Google LLC patent applications on April 24th, 2025
Patent Applications by Google LLC on April 24th, 2025
Google LLC: 45 patent applications
Google LLC has applied for patents in the areas of G02B27/01 (4), H04W68/02 (3), G06N20/00 (3), G10L13/08 (2), G06F21/62 (2) G02B27/0172 (2), G06N20/00 (2), G16B30/00 (1), G10L13/08 (1), G10L15/01 (1)
With keywords such as: data, image, device, user, based, including, computing, text, systems, and include in patent application abstracts.
Patent Applications by Google LLC
20250128175. Playability Service Application Programming Interface_simplified_abstract_(google llc)
Inventor(s): Mackenzie Lee Jacoby of Pyrmont AU for google llc, Andrew David Foster of Naremburn AU for google llc
IPC Code(s): A63F13/79, A63F13/216, G06F9/54, G06F16/29, G06F16/9537
CPC Code(s): A63F13/79
Abstract: the present disclosure provides systems and methods for providing geographic information for software application development. in one example, a computer-implemented method is provided for determining candidate locations for a playability service, which includes obtaining, by one or more computing devices, a plurality of location points and filtering the plurality of location points to obtain a plurality of candidate location points based at least in part on a suitability of each of the location points for use in generating location-based application content. the method further includes generating, by the one or more computing devices, a candidate location dataset based on the plurality of candidate location points. the method further includes receiving, by the one or more computing devices, a request for one or more of the plurality of candidate location points and providing data associated with one or more of the plurality of candidate location points in response to the request.
20250130426. ACTIVE CONTROL OF VIRTUAL IMAGE DEPTH POSITIONING_simplified_abstract_(google llc)
Inventor(s): Lloyd Frederick Holland of Waterloo CA for google llc, Matthew Thomas Valente of Sunnyvale CA US for google llc
IPC Code(s): G02B27/01, G02C7/08, G06F3/01, G06V20/00, G06V20/50
CPC Code(s): G02B27/0172
Abstract: a head-mounted display device includes a controller configured to activate a display of a head-mounted display device. the head-mounted display device includes an eye-side lens and a world-side lens. the controller may activate the eye-side lens and the world-side lens to display virtual content at a first virtual depth. the controller may deactivate the eye-side lens and the world-side lens to display the virtual content at a second virtual depth, where the second virtual depth is greater than the first virtual depth.
20250130428. REFERENCE PROJECTION FOR A WEARABLE DISPLAY_simplified_abstract_(google llc)
Inventor(s): Daniel Adema of Kitchener CA for google llc, Shreyas Potnis of Kitchener CA for google llc
IPC Code(s): G02B27/01, H04N19/895
CPC Code(s): G02B27/0172
Abstract: according to an aspect, a method includes generating a first projection from a first image source, the first projection displayed on a surface of a device. the method further includes generating a second projection from a second image source, the second projection displayed on the surface of the device. the method also includes identifying at least one error in an alignment associated with the first image source based on the first projection and the second projection.
20250130431. PIXEL ALIGNMENT FOR BINOCULAR DISPLAY SYSTEMS_simplified_abstract_(google llc)
Inventor(s): Daniel Adema of Kitchener CA for google llc
IPC Code(s): G02B27/01
CPC Code(s): G02B27/0176
Abstract: according to an aspect, a system includes a first image source for a left eye and a second image source for a right eye. the system further includes at least one window in a first optical path for the first image source or a second optical path for the second image source, the at least one window configured to align first pixels from the first image source with second pixels from the second image source.
Inventor(s): Daniel Adema of Kitchener CA for google llc, Shreyas Potnis of Kitchener CA for google llc
IPC Code(s): G02B27/01
CPC Code(s): G02B27/0179
Abstract: according to an aspect, a method includes identifying a lens pitch associated with a wafer. the method further includes determining a projector pitch for a first projector and a second projector on the wafer based on the lens pitch. the method also includes selecting a portion of the wafer for a device based on the projector pitch.
20250130613. FOLDING PORTABLE DISPLAY DEVICE_simplified_abstract_(google llc)
Inventor(s): Yongho Lim of Chicago IL US for google llc, Peiwen Hung of New Taipei City TW for google llc, Han-Wen Yeh of New Taipei City TW for google llc, Wen Shian Lin of New Taipei City TW for google llc
IPC Code(s): G06F1/16
CPC Code(s): G06F1/1681
Abstract: an example folding device includes a first assembly; a second assembly; a hinge assembly comprising: a first gear defining a first gear axis; a first scoop receiver defining a first scoop axis; and a continuous display spanning the hinge assembly from the first assembly to the second assembly; and first assembly linkage components comprising: a first arm having a. medial end rotatably connected to the hinge assembly about the first gear axis and a lateral end slidably connected to the first assembly; and a first scoop having a. curved medial end that slides within the first scoop receiver about the first scoop axis and a lateral end rotatably connected to the first assembly about a first scoop rotating center.
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
CPC Code(s): G06F9/4881
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.
20250131092. Structure-Aware Neural Networks for Malware Detection_simplified_abstract_(google llc)
Inventor(s): David Benjamin Krisiloff of Arlington VA US for google llc, Scott Eric Coull of Cary NC US for google llc
IPC Code(s): G06F21/56
CPC Code(s): G06F21/566
Abstract: provided is a malware detection system that provides structure-aware neural networks for performing malware detection. in particular, rather than treat the entire computer file as one large input to a deep neural network, the malware detection system can break the file up based on the internal file structure. each portion of the computer file can then be processed using individual neural networks and the outputs of these networks can be combined and similarly processed. in this way the overall system can evaluate the file with knowledge of the structure of the file, enabling the malware detection to have a higher-order understanding of the interoperation of different portions of the computer file.
Inventor(s): Sebastian Lekies of ZĂźrich CH for google llc, Yousef Alowayed of New York NY US for google llc
IPC Code(s): G06F21/57
CPC Code(s): G06F21/577
Abstract: a method includes identifying, by a processing device, a set of parameters to generate a container image for a container. the parameters comprise one or more dependencies associated with running the container in a cloud-based environment. a manifest file referencing the one or more dependencies is obtained and the container image is generated based on the set of parameters, wherein the manifest file is stored in a predetermined location associated with the container.
20250131107. SIDE CHANNEL RESISTANT MEMORY OPERATIONS_simplified_abstract_(google llc)
Inventor(s): Miguel Cristian Young de la Sota of Cambridge MA US for google llc
IPC Code(s): G06F21/60, G06F21/55
CPC Code(s): G06F21/602
Abstract: methods, systems, and apparatus, including computer programs encoded on computer-storage media, for privacy preserving digital component provider. in some implementations, a method includes accessing a buffer including one or more sets of bits; generating a random sequence of values; generating, from the random sequence of values, a sequence of indices representing an order in which to access particular sets of bits of the buffer; in response to determining an index of the sequence of indices corresponds to a location in the buffer, accessing a set of the particular sets of bits of the buffer at the index in the order of the sequence of indices; and performing one or more memory operations on the set of the one or more sets of bits after accessing the set.
Inventor(s): Pasin Manurangsi of Bangkok TH for google llc, Badih Ghazi of Cupertino CA US for google llc, Shanmugasundaram Ravikumar of Piedmont CA US for google llc, Jelani Osei Nelson of Berkeley CA US for google llc
IPC Code(s): G06F21/62
CPC Code(s): G06F21/62
Abstract: in one aspect, there is provided a method performed by one or more computers that includes: obtaining access data for a digital resource, access data including data identifying a set of users that accessed the digital resource at a time point, processing the access data to generate data defining a tree model, where each node in the tree model is associated with: (i) a key that specifies time intervals in the time span, and (ii) a value that is based on a respective number of users that satisfy a node-specific selection, receiving a request to determine a number of users that accessed the digital resource at least a predefined number of times within a time window, and in processing the tree model to generate an estimate for the number of users that accessed the digital resource at least the predefined number of times within the time window.
Inventor(s): Gang WANG of Mountain View CA US for google llc, Marcel M. Moti YUNG of Mountain View CA US for google llc, Kevin Wei Li YEO of Mountain View CA US for google llc
IPC Code(s): G06F21/62, H04L9/08
CPC Code(s): G06F21/6218
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for batch retrieving data are described. in one aspect, a method includes receiving, from a client device and by a first multi-party computation (mpc) server of a cluster of mpc servers, a batch request for retrieving multiple database values stored in one or more databases. the batch request includes a first byte array that includes, for each requested key of multiple requested keys, a first secret share of the requested key. each database includes multiple data items that each include a database key and a corresponding value. the mpc server processes each database key to generate first secret shares of matching data indicating whether the database key matches at least one requested key. the mpc server generates one or more results that represent database values corresponding to each database key that matches at least one requested key.
20250131208. Contrastive Pre-Training for Language Tasks_simplified_abstract_(google llc)
Inventor(s): Thang Minh Luong of Santa Clara CA US for google llc, Quoc V. Le of Sunnyvale CA US for google llc, Kevin Stefan Clark of San Francisco CA US for google llc
IPC Code(s): G06F40/40, G06N5/04, G06N20/00
CPC Code(s): G06F40/40
Abstract: systems and methods are provided that train a machine-learned language encoding model through the use of a contrastive learning task. in particular, the present disclosure describes a contrastive learning task where the encoder learns to distinguish input tokens from plausible alternatives. in some implementations, on each training example the proposed method masks out some subset (e.g., 15%) of the original input tokens, replaces the masked tokens with samples from a âgeneratorâ (e.g., which may be a small masked language model), and then trains the encoder to predict whether each token comes from the original data or is a replacement produced by the generator.
20250131215. TRANSLATION OF TEXT DEPICTED IN IMAGES_simplified_abstract_(google llc)
Inventor(s): Puneet Jain of Saratoga CA US for google llc, Orhan Firat of Mountain View CA US for google llc, Sihang Liang of Princeton NJ US for google llc
IPC Code(s): G06F40/58, G06V10/44, G06V10/77, G06V10/82, G06V20/62
CPC Code(s): G06F40/58
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that translate text depicted in images from a source language into a target language. methods can include obtaining a first image that depicts first text written in a source language. the first image is input into an image translation model, which includes a feature extractor and a decoder. the feature extractor accepts the first image as input and in response, generates a first set of image features that are a description of a portion of the first image in which the text is depicted is obtained. the first set of image features are input into a decoder. in response to the input first set of image features, the decoder outputs a second text that is a predicted translation of text in the source language that is represented by the first set of image features.
Inventor(s): Hanxiao Liu of Santa Clara CA US for google llc, Quoc V. Le of Sunnyvale CA US for google llc, Yanqi Zhou of Sunnyvale CA US for google llc, Tao Lei of Sunnyvale CA US for google llc, Yuzhe Zhao of San Francisco CA US for google llc, Yanping Huang of Mountain View CA US for google llc, Nan Du of San Jose CA US for google llc, Zhifeng Chen of Sunnyvale CA US for google llc, Andrew M. Dai of San Francisco CA US for google llc, James Laudon of Madison WI US for google llc
IPC Code(s): G06N3/048
CPC Code(s): G06N3/048
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. in one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more expert neural network blocks that each include router that performs expert-choice routing between multiple expert neural networks.
Inventor(s): Soroosh Mariooryad of Redwood City CA US for google llc, Sean Matthew Shannon of San Francisco CA US for google llc, Thomas Edward Bagby of Monte Rio CA US for google llc, Siyuan Ma of San Jose CA US for google llc, David Teh-Hwa Kao of Philadelphia PA US for google llc, Daisy Antonia Stanton of San Francisco CA US for google llc, Eric Dean Battenberg of Walnut Creek CA US for google llc, Russell John Wyatt Skerry-Ryan of Mountain View CA US for google llc
IPC Code(s): G06N3/088, G06N3/0455
CPC Code(s): G06N3/088
Abstract: provided is a noisy channel generative model of two sequences, for example text and speech, which enables uncovering the associations between the two modalities when limited paired data is available. to address the intractability of the exact model under a realistic data set-up, example aspects of the present disclosure include a variational inference approximation. to train this variational model with categorical data, a kl encoder loss approach is proposed which has connections to the wake-sleep algorithm.
20250131280. Meta-Reinforcement Learning Hypertransformers_simplified_abstract_(google llc)
Inventor(s): Gus Kristiansen of Cold Springs NY US for google llc
IPC Code(s): G06N3/092
CPC Code(s): G06N3/092
Abstract: machine-learning systems for meta-reinforcement learning (meta-rl) can include a transformer-based hypernetwork to generate policy parameters in an episodic fashion. an initial policy can be executed in a computing environment over an initial exploration episode during which the computing environment generates episode data. the episode data can be provided as an input to the hypertransformer network which generates an improved policy which is executed in the computing environment to generate episode data. this process is repeated over a predetermined number of episodes. a cumulative reward associated with execution of the policy for a final policy is optimized. the final policy can be optimized for both exploration and exploitation associated with a particular task. the final policy can include a machine-learned model and/or weights for a machine-learned model.
20250131310. QUBIT CALIBRATION_simplified_abstract_(google llc)
Inventor(s): Amit Vainsencher of Goleta CA US for google llc, Julian Shaw Kelly of Santa Barbara CA US for google llc
IPC Code(s): G06N10/40, G06N3/045, G06N3/084, G06N7/01, G06N10/60, G06N10/70
CPC Code(s): G06N10/40
Abstract: a method comprises causing a plurality of qubit calibration procedures to be performed on one or more qubits in accordance with an automatic qubit calibration process. log data is stored comprising at least: a record identifying one or more calibration procedures that have been performed, and information relating to the result of the respective calibration procedures. training data is selected from the log data and is received at a learning module operating at one or more computing devices. a supervised learning model is trained at the learning module to select qubit parameters to be calibrated and/or checked.
Inventor(s): Wei Yu of Palo Alto CA US for google llc, Sang Xie of Mountain View CA US for google llc, Hieu Hy Pham of Mountain View 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: systems and methods are provided for efficiently calibrating a data mixture for training machine-learned models (e.g., machine-learned sequence processing models, such as transformer-based models). for example, machine-learned models can be trained over a broad dataset that can include multiple different categories of data. the mixture of data categories within the dataset can influence model performance. to improve the performance of machine-learned models, example implementations of the present disclosure can learn a distribution of data categories using a lightweight proxy model before initiating training of a large primary model. in this manner, for instance, example implementations can obtain an improved training data distribution with less computational expense and can leverage the learned training data distribution to better train a large primary model.
Inventor(s): Adrian Li of San Francisco CA US for google llc, Benjamin Holson of Sunnyvale CA US for google llc, Alexander Herzog of San Jose CA US for google llc, Mrinal Kalakrishnan of Mountain View CA US for google llc
IPC Code(s): G06N20/00, G06N3/008, G06N5/04
CPC Code(s): G06N20/00
Abstract: implementations disclosed herein relate to utilizing at least one existing manually engineered policy, for a robotic task, in training an rl policy model that can be used to at least selectively replace a portion of the engineered policy. the rl policy model can be trained for replacing a portion of a robotic task and can be trained based on data from episodes of attempting performance of the robotic task, including episodes in which the portion is performed based on the engineered policy and/or other portion(s) are performed based on the engineered policy. once trained, the rl policy model can be used, at least selectively and in lieu of utilization of the engineered policy, to perform the portion of robotic task, while other portion(s) of the robotic task are performed utilizing the engineered policy and/or other similarly trained (but distinct) rl policy model(s).
20250131471. Surfacing Cross-Channel Data for Impression Reporting_simplified_abstract_(google llc)
Inventor(s): Matthew Aaron Jacobson of Scarsdale CA US for google llc, Yuval Segal of New York NY US for google llc, Alman Shibli of Hoboken NJ US for google llc, Saurav Mohapatra of Orinda CA US for google llc
IPC Code(s): G06Q30/0242
CPC Code(s): G06Q30/0246
Abstract: computing systems and methods for surfacing impression data are disclosed herein. the method can include periodically providing a reporting data request to one or more data sources requesting impression data associated with content presented at the data sources. reporting data is received and processed into a data format usable by the database. the reporting data is then saved in a database. in response to receiving a request from a user to generate a report the reporting data stored in the database is processed using a machine-learned model to generate a model output, and a portion of the reporting data and the model output are output for display to the user.
Inventor(s): Changgeng Liu of San Jose CA US for google llc, Marek Mienko of San Jose CA US for google llc, Hart Levy of Redwood City CA US for google llc, Ion Bita of Los Altos CA US for google llc, Xi Chen of Mountain View CA US for google llc
IPC Code(s): G06T5/50, G06T5/20, G06T5/60, G06T7/70, H04N23/56, H04N23/90, H04N23/95, H04N25/40, H04N25/532
CPC Code(s): G06T5/50
Abstract: systems and techniques directed at an electronic device with a centrally located under-display image sensor are disclosed. the electronic device includes a first image sensor and a second image sensor, the second image sensor being an under-display sensor located at substantially a center of a display of the electronic device. the first image sensor may be located adjacent to an edge of the display. the second image sensor is configured to capture an eye gaze of a user and provide the captured eye gaze to correct the eye gaze of images captured by the first image sensor. the first image sensor may also be an under-display image sensor. during video communications with the electronic device, a user usually looks at the center of the display of the electronic device. the second image sensor is configured to capture the correct eye gaze of the user during video communications.
Inventor(s): Eric James Edmond of Redmond WA US for google llc
IPC Code(s): G06T19/00, G06T15/06, G06V10/762
CPC Code(s): G06T19/003
Abstract: a computing system obtains a plurality of images and associated image information. each of the plurality of images depicts a particular point of interest (poi). for each of the plurality of images, the image information is descriptive of a plurality of image characteristics, such as a geolocation characteristic indicative of a geolocation at which the image was captured and/or an interaction metric derived from previous user interactions with the image. the computing system selects a particular image of the plurality of images based on the image information and generates a movement pattern for a camera viewpoint within a three-dimensional environment. the movement pattern for the camera viewpoint moves around a three-dimensional representation of the particular poi within the three-dimensional environment, and a starting position for the movement pattern is based, at least in part, on the geolocation at which the particular image was captured.
20250131694. Learning with Neighbor Consistency for Noisy Labels_simplified_abstract_(google llc)
Inventor(s): Ahmet Iscen of Grenoble FR for google llc, Jack Louis Valmadre of Grenoble, Auvergne-Thone-Alpes FR for google llc, Anurag Arnab of Grenoble FR for google llc, Cordelia Luise Schmid of Saint-Ismier FR for google llc
IPC Code(s): G06V10/774, G06V10/74, G06V10/764, G06V10/77, G06V10/776, G06V10/82, G06V20/70
CPC Code(s): G06V10/774
Abstract: systems and methods for classification model training can use feature representation neighbors for mitigating label training overfitting. the systems and methods disclosed herein can utilize neighbor consistency regularization for training a classification model with and without noisy labels. the systems and methods can include a combined loss function with both a supervised learning loss and a neighbor consistency regularization loss.
20250131740. System for Estimating Changes in Lane Marker Geometry_simplified_abstract_(google llc)
Inventor(s): Dan Lingenfelter of Mountain View CA US for google llc, Stephen Russell of Mountain View CA US for google llc
IPC Code(s): G06V20/56, G06V10/75
CPC Code(s): G06V20/588
Abstract: to detect a change in lane marker geometry, a computing device receives map patch data from one or more vehicles within a geographic area indicative of measured lane marker positions. for each data point within the map patch data, the computing device determines an error metric based on one or more differences between one or more measured lane marker positions for the data point and one or more reference lane marker positions from a database. the computing device identifies relationships between the data points according to the error metric for each data point, a time when each data point was collected, or a location of each data point, and identifies a lane marker change event occurring within the geographic area based on the relationships between the data points. then the computing device discards reference lane marker positions from the database corresponding to the lane marker change event.
Inventor(s): Matthew Sharifi of Kilchberg CH for google llc, Jakob Nicolaus Foerster of San Francisco CA US for google llc
IPC Code(s): G10L13/00, G06F40/253, G06F40/289, G10L13/08
CPC Code(s): G10L13/00
Abstract: in some implementations, a language proficiency of a user of a client device is determined by one or more computers. the one or more computers then determines a text segment for output by a text-to-speech module based on the determined language proficiency of the user. after determining the text segment for output, the one or more computers generates audio data including a synthesized utterance of the text segment. the audio data including the synthesized utterance of the text segment is then provided to the client device for output.
Inventor(s): Leonid VELIKOVICH of New York NY US for google llc, Ăgoston WEISZ of Pfaeffikon CH for google llc
IPC Code(s): G10L13/08
CPC Code(s): G10L13/08
Abstract: a method, device, and computer-readable storage medium for predicting pronunciation of a text sample, including generating an encoding of allowable pronunciations of the text sample, selecting predicted text samples corresponding to an audio sample, the predicted text samples including the text sample and one or more co-emitted text samples, outputting the text sample, and updating the encoding of allowable pronunciations of the text sample based on pronunciations of the one or more co-emitted text samples.
Inventor(s): Matthew Sharifi of Kilchberg CH for google llc, Victor Carbune of Zurich CH for google llc
IPC Code(s): G10L15/01, G01S3/80, G10L15/08, G10L15/32, H04R29/00
CPC Code(s): G10L15/01
Abstract: implementations can detect respective audio data that captures an acoustic event at multiple assistant devices in an ecosystem that includes a plurality of assistant devices, process the respective audio data locally at each of the multiple assistant devices to generate respective measures that are associated with the acoustic event using respective event detection models, process the respective measures to determine whether the detected acoustic event is an actual acoustic event, and cause an action associated with the actional acoustic event to be performed in response to determining that the detected acoustic event is the actual acoustic event. in some implementations, the multiple assistant devices that detected the respective audio data are anticipated to detect the respective audio data that captures the actual acoustic event based on a plurality of historical acoustic events being detected at each of the multiple assistant devices.
20250131916. TEXT INDEPENDENT SPEAKER RECOGNITION_simplified_abstract_(google llc)
Inventor(s): Pu-sen Chao of Los Altos CA US for google llc, Diego Melendo Casado of Mountain View CA US for google llc, Ignacio Lopez Moreno of New York NY US for google llc, Quan Wang of Hoboken NJ US for google llc
IPC Code(s): G10L15/06, G10L15/07, G10L15/22, G10L15/32, G10L17/24
CPC Code(s): G10L15/063
Abstract: text independent speaker recognition models can be utilized by an automated assistant to verify a particular user spoke a spoken utterance and/or to identify the user who spoke a spoken utterance. implementations can include automatically updating a speaker embedding for a particular user based on previous utterances by the particular user. additionally or alternatively, implementations can include verifying a particular user spoke a spoken utterance using output generated by both a text independent speaker recognition model as well as a text dependent speaker recognition model. furthermore, implementations can additionally or alternatively include prefetching content for several users associated with a spoken utterance prior to determining which user spoke the spoken utterance.
20250131917. LANGUAGE MODEL BIASING SYSTEM_simplified_abstract_(google llc)
Inventor(s): Petar Aleksic of Jersey City NJ US for google llc, Pedro J. Moreno Mengibar of Jersey City NJ US for google llc
IPC Code(s): G10L15/07, G10L15/01, G10L15/18, G10L15/187, G10L15/197, G10L15/30
CPC Code(s): G10L15/07
Abstract: methods, systems, and apparatus for receiving audio data corresponding to a user utterance and context data, identifying an initial set of one or more n-grams from the context data, generating an expanded set of one or more n-grams based on the initial set of n-grams, adjusting a language model based at least on the expanded set of n-grams, determining one or more speech recognition candidates for at least a portion of the user utterance using the adjusted language model, adjusting a score for a particular speech recognition candidate determined to be included in the expanded set of n-grams, determining a transcription of user utterance that includes at least one of the one or more speech recognition candidates, and providing the transcription of the user utterance for output.
Inventor(s): Matthew Sharifi of Kilchberg CH for google llc, Victor Carbune of ZĂźrich CH for google llc
IPC Code(s): G10L15/22, G06F3/16, G06F16/638, G10L17/00, G10L17/22
CPC Code(s): G10L15/22
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): Neil Zeghidour of Paris FR for google llc, Marco Tagliasacchi of Ruvigliana CH for google llc, Dominik Roblek of Meilen CH for google llc
IPC Code(s): G10L19/038, G06N3/045, G06N3/08, G10L19/00, G10L25/30
CPC Code(s): G10L19/038
Abstract: methods, systems and apparatus, including computer programs encoded on computer storage media. according to one aspect, there is provided a method comprising: receiving a new input; processing the new input using an encoder neural network to generate a feature vector representing the new input; and generating a coded representation of the feature vector using a sequence of vector quantizers that are each associated with a respective codebook of code vectors, wherein the coded representation of the feature vector identifies a plurality of code vectors, including a respective code vector from the codebook of each vector quantizer, that define a quantized representation of the feature vector.
20250131951. SIGNAL SYNCHRONIZATION FOR A DISPLAY_simplified_abstract_(google llc)
Inventor(s): Edwin Lyle Hudson of San Jose CA US for google llc, Bo Li of Folsom CA US for google llc, Samuel Tien-en Lee of Mountain View CA US for google llc, Kaushik Indravadan Sheth of Los Altos CA US for google llc
IPC Code(s): G11C7/22, G09G3/32, G11C11/418, G11C11/419
CPC Code(s): G11C7/222
Abstract: a backplane including bit lines and word lines to update a radiative state of a pixel is disclosed. the back plane includes a first delay line that replicates delays caused by a bit line and a second delay line that replicates delays caused by a word line. the replicated delays cause word line signals traveling along a first path to arrive at a pixel at approximately the same time as bit line signals traveling along a second path. the delays are added incrementally row-by-row and column-by-column so that each pixel can receive synchronized signals regardless of its position in the array of pixels.
20250131984. SEQUENCE ERROR CORRECTION USING NEURAL NETWORKS_simplified_abstract_(google llc)
Inventor(s): Andrew Walker Carroll of Mountain View CA US for google llc, Gunjan Baid of San Francisco CA US for google llc, Pi-Chuan Chang of Mountain View CA US for google llc, Daniel Elwood Cook of Waterville OH US for google llc, Maria Nattestad of Sunnyvale CA US for google llc, Taedong Yun of Boston MA US for google llc, Cory Yuen Fu McLean of Newton MA US for google llc, MD Kishwar Shafin of Richmond CA US for google llc, Jean-Philippe Vert of Paris FR for google llc, Quentin Didier Olivier Berthet of Paris FR for google llc, Felipe Llinares LĂłpez of Paris FR for google llc, Ashish Teku Vaswani of San Francisco CA US for google llc
IPC Code(s): G16B30/00, G06N3/09, G16B40/20
CPC Code(s): G16B30/00
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for sequence error correction using neural networks.
Inventor(s): Dexiang Wang of Sunnyvale CA US for google llc, Matthew John Stevenson of Mountain View CA US for google llc, Sophie Schmieg of Mountain View CA US for google llc, Rafael Misoczki of Miami FL US for google llc, Michael David Schiffman of Moraga CA US for google llc, Dmitri Rubakha of San Jose CA US for google llc, Dan Born of Mountain View CA US for google llc
IPC Code(s): H04L9/08, H04L9/40
CPC Code(s): H04L9/085
Abstract: an example method is provided for resuming a communication session encrypted using a post-quantum cipher. the example method can include receiving, by a first computing system, a resumption message from a second computing system. the example method can include decrypting, by the first computing system, the resumption message to obtain a resumption secret, wherein the resumption secret is based on at least a portion of a shared secret that was obtained using a post-quantum cipher during a prior handshake sequence between the first computing system and the second computing system. the example method can include encrypting, by the first computing system, one or more messages using a session key based on the resumption secret. the example method can include sending, by the first computing system, the encrypted one or more messages to the second computing system.
20250132942. MANAGING RECEPTION OF MULTICAST AND BROADCAST SERVICES_simplified_abstract_(google llc)
Inventor(s): Chih-Hsiang Wu of Taoyuan City TW for google llc
IPC Code(s): H04L12/18, H04W68/02, H04W72/30, H04W76/27
CPC Code(s): H04L12/185
Abstract: to manage reception of multicast and broadcast services (mbs) data, a user equipment (ue) receives, from a radio access network (ran), a paging message including an mbs session identifier (id), the mbs session id including a temporary mobile group identity (tmgi); and initiates reception of mbs in response to the paging message.
20250133036. SIMULATION OF AUTOMATED TELEPHONE CALL(S)_simplified_abstract_(google llc)
Inventor(s): Sasha Goldshtein of Tel Aviv IL for google llc, Yoav Tzur of Tel Aviv IL for google llc
IPC Code(s): H04L51/02, G06F40/205, G06F40/30
CPC Code(s): H04L51/02
Abstract: implementations are directed to simulating automated telephone call(s) to be performed by an automated assistant. processor(s) can receive user input and determine, based on the user input, that the user input includes: a request to cause the automated assistant to initiate an automated telephone call with an entity, and a task to be performed during the automated telephone call. in some implementations, the processor(s) can cause a simulation of the automated telephone call to be performed to simulate the task, and, based on a result of the simulation, determine whether to initiate the automated telephone call or to refrain from initiating the automated telephone call. in additional or alternative implementations, the processor(s) can determine whether to cause the simulation of the automated telephone call to be performed based on a type of the entity, a type of the task, and/or whether a prior simulation of the task has been performed.
20250133139. DEMAND SERVERLESS CONTAINER BASED STORAGE TRANSFER_simplified_abstract_(google llc)
Inventor(s): Alankrit Kharbanda of Seattle WA US for google llc, Shyam Venkataraman of San Jose CA US for google llc, Sowmya Dayanand of Redmond WA US for google llc, Xiangqian Yu of Fremont CA US for google llc, Juan Esteller of Mountain View CA US for google llc
IPC Code(s): H04L67/1097, H04L9/40, H04L67/06
CPC Code(s): H04L67/1097
Abstract: a method for on demand serverless container based storage transfer includes receiving a request to transfer data from a first device to a second device, the first device hosted at a private cloud, the private cloud isolated from the internet. the method includes determining that the first device is communicatively connected to the private cloud. the method also includes, in response to determining that the first device is communicatively connected to the private cloud, instantiating a container at the first device, the container configured to receive the data from the first device without directly accessing a local storage of the first device. the method includes transferring, using the container, the data from the first device to the second device.
Inventor(s): Francesco Infante of Mountain View CA US for google llc, Haotian Fang of Mountain View CA US for google llc, Aiden Liu of Mountain View CA US for google llc, Melis Atarim of Mountain View CA US for google llc, Laurynas Tamulevicius of Mountain View CA US for google llc, Bence DemkĂł of Mountain View CA US for google llc, Miquel FarrĂŠ of Mountain View CA US for google llc
IPC Code(s): H04N21/81, G06F40/40
CPC Code(s): H04N21/816
Abstract: a method for generating video content includes obtaining first information that includes information associated with a user or a content sponsor. the method also includes generating text content at least in part by applying the first information to a generative artificial intelligence model, and obtaining image content. the method further includes generating video content, at least by applying the text content and the image content as inputs to a template model. the template model causes the generated video content to conform to one or more temporal characteristics defined by the template model.
Inventor(s): Chih-Hsiang Wu of Taoyuan City TW for google llc, Jing-Rong Hsieh of Taipei City TW for google llc
IPC Code(s): H04W36/00, H04W76/15, H04W76/28
CPC Code(s): H04W36/0069
Abstract: base stations perform methods for supporting a conditional procedure for a user equipment (ue). a method performed by a first base station may include receiving (), by the first base station from a second base station, an indication of one or more candidate secondary cells to which the ue can connect, subject to a condition, to communicate in dual connectivity (dc); receiving (), by the first base station, subsequently to the ue connecting to a secondary cell among the one or more candidate secondary cells for which the condition is satisfied, coordination information for the secondary cell, the coordinating information being usable for coordinating usage of radio resources with the second base station while the ue communicates in dc; and applying (), by the first base station, the coordination information to coordinate the usage of radio resources with the second base station.
Inventor(s): Chih-Hsiang Wu of Taoyuan City TW for google llc, Jing-Rong Hsieh of Taipei City TW for google llc
IPC Code(s): H04W36/36, H04W36/00, H04W76/20
CPC Code(s): H04W36/362
Abstract: a master node (mn) can implement a method for managing a conditional procedure that involves a user equipment (ue), a candidate secondary node (c-sn), and the mn. the method may include transmitting, to the c-sn, a request to perform the conditional procedure related to the c-sn and the ue, the conditional procedure associated with a condition and a conditional configuration according to which the ue connects to the c-sn when the condition is satisfied; receiving, from the c-sn, a response to the request, the response including an sn-to-mn container; and retrieving the conditional configuration from the sn-to-mn container.
Inventor(s): Ananya Simlai of London GB for google llc, Rittwik Jana of Montville NJ US for google llc, Ian Kenneth Coolidge of San Diego CA US for google llc, Santanu Dasgupta of Fremont CA US for google llc
IPC Code(s): H04W52/02
CPC Code(s): H04W52/0203
Abstract: aspects of the disclosure are directed to network optimization of various workload servers running in a distributed cloud platform through closed loop machine learning inferencing performed locally on the workload servers. the workload servers can each be equipped with one or more machine learning accelerators to respectively perform local predictions for the workload servers. in response to the local predictions, attributes of the workload servers can be adjusted automatically for optimizing the network.
20250133535. MANAGING PAGING FOR DIFFERENT SERVICES_simplified_abstract_(google llc)
Inventor(s): Chih-Hsiang Wu of Taoyuan City TW for google llc
IPC Code(s): H04W68/00, H04W68/02, H04W88/08
CPC Code(s): H04W68/005
Abstract: a method for paging a ue is implemented in a distributed unit (du) of a distributed base station. the method includes receiving, by processing hardware from a central unit (cu) of the distributed base station and when the ue is not operating in a connected state of a protocol associated with controlling radio resources, a cu-to-du message related to the ue and indicating a voice call; and transmitting, by the processing hardware to the ue via a radio interface, a paging message including an indication of the voice call.
20250133629. Activating MBS Transmission and Reception_simplified_abstract_(google llc)
Inventor(s): Chih-Hsiang Wu of Taoyuan City TW for google llc
IPC Code(s): H04W76/40, H04W68/02, H04W74/0833, H04W76/27
CPC Code(s): H04W76/40
Abstract: to activate reception of multicast and/or broadcast services (mbs), a ue operating in an inactive state of a protocol for controlling radio resources receives, in the inactive state from a radio access network (ran), a message including an mbs session identifier (id). the ue initiates reception of mbs data corresponding to the mbs session id in response to the message.
20250133709. Component Shielding_simplified_abstract_(google llc)
Inventor(s): Chien Hua Hsu of New Taipei City TW for google llc, ChanWei Chiu of Taoyuan City TW for google llc, Bing-Feng Wang of New Taipei City TW for google llc, Shen Hao Lee of Taipei City TW for google llc, Jui Hung Hsu of Taipei TW for google llc, Jehyoung Lee of Saratoga CA US for google llc
IPC Code(s): H05K9/00, H05K1/02, H05K1/18
CPC Code(s): H05K9/0032
Abstract: this document describes a system including a printed circuit board oriented along a first plane, the printed circuit board having a device that extends in a direction away from the first plane and is capable of producing a radiated signal or is sensitive to a radiated signal produced by another device. the system includes a component shield with a wall structure and a cover structure, the cover structure connected to the wall structure. a housing structure oriented along a second plane defines a shielded space within which the component shield and the device reside. a shielding layer oriented along a third plane substantially parallel with the second plane is disposed at least partially between the cover structure and the housing structure and configured to attenuate radiated signals. a number of capacitor spot welds affix the shielding layer to the cover structure to improve component shielding.
- Google LLC
- A63F13/79
- A63F13/216
- G06F9/54
- G06F16/29
- G06F16/9537
- CPC A63F13/79
- Google llc
- G02B27/01
- G02C7/08
- G06F3/01
- G06V20/00
- G06V20/50
- CPC G02B27/0172
- H04N19/895
- CPC G02B27/0176
- CPC G02B27/0179
- G06F1/16
- CPC G06F1/1681
- G06F9/48
- CPC G06F9/4881
- G06F21/56
- CPC G06F21/566
- G06F21/57
- CPC G06F21/577
- G06F21/60
- G06F21/55
- CPC G06F21/602
- G06F21/62
- CPC G06F21/62
- H04L9/08
- CPC G06F21/6218
- G06F40/40
- G06N5/04
- G06N20/00
- CPC G06F40/40
- G06F40/58
- G06V10/44
- G06V10/77
- G06V10/82
- G06V20/62
- CPC G06F40/58
- G06N3/048
- CPC G06N3/048
- G06N3/088
- G06N3/0455
- CPC G06N3/088
- G06N3/092
- CPC G06N3/092
- G06N10/40
- G06N3/045
- G06N3/084
- G06N7/01
- G06N10/60
- G06N10/70
- CPC G06N10/40
- CPC G06N20/00
- G06N3/008
- G06Q30/0242
- CPC G06Q30/0246
- G06T5/50
- G06T5/20
- G06T5/60
- G06T7/70
- H04N23/56
- H04N23/90
- H04N23/95
- H04N25/40
- H04N25/532
- CPC G06T5/50
- G06T19/00
- G06T15/06
- G06V10/762
- CPC G06T19/003
- G06V10/774
- G06V10/74
- G06V10/764
- G06V10/776
- G06V20/70
- CPC G06V10/774
- G06V20/56
- G06V10/75
- CPC G06V20/588
- G10L13/00
- G06F40/253
- G06F40/289
- G10L13/08
- CPC G10L13/00
- CPC G10L13/08
- G10L15/01
- G01S3/80
- G10L15/08
- G10L15/32
- H04R29/00
- CPC G10L15/01
- G10L15/06
- G10L15/07
- G10L15/22
- G10L17/24
- CPC G10L15/063
- G10L15/18
- G10L15/187
- G10L15/197
- G10L15/30
- CPC G10L15/07
- G06F3/16
- G06F16/638
- G10L17/00
- G10L17/22
- CPC G10L15/22
- G10L19/038
- G06N3/08
- G10L19/00
- G10L25/30
- CPC G10L19/038
- G11C7/22
- G09G3/32
- G11C11/418
- G11C11/419
- CPC G11C7/222
- G16B30/00
- G06N3/09
- G16B40/20
- CPC G16B30/00
- H04L9/40
- CPC H04L9/085
- H04L12/18
- H04W68/02
- H04W72/30
- H04W76/27
- CPC H04L12/185
- H04L51/02
- G06F40/205
- G06F40/30
- CPC H04L51/02
- H04L67/1097
- H04L67/06
- CPC H04L67/1097
- H04N21/81
- CPC H04N21/816
- H04W36/00
- H04W76/15
- H04W76/28
- CPC H04W36/0069
- H04W36/36
- H04W76/20
- CPC H04W36/362
- H04W52/02
- CPC H04W52/0203
- H04W68/00
- H04W88/08
- CPC H04W68/005
- H04W76/40
- H04W74/0833
- CPC H04W76/40
- H05K9/00
- H05K1/02
- H05K1/18
- CPC H05K9/0032
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide
