): Kanishka Rao of Santa Clara CA (US) for google llc, Chris Harris of Los Altos CA (US) for google llc, Julian Ibarz of Mountain View CA (US) for google llc, Alexander Irpan of Palo Alto CA (US) for google llc, Seyed Mohammad Khansari Zadeh of San Carlos CA (US) for google llc, Sergey Levine of Berkeley CA (US) for google llc
IPC Code(s): G05B13/02, B25J9/16, B25J19/02
Abstract: implementations disclosed herein relate to mitigating the reality gap through training a simulation-to-real machine learning model (“sim2real” model) using a vision-based robot task machine learning model. the vision-based robot task machine learning model can be, for example, a reinforcement learning (“rl”) neural network model (rl-network), such as an rl-network that represents a q-function.
20240118738.MANAGING POWER IN DATA CENTERS_simplified_abstract_(google llc)
Inventor(s): Sourav Kumar Patel of San Jose CA (US) for google llc, Anand Ramesh of Sunnyvale CA (US) for google llc, Adam Christopher Forni of South Pasadena CA (US) for google llc, Krishnanjan Gubba Ravikumar of Pullman WA (US) for google llc
IPC Code(s): G06F1/329, G06F1/3209
Abstract: systems and methods for managing power loads of one or more data centers using a wide-area energy controller to operate local energy resources of the data center based on power control information generated by a remote data center control system are described. in one aspect, a system includes a set of local energy sources configured to provide power to the loads of the energy system and a wide-area energy controller. the wide-area energy controller includes a first interface communicably coupled to an application programming interface (api) that connects a remote data center control system to respective wide-area energy controllers of multiple data centers, the first interface being configured to receive power control information from the remote data center control system via the api. the wide-area energy controller includes a control unit configured to schedule the local energy sources to provide power to the loads based on the power control information.
20240118740.Workload-Aware Voltage Regulator Tuning_simplified_abstract_(google llc)
Inventor(s): Houle Gan of Santa Clara CA (US) for google llc, Shuai Jiang of San Jose CA (US) for google llc, Sanjay Nilamboor of Santa Clara CA (US) for google llc, Rammohan Padmanabhan of Palo Alto CA (US) for google llc, Mohamed Elgebaly of Cupertino CA (US) for google llc
IPC Code(s): G06F1/3296, G06F1/329, G06F9/48
Abstract: a method and system of tuning a voltage regulator including receiving, at a voltage regulator, workload information for a workload to be executed by a processor that receives power from the voltage regulator; setting at least one of a load line value for the voltage regulator, a setpoint voltage supplied by the voltage regulator to the processor, or a phase shedding configuration of the voltage regulator based on the workload information; and sending to the processor, after the setting is complete, an acknowledgement signal indicating that the workload can proceed.
Inventor(s): Xi Chen of Mountain View CA (US) for google llc, Changgeng Liu of San Jose CA (US) for google llc, Ion Bita of Los Altos CA (US) for google llc, Marek Mienko of San Jose CA (US) for google llc
IPC Code(s): G06F3/042
Abstract: this document describes systems and techniques directed at mitigating display diffraction flares for under-display sensing. in aspects, an equation may be derived that models the effects of a display in producing a diffraction phenomenon at an image plane of a sensing region for an under-display light-sensing device. the equation may be used to determine an arrangement (e.g., an optimized arrangement) of components (e.g., sub-pixels) within the display that minimizes a diffraction efficiency for at least one diffraction order and, thereby, mitigates an intensity and/or a prevalence of optical artifacts in light-sensing data. in implementations, an image intensity point-spread-function is utilized to calculate diffraction efficiencies for respective diffraction orders (e.g., the lowest diffraction orders, the diffraction orders with the greatest brightness).
Inventor(s): Yu Wang of San Jose CA (US) for google llc, Dehao Chen of Fremont CA (US) for google llc, Phitchaya Mangpo Phothilimthana of Mountain View CA (US) for google llc
IPC Code(s): G06F8/41
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for feedback-directed optimization. one of the methods includes maintaining a data store comprising a plurality of optimization profiles that are used by a compiler to compile respective computer programs. the computer programs can be invoked by a set of executing workloads. operations are repeatedly performed that include, for each optimization profile in at least a subset of the optimization profiles: determining or predicting whether the optimization profile is a valid optimization profile for a current software version of the compiler, and in response to determining or predicting that the optimization profile is not a valid optimization profile for the current software version of the compiler, removing the optimization profile from the data store.
Inventor(s): Diego Accame of San Francisco CA (US) for google llc, Abraham Lee of Belmont CA (US) for google llc, Yujie Wan of Mountain View CA (US) for google llc, Shriya Raghunathan of Redwood City CA (US) for google llc, Raymond Carino of San Francisco CA (US) for google llc, Feng Ji of Burlingame CA (US) for google llc, Shashwat Lal Das of San Francisco CA (US) for google llc, Nickolas Westman of San Jose CA (US) for google llc
IPC Code(s): G06F9/451, G06F9/445, G06F9/455, G10L15/22
Abstract: some implementations are directed to adapting a client application on a feature phone based on experiment parameters. some of those implementations are directed to adapting an assistant client application, where the assistant client application interacts with remote assistant component(s) to provide automated assistant functionalities via the assistant client application of the feature phone. some implementations are additionally or alternatively directed to determining whether an invocation, of an assistant client application on a feature phone, is a request for transcription of voice data received in conjunction with the invocation, or is instead a request for an assistant response that is responsive to the transcription of the voice data (e.g., includes assistant content that is based on and in addition to the transcription, and that optionally lacks the transcription itself).
Inventor(s): Yu Wang of San Jose CA (US) for google llc, Thomas Benjamin Jablin of Saratoga CA (US) for google llc, Caitlin King Stanton of San Francisco CA (US) for google llc
IPC Code(s): G06F9/48
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling workloads on computing resources using a high priority queue and a low priority queue. the high priority queue maintains pending high priority workloads to be scheduled for execution, and the low priority queue maintains pending low priority workloads to be scheduled for execution. the computing system as described in this specification schedules the pending low priority workloads for execution by utilizing computing resources provided by the system only when the high priority queue is empty.
20240118956.Aggregatable Application Programming Interface_simplified_abstract_(google llc)
Inventor(s): Naitian Liu of Sunnyvale CA (US) for google llc
IPC Code(s): G06F9/54, H04L9/40
Abstract: a method for an aggregatable application programming interface (api) includes receiving, from a third party service, an aggregation request requesting aggregation of client data from a client of the third party service. the method also includes receiving, from an api executed by a client device of the client, a first portion of the client data. the method includes storing the first portion of the client data and receiving, from the api, a second portion of the client data. the method includes determining that the second portion of the client data is a final portion of the client data. in response, the method includes aggregating the first portion of the client data with the second portion of the client data. the method also includes transmitting the aggregated client data to the third party service.
20240119047.ANSWER FACTS FROM STRUCTURED CONTENT_simplified_abstract_(google llc)
Inventor(s): Jayant Madhavan of San Francisco CA (US) for google llc, Hongrae Lee of Santa Clara CA (US) for google llc, Sreeram Viswanath Balakrishnan of Los Altos CA (US) for google llc, Warren H.Y. Shen of Sunnyvale CA (US) for google llc
IPC Code(s): G06F16/2452, G06F16/245, G06F16/2457, G06F16/951
Abstract: in one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.
Inventor(s): Philip Wenjie Sun of New York NY (US) for google llc, Ruiqi Guo of Elmhurst NY (US) for google llc, Sanjiv Kumar of Jericho NY (US) for google llc
IPC Code(s): G06F16/2453, G06F16/953
Abstract: the disclosure is directed towards automatically tuning quantization-based approximate nearest neighbors (ann) search methods and systems (e.g., search engines) to perform at the speed-recall pareto frontier. with a desired search cost or recall as input, the embodiments employ lagrangian-based methods to perform constrained optimization on theoretically-grounded search cost and recall models. the resulting tunings, when paired with the efficient quantization-based ann implementation of the embodiments, exhibit excellent performance on standard benchmarks while requiring minimal tuning or configuration complexity.
Inventor(s): Emily Burd of New York NY (US) for google llc, Akshat Sharma of Cambridge MA (US) for google llc
IPC Code(s): G06F16/332, G06N20/00, G10L15/06, G10L15/26, H04L12/18, H04M3/56
Abstract: data indicating one or more verbal phrases provided by one or more participants during a conference call is fed as input to a machine learning model. one or more outputs of the machine learning model are obtained. a polling question for polling at least a portion of the participants is extracted from the one or more outputs of the machine learning model. the polling question is based on one or more verbal phrases provided by the one or more participants. the polling question is provided for polling the at least the portion of the participants during the conference call.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G06F16/432, G06F3/16, G06F40/30, G10L15/22
Abstract: implementations described herein relate to receiving user input directed to an automated assistant, processing the user input to determine whether data from a server and/or third-party application is needed to perform certain fulfillment of an assistant command included in the user input, and generating a prompt that requests a user consent to transmitting of a request to the server and/or the third-party application to obtain the data needed to perform the certain fulfillment. in implementations where the user consents, the data can be obtained and utilized to perform the certain fulfillment. in implementations where the user does not consent, client data can be generated locally at a client device and utilized to perform alternate fulfillment of the assistant command. in various implementations, the request transmitted to the server and/or third-party application can be modified based on ambient noise captured when the user input is received.
20240119086.MEDIA COMSUMPTION HISTORY_simplified_abstract_(google llc)
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc
IPC Code(s): G06F16/487, G06F16/245, G06F16/2455, G06F16/2457, G06F16/432, G06F16/435, G06F16/48, G06F16/683, G06F16/783, G06F16/9535, G06F16/955, G06Q30/02, G06Q30/0601
Abstract: methods, systems, and apparatus for receiving, from a user, a request that includes an entity identifier associated with an entity that is referenced by one or more query terms of a search query, determining that the entity is identified in a media consumption database as a media item that has been indicated as consumed by the user or that the entity is associated with a media item that is identified in the media consumption database as a media item that has been indicated as consumed by the user, and based on the determination, providing a response to the request, the response including data indicating that the entity is a media item that has been indicated as consumed by the user or that the entity is associated with a media item that has been indicated as consumed by the user.
20240119088.Handling Contradictory Queries on a Shared Device_simplified_abstract_(google llc)
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G06F16/632, G06F16/638, G10L17/02, G10L17/06, G10L17/22
Abstract: a method for handling contradictory queries on a shared device includes receiving a first query issued by a first user, the first query specifying a first long-standing operation for a digital assistant to perform, and while the digital assistant is performing the first long-standing operation, receiving a second query, the second query specifying a second long-standing operation for the digital assistant to perform. the method also includes determining that the second query was issued by another user different than the first user and determining, using a query resolver, that performing the second long-standing operation would conflict with the first long-standing operation. the method further includes identifying one or more compromise operations for the digital assistant to perform, and instructing the digital assistant to perform a selected compromise operation among the identified one or more compromise operations.
Inventor(s): Michael Jeffrey Procopio of Boulder CO (US) for google llc, Sarmad Hashmi of San Jose CA (US) for google llc
IPC Code(s): G06F40/174, G06F9/451, G06F21/31, H04L51/42
Abstract: a method for using a user-fillable form in a host container includes receiving, at a host container, a user-fillable form bound to dynamic data from an underlying data source where the user-fillable form has a data structure generated by prepopulated coding. the method further includes translating the user-fillable form into a hostable format for the host container. the method also includes rendering, using the hostable format for the host container, the user-fillable form in a user interface. the method further includes receiving, at the user interface of the host container, from a user of the host container, a data entry for input to the user-fillable form and updating, by the host container, the dynamic data from the underlying data source by persisting data from the data entry in a data store associated with the underlying data source.
20240119224.TABLE CELL SPLITTING IN AN ONLINE DOCUMENT EDITOR_simplified_abstract_(google llc)
Inventor(s): Tomer Aberbach of Hoboken NJ (US) for google llc, Gregory George Galante of Little Silver NJ (US) for google llc
IPC Code(s): G06F40/177
Abstract: techniques are described herein for table cell splitting in an online document editor. a method includes: responsive to a request to split a cell in a table, determining a target number of rows and a target number of columns, automatically inserting rows adjacent to rows of the cell to reach the target number of rows, automatically inserting columns adjacent to columns of the cell to reach the target number of columns, and automatically merging groups of cells within an initial boundary of the cell, each group spanning a determined number of rows per group and a determined number of columns per group.
20240119256.Highly Efficient Convolutional Neural Networks_simplified_abstract_(google llc)
Inventor(s): Andrew Gerald Howard of Culver City CA (US) for google llc, Mark Sandler of Mountain View CA (US) for google llc, Liang-Chieh Chen of Los Angeles CA (US) for google llc, Andrey Zhmoginov of Mountain View CA (US) for google llc, Menglong Zhu of Playa Vista CA (US) for google llc
IPC Code(s): G06N3/04, G06N3/045, G06N3/08
Abstract: the present disclosure provides directed to new, more efficient neural network architectures. as one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. as another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. for example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. a residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.
Inventor(s): Sercan Omer Arik of San Francisco CA (US) for google llc, Yihe Dong of New York NY (US) for google llc, Qi Yu of San Diego CA (US) for google llc, Rui Wang of Mountain View CA (US) for google llc
IPC Code(s): G06N3/0455, G06N3/08
Abstract: aspects of the disclosure provide a deep sequence model, referred to as koopman neural forecaster (knf), for time series forecasting. knf leverages deep neural networks (dnns) to learn the linear koopman space and the coefficients of chosen measurement functions. knf imposes appropriate inductive biases for improved robustness against distributional shifts, employing both a global operator to learn shared characteristics, and a local operator to capture changing dynamics, as well as a specially-designed feedback loop to continuously update the learnt operators over time for rapidly varying behaviors. knf achieves superior performance on multiple time series datasets that are shown to suffer from distribution shifts.
20240119286.ADAPTIVE ARTIFICIAL NEURAL NETWORK SELECTION TECHNIQUES_simplified_abstract_(google llc)
Inventor(s): Matthew SHARIFI of Kilchberg (CH) for google llc, Jakob Nicolaus FOERSTER of Zurich (CH) for google llc
IPC Code(s): G06N3/08, G06F9/50, G06N3/045, H04L67/01
Abstract: computer-implemented techniques can include obtaining, by a client computing device, a digital media item and a request for a processing task on the digital item and determining a set of operating parameters based on (i) available computing resources at the client computing device and (ii) a condition of a network. based on the set of operating parameters, the client computing device or a server computing device can select one of a plurality of artificial neural networks (anns), each ann defining which portions of the processing task are to be performed by the client and server computing devices. the client and server computing devices can coordinate processing of the processing task according to the selected ann. the client computing device can also obtain final processing results corresponding to a final evaluation of the processing task and generate an output based on the final processing results.
20240119295.Generalized Bags for Learning from Label Proportions_simplified_abstract_(google llc)
Inventor(s): Rishi Saket of Bangalore, Karnataka (IN) for google llc, Aravindan Raghuveer of Bangalore, Karnataka (IN) for google llc, Balaraman Ravindran of Chennai, Tamil Nadu (IN) for google llc
IPC Code(s): G06N3/09
Abstract: example aspects of the present disclosure relate to an example method. the example method includes obtaining, by a computing system comprising one or more processors, a plurality of data bags. in the example method, each respective data bag of the plurality of data bags comprises a respective plurality of instances and is respectively associated with one or more proportion labels. the example method also includes generating, by the computing system, a plurality of training bags from the plurality of data bags according to a plurality of weights. in the example method, the training bags are generated such that a bag-level predicted proportion label error by a machine-learned prediction model over the plurality of training bags correlates to an instance-level predicted proportion label error by the machine-learned prediction model.
Inventor(s): Hong-You Chen of Hilliard OH (US) for google llc, Boqing Gong of Bellevue WA (US) for google llc, Mingda Zhang of Pittsburgh PA (US) for google llc, Hang Qi of Mountain View CA (US) for google llc, Xuhui Jia of Seattle WA (US) for google llc, Li Zhang of Seattle WA (US) for google llc
IPC Code(s): G06N3/098
Abstract: the embodiments are directed towards providing personalized federated learning (pfl) models via sharable federated basis models. a model architecture and learning algorithm for pfl models is disclosed. the embodiments learn a set of basis models, which can be combined layer by layer to form a personalized model for each client using specifically learned combination coefficients. the set of basis models are shared with each client of a set of the clients. thus, the set of basis models is common to each client of the set of clients. however, each client may generate a unique pfl based on their specifically learned combination coefficients. the unique combination of coefficients for each client may be encoded in a separate personalized vector for each of the clients.
20240119326.Multi-State Qubit Readout with Permutation Sequences_simplified_abstract_(google llc)
Inventor(s): Kevin Joseph Satzinger of Goleta CA (US) for google llc, Julian Shaw Kelly of Santa Barbara CA (US) for google llc, Paul Victor Klimov of Santa Barbara CA (US) for google llc, Alexander Nikolaevich Korotkov of Riverside CA (US) for google llc
IPC Code(s): G06N10/00, B82Y10/00, G06F15/16
Abstract: systems and methods for measuring quantum states of qubits with more than two levels are provided. a method can include, for a plurality of shuffling sequences, applying, by a quantum computer, one or more quantum gates to the one or more qubits to execute a quantum algorithm; applying, by the quantum computer, a shuffling sequence to the one or more qubits; and measuring, using a readout apparatus, the state of the one or more qubits to determine a readout state. the method can further include determining, by a classical computer or the quantum computer, an average occupation for one or more of the quantum states of the one or more qubits using the readout states for each of the shuffling sequences. the readout states can correspond to a state in a subset of the quantum states of the one or more qubits.
Inventor(s): Matthew Jones of Mountain View CA (US) for google llc, Michael Curtis Mozer of Mountain View CA (US) for google llc
IPC Code(s): G06N20/00
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for online training of machine learning models predicting time-series data. in one aspect, a method comprises training a machine learning model having a plurality of weights by maintaining weight data, specifying a plurality of sub-weights for each of the plurality of weights and covariance data that estimates the joint uncertainty between the sub-weights, and, at each of a plurality of time steps, receiving model inputs, processing the model inputs using the weight data to generate corresponding model outputs, receiving corresponding ground truth outputs, and updating the weight data using the corresponding ground truth outputs.
Inventor(s): Ramprasad Sedouram of Bangalore (IN) for google llc
IPC Code(s): G06Q10/10, G06F3/14, G06F9/451, G06T11/00, G06V20/20
Abstract: implementations relate to an automated assistant that provides augmented reality content, via a display interface of computerized glasses, resulting from post-processing of application content. the application content can be identified based on prior interactions between a user and one or more applications, and the application content can be processed to determine objects, and/or object classifications, that may be associated with the application content. when the user is wearing the computerized glasses, and the object is detected within a field of view of the computerized glasses, the automated assistant can cause certain content to be rendered at the display interface of the computerized glasses. in some implementations, the content can be generated to supplement, and/or be different from, existing content that the user may have already accessed, in furtherance of preventing duplicative usage of applications and/or preserving computational resources.
20240119515.MATCHING CONTENT PROVIDERS AND INTERESTED CONTENT USERS_simplified_abstract_(google llc)
Inventor(s): Adrian Dumitru Corduneanu of Palo Alto CA (US) for google llc, Eyal Manor of Plainview NY (US) for google llc, Scott Spencer of New York NY (US) for google llc, Joerg Heilig of Los Altos CA (US) for google llc
IPC Code(s): G06Q30/08, G06Q30/02, G06Q30/0241, G06Q30/0242, G06Q30/0273
Abstract: methods, systems, and apparatuses to match content providers and interested content users are described. input indicating an accessing of a network location by a user is received along with the user's identifier. the identifier is obfuscated and transmitted to a content provider configured to provide content to the user at the network location. a re-direct identifier is transmitted to the user instructing the user to directly contact the content provider. when the user contacts the content provider, the user transmits a provider-specific identifier by which the content provider identifies the user and the obfuscated user identifier. the content provider updates a database of obfuscated user identifiers and provider-specific user identifiers based on the received identifiers. thus, the content provider is enabled to identify interested users based on obfuscated and provider-specific user identifiers.
20240119555.Multi-scale Transformer for Image Analysis_simplified_abstract_(google llc)
Inventor(s): Junjie Ke of East Palo Alto CA (US) for google llc, Feng Yang of Sunnyvale CA (US) for google llc, Qifei Wang of Mountain View CA (US) for google llc, Yilin Wang of Sunnyvale CA (US) for google llc, Peyman Milanfar of Menlo Park CA (US) for google llc
IPC Code(s): G06T3/00, G06T3/40, G06T7/00
Abstract: the technology employs a patch-based multi-scale transformer () that is usable with various imaging applications. this avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. a native resolution image () is transformed into a multi-scale representation (), enabling the transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. spatial embedding () is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. a separate scale embedding () is employed to distinguish patches coming from different scales in the multiscale representation. self-attention () is performed to create a final image representation. in some instances, prior to performing self-attention, the system may prepend a learnable classification token () to the set of input tokens.
Inventor(s): Vivek Natarajan of Mountain View CA (US) for google llc, Yuan Liu of Mountain View CA (US) for google llc, David Coz of Mountain View CA (US) for google llc, Amirata Ghorbani of Mountain View CA (US) for google llc
IPC Code(s): G06T7/00, G06T11/00, G16H10/60, G16H50/70
Abstract: we disclose the generation and training of generative adversarial networks (gan) to synthesize clinical images with skin conditions. synthetic images for a pre-specified skin condition are generated, while being able to vary its size, location and the underlying skin color. we demonstrate that the generated images are of high fidelity using objective gan evaluation metrics. the synthetic images are not only visually similar to real images, but also embody the respective skin conditions. additionally, synthetic skin images can be used as a data augmentation technique for training a skin condition classifier, and improve the ability of the classifier to detect rare but malignant conditions.
Inventor(s): Daniel Christopher Duckworth of Berlin (DE) for google llc, Suhani Deepak-Ranu Vora of San Mateo CA (US) for google llc, Noha Radwan of Zurich (CH) for google llc, Klaus Greff of Berlin (DE) for google llc, Henning Meyer of Berlin (DE) for google llc, Kyle Adam Genova of San Mateo CA (US) for google llc, Seyed Mohammad Mehdi Sajjadi of Berlin (DE) for google llc, Etienne François Régis Pot of Berlin (DE) for google llc, Andrea Tagliasacchi of Victoria (CA) for google llc
IPC Code(s): G06V10/26, G06T7/143, G06T15/08
Abstract: example embodiments of the present disclosure provide an example computer-implemented method for constructing a three-dimensional semantic segmentation of a scene from two-dimensional inputs. the example method includes obtaining, by a computing system comprising one or more processors, an image set comprising one or more views of a subject scene. the example method includes generating, by the computing system and based at least in part on the image set, a scene representation describing the subject scene in three dimensions. the example method includes generating, by the computing system and using a machine-learned semantic segmentation model framework, a multidimensional field of probability distributions over semantic categories, the multidimensional field defined over the three dimensions of the subject scene. the example method includes outputting, by the computing system, classification data for at least one location in the subject scene.
Inventor(s): Anthony J. Piergiovanni of Denver CO (US) for google llc, Maxwell Mbabilla Aladago of Hanover NH (US) for google llc
IPC Code(s): G06V10/80, G06V10/774, G06V30/19
Abstract: provided is an approach that aligns multi-modal tokens using cross-attention without losing the advantages of global self-attention. in contrast to previous works that concatenate the unimodal tokens along the sequence dimension, example approaches described herein align per-modality tokens by chaining them along the channels. specifically, the tokens from one modality can be used to query the other modality and the output can be concatenated with the query tokens on the channels. an analogous process can also be repeated (or performed in parallel) where the roles of the two modalities are switched. the resulting sets of compound tokens can be concatenated and fed into a self-attention encoder such as a transformer encoder that performs self-attention.
Inventor(s): Scott Davies of Santa Monica CA (US) for google llc, Ruxandra Davies of Santa Monica CA (US) for google llc
IPC Code(s): G10L15/22, G06F3/16
Abstract: implementations set forth herein (elate to an automated assistant capable of bypassing soliciting a user for supplemental data for completing an action when a previously-queried application is capable of providing the supplemental data. for instance, when a user invokes the automated assistant to complete a first action with a first application, the user may provide many pertinent details. those details may be useful to a second application that the user may subsequently invoke via the automated assistant for completing a second action. in order to save the user from having to repeat the details to the automated assistant, the automated assistant can interact with the first application in order to obtain any information that may be essential for the second application to complete the second action. the automated assistant can then provide the information to the second application, without soliciting the user for the information.
20240119936.LOCATION-BASED RESPONSES TO TELEPHONE REQUESTS_simplified_abstract_(google llc)
Inventor(s): Gudmundur HAFSTEINSSON of Los Gatos CA (US) for google llc, Michael J. Lebeau of New York NY (US) for google llc, Natalia Marmasse of Ichud (IL) for google llc, Sumit Agarwal of Washington DC (US) for google llc, Dipochand Nishar of Los Altos CA (US) for google llc
IPC Code(s): G10L15/22, G06F3/16, G10L15/26, G10L15/30, H04M1/72403, H04W4/14
Abstract: a method for receiving processed information at a remote device is described. the method includes transmitting from the remote device a verbal request to a first information provider and receiving a digital message from the first information provider in response to the transmitted verbal request. the digital message includes a symbolic representation indicator associated with a symbolic representation of the verbal request and data used to control an application. the method also includes transmitting, using the application, the symbolic representation indicator to a second information provider for generating results to be displayed on the remote device.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zürich (CH) for google llc
IPC Code(s): G10L17/22, G06F16/638
Abstract: a method includes detecting multiple users, receiving a first query issued by a first user, the first query including a command for a digital assistant to perform a first action, and enabling a round robin mode to control performance of actions commanded by queries. the method also includes, while performing the first action, receiving audio data corresponding to a second query including a command to perform a second action, performing speaker identification on the audio data, determining that the second query was spoken by the first user, preventing performing the second action, and prompting at least another user to issue a query. the method further includes receiving a third query issued by a second user, the third query including a command for the digital assistant to perform a third action, and when the digital assistant completes performing the first action, executing performance of the third action.
Inventor(s): Anshul Kothari of Cupertino CA (US) for google llc, Gaurav Bhaya of Sunnyvale CA (US) for google llc, Tarun Jain of Los Altos CA (US) for google llc
IPC Code(s): G10L25/60, G06N20/00, G10L25/03, H04L12/28
Abstract: coordinating signal processing among computing devices in a voice-driven computing environment is provided. a first and second digital assistant can detect an input audio signal, perform a signal quality check, and provide indications that the first and second digital assistants are operational to process the input audio signal. a system can select the first digital assistant for further processing. the system can receive, from the first digital assistant, data packets including a command. the system can generate, for a network connected device selected from a plurality of network connected devices, an action data structure based on the data packets, and transmit the action data structure to the selected network connected device.
20240120446.LIGHT-EMITTING DIODES WITH INTEGRATED OPTICAL ELEMENTS_simplified_abstract_(google llc)
Inventor(s): Benjamin Leung of Sunnyvale CA (US) for google llc, Miao-Chan Tsai of Sunnyvale CA (US) for google llc, Sheila Hurtt of Palo Alto CA (US) for google llc, Gang He of Fremont CA (US) for google llc, Richard Peter Schneider, JR. of Sunnyvale CA (US) for google llc
IPC Code(s): H01L33/32, G02B3/04, G02B27/30, H01L33/00, H01L33/18, H01L33/60
Abstract: the disclosure describes various aspects of using optical elements monolithically integrated with light-emitting diode (led) structures. in an aspect, a light emitting device includes a single led structure having an active region and a single optical element disposed on the led structure and configured to collimate and steer light emitted by the led structure. one or more additional optical elements may also be disposed on the led structure. in another aspect, a light emitting device may include multiple led structures and a single optical element disposed on the multiple led structures and configured to collimate and steer light emitted by the multiple led structures. for each of these aspects, the led structure(s) and the optical element(s) are made of a material that includes gan, the led structure(s) has a corresponding active region, and the led structure(s) has a corresponding reflective contact disposed opposite to the optical element(s).
Inventor(s): Shuai Jiang of San Jose CA (US) for google llc, Xin Li of Cupertino CA (US) for google llc, Woon-Seong Kwon of Santa Clara CA (US) for google llc, Cheng Chung Yang of New Taipei City (TW) for google llc, Qiong Wang of Palo Alto CA (US) for google llc, Nam Hoon Kim of San Jose CA (US) for google llc, Mikhail Popovich of Danville CA (US) for google llc, Houle Gan of Santa Clara CA (US) for google llc, Chenhao Nan of Santa Clara CA (US) for google llc
IPC Code(s): H02M3/335, H02M1/00
Abstract: a voltage regulator having a multiple of main stages and at least one accelerated voltage regulator (avr) bridge is provided. the main stages may respond to low frequency current transients and provide dc output voltage regulation. the avr bridges are switched much faster than the main stages and respond to high frequency current transients without regulating the dc output voltage. the avr bridge frequency response range can overlap with the main stage frequency response range, and the lowest frequency to which the avr bridges respond may be set lower than the highest frequency to which the main stages respond.
Inventor(s): Daniel Barros of Sra da Hora (PT) for google llc, Sunil Kumar of Cupertino CA (US) for google llc
IPC Code(s): H04L5/00, H04W76/15
Abstract: various arrangements for short-range wireless communication are presented herein. an earbud of a pair of true wireless earbuds can receive an audio packet addressed to the other earbud of the pair. a single connected isochronous stream (cis) within a connected isochronous group (cig) may be present between the pair of true wireless earbuds and an audio source which transmitted the audio packet. the earbud can transmit a cross-acknowledgement indicating receipt of the audio packet to the other earbud. the earbud can also transmit audio data from the audio packet to the other earbud after the cross acknowledgement.
Inventor(s): Ramprasad Sedouram of Bangalore (IN) for google llc, Daniel V. Klein of Pittsburgh PA (US) for google llc
IPC Code(s): H04L9/40, H04L67/306, H04L67/52
Abstract: implementations relate to an automated assistant that can proactively detect and respond to a request for credentials. characteristics of an entity requesting the credentials can be preemptively determined by the automated assistant using data that may be provided by the user or other previous visitors to a location. for example, the automated assistant can determine that the entity may expressly request certain information from a user when the user arrives at the location. based on this determination, the automated assistant can operate to initialize an interface of a computing device of the user, when the user is determined to be at or near the location. for example, an audio interface of the computing device can be initialized to capture an audible request from a person who views credentials before granting access to a feature of the location.
20240121320.High Performance Connection Scheduler_simplified_abstract_(google llc)
Inventor(s): Abhishek Agarwal of Santa Clara CA (US) for google llc, Weihuang Wang of Los Gatos CA (US) for google llc, Weiwei Jiang of Santa Clara CA (US) for google llc, Srinivas Vaduvatha of San Jose CA (US) for google llc, Jiazhen Zheng of Santa Clara CA (US) for google llc
IPC Code(s): H04L67/61, H04L67/55
Abstract: aspects of the disclosure are directed to a high performance connection scheduler for reliable transport protocols in data center networking. the connection scheduler can handle enqueue events, dequeue events, and update events. the connection scheduler can include a connection queue, scheduling queue, and quality of service arbiter to support scheduling a large number of connections at a high rate.
Inventor(s): Michael J. Lombardi of South Barrington IL (US) for google llc, Joe Allore of Mundelein IL (US) for google llc
IPC Code(s): H04M1/02
Abstract: a foldable computing device may comprise a top housing assembly, a bottom housing assembly, and a flexible electrical inter-assembly coupling circuit. the top housing assembly may house a first subset of electrical component. the bottom housing assembly is mechanically coupled to the top housing assembly such that the top housing assembly is operable to cover, when closed, at least a portion of the bottom housing assembly. the bottom housing assembly may also house a second subset of the electrical components. the flexible electrical inter-assembly coupling circuit may electrically couple the first subset of the electrical components and the second subset of the electrical components. the flexible electrical intercoupling circuit configured may remain flat when the top housing assembly is open relative to the bottom housing assembly and flex when the top housing assembly is at least partially closed relative to the bottom housing assembly.
Inventor(s): Daniel Barros of Sra da Hora (PT) for google llc, Sunil Kumar of Cupertino CA (US) for google llc
IPC Code(s): H04R1/10
Abstract: various arrangements for short-range wireless communication between audio output devices, such as true wireless earbuds, are presented herein. a first earbud of a pair of earbuds may determine that a first audio packet addressed to the first earbud from an audio source was not properly received. however, a second earbud of the pair of earbuds may properly receive the first audio packet addressed to the first earbud. the second earbud can then, directly to the first earbud, transmit a cross acknowledgement indicating that the second earbud properly received the audio packet.
20240121550.EARBUD-TO-EARBUD COMMUNICATION RELAY_simplified_abstract_(google llc)
Inventor(s): Sunil Kumar of Cupertino CA (US) for google llc, Daniel Barros of Sra da Hora (PT) for google llc
IPC Code(s): H04R1/10
Abstract: various arrangements of wireless earbuds are presented. a first earbud, can include a first speaker, a first processing system, and a first wireless communication interface, that communicates with an audio source device using bluetooth communications. a second earbud can include a second speaker, a second processing system, and a second wireless communication interface, that communicates with the audio source device and the first earbud using bluetooth communications. the first earbud and the second earbud may be configured to wirelessly communicate with each other following completion of a first connected isochronous stream (cis) event for the first earbud and second cis event for the second earbud within a connected isochronous group (cig) event.
Inventor(s): Yingshi Tang of Danville CA (US) for google llc, Yingying Wang of Sunnyvale CA (US) for google llc, Padam Jain of San Jose CA (US) for google llc, Emad Samadiani of Cypress CA (US) for google llc, Sudharshan Sugavanesh Udhayakumar of San Jose CA (US) for google llc, Madhusudan K. Iyengar of Foster City CA (US) for google llc
IPC Code(s): H05K13/04, H05K1/02, H05K7/20
Abstract: methods and structures for providing thermal dissipating elements on integrated circuit (“ic”) dies are disclosed. a thermal dissipating element placement assembly, such as a pin fin placement assembly, along with a vacuum pickup assembly, can be used to assist with simultaneous placement of multiple pin fins with desired profiles on desired locations of the ic die. the pin fin placement assembly may be comprised of one or more plates with a plurality of apertures therein for receiving the pin fins. the pin fin placement assembly can be further incorporated into a thermal cooling structure, which can include a manifold configured to encase the ic die and attached pin fins.
- GOOGLE LLC
- G01S5/02
- Google llc
- F21V8/00
- G02B27/01
- G05B13/02
- B25J9/16
- B25J19/02
- G06F1/329
- G06F1/3209
- G06F1/3296
- G06F9/48
- G06F3/042
- G06F8/41
- G06F9/451
- G06F9/445
- G06F9/455
- G10L15/22
- G06F9/54
- H04L9/40
- G06F16/2452
- G06F16/245
- G06F16/2457
- G06F16/951
- G06F16/2453
- G06F16/953
- G06F16/332
- G06N20/00
- G10L15/06
- G10L15/26
- H04L12/18
- H04M3/56
- G06F16/432
- G06F3/16
- G06F40/30
- G06F16/487
- G06F16/2455
- G06F16/435
- G06F16/48
- G06F16/683
- G06F16/783
- G06F16/9535
- G06F16/955
- G06Q30/02
- G06Q30/0601
- G06F16/632
- G06F16/638
- G10L17/02
- G10L17/06
- G10L17/22
- G06F40/174
- G06F21/31
- H04L51/42
- G06F40/177
- G06N3/04
- G06N3/045
- G06N3/08
- G06N3/0455
- G06F9/50
- H04L67/01
- G06N3/09
- G06N3/098
- G06N10/00
- B82Y10/00
- G06F15/16
- G06Q10/10
- G06F3/14
- G06T11/00
- G06V20/20
- G06Q30/08
- G06Q30/0241
- G06Q30/0242
- G06Q30/0273
- G06T3/00
- G06T3/40
- G06T7/00
- G16H10/60
- G16H50/70
- G06V10/26
- G06T7/143
- G06T15/08
- G06V10/80
- G06V10/774
- G06V30/19
- G10L15/30
- H04M1/72403
- H04W4/14
- G10L25/60
- G10L25/03
- H04L12/28
- H01L33/32
- G02B3/04
- G02B27/30
- H01L33/00
- H01L33/18
- H01L33/60
- H02M3/335
- H02M1/00
- H04L5/00
- H04W76/15
- H04L67/306
- H04L67/52
- H04L67/61
- H04L67/55
- H04M1/02
- H04R1/10
- H05K13/04
- H05K1/02
- H05K7/20
