GOOGLE LLC patent applications on August 1st, 2024
Patent Applications by GOOGLE LLC on August 1st, 2024
GOOGLE LLC: 34 patent applications
GOOGLE LLC has applied for patents in the areas of G06N3/08 (4), G06V10/82 (4), G06N20/00 (3), G06V10/44 (3), G06F8/41 (2) G06N20/00 (3), G06N3/08 (3), G06V10/82 (2), B25J9/163 (1), G06N3/0455 (1)
With keywords such as: network, device, user, based, training, output, data, layer, content, and example in patent application abstracts.
Patent Applications by GOOGLE LLC
Inventor(s): Matthew Bennice of San Jose CA (US) for google llc, Paul Bechard of Ogdensburg NY (US) for google llc, Joséphine Simon of San Francisco CA (US) for google llc, Jiayi Lin of Sunnyvale CA (US) for google llc
IPC Code(s): B25J9/16
CPC Code(s): B25J9/163
Abstract: implementations are provided for training a robot control policy for controlling a robot. during a first training phase, the robot control policy is trained using a first set of training data that includes (i) training data generated based on simulated operation of the robot in a first fidelity simulation, and (ii) training data generated based on simulated operation of the robot in a second fidelity simulation, wherein the second fidelity is greater than the first fidelity. when one or more criteria for commencing a second training phase are satisfied, the robot control policy is further trained using a second set of training data that also include training data generate based on simulated operation of the robot in the first and second fidelity simulations, which has a ratio therebetween lower than that in the first set of training data.
20240253253. Sensorized Robotic Gripping Device_simplified_abstract_(google llc)
Inventor(s): Jeffrey Bingham of Sunnyvale CA (US) for google llc, Taylor Alexander of Mountain View CA (US) for google llc, Bianca Homberg of Mountain View CA (US) for google llc, Joseph DelPreto of Los Altos CA (US) for google llc, Alex Shafer of San Francisco CA (US) for google llc
IPC Code(s): B25J19/02, B25J9/10, B25J13/08, B25J15/00, B25J15/02, B25J15/12
CPC Code(s): B25J19/023
Abstract: a robotic gripping device is provided. the robotic gripping device includes a palm and a plurality of digits coupled to the palm. the robotic gripping device also includes a time-of-flight sensor arranged on the palm such that the time-of-flight sensor is configured to generate time-of-flight distance data in a direction between the plurality of digits. the robotic gripping device additionally includes an infrared camera, including an infrared illumination source, where the infrared camera is arranged on the palm such that the infrared camera is configured to generate grayscale image data in the direction between the plurality of digits.
20240255294. Identifying And Displaying Smooth And Demarked Paths_simplified_abstract_(google llc)
Inventor(s): Stephen Charles Hsu of San Carlos CA (US) for google llc
IPC Code(s): G01C21/34, G01C21/36, G06F16/29, G06F16/9537
CPC Code(s): G01C21/3446
Abstract: described is a computer-implemented method which comprises receiving a plurality of images captured by at least one user device, wherein each image is associated with one of a corresponding plurality of geographic locations; determining a path between the plurality of geographic locations; determining a confidence indicator representative of whether the determined path corresponds to a demarked path, wherein determining the confidence indicator comprises determining a time of capture of each of the plurality of images; identifying the path as corresponding to a demarked route, based on the confidence indicator; and marking the plurality of images for display as a demarked route.
Inventor(s): Alex Faaborg of Mountain View CA (US) for google llc
IPC Code(s): G01C21/36, G01S19/13
CPC Code(s): G01C21/3605
Abstract: a request for directions for traveling to a destination is received via a user interface of a user device, where a mode of transport is not selected via the user interface. a current geographic context of the user device is determined, which includes determining proximity of the starting point and/or the destination to public transport, and suggested mode of transport for travelling to the destination is determined based on the current geographic context. directions for travelling to the destination using the suggested mode of transport are obtained and provided via the user interface of the user device.
Inventor(s): Xuelin Huang of Mountain View CA (US) for google llc, Shumin Zhai of Los Altos CA (US) for google llc
IPC Code(s): G06F3/01, G06F1/16, G06F3/0346, G06F3/04817, G06F3/0482, G06F3/04883, G06F3/04886, G06F3/16
CPC Code(s): G06F3/017
Abstract: an example method includes identifying, by a mobile computing device that includes a housing and a presence-sensitive display, and based on a first group of sensor signals provided at least by an inertial measurement unit included in one or more sensors, at least one first gesture that is performed at portions of the housing, wherein the one or more portions are separate from the display, initiating an interaction mode, outputting at least one visual or audio indicator for the interaction mode that is associated with a particular function of the mobile computing device, identifying, based on a third group of sensor signals provided by the one or more sensors, at least one second gesture that is performed at the one or more portions of the housing to confirm a user selection of the particular function, and, responsive to identifying the at least one second gesture, performing the particular function.
20240256235. SYNTACTICALLY COHERENT CODE SEGMENTATION_simplified_abstract_(google llc)
Inventor(s): Navneet Potti of Sunnyvale CA (US) for google llc, Joshua Howland of Mountain View CA (US) for google llc
IPC Code(s): G06F8/41
CPC Code(s): G06F8/433
Abstract: techniques are described herein for segmenting source code into syntactically coherent sequences of tokens that satisfy constraints inherent in sequence-to-sequence networks. in various implementations, source code may be processed to generate one or more graphs representing the source code. one or more of the graphs may then be traversed to identify one or more sequences of tokens within the source code that satisfy an input constraint of a sequence-to-sequence network. the source code may be segmented into the identified one or more sequences of tokens. the one or more sequences of tokens may then be processed using the sequence-to-sequence network.
Inventor(s): John Navil Joseph of Kirkland WA (US) for google llc, Jack Liu of Saratoga CA (US) for google llc, Dong Hyuk Woo of San Jose CA (US) for google llc, Jing Pu of Santa Clara CA (US) for google llc
IPC Code(s): G06F8/41, G06F9/451
CPC Code(s): G06F8/451
Abstract: this disclosure describes a system and method for compiling and executing machine learning inferences in an array of multi-core computing devices. each multi-core computing device can be an application specific integrated circuit (asic) or group of asics. in many applications, the array of computing devices changes from inference to inference, and can be adjusted based on the requirements of the inference. additionally, each asic can have multiple processing cores, and multiple types of processing cores. therefore, performing optimizations and scheduling at compile time, can dramatically increase the efficiency of the array in executing the inference. in some implementations, it is possible to select an amount of time or effort to be spent optimizing during compiling, giving the user flexibility in determining whether to spend time during compilation or during execution.
Inventor(s): Sylvanus Garnet Bent, III of Palo Alto CA (US) for google llc, Xiaolan Zhou of Santa Clara CA (US) for google llc, Mehmet Levent Koc of Redwood City CA (US) for google llc, Wei Luo of Jersey City NJ (US) for google llc
IPC Code(s): G06F9/451, G06F40/166
CPC Code(s): G06F9/453
Abstract: example embodiments of the present disclosure provide for an example method. the example method includes generating an initial user interface including a content assistant component. the example method include obtaining user input data. the example method includes processing, by a machine learned model interfacing with the content assistant component, the data indicative of the input received from the user. the method includes obtaining output data, from the machine learned model interfacing with the content assistant component, indicative of one or more content item components. the method includes transmitting data which causes the content item components to be provided for display via an updated user interface. the method includes obtaining data indicative of user selection of approval of the content item components. the method includes generating, in response to obtaining the data indicative of the user selection of the approval of the content item components, content items.
Inventor(s): Yong Wang of San Jose CA (US) for google llc, Maxime Deputter Renaud of Livermore CA (US) for google llc
IPC Code(s): G06F11/14
CPC Code(s): G06F11/1469
Abstract: the disclosed technology comprises a technique and/or mechanism for performing backup/restore and/or dr in cloud computing environments, particularly in environments that make use of k8s. the technique generally includes capturing the create, update, and delete (“cud”) object mutation orders of resources or objects that are proven to be working on a primary site, as well their dependencies, and using those orders and dependencies at a secondary site for restoration.
Inventor(s): Wangqing Yuan of Wilmington MA (US) for google llc, Bryan Christopher Horling of Belmont MA (US) for google llc
IPC Code(s): G06F16/2452, G06F40/30
CPC Code(s): G06F16/24522
Abstract: techniques disclosed herein are directed towards generating structured data output based on processing a natural language user query using a semantic parser model. many implementations include identifying one or more argument spans in the given natural language user query based on comparing an embedding space representation of a candidate argument with an embedding space representation of an example query, where the example query is provided by a developer. various implementations include hotfixing an under-triggering model and/or an over-triggering model based on additional or alternative example queries provided by a developer.
20240256599. RESPONDING TO QUERIES WITH VOICE RECORDINGS_simplified_abstract_(google llc)
Inventor(s): Sowmya Subramanian of San Francisco CA (US) for google llc, Benton Davis DeLoache of Mountain View CA (US) for google llc, Lauren Clark of San Francisco CA (US) for google llc, Rami Banna of Menlo Park CA (US) for google llc, Igor Benko of Sunnyvale CA (US) for google llc
IPC Code(s): G06F16/635, G10L15/22
CPC Code(s): G06F16/635
Abstract: implementations are provided for providing responsive audio recordings to user queries that are prerecorded by human beings, rather than generated automatically using speech synthesis processing. in various implementations, a query provided by a user at an input component of a computing device may be used to search a corpus of voice recordings. from the searching, a plurality of candidate responsive voice recordings may be identified and ranked based on measures of credibility associated with speakers that created the candidate responsive voice recordings. based on the ranking, one or more of the plurality of candidate responsive voice recordings may be provided for presentation to the user at an output component of the same computing device or a different computing device.
Inventor(s): Michael Schaer of Pfaffikon (CH) for google llc, Alexandru Tudor of Uitikon (CH) for google llc, Ori Gershony of Redmond WA (US) for google llc, Fredrik Bergenlid of Zurich (CH) for google llc, Behshad Behzadi of Freienbach (CH) for google llc, Tomislav Grbin of Zurich (CH) for google llc
IPC Code(s): G06F16/9032, G06F3/0482, G06F3/04842, G06F16/25, G06F16/9535, H04L51/046, H04L51/216
CPC Code(s): G06F16/90324
Abstract: providing at least one contextually relevant suggestion to one or more users of an ongoing message exchange thread between the users. the suggestion is provided for presentation to the user(s) via user interface output device(s) of computing device(s) of the user(s). the suggestion indicates a query that can be submitted to an automated assistant to cause the automated assistant to incorporate, into the message exchange thread, content that is responsive to the query. in some implementations, the suggestion is a selectable suggestion and content that is responsive to the query is incorporated into the message exchange thread in response to user interface input that is directed to the selectable suggestion. in some implementations, the suggestion is determined based on one or more messages that have already been communicated between users of the message exchange thread.
20240256626. SPEEDING UP DOCUMENT LOADING_simplified_abstract_(google llc)
Inventor(s): Ramkumar Ramani of Cupertino CA (US) for google llc, Robert J. Ennals of Sunnyvale CA (US) for google llc
IPC Code(s): G06F16/957, G06F40/143
CPC Code(s): G06F16/9574
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speeding up document loading. in some implementations, a resource of a document is requested from a first source, and metadata for the document is requested from a second source that is different from the first source. the requested metadata is received from the second source, and the requested resource is received from the first source. a first representation of the document based on the received metadata is provided for display. after providing the first representation, a second representation of the document that combines portions of the first representation with additional portions of the document is generated, and the second representation is provided for display.
Inventor(s): Noam Shazeer of Palo Alto CA (US) for google llc, Daniel De Freitas Adiwardana of Mountain View CA (US) for google llc
IPC Code(s): G06F40/35, G06F40/20, G06F40/284, G10L13/02
CPC Code(s): G06F40/35
Abstract: the present disclosure is directed to systems and methods that include and/or leverage one or more machine-learned language models that generate intermediate textual analysis (e.g., including usage of structural tools such as apis) in service of contextual text generation. for example, a computing system can obtain a contextual text string that includes one or more contextual text tokens. the computing system can process the contextual text string with the machine-learned language model to generate one or more intermediate text strings that include one or more intermediate text tokens. the computing system can process the one or more intermediate text strings with the machine-learned language model to generate an output text string comprising one or more output text tokens. the one or more intermediate text strings can include textual analysis of the contextual text string that supports the output text string.
Inventor(s): Francois Chollet of Mountain View CA (US) for google llc, Andrew Gerald Howard of Culver City CA (US) for google llc
IPC Code(s): G06N3/045, G06F18/2413, G06N3/0464, G06N3/08, G06V10/44, G06V10/82, G06V40/16
CPC Code(s): G06N3/045
Abstract: a neural network system is configured to receive an input image and to generate a classification output for the input image. the neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.
Inventor(s): Mostafa Dehghani of Amsterdam (NL) for google llc, Josip Djolonga of Zürich (CH) for google llc, Jonathan Heek of Hilversum (NL) for google llc, Basil Mustafa of Zürich (CH) for google llc, Piotr Michal Padlewski of Zürich (CH) for google llc, Justin Morgan Gilmer of Mountain View CA (US) for google llc, Neil Matthew Tinmouth Houlsby of Zürich (CH) for google llc
IPC Code(s): G06N3/0455, G06N3/088
CPC Code(s): G06N3/0455
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing an input through each of a plurality of layers of a neural network to generate an output using a plurality of hardware accelerators. the plurality of layers comprise a fully connected layer having a plurality of parameters arranged in a row dimension and a column dimension. one of the methods comprises: generating a plurality of parameter blocks by partitioning the plurality of parameters along the row dimension and the column dimension; determining a ratio of a number of parameters along the row dimension relative to a number of parameters along the column dimension; and determining whether to use row sharding or column sharding with the plurality of hardware accelerators to calculate an output for the fully connected layer and then calculating the output for the fully connected layer using either row sharding or column sharding.
Inventor(s): Noam M. Shazeer of Palo Alto CA (US) for google llc, Lukasz Mieczyslaw Kaiser of San Francisco CA (US) for google llc, Etienne Pot of Palo Alto CA (US) for google llc, Mohammad Saleh of Santa Clara CA (US) for google llc, Ben David Goodrich of San Francisco CA (US) for google llc, Peter J. Liu of Santa Clara CA (US) for google llc, Ryan Sepassi of Beverly Hills CA (US) for google llc
IPC Code(s): G06N3/08, G06N3/045
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. one of the methods includes, at each of a plurality of generation time steps: generating a combined sequence for the generation time step that includes the input sequence followed by the output tokens that have already been generated as of the generation time step; processing the combined sequence using a self-attention decoder neural network to generate a time step output that defines a score distribution over a set of possible output tokens; and selecting, using the time step output, an output token from the set of possible output tokens as the next output token in the output sequence.
20240256862. NOISE SCHEDULING FOR DIFFUSION NEURAL NETWORKS_simplified_abstract_(google llc)
Inventor(s): Ting Chen of Mountain View CA (US) for google llc
IPC Code(s): G06N3/08, G06N3/048
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a network output using a diffusion neural network and for training a diffusion neural network with a modified noise scheduling strategy.
20240256865. TRAINING NEURAL NETWORKS USING LEARNED OPTIMIZERS_simplified_abstract_(google llc)
Inventor(s): Deepali Jain of Bangalore (IN) for google llc, Krzysztof Marcin Choromanski of Lincroft NJ (US) for google llc, Sumeet Singh of New York NY (US) for google llc, Vikas Sindhwani of Hastings-on-Hudson NY (US) for google llc, Tingnan Zhang of Sunnyvale CA (US) for google llc, Jie Tan of Mountain View CA (US) for google llc, Kumar Avinava Dubey of Palo Alto 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 training neural networks. one of the methods for training a neural network configured to perform a machine learning task includes performing, at each of a plurality of iterations: performing a training step to obtain respective new gradients of a loss function; for each network parameter: generating an optimizer network input; processing the optimizer network input using an optimizer neural network, wherein the processing comprises, for each cell: generating a cell input for the cell; and processing the cell input for the cell to generate a cell output, wherein the processing comprises: obtaining latent embeddings from the cell input; generating the cell output from the hidden state; and determining an update to the hidden state; and generating an optimizer network output defining an update for the network parameter; and applying the update to the network parameter.
20240256873. TRAINING NEURAL NETWORKS BY RESETTING DORMANT NEURONS_simplified_abstract_(google llc)
Inventor(s): Utku Evci of Montreal (CA) for google llc, Pablo Samuel Castro Rivadeneira of Ottawa (CA) for google llc, Ghada AbdElRahman Zaki Nabawy Sokar of Eindhoven (NL) for google llc, Rishabh Agarwal of Montreal (CA) for google llc
IPC Code(s): G06N3/082, G06N3/092
CPC Code(s): G06N3/082
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network and, during the training, resetting neurons that have been classified as being dormant.
Inventor(s): Yi Tay of Singapore (SG) for google llc, Mostafa Dehghani of Amsterdam (NL) for google llc
IPC Code(s): G06N20/00, G06F7/483
CPC Code(s): G06N20/00
Abstract: an example method includes obtaining a pretrained machine-learned model that was initially pretrained using a pretraining dataset and further pretraining the model by generating, using a pretraining objective framework, a plurality of corrupted training examples from one or more training examples obtained from the pretraining dataset. a first set of one or more training examples can be corrupted according to a first set of configuration parameters of the pretraining objective framework. a second set can be corrupted according to a second set of configuration parameters of the pretraining objective framework. the example method includes inputting the plurality of corrupted training examples into model; obtaining from the model, a plurality of outputs respectively generated by model based on the plurality of corrupted training examples; and updating one or more parameters of model based on an evaluation of the plurality of outputs.
Inventor(s): Hyung Won Chung of Mountain View CA (US) for google llc, Barret Zoph of San Francisco CA (US) for google llc, Dengyong Zhou of Redmond WA (US) for google llc, Liam Fedus of Palo Alto CA (US) for google llc, Shayne Longpre of Surrey (CA) for google llc, Le Hou of South Setauket NY (US) for google llc, Yi Tay of Singapore (SG) for google llc, Jason Weng Wei of Mountain View CA (US) for google llc, Siddhartha Brahma of San Jose CA (US) for google llc, Quoc V. Le of Sunnyvale CA (US) for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: an example method for training a machine-learned sequence processing model includes obtaining a plurality of training examples for training the machine-learned sequence processing model. for each respective training example of the plurality of training examples, the example method includes: obtaining a respective query associated with the respective training example; inputting the respective query to the machine-learned sequence processing model; obtaining, from the machine-learned sequence processing model a response to the respective query and a trace of intermediate states from the respective query to the response; evaluating the response using a ground truth response associated with the respective training example; evaluating the trace using a ground truth trace associated with the respective training example; and updating one or more parameters of the machine-learned sequence processing model based on the evaluation of the response and based on the evaluation of the trace.
Inventor(s): Ankush Garg of Sunnyvale CA (US) for google llc, Yichi Zhang of Ithaca NY (US) for google llc, Yuan Cao of Mountain View CA (US) for google llc, Lukasz Lew of Sunnyvale CA (US) for google llc, Orhan Firat of Mountain View CA (US) for google llc, Behrooz Ghorbani of San Francisco CA (US) for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence generation tasks using binarized neural networks. the binarized neural network is an attention neural network configured to perform the task and the attention neural network includes a plurality of attention blocks, with each block including an attention block and a binarized feedforward block.
Inventor(s): Samsudin Kamis of Santa Clara CA (US) for google llc, Chitra Kannan Kashyap of Los Altos CA (US) for google llc, William Frazier Pierpont Grose of Los Angeles CA (US) for google llc, Alex Pan of Mountain View CA (US) for google llc, Yi Yang of Los Angeles CA (US) for google llc, Charlotte Yao of Mountain View CA (US) for google llc, Chunlei Zhu of Shanghai (CN) for google llc, Zaiyue Xue of Shanghai (CN) for google llc, Benjamin Schaeffer of Mountain View CA (US) for google llc
IPC Code(s): G06Q30/0242, G06Q30/0235
CPC Code(s): G06Q30/0244
Abstract: the present disclosure provides techniques for presenting a reward impression. a computing system can receive, from a client device, a request to view the reward impression having a first time slot and a second time slot. the computing system can calculate a first conversion rate associated with a first content item being presented in the first time slot and a second conversion rate associated with a second content item being presented in the second time slot. the computing system can select, using the one or more machine-learned models based on the first conversion rate and the second conversion rate, the first content item and the second content item from a plurality of content items. the computing system can cause the presentation of the first content item in the first time slot and the second content item in the second time slot of the reward impression.
Inventor(s): Weicheng Kuo of Oakland CA (US) for google llc, Tsung-Yi Lin of Sunnyvale CA (US) for google llc, Anelia Angelova of Sunnyvale CA (US) for google llc, Dahun Kim of Guseong-dong (KR) for google llc
IPC Code(s): G06V10/82, G06V10/44, G06V10/774, G06V10/776, G06V20/00
CPC Code(s): G06V10/82
Abstract: an object localization network (oln) can be used to localize object(s) (e.g., known and/or unknown object(s)) in an instance of vision data. various implementations include detecting the localized object(s) based on the localization. many implementations include processing the instance of vision data using the oln to generate a objectness score (e.g., a centerness score) as well as an intersection of union (iou) score for one or more proposed object locations in the instance of vision data. object(s) can be localized in the instance of vision data based on the objectness scores and the iou scores.
Inventor(s): Manoj Kumar Sivaraj of Amsterdam (NL) for google llc, Neil Matthew Tinmouth Houlsby of Zürich (CH) for google llc, Mostafa Dehghani of Amsterdam (NL) for google llc
IPC Code(s): G06V10/82, G06V10/26
CPC Code(s): G06V10/82
Abstract: one example aspect of the present disclosure is directed to a neural network for machine vision. the neural network may include a stem block that includes a set of stem layers. the neural network may additionally include a visual transformer block. the set of stem layers may include a patch layer, a first normalization layer, an embedding layer, and a second normalization layer. the patch layer subdivides an input image into a set of image patches. the first normalization layer generates a set of normalized image patches by performing a first normalization process on each image patch of the set of image patches. the patch layer feeds forward to the first normalization layer. the embedding layer generates a set of vector embeddings. each vector embedding of the set of embedding vectors is a projection of a corresponding normalized image patch from the set of normalized image patches onto a visual token. the first normalization layer feeds forward to the embedding layer. the second normalization layer generates a set of normalized vector embeddings by performing a second normalization process on each vector embedding of the set of vector embeddings. the embedding layer feeds forward to the second normalization layer. the transformer block enables one or more machine vision tasks for the input image based on the set of normalized vectors. the second normalization layer feeds forward to the transformer block.
20240257550. READING ORDER WITH POINTER TRANSFORMER NETWORKS_simplified_abstract_(google llc)
Inventor(s): Henri Rebecq of Zurich (CH) for google llc, Federico Tombari of Zug (CH) for google llc, Diego Martin Arroyo of Zurich (CH) for google llc
IPC Code(s): G06V30/416, G06V10/44, G06V10/82, G06V30/412
CPC Code(s): G06V30/416
Abstract: a method including receiving an image representing a document including a plurality of layout components, identifying textual information associated with the plurality of layout components, identifying visual information associated with the plurality of layout components, combining the textual information with the visual information, and predicting a reading order of the plurality of layout components based on the combined textual information and visual information using a self-attention encoder/decoder.
Inventor(s): Dragan Zivkovic of Sunnyvale CA (US) for google llc, Agoston Weisz of Zurich (CH) for google llc
IPC Code(s): G10L15/06, G10L15/08, G10L15/22
CPC Code(s): G10L15/063
Abstract: a method includes receiving a biased transcription for a voice command spoken by a user and captured by a user device, the biased transcription biased to include a biasing phrase from a set of biasing phrases specific to the user. the method also includes instructing an application executing on the user device to perform an action specified by the biased transcription for the voice command, and receiving one or more user behavior signals responsive to the application performing the action specified by the biased transcription. the method further includes generating, as output from a confidence model, a confidence score of the biased transcription based on the one or more user behavior signals input to the confidence model and, based on the confidence score output from the confidence model, training a speech recognizer on the biased transcription.
Inventor(s): Marcin Nowak-Przygodzki of Bäch (CH) for google llc, Andrei Giurgiu of Zurich (CH) for google llc, Mugurel-Ionut Andreica of Adliswil (CH) for google llc, Joseph Lange of Zurich (CH) for google llc
IPC Code(s): G10L17/22, G06F3/16
CPC Code(s): G10L17/22
Abstract: techniques are described herein for delegation of request fulfillment, by an assistant, to other devices. a method includes: receiving, by a first device, a request from a first user; identifying, based on the request from the first user, (i) an action corresponding to the request and (ii) a first parameter corresponding to the action; determining that fulfillment of the action is to be delegated to a device other than the first device; in response: selecting, as the device other than the first device, a second device on which an application corresponding to the action is installed; identifying, by the first device, based on the first parameter and information associated with an account of the first user, a first disambiguated parameter corresponding to the action; and sending, to the second device, a command that specifies the action and the first disambiguated parameter, to cause the second device to fulfill the action.
20240258805. Safe Battery Charging During High Ambient Temperatures_simplified_abstract_(google llc)
Inventor(s): David Wang of San Jose CA (US) for google llc, Arun Prakash Raghupathy of Pleasanton CA (US) for google llc, Chang Hong Ye of Mountain View CA (US) for google llc, Ford Rylander of San Francisco CA (US) for google llc
IPC Code(s): H02J7/00
CPC Code(s): H02J7/00309
Abstract: the present document describes techniques for safe battery charging during high ambient temperatures. these techniques extend device runtime during peak use periods when ambient temperature is high by increasing the possibility for battery charging during high ambient temperature conditions. in an example, a device, during high ambient temperatures, checks future ambient temperatures over a network to identify if the minimum future ambient temperature over a block of time within the next n number of days is predicted to be sufficiently low that, when combined with device-performance throttling, is estimated to reduce the temperature of the battery to below the maximum charge temperature to enable the battery to be safely charged. the device can also use the future ambient temperatures to budget current battery usage by implementing and/or adjusting device-performance throttling.
Inventor(s): Hui Liu of San Ramon CA (US) for google llc, Leslie Choong of Mountain View CA (US) for google llc, Hongkun Yang of San Jose CA (US) for google llc, Shishir Agrawal of Mountain View CA (US) for google llc, Raj Yavatkar of Saratoga CA (US) for google llc, Tianqiong Luo of San Clara CA (US) for google llc, Gargi Adhav of San Jose CA (US) for google llc, Steffen Smolka of Ithaca NY (US) for google llc
IPC Code(s): H04L45/02, H04L41/12, H04L45/74
CPC Code(s): H04L45/02
Abstract: a method includes receiving, from a user device, a reachability request requesting a reachability status of network traffic from a first vm of a vpc to a second vm of the vpc. the method also includes obtaining network configuration information defining a configuration of a network connecting the first vm and the second vm, generating, using the network configuration information associated with the vpc, a simulated path between the first vm and the second vm, and, determining, based on the simulated path, that the second vm is unreachable from the first vm. the method further includes, based on determining that the second vm is unreachable from the first vm, generating a reachability report, the reachability report including each hop of the plurality of hops of the simulated path, and a rationale that the second vm is unreachable from the first vm, and providing the reachability report to the user device.
20240259455. QP Range Specification For External Video Rate Control_simplified_abstract_(google llc)
Inventor(s): Michael Horowitz of Austin TX (US) for google llc, Wonkap Jang of Mountain View CA (US) for google llc
IPC Code(s): H04L65/70, H04N19/124
CPC Code(s): H04L65/70
Abstract: operations of a method include obtaining a segment of image data that represents a portion of a frame of video image data to be encoded. the operations include determining, based on the segment and a target bitrate, a quantization parameter (qp) value for the segment. the operations include determining a minimum qp value and a maximum qp value that establishes a range of qp values an integrated bit rate control algorithm may use to encode the segment. the operations include encoding the segment with a first qp value that is greater than the minimum qp value and less than the maximum qp value. the operations include adjusting, by the bit rate control algorithm, the first qp value to a second qp value that is greater than the minimum qp value and less than the maximum qp value. the operations include transmitting the encoded segment to a remote device.
20240259614. AUTOMATICALLY DETERMINING PARAMETER VALUES_simplified_abstract_(google llc)
Inventor(s): Wenbo Zhang of Mountain View CA (US) for google llc, Son Khanh Pham of Mountain View CA (US) for google llc
IPC Code(s): H04N21/234, H04N21/25, H04N21/442
CPC Code(s): H04N21/234
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically determining parameter values that control or affect provision of content by a content platform. in one aspect, evaluation points are identified for a parameter. each evaluation point includes an evaluated parameter value of the parameter and a metric value of a metric corresponding to the provision of digital components by the content platform. a first model is generated using the set of evaluation points. a second model is generated based on the first model and an acquisition function that is based on mean values and confidence intervals of the first model and a configurable exploration weight that controls a priority of exploration for evaluating the parameter. a next parameter value to evaluate is determined from the second model and the content platform is configured to use the next parameter value to provide digital components.
Inventor(s): Edison Chen of Taipei (TW) for google llc, Shih-Che Chou of Taipei (TW) for google llc, Chih-Cheng Wang of New Taipei City (TW) for google llc, Hsueh-Feng Hsieh of New Taipei City (TW) for google llc
IPC Code(s): H04W8/18
CPC Code(s): H04W8/18
Abstract: a user equipment (ue) device performs fast network camping when multiple sims of the ue device are out of service. a first software stack begins scanning for available networks and finds an available network at a frequency x. the first software stack decodes system information received from the available network at frequency x and determines that the available network is mapped to the sim associated with a second software stack of the ue device. the first software stack signals the second software stack that an available network is mapped to the sim associated with the second software stack at frequency x. in response to receiving the signal, the second software stack sends an attach request to the available network and completes a network attach procedure.
- GOOGLE LLC
- B25J9/16
- CPC B25J9/163
- Google llc
- B25J19/02
- B25J9/10
- B25J13/08
- B25J15/00
- B25J15/02
- B25J15/12
- CPC B25J19/023
- G01C21/34
- G01C21/36
- G06F16/29
- G06F16/9537
- CPC G01C21/3446
- G01S19/13
- CPC G01C21/3605
- G06F3/01
- G06F1/16
- G06F3/0346
- G06F3/04817
- G06F3/0482
- G06F3/04883
- G06F3/04886
- G06F3/16
- CPC G06F3/017
- G06F8/41
- CPC G06F8/433
- G06F9/451
- CPC G06F8/451
- G06F40/166
- CPC G06F9/453
- G06F11/14
- CPC G06F11/1469
- G06F16/2452
- G06F40/30
- CPC G06F16/24522
- G06F16/635
- G10L15/22
- CPC G06F16/635
- G06F16/9032
- G06F3/04842
- G06F16/25
- G06F16/9535
- H04L51/046
- H04L51/216
- CPC G06F16/90324
- G06F16/957
- G06F40/143
- CPC G06F16/9574
- G06F40/35
- G06F40/20
- G06F40/284
- G10L13/02
- CPC G06F40/35
- G06N3/045
- G06F18/2413
- G06N3/0464
- G06N3/08
- G06V10/44
- G06V10/82
- G06V40/16
- CPC G06N3/045
- G06N3/0455
- G06N3/088
- CPC G06N3/0455
- CPC G06N3/08
- G06N3/048
- G06N3/082
- G06N3/092
- CPC G06N3/082
- G06N20/00
- G06F7/483
- CPC G06N20/00
- G06Q30/0242
- G06Q30/0235
- CPC G06Q30/0244
- G06V10/774
- G06V10/776
- G06V20/00
- CPC G06V10/82
- G06V10/26
- G06V30/416
- G06V30/412
- CPC G06V30/416
- G10L15/06
- G10L15/08
- CPC G10L15/063
- G10L17/22
- CPC G10L17/22
- H02J7/00
- CPC H02J7/00309
- H04L45/02
- H04L41/12
- H04L45/74
- CPC H04L45/02
- H04L65/70
- H04N19/124
- CPC H04L65/70
- H04N21/234
- H04N21/25
- H04N21/442
- CPC H04N21/234
- H04W8/18
- CPC H04W8/18
