View source for GOOGLE LLC patent applications on March 28th, 2024

=Patent Applications by GOOGLE LLC on March 28th, 2024=



[[:Category:GOOGLE LLC|GOOGLE LLC]]: 37 patent applications[[Category:GOOGLE LLC]]

GOOGLE LLC has applied for patents in the areas of [[:Category:G06N20/00|G06N20/00]] (8), [[:Category:G06N3/045|G06N3/045]] (6), [[:Category:G06F16/9535|G06F16/9535]] (6), [[:Category:G06F16/955|G06F16/955]] (4), [[:Category:G06F16/29|G06F16/29]] (4)

With keywords such as: data, content, device, user, computing, based, item, image, learning, and query in patent application abstracts.




====Patent Applications by GOOGLE LLC====


[[20240100693.USING EMBEDDINGS, GENERATED USING ROBOT ACTION MODELS, IN CONTROLLING ROBOT TO PERFORM ROBOTIC TASK_simplified_abstract_(google llc)]]

Inventor(s): Daniel Ho of Fremont CA (US) for google llc, Eric Jang of Cupertino CA (US) for google llc, Mohi Khansari of San Carlos CA (US) for google llc, Yu Qing Du of Berkeley CA (US) for google llc, Alexander A. Alemi of Kissimmee FL (US) for google llc

IPC Code(s): B25J9/16




Abstract: some implementations relate to using trained robotic action ml models in controlling a robot to perform a robotic task. some versions of those implementations include (a) a first modality robotic action ml model that is used to generate, based on processing first modality sensor data instances, first predicted action outputs for the robotic task and (b) a second modality robotic action ml model that is used to generate, in parallel and based on processing second modality sensor data instances, second predicted action outputs for the robotic task. in some of those versions, respective weights for each pair of the first and second predicted action outputs are dynamically determined based on analysis of embeddings generated in generating the first and second predicted action outputs. a final predicted action output, for controlling the robot, is determined based on the weights.[[Category:B25J9/16]][[Category:google llc]]



[[20240102677.SYSTEMS AND METHODS FOR PREDICTING REFRIGERANT LEAKAGE OF A CRITICALLY CHARGED HVAC/REFRIGERATION SYSTEM_simplified_abstract_(google llc)]]

Inventor(s): Evan Aschow of Fair Oaks CA (US) for google llc, Michael May of Reno NV (US) for google llc, Joel Cesare of Santa Cruz CA (US) for google llc, Tony Cacace of Santa Cruz CA (US) for google llc

IPC Code(s): F24F11/38, F24F11/36, F24F11/63, F25B45/00




Abstract: a system for predicting a leak of a hvac/refrigeration system includes a critically charged hvac/refrigeration system configured to circulate a refrigerant to cool a space, and processing circuitry. the processing circuitry is configured to obtain the subcooling data from the critically charged hvac/refrigeration system. the processing circuitry is configured to predict a leak event by providing the subcooling data as an input to a neural network. the neural network is trained using historical data of one or more subcooling parameters of a plurality of critically charged hvac/refrigeration systems. the processing circuitry is configured to operate a display to provide a notification to a technician or a manager regarding the predicted leak event at the critically charged hvac/refrigeration system.[[Category:F24F11/38]][[Category:F24F11/36]][[Category:F24F11/63]][[Category:F25B45/00]][[Category:google llc]]



[[20240102816.Customizing Instructions During a Navigations Session_simplified_abstract_(google llc)]]

Inventor(s): Matthew Sharifi of Kilchberg  (CH) for google llc

IPC Code(s): G01C21/34, G01C21/36, G10L15/16, G10L15/26




Abstract: methods and systems for customizing the presentation of navigation instructions to a user during a navigation session are disclosed herein. during a navigation session, a user can request to customize instructions being provided for the navigation session, such as increasing or decreasing a level of detail being provided to the user. based on the request, the system can determine one or modifications for instructions remaining in the navigation session, modify those instructions, and store the modified instructions for presentation to the user.[[Category:G01C21/34]][[Category:G01C21/36]][[Category:G10L15/16]][[Category:G10L15/26]][[Category:google llc]]



[[20240103270.OPTICAL COMBINERS WITH IMPROVED EFFICIENCY AND UNIFORMITY_simplified_abstract_(google llc)]]

Inventor(s): Shreyas Potnis of Kitchener  (CA) for google llc, Timothy Paul Bodiya of Toronto  (CA) for google llc

IPC Code(s): G02B27/01, G02B27/42




Abstract: systems, devices, and methods for directing display light employ one or more optical combiners that include recycle optics such as diffraction gratings, which can receive wasted display light travelling in a volume of an optical combiner, and redirect the wasted display light towards other optics so the wasted display light may be effectively used to produce a display. the optical combiners may also include a uniformization optic which can redistribute non-uniform display light, to produce a more uniform display, which in turn enables higher efficiency optics to be used.[[Category:G02B27/01]][[Category:G02B27/42]][[Category:google llc]]



[[20240103593.POWER ADAPTER THAT COMBINES  POWER INPUT AND COMMUNICATION INPUT_simplified_abstract_(google llc)]]

Inventor(s): Chia-Hang Yeh of Campbell CA (US) for google llc, Yuan-Jen Chang of New Taipei City  (TW) for google llc

IPC Code(s): G06F1/26, H04B3/54




Abstract: a power adapter can include a power input node, a communication channel node, an output node, a low-pass filter, a modulator, and a high-pass filter. the low-pass filter can include a low-pass input node coupled to the power input node and a low-pass output node coupled to the output node. the modulator can include a modulator input node coupled to the communication channel node and a modulator output node. the modulator can be configured to modulate data received from the communication channel node onto a signal having a higher frequency than a data-carrying signal carrying the data received from the communication channel node and output the modulated data to a high-pass input node of a high-pass filter. the high-pass filter can include the high-pass input node coupled to the modulator output node and a high-pass output node coupled to the output node.[[Category:G06F1/26]][[Category:H04B3/54]][[Category:google llc]]



[[20240103893.GENERATING CONTENT ENDORSEMENTS USING MACHINE LEARNING NOMINATOR(S)_simplified_abstract_(google llc)]]

Inventor(s): Deepak Ramachandran of Sunnyvale CA (US) for google llc, Sarvjeet Singh of Palo Aito CA (US) for google llc, Tania Bedrax-Weiss of Sunnyvale CA (US) for google llc

IPC Code(s): G06F9/451, H04L51/02




Abstract: techniques are disclosed that enable the generation of candidate endorsements for recommended items of content using an ensemble of nominators. various implementations include each nominator in the ensemble providing a candidate endorsement for each recommended item of content. additionally or alternatively, an endorsement is selected to present to the user based on a score determined for each candidate endorsement.[[Category:G06F9/451]][[Category:H04L51/02]][[Category:google llc]]



[[20240104012.TOPOLOGICAL SCHEDULING_simplified_abstract_(google llc)]]

Inventor(s): Lukasz Lew of Sunnyvale CA (US) for google llc

IPC Code(s): G06F12/02, G06F7/523, G06N3/063, G06N20/00




Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing topological scheduling on a machine-learning accelerator having an array of tiles. one of the methods includes performing, at each time step of a plurality of time steps corresponding respectively to columns within each of a plurality of wide columns of the tile array, operations comprising: performing respective multiplications using tiles in a respective tile column for the time step, computing a respective output result for each respective tile column for the time step including computing a sum of results of the multiplications for the tile column, and storing the respective output result for the tile column in a particular output ram having a location within the same tile column and on a row from which the output result will be read by a subsequent layer of the model.[[Category:G06F12/02]][[Category:G06F7/523]][[Category:G06N3/063]][[Category:G06N20/00]][[Category:google llc]]



[[20240104104.CONTEXTUAL SEARCH ON MULTIMEDIA CONTENT_simplified_abstract_(google llc)]]

Inventor(s): Gökhan Hasan BAKIR of Zurich  (CH) for google llc, Károly CSALOGÁNY of Zurich  (CH) for google llc, Behshad Behzadi of Zurich  (CH) for google llc

IPC Code(s): G06F16/2457, G06F16/43, G06F16/951, G06F16/9538




Abstract: techniques for contextual search on multimedia content are provided. an example method includes extracting entities associated with multimedia content, wherein the entities include values characterizing one or more objects represented in the multimedia content, generating one or more query rewrite candidates based on the extracted entities and one or more terms in a query related to the multimedia content, providing the one or more query rewrite candidates to a search engine, scoring the one or more query rewrite candidates, ranking the scored one or more query rewrite candidates based on their respective scores, rewriting the query related to the multimedia content based on a particular ranked query rewrite candidate and providing for display, responsive to the query related to the multimedia content, a result set from the search engine based on the rewritten query.[[Category:G06F16/2457]][[Category:G06F16/43]][[Category:G06F16/951]][[Category:G06F16/9538]][[Category:google llc]]



[[20240104108.Granular Signals for Offline-to-Online Modeling_simplified_abstract_(google llc)]]

Inventor(s): Loc Do of Irvine CA (US) for google llc

IPC Code(s): G06F16/248




Abstract: example aspects of embodiments of the present disclosure provide an example computer-implemented method. the example method includes receiving source activity data. the example method includes executing a query for target activity related to the source activity data. in the example method, executing the query includes determining, using a first machine-learned model of a machine-learned model framework, predicted target activity related to the source activity data. in the example method, executing the query includes generating, using a second machine-learned model of the machine-learned model framework, a predicted temporal distribution of target activity. the example method includes outputting, in response to the query, query results based at least in part on the predicted target activity and the predicted temporal distribution of target activity.[[Category:G06F16/248]][[Category:google llc]]



[[20240104126.METHODS, SYSTEMS, AND MEDIA FOR MODIFYING THE PRESENTATION OF CONTEXTUALLY RELEVANT DOCUMENTS IN BROWSER WINDOWS OF A BROWSING APPLICATION_simplified_abstract_(google llc)]]

Inventor(s): Eric HC Liu of Redwood City CA (US) for google llc

IPC Code(s): G06F16/335, G06F40/134, G06F40/14, G06Q10/107, G06Q50/00, H04J3/06, H04J3/16, H04L51/08




Abstract: methods, systems, and media for presenting contextually relevant information are provided. in some implementations, the method includes: receiving information associated with a user of a user device from multiple data sources, where the user device comprises a display; identifying, without user intervention, a relevant document based on the received information associated with the user of the user device; determining that a new browser window or a new browser tab has been opened by a browser application being executed by the user device; and causing, without user intervention, the relevant document to be presented using the new browser window or new browser tab.[[Category:G06F16/335]][[Category:G06F40/134]][[Category:G06F40/14]][[Category:G06Q10/107]][[Category:G06Q50/00]][[Category:H04J3/06]][[Category:H04J3/16]][[Category:H04L51/08]][[Category:google llc]]



[[20240104135.System and Method of Identifying Visual Objects_simplified_abstract_(google llc)]]

Inventor(s): David Petrou of Brooklyn NY (US) for google llc, Matthew Bridges of New Providence NJ (US) for google llc, Shailesh Nalawadi of Morgan Hill CA (US) for google llc, Hartwig Adam of Marina del Rey CA (US) for google llc, Matthew R. Casey of San Francisco CA (US) for google llc, Hartmut Neven of Malibu CA (US) for google llc, Andrew Harp of New York NY (US) for google llc

IPC Code(s): G06F16/535, G06F3/048, G06F16/50, G06F16/583, G06F16/9535, G06F16/9538, G06F18/2413, G06V10/10, G06V10/56, G06V10/96, G06V20/20, G06V20/62, G06V30/142, G06V30/19, H04N23/00




Abstract: a system and method of identifying objects is provided. in one aspect, the system and method includes a hand-held device with a display, camera and processor. as the camera captures images and displays them on the display, the processor compares the information retrieved in connection with one image with information retrieved in connection with subsequent images. the processor uses the result of such comparison to determine the object that is likely to be of greatest interest to the user. the display simultaneously displays the images the images as they are captured, the location of the object in an image, and information retrieved for the object.[[Category:G06F16/535]][[Category:G06F3/048]][[Category:G06F16/50]][[Category:G06F16/583]][[Category:G06F16/9535]][[Category:G06F16/9538]][[Category:G06F18/2413]][[Category:G06V10/10]][[Category:G06V10/56]][[Category:G06V10/96]][[Category:G06V20/20]][[Category:G06V20/62]][[Category:G06V30/142]][[Category:G06V30/19]][[Category:H04N23/00]][[Category:google llc]]



[[20240104140.INFERRING SEMANTIC LABEL(S) FOR ASSISTANT DEVICE(S) BASED ON DEVICE-SPECIFIC SIGNAL(S)_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): G06F16/9032, G10L15/30, G16Y10/80, G16Y40/35




Abstract: implementations can identify a given assistant device from among a plurality of assistant devices in an ecosystem, obtain device-specific signal(s) that are generated by the given assistant device, process the device-specific signal(s) to generate candidate semantic label(s) for the given assistant device, select a given semantic label for the given semantic device from among the candidate semantic label(s), and assigning, in a device topology representation of the ecosystem, the given semantic label to the given assistant device. implementations can optionally receive a spoken utterance that includes a query or command at the assistant device(s), determine a semantic property of the query or command matches the given semantic label to the given assistant device, and cause the given assistant device to satisfy the query or command.[[Category:G06F16/9032]][[Category:G10L15/30]][[Category:G16Y10/80]][[Category:G16Y40/35]][[Category:google llc]]



[[20240104150.Presenting Related Content while Browsing and Searching Content_simplified_abstract_(google llc)]]

Inventor(s): Srikanth Jalasutram of San Francisco CA (US) for google llc, Jia Sin Lua of San Mateo CA (US) for google llc, Damon Chizuru Kawamoto of Santa Cruz CA (US) for google llc, Jeffrey Allen Shaffer of Portland OR (US) for google llc, Jacob Francis Contreras of San Francisco CA (US) for google llc, Maurice Kenji Clarke of Oakland CA (US) for google llc, Ryan Michael Henbest of San Francisco CA (US) for google llc, Chengcheng Wang of Menlo Park CA (US) for google llc

IPC Code(s): G06F16/9535, G06F16/955, G06F16/957




Abstract: systems and methods for presenting an interface for additional content suggestion can include obtaining data descriptive of the displayed content and determining additional content associated with the displayed content. an interface can then be provided that displays data associated with the displayed content and the additional content. the interface can include a first viewing window for displaying a portion of the displayed content and a second viewing window for displaying a snippet associated with the additional content.[[Category:G06F16/9535]][[Category:G06F16/955]][[Category:G06F16/957]][[Category:google llc]]



[[20240104152.PROTOCOL BASED COMPUTER NETWORK CONTENT TRANSMISSION BASED ON CLIENT COMPUTING DEVICE PARAMETERS_simplified_abstract_(google llc)]]

Inventor(s): Krzystof Duleba of Zurich  (CH) for google llc, Amin charaniya of Santa Clara CA (US) for google llc, Vibhor Nanavati of Santa Clara CA (US) for google llc, Aileen Tang of Mountain View CA (US) for google llc

IPC Code(s): G06F16/9535, G06F16/29, G06F16/9038, G06F16/9537, H04L67/01, H04L67/303, H04L67/52




Abstract: a content management system server can obtain a protocol based data transmission via a computer network from a script that executes at the publisher device server, and can obtain search result content items from an index of electronic documents that include snippets of text extracted from the search result content items and that include hypertext links to the search result content items. the system can extract feature vectors and document identifiers of the search result content items, and can determine information retrieval scores of search result content items. based on the network identifier, location probabilities of device locations can be ranked and compared to thresholds. the system can determine a confidence threshold representing a minimum degree of certainty of the geographical location of the devices and can select content for protocol based transmission accordingly.[[Category:G06F16/9535]][[Category:G06F16/29]][[Category:G06F16/9038]][[Category:G06F16/9537]][[Category:H04L67/01]][[Category:H04L67/303]][[Category:H04L67/52]][[Category:google llc]]



[[20240104156.Systems and Methods for Selecting Content Based on Linked Devices_simplified_abstract_(google llc)]]

Inventor(s): Jianjun Qiu of Chicago IL (US) for google llc

IPC Code(s): G06F16/955, G06F3/16, G06F16/21, G06F16/22, G06F16/2457, G06F16/29, G06F16/951, G06N20/00, G06Q10/10, G06Q30/0241, G06Q30/0251, H04L67/02, H04L67/04, H04L67/10, H04L67/12, H04L67/125, H04L67/14, H04L67/50, H04L67/52




Abstract: a system includes a data processing system comprising one or more processors. the processor(s) are configured to identify one or more linking factors to determine that a first computing device is linked to a second computing device, with a certain probability, where the second computing device is proximate to the first computing device. the processor(s) are further configured to link the first computing device with the second computing device based on the determining, receive a request for content from the first computing device, provide the content to the second computing device, and generate a data structure to indicate a link between the first computing device and the second computing device.[[Category:G06F16/955]][[Category:G06F3/16]][[Category:G06F16/21]][[Category:G06F16/22]][[Category:G06F16/2457]][[Category:G06F16/29]][[Category:G06F16/951]][[Category:G06N20/00]][[Category:G06Q10/10]][[Category:G06Q30/0241]][[Category:G06Q30/0251]][[Category:H04L67/02]][[Category:H04L67/04]][[Category:H04L67/10]][[Category:H04L67/12]][[Category:H04L67/125]][[Category:H04L67/14]][[Category:H04L67/50]][[Category:H04L67/52]][[Category:google llc]]



[[20240104228.HIGH SPEED PRIVATE AND SECURE CROSS-ENTITY DATA PROCESSING_simplified_abstract_(google llc)]]

Inventor(s): Matthew Tran Clegg of Los Angeles CA (US) for google llc

IPC Code(s): G06F21/60




Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium. in one aspect, a method includes receiving, from a content distributor, plan data specifying a set of distribution plans that cause distribution of content. instructions are transmitted to publishers to submit secret shares of a multi-register sketch representing presentations of the content. a notification that the content distributor has requested an analysis of the presentations of the content is sent to a multi-party computing group. a result share of the analysis of the presentation of the content is received from multiple mpc devices in the mpc group. a set of result shares received from the of mpc devices are transmitted to the content distributor.[[Category:G06F21/60]][[Category:google llc]]



[[20240104234.ENCRYPTED INFORMATION RETRIEVAL_simplified_abstract_(google llc)]]

Inventor(s): Eli Simon Fox-Epstein of Los Angeles CA (US) for google llc, Kevin Wei Li Yeo of New York City NY (US) for google llc, Sarvar Patel of Montville NJ (US) for google llc, Raimundo Mirisola of Los Angeles CA (US) for google llc, Craig William Wright of Louisville CO (US) for google llc

IPC Code(s): G06F21/62




Abstract: encrypted information retrieval can include generating a database that is partitioned into shards each having a shard identifier, and database entries in each shard that are partitioned into buckets having a bucket identifier. a batch of client-encrypted queries are received. the batch of client-encrypted queries are processed using a set of server-encrypted data stored in a database. the processing includes grouping the client-encrypted queries according to shard identifiers of the client-encrypted queries, executing multiple queries in the group of client-encrypted queries for the shard together in a batch execution process, and generating multiple server-encrypted results to the multiple queries in the group of client-encrypted queries. the multiple server-encrypted results for each shard are transmitted to the client device.[[Category:G06F21/62]][[Category:google llc]]



[[20240104247.PRIVACY-AWARE MEETING ROOM TRANSCRIPTION FROM AUDIO-VISUAL STREAM_simplified_abstract_(google llc)]]

Inventor(s): Oliver Siohan of Mountain View CA (US) for google llc, Takaki Makino of Mountain View CA (US) for google llc, Richard Rose of Mountain View CA (US) for google llc, Otavio Braga of Mountain View CA (US) for google llc, Hank Liao of New York NY (US) for google llc, Basilio Garcia Castillo of Mountain View CA (US) for google llc

IPC Code(s): G06F21/62, G10L17/02, H04L12/18




Abstract: a method for a privacy-aware transcription includes receiving audio-visual signal including audio data and image data for a speech environment and a privacy request from a participant in the speech environment where the privacy request indicates a privacy condition of the participant. the method further includes segmenting the audio data into a plurality of segments. for each segment, the method includes determining an identity of a speaker of a corresponding segment of the audio data based on the image data and determining whether the identity of the speaker of the corresponding segment includes the participant associated with the privacy condition. when the identity of the speaker of the corresponding segment includes the participant, the method includes applying the privacy condition to the corresponding segment. the method also includes processing the plurality of segments of the audio data to determine a transcript for the audio data.[[Category:G06F21/62]][[Category:G10L17/02]][[Category:H04L12/18]][[Category:google llc]]



[[20240104312.Photorealistic Text Inpainting for Augmented Reality Using Generative Models_simplified_abstract_(google llc)]]

Inventor(s): Thomas Jonathan Stone of Zurich  (CH) for google llc, Darkhan Zholmukhanov of Adliswil  (CH) for google llc, Dawid Michal Wegner of Zurich  (CH) for google llc

IPC Code(s): G06F40/58, G06N3/04, G06T19/00




Abstract: provided are systems and methods that use generative models (e.g., generative adversarial networks) to enable photorealistic text inpainting in augmented reality. one example application of the proposed systems is to perform augmented reality translation. for example, a user can operate an image capture device (e.g., camera, smartphone, etc.) to capture imagery of a real-world scene that includes real-world text (e.g., signage, restaurant menus, etc.). the real-world text can be translated into a different language. further, the captured imagery can be processed with a machine-learned generative model to produce an augmented image. the augmented image can depict the real-world scene with the real-world text removed. specifically, because a machine-learned generative model is used, the augmented image can appear significantly more realistic, for example versus an image in which the real-world text has simply been blocked using a box with a single color.[[Category:G06F40/58]][[Category:G06N3/04]][[Category:G06T19/00]][[Category:google llc]]



[[20240104352.Contrastive Learning and Masked Modeling for End-To-End Self-Supervised Pre-Training_simplified_abstract_(google llc)]]

Inventor(s): Yu Zhang of Mountain View CA (US) for google llc, Yu-An Chung of Mountain View CA (US) for google llc, Wei Han of Mountain View CA (US) for google llc, Chung-Cheng Chiu of Mountain View CA (US) for google llc, Weikeng Qin of Sunnyvale CA (US) for google llc, Ruoming Pang of New York NY (US) for google llc, Yonghui Wu of Palo Alto CA (US) for google llc

IPC Code(s): G06N3/0455




Abstract: provided are improved end-to-end self-supervised pre-training frameworks that leverage a combination of contrastive and masked modeling loss terms. in particular, the present disclosure provides framework that combines contrastive learning and masked modeling, where the former trains the model to discretize input data (e.g., continuous signals such as continuous speech signals) into a finite set of discriminative tokens, and the latter trains the model to learn contextualized representations via solving a masked prediction task consuming the discretized tokens. in contrast to certain existing masked modeling-based pre-training frameworks which rely on an iterative re-clustering and re-training process or other existing frameworks which concatenate two separately trained modules, the proposed framework can enable a model to be optimized in an end-to-end fashion by solving the two self-supervised tasks (the contrastive task and masked modeling) simultaneously.[[Category:G06N3/0455]][[Category:google llc]]



[[20240104394.Platform for Automatic Production of Machine Learning Models and Deployment Pipelines_simplified_abstract_(google llc)]]

Inventor(s): Amy Skerry-Ryan of Mountain View CA (US) for google llc, Quentin Lascombes de Laroussilhe of Zurich  (CH) for google llc, Ronald Rong Yang of Cupertino CA (US) for google llc, Carla Marie Riggi of Richmond CA (US) for google llc, Chansoo Lee of Pittsburgh PA (US) for google llc, Jordan Arthur Grimstad of Zurich  (CH) for google llc, Christopher Mark Lamb of San Francisco CA (US) for google llc, Joseph Michael Moran of Arlington MA (US) for google llc, Nihesh Anderson Klutto Milleth of Mountain View CA (US) for google llc, Noah Weston Hadfield-Menell of San Francisco CA (US) for google llc, Volodymyr Shtenovych of Zurich  (CH) for google llc, Ziqi Huang of Mountain View CA (US) for google llc, Sagi Perel of Irvine CA (US) for google llc, Michael David Gerard of Orange CA (US) for google llc, Mehadi Seid Hassen of Milpitas CA (US) for google llc

IPC Code(s): G06N3/10, G06N3/045, G06N3/08




Abstract: provided are computing systems, methods, and platforms that automatically produce production-ready machine learning models and deployment pipelines from minimal input information such as a raw training dataset. in particular, one example computing system can import a training dataset associated with a user. the computing system can execute an origination machine learning pipeline to perform a model architecture search that selects and trains a machine learning model for the training dataset. execution of the origination machine learning pipeline can also result in generation of a deployment machine learning pipeline configured to enable deployment of the machine learning model (e.g., running the machine learning model to produce inferences and/or optionally other tasks such as re-training and/or re-tuning the model). the computing system can export the machine learning model and the deployment machine learning pipeline for deployment of the machine learning model with the deployment machine learning pipeline[[Category:G06N3/10]][[Category:G06N3/045]][[Category:G06N3/08]][[Category:google llc]]



[[20240104429.Model-Agnostic System for Automatic Investigation of the Impact of New Features on Performance of Machine Learning Models_simplified_abstract_(google llc)]]

Inventor(s): Madhav Datt of Mountain View CA (US) for google llc, Nikhil Shirish Ketkar of Bengaluru  (IN) for google llc, Arooshi Verma of Bengaluru  (IN) for google llc

IPC Code(s): G06N20/00, G06F11/34




Abstract: provided are computing systems, methods, and platforms that automatically investigate and analyze the impact of new features or signals on the performance of a machine learning model by producing a ranked list of the most impactful features from input of a set of candidate features. in particular, one example computing system can import a training dataset associated with a user. the computing system can train a machine learning model for the training dataset and generate baseline metrics for the machine learning model. correlations between features or signals in the training dataset can be identified and the features or signals can be grouped into clusters based on the correlations. the computing system can determine the importance of each cluster and each feature or signal. a ranked list of signals and their importances can be exported in decreasing order of machine learning model performance lift based on cluster importance and signal importance.[[Category:G06N20/00]][[Category:G06F11/34]][[Category:google llc]]



[[20240104435.USING MACHINE LEARNING TO DETECT WHICH PART OF THE SCREEN INCLUDES EMBEDDED FRAMES OF AN UPLOADED VIDEO_simplified_abstract_(google llc)]]

Inventor(s): Filip Pavetic of Zürich  (CH) for google llc, King Hong Thomas Leung of Saratoga CA (US) for google llc, Dmitrii Tochilkin of Zürich  (CH) for google llc

IPC Code(s): G06N20/00, G06F18/214, G06F18/241, G06V10/25, G06V10/764, G06V20/40




Abstract: a system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. a method may include providing data identifying a first image as input to a machine learning model trained using training data identifying a plurality of composite images that each include one or more constituent images, and determining, using one or more outputs of the trained machine learning model, that the first image is a composite image that includes a first constituent image, wherein at least a portion of the first constituent image is in a spatial area of the first image, and wherein the first constituent image corresponds to a frame of a video embedded into the first image.[[Category:G06N20/00]][[Category:G06F18/214]][[Category:G06F18/241]][[Category:G06V10/25]][[Category:G06V10/764]][[Category:G06V20/40]][[Category:google llc]]



[[20240104491.Auto-Constraint Generation for the Optimization of Planned Pickups and Deliveries_simplified_abstract_(google llc)]]

Inventor(s): Herbert Czymontek of Mountain View CA (US) for google llc

IPC Code(s): G06Q10/0835




Abstract: the present disclosure provides computer-implemented methods, systems, and devices for generating optimized delivery routes. a computing device receives a list of tasks to be performed. the computing device receives delivery constraint data describing constraints associated with one or more tasks in the list of tasks. the computing device accesses location constraint data describing constraints associated with one or more locations of one or more tasks in the list of tasks. the computing device generates an optimized delivery route based on the delivery constraint data and the location constraint data. the computing device transmits the optimized delivery route to a user computing device.[[Category:G06Q10/0835]][[Category:google llc]]



[[20240104786.DATA COMPRESSION USING INTEGER NEURAL NETWORKS_simplified_abstract_(google llc)]]

Inventor(s): Nicholas Johnston of San Jose CA (US) for google llc, Johannes Balle of San Francisco CA (US) for google llc

IPC Code(s): G06T9/00, G06F17/18, G06N3/045, G06N3/084




Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. in one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.[[Category:G06T9/00]][[Category:G06F17/18]][[Category:G06N3/045]][[Category:G06N3/084]][[Category:google llc]]



[[20240104930.Interacting with Visitors of a Connected Home Environment_simplified_abstract_(google llc)]]

Inventor(s): William Alexander Finlayson of San Francisco CA (US) for google llc, Liana Kong of Redwood City CA (US) for google llc, John Jordan Nold of Longmont CO (US) for google llc, Sahana Mysore of Menlo Park CA (US) for google llc, Ruiyi Song of Sunnyvale CA (US) for google llc

IPC Code(s): G06V20/52, G06F3/16, G06V20/40, G06V40/10, G06V40/20, G08B13/196




Abstract: the disclosure describes techniques for interacting with visitors at a visitor interaction system. a method includes obtaining video data captured by the visitor interaction system, identifying an approach of a person, and analyzing the video data to determine an identity of the person. the method includes automatically and without user intervention determining that the person belongs to a visitor groups of a plurality of visitor groups. each of the visitor groups corresponds to a response model that includes a plurality of response actions. at least one of the response actions includes an autonomous response action. the method includes identifying a response model corresponding to the visitor groups and initiating an autonomous response action associated with the response model. initiating the autonomous response action including presenting a message to the person, monitoring a response to the message, and sending a report message to the user via a client device.[[Category:G06V20/52]][[Category:G06F3/16]][[Category:G06V20/40]][[Category:G06V40/10]][[Category:G06V40/20]][[Category:G08B13/196]][[Category:google llc]]



[[20240105178.GROUP HOTWORDS_simplified_abstract_(google llc)]]

Inventor(s): Matthew Sharifi of Kilchberg  (CH) for google llc, Victor Carbune of Zürich  (CH) for google llc

IPC Code(s): G10L15/22, G06F3/16, G10L15/02, G10L15/08, G10L17/24




Abstract: a method includes a first assistant-enabled device (aed) receiving an assignment instruction assigning a group hotword to a selected group of aeds that includes the first aed and one or more other aeds. each aed is configured to wake-up from a low-power state when the group hotword is detected in streaming audio by at least one of the aeds. the method also includes receiving audio data that corresponds to an utterance spoken by the user and includes a query that specifies an operation to perform. in response to detecting the group hotword in the audio data, the method also includes triggering the first aed to wake-up from the low-power state and executing a collaboration routine to cause the first aed and each other aed in the selected group of aeds to collaborate with one another to fulfill performance of the operation specified by the query.[[Category:G10L15/22]][[Category:G06F3/16]][[Category:G10L15/02]][[Category:G10L15/08]][[Category:G10L17/24]][[Category:google llc]]



[[20240105180.SYSTEMS, METHODS, AND APPARATUSES FOR RESUMING DIALOG SESSIONS VIA AUTOMATED ASSISTANT_simplified_abstract_(google llc)]]

Inventor(s): Vikram Aggarwal of Palo Alto CA (US) for google llc, Jung Eun Kim of San Francisco CA (US) for google llc, Deniz Binay of Sunnyvale CA (US) for google llc

IPC Code(s): G10L15/22, G06F3/04842, G06F9/48, G10L25/51




Abstract: methods, apparatus, systems, and computer-readable media are provided for storing incomplete dialog sessions between a user and an automated assistant in order that the dialog sessions can be completed in furtherance of certain actions. while interacting with an automated assistant, a user can become distracted and not complete the interaction to the point of the automated assistant performing some action. in response, the automated assistant can store the interaction as a dialog session. subsequently, the user may express interest, directly or indirectly, in completing the dialog session, and the automated assistant can provide the user with a selectable element that, when selected, causes the dialog session to be reopened. the user can then continue the dialog session with the automated assistant in order that the originally intended action can be performed by the automated assistant.[[Category:G10L15/22]][[Category:G06F3/04842]][[Category:G06F9/48]][[Category:G10L25/51]][[Category:google llc]]



[[20240105190.GUIDING AMBISONIC AUDIO COMPRESSION BY DECONVOLVING LONG WINDOW FREQUENCY ANALYSIS_simplified_abstract_(google llc)]]

Inventor(s): Martin Bruse of Tyreso  (SE) for google llc, Jyrki Antero Alakuijala of Wollerau  (CH) for google llc, Moritz Firsching of Basel  (CH) for google llc, Thomas Fischbacher of Gattikon  (CH) for google llc, Sami Boukortt of Zurich  (CH) for google llc, Evgenii Kliuchnikov of Thalwil  (CH) for google llc

IPC Code(s): G10L19/022




Abstract: a method including receiving an audio signal, generating a transformed audio signal by transforming the audio signal using a plurality of windows each separated in time, generating an interpolated audio signal by interpolating the transformed audio signal, generating a separated audio signal by applying a mask to the interpolated audio signal, and compressing the separated audio signal.[[Category:G10L19/022]][[Category:google llc]]



[[20240105581.SIGNAL ROUTING IN INTEGRATED CIRCUIT PACKAGING_simplified_abstract_(google llc)]]

Inventor(s): Jin Young Kim of Mountain View CA (US) for google llc, Zhonghua Wu of Fremont CA (US) for google llc

IPC Code(s): H01L23/50, H01L23/498, H01L23/528




Abstract: in some implementations, a substrate for coupling to an integrated circuit includes multiple layers. each of the multiple layers has, in a particular region of the substrate, a repeating pattern of regions corresponding to power and ground. the multiple layers include (i) a top layer having, in the particular region, power contacts and ground contacts for coupling to an integrated circuit and (ii) a bottom layer having, in the particular region, power contacts and ground contacts for coupling to another device. at least one layer of the multiple layers has a repeating pattern of signal traces that extend along and are located between the regions corresponding to ground in the at least one layer.[[Category:H01L23/50]][[Category:H01L23/498]][[Category:H01L23/528]][[Category:google llc]]



[[20240105981.Multiple Battery Configurations for Space Utilization_simplified_abstract_(google llc)]]

Inventor(s): Ramesh C. Bhardwaj of Fremont CA (US) for google llc, Taisup Hwang of Santa Clara CA (US) for google llc

IPC Code(s): H01M10/04, G06F1/26, H01M6/02, H01M50/105, H01M50/211, H01M50/247, H01M50/512, H04M1/02




Abstract: example embodiments relate to multiple battery configurations for space utilization. one embodiment includes a device. the device includes a primary battery. the device also includes an auxiliary battery configured to supply auxiliary electrical power. a first surface of the auxiliary battery is positioned along a first surface of the primary battery. the auxiliary battery is a thin-film battery. the first surface of the auxiliary battery has a smaller area than the first surface of the primary battery.[[Category:H01M10/04]][[Category:G06F1/26]][[Category:H01M6/02]][[Category:H01M50/105]][[Category:H01M50/211]][[Category:H01M50/247]][[Category:H01M50/512]][[Category:H04M1/02]][[Category:google llc]]



[[20240106879.IDENTIFYING INSERTION POINTS FOR INSERTING LIVE CONTENT INTO A CONTINUOUS CONTENT STREAM_simplified_abstract_(google llc)]]

Inventor(s): Justin Lewis of Marina del Rey CA (US) for google llc, Ruxandra Georgiana Davies of Santa Monica CA (US) for google llc

IPC Code(s): H04L65/60, G11B27/02, H04N21/2187, H04N21/262, H04N21/414, H04N21/431, H04N21/482




Abstract: a system and method for identifying insertion points for inserting live content into a continuous content stream is disclosed. a live content item to include in a content stream presented to a user of a client device is identified. the live content item is identified based on a user preference of the user of the user. the live content item is determined to be presented based on a start time of the live content item. an indicator of the live content item is caused to be presented on a user interface at the start time of the live content item during playback of the content stream.[[Category:H04L65/60]][[Category:G11B27/02]][[Category:H04N21/2187]][[Category:H04N21/262]][[Category:H04N21/414]][[Category:H04N21/431]][[Category:H04N21/482]][[Category:google llc]]



[[20240107079.HIGH-FIDELITY GENERATIVE IMAGE COMPRESSION_simplified_abstract_(google llc)]]

Inventor(s): George Dan Toderici of Mountain View CA (US) for google llc, Fabian Julius Mentzer of Zürich  (CH) for google llc, Eirikur Thor Agustsson of Zürich  (CH) for google llc, Michael Tobias Tschannen of Zürich  (CH) for google llc

IPC Code(s): H04N19/91, G06N3/045, G06N3/088, H04N19/124, H04N19/154




Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an encoder neural network configured to receive a data item and to process the data item to output a compressed representation of the data item. in one aspect, a method includes, for each training data item: processing the data item using the encoder neural network to generate a latent representation of the training data item; processing the latent representation using a hyper-encoder neural network to determine a conditional entropy model; generating a compressed representation of the training data item; processing the compressed representation using a decoder neural network to generate a reconstruction of the training data item; processing the reconstruction of the training data item using a discriminator neural network to generate a discriminator network output; evaluating a first loss function; and determining an update to the current values of the encoder network parameters.[[Category:H04N19/91]][[Category:G06N3/045]][[Category:G06N3/088]][[Category:H04N19/124]][[Category:H04N19/154]][[Category:google llc]]



[[20240107106.DYNAMICALLY ADJUSTABLE ELECTRONIC PROGRAM GUIDE_simplified_abstract_(google llc)]]

Inventor(s): Michael Kleinerman of New York NY (US) for google llc, Neil Cormican of Menlo Park CA (US) for google llc

IPC Code(s): H04N21/431, H04N21/262, H04N21/414, H04N21/47, H04N21/482, H04N21/485




Abstract: metadata for media content items is received. the metadata identifies a thumbnail representation of the media content items. at least some of media content items are displayed in an overview area in an epg of a user interface. the overview area includes cells aligned in one or more rows. the cells include a subset of the metadata for a respective media content item. the subset of the metadata includes the thumbnail representations of media content items. a first media content item is displayed in a focus area in the epg of the user interface. the focus area includes expanded metadata having a sample of the first media content item that is played as an underlay of a display of at least some other metadata of the first media content item such that playback is presented underneath the display of the other metadata of the first media content item.[[Category:H04N21/431]][[Category:H04N21/262]][[Category:H04N21/414]][[Category:H04N21/47]][[Category:H04N21/482]][[Category:H04N21/485]][[Category:google llc]]



[[20240107125.SYSTEM AND METHOD FOR MODELLING ACCESS REQUESTS TO MULTI-CHANNEL CONTENT SHARING PLATFORMS_simplified_abstract_(google llc)]]

Inventor(s): Brian James Mulford of Rolling Hills Estates CA (US) for google llc, T.J. Gaffney of Mountain View CA (US) for google llc, Michael John de Ridder of Sunnyvale CA (US) for google llc, Colby D. Ranger of Palo Alto CA (US) for google llc

IPC Code(s): H04N21/647, H04N21/24, H04N21/25, H04N21/262, H04N21/472




Abstract: a system and method are disclosed for identifying a plurality of past videos posted via a first group of channels, determining, for each channel of a second group, an average number of access requests that a future video to be posted via a respective channel is predicted to receive within a first time interval after posting, determining, for each channel of the second group, a plurality of adjusted average numbers of access requests that the future video to be posted via the respective channel of the second group is predicted to receive within the first time interval, wherein each of the plurality of adjusted average numbers of access requests is determined using an adjustment factor reflecting a number of access requests received by a past video posted via a respective channel of the first group, and determining whether the second group of channels satisfies a predetermined access criterion.[[Category:H04N21/647]][[Category:H04N21/24]][[Category:H04N21/25]][[Category:H04N21/262]][[Category:H04N21/472]][[Category:google llc]]



[[20240107163.Multi-Camera Video Stabilization_simplified_abstract_(google llc)]]

Inventor(s): Youyou Wang of Cupertino CA (US) for google llc, Fuhao Shi of San Jose CA (US) for google llc, Chia-Kai Liang of San Jose CA (US) for google llc

IPC Code(s): H04N23/68, H04N23/69, H04N23/90




Abstract: methods, systems, and apparatus, including computer programs encoded on computer-storage media, for multi-camera video stabilization. in some implementations, a video capture device has a first camera and a second camera. the video capture device provides a digital zoom capability permitting user-specified magnification changes within a digital zoom range during video recording. the video capture device is configured to use video data from different cameras over different portions of the digital zoom range. the video capture device can process image data captured using the second camera by applying a set of transformations including (i) a first transformation to a canonical reference space for the second camera, (ii) a second transformation to a canonical reference space for the first camera, and (iii) a third transformation to apply electronic image stabilization to image data in the canonical reference space for the first camera.[[Category:H04N23/68]][[Category:H04N23/69]][[Category:H04N23/90]][[Category:google llc]]



[[20240107864.FOLDABLE DEVICE WITH BEZEL LOCATED CAMERA_simplified_abstract_(google llc)]]

Inventor(s): Michael J. Lombardi of South Barrington IL (US) for google llc, Joseph Allore of Mountain View CA (US) for google llc, Sangsoo Park of Mundelein IL (US) for google llc

IPC Code(s): H10K59/90, G06F1/16, H10K59/80




Abstract: a hinge assembly defining a first axis and a second axis; a first assembly rotatably connected to the hinge assembly about the first axis; a second assembly rotatably connected to the hinge assembly about the second axis, wherein, when the folding device is fully opened about the hinge assembly, an inner surface of the first assembly is coplanar with an inner surface of the second assembly; a flexible continuous display spanning an inner surface of the first assembly and an inner surface of the second assembly; and a camera having an aperture located in a bezel of the second assembly that borders the flexible continuous display.[[Category:H10K59/90]][[Category:G06F1/16]][[Category:H10K59/80]][[Category:google llc]]



[[GOOGLE LLC patent applications on March 28th, 2024]]



[[Category:GOOGLE LLC]] [[Category:G06N20/00]] [[Category:G06N3/045]] [[Category:G06F16/9535]] [[Category:G06F16/955]] [[Category:G06F16/29]]