GOOGLE LLC patent applications on June 20th, 2024
Patent Applications by GOOGLE LLC on June 20th, 2024
GOOGLE LLC: 69 patent applications
GOOGLE LLC has applied for patents in the areas of G10L15/22 (12), G06F3/16 (5), G10L15/06 (4), G06F21/62 (4), G06N20/00 (3) G10L15/22 (4), G10L15/063 (2), G06Q30/0627 (2), H04L51/02 (2), H02J50/70 (1)
With keywords such as: user, device, data, assistant, based, automated, audio, computing, include, and input in patent application abstracts.
Patent Applications by GOOGLE LLC
20240198232.EFFICIENT GAMEPLAY TRAINING FOR ARTIFICIAL INTELLIGENCE_simplified_abstract_(google llc)
Inventor(s): Nathan Sun Martz of San Francisco CA (US) for google llc, Horacio Hernan Moraldo of Mountain View CA (US) for google llc, Stewart Miles of San Francisco CA (US) for google llc, Leopold Haller of Berkeley CA (US) for google llc, Hinako Sakazaki of Albany CA (US) for google llc
IPC Code(s): A63F13/67, A63F13/352, A63F13/79, G06N5/04
CPC Code(s): A63F13/67
Abstract: systems and methods are described for training a locally executed actor component to execute real-time gameplay actions in a gaming application based on one or more gameplay data models generated by a remote learning service. a gameplay data model for the gaming application is provided from one or more server computing systems executing the remote learning service to the client computing device. observational data is generated by the local actor component based on in-game results of artificial gameplay actions performed by the local actor component, based at least in part on inferences generated by the actor component using the provided gameplay data model. based on the received observational data, the remote learning service modifies the gameplay data model and provides the modified gameplay data model to the local actor component to improve future artificial gameplay actions.
20240198541.ROBOT APPENDAGE ACTUATION_simplified_abstract_(google llc)
Inventor(s): J. Chase Kew of San Francisco CA (US) for google llc, James Lubin of Oakland CA (US) for google llc, Ken Caluwaerts of Los Angeles CA (US) for google llc, Stefano Saliceti of London (GB) for google llc, Brandon Kinman of Santa Cruz CA (US) for google llc, Byron David of San Jose CA (US) for google llc, Claudio Fantacci of London (GB) for google llc
IPC Code(s): B25J17/02, B25J19/00
CPC Code(s): B25J17/02
Abstract: in various implementations a removable appendage of a robot can allow for stable pitch and yaw, while mitigating interference with other movements of the robot. a neck of the robot can include at least two linear actuators, each coupled to a rod that is driven to move linearly from the linear actuators. an appendage of the robot can be coupled to the neck. the appendage can include a at least two tracks, where each track receives an end of the rods to slidably engage the rod.
20240200763.Modular Floodlight System_simplified_abstract_(google llc)
Inventor(s): Poll Shih of New Taipei City (TW) for google llc, Che-Wei Liu of New Taipei City (TW) for google llc, Chia-Chi Liu of Taipei City (TW) for google llc, Wen-Pin Chou of New Taipei City (TW) for google llc
IPC Code(s): F21V23/04, F21S8/00, F21V17/10, F21V33/00, F21W131/10, G08B13/19
CPC Code(s): F21V23/0471
Abstract: this document describes techniques directed to a modular floodlight system. the modular floodlight system includes a floodlight device having a main housing that supports multiple floodlights and a modular camera device. the main housing includes a magnetic mount that magnetically secures the camera device to a mounting surface and enables 3-axis articulation of the camera device relative to the main housing. the main housing also includes a power supply unit that supplies electrical power to the camera device and the floodlights. in aspects, the floodlights are assembled to opposing sides of the main housing. in addition, the main housing includes passive infrared sensors that expand and supplement motion-detection capabilities of the camera device. the modular aspect of the modular floodlight system enables the camera device to be easily replaced with another modular device, simplifies installation for consumers, and increases an ability of the modular floodlight system to be reworked.
Inventor(s): Dongeek Shin of Mountain View CA (US) for google llc
IPC Code(s): G01C21/34
CPC Code(s): G01C21/3484
Abstract: a computing system and method that can be used for a mapping system that can recommend paths for navigational routing to a primary user. more particularly, a primary user may be interested in navigational routes that secondary users, different from the primary user, have taken in the past. the mapping systems described herein can provide improved user navigational services by leveraging the insight that users who are connected (e.g., via social media, address books, etc.) may often be interested in visiting similar points of interest. more particularly, aspects of the present disclosure enable various interactions between connected users such as following in prior users' footsteps and taking a tour according to one or more prior users' route. alternatively, aspects of the present disclosure enable an optimization of a primary user's navigational routing by leveraging the insight that the primary user may share interests with connected secondary users. thus, the mapping system can generate a tailored navigational routing that guides the primary user optimally to the one or more predicted points of interests based on one or more historical navigational routings by connected secondary users.
Inventor(s): Sachin Prakash Nadig of San Francisco CA (US) for google llc, Isaac Chase Novet of Escondido CA (US) for google llc
IPC Code(s): G01K7/30, A61B5/00, A61B5/01, G01K1/143, G01K13/20
CPC Code(s): G01K7/30
Abstract: a known signal is sent to a resistor of a mobile computing device, wherein the resistor directly contacts a surface. a signal is from the resistor, wherein the signal comprises the known signal and a degree of thermal noise from the resistor, and wherein the degree of thermal noise is associated with a temperature of the surface. the thermal noise is extracted from the signal from the resistor. the temperature of the surface is determined based on the thermal noise extracted from the signal from the resistor.
Inventor(s): Anthony M. Fadell of Portola Valley CA (US) for google llc, Yoky Matsuoka of Los Altos Hills CA (US) for google llc, David Sloo of Menlo Park CA (US) for google llc, Maxime Veron of Los Altos CA (US) for google llc
IPC Code(s): G05B15/02, H04L12/28, H04W4/80
CPC Code(s): G05B15/02
Abstract: embodiments provided herein relate to enforcing a device restriction policy. a device restriction policy may be stored that maps one or more portions of a household with particular household occupants of a plurality of household occupants. a request may be received to activate the device restriction policy on a household occupant. the device restriction policy may be activated against the household occupant based on the received request. one or more electronic devices may be disabled that are located in a portion of the household linked with the household occupant based on the received request and the device restriction policy.
Inventor(s): Stiven Guillaume Francois Morvan of New York NY (US) for google llc, Dongeek Shin of San Jose CA (US) for google llc, Andrea Colaco of Los Altos CA (US) for google llc, Sambuddha Basu of San Jose CA (US) for google llc, Sean Kyungmok Bae of San Francisco CA (US) for google llc, Junyi Zhu of Cambridge MA (US) for google llc
IPC Code(s): G06F3/01, A61B5/0536, A61B5/263, G06V10/12, G06V10/764, G06V40/20
CPC Code(s): G06F3/017
Abstract: techniques include determining hand gestures formed by a user based on an electrical impedance tomograph of the wrist. for example, a user may be outfitted with a flexible wristband that fits snugly around the wrist and contains a plurality of electrodes, e.g., 32 electrodes. when a current is applied to a first subset of the electrodes, e.g., two of 32 electrodes, the electric field induced through at least one cross-section of the wrist will in turn induce a voltage across adjacent pairs of a second subset of the electrodes (e.g., the other 30 of 32 electrodes). from this current and induced voltage, one may use techniques of electrical impedance tomography (eit) to determine the electrical impedance throughout the at least one cross-section of the wrist, e.g., in an electrical impedance tomograph. one may use a neural network to map the electrical impedance tomograph to a hand gesture.
Inventor(s): Dongeek Shin of San Jose CA (US) for google llc
IPC Code(s): G06F3/16, G10L15/22
CPC Code(s): G06F3/165
Abstract: techniques disclosed herein are directed towards pairing a first audio data stream of a first client device with a second audio data stream of a second client device based on identifying a user has imitated playback of media at the second client device, where the imitation of the playback by the user occurs at the first client device. many implementations include the user controlling the media playback at the second client device using one or more automated assistant queries. various implementations include deleting the pairing between the first audio data stream and the second audio data stream in response to determining whether one or more conditions have been satisfied (e.g., whether the user stops the playback, whether the first client device is a threshold distance away from the second client device, whether a period of time has elapsed, whether the entire media has played at the second client device, whether one or more additional or alternative conditions are satisfied, and/or combinations thereof).
20240202072.Hardware Memory Error Tolerant Software System_simplified_abstract_(google llc)
Inventor(s): Jue Wang of Redmond WA (US) for google llc, Daniel Ryan Vance of Seattle WA (US) for google llc
IPC Code(s): G06F11/10, G06F11/07, G06F12/02, G06F12/0882
CPC Code(s): G06F11/1068
Abstract: systems and methods that enable hardware memory error tolerant software systems. for instance, the system may comprise a host device that instantiates a kernel agent in response to one or more requests to access hardware memory, determines, by the kernel agent based on the received information, whether the request to access memory will cause access to a corrupt memory location, and skip an operation associated with the corrupt memory location in response to determining that the request will access a corrupt memory location. the systems may also include a system that detects software vulnerabilities to hardware memory errors.
20240202102.Pre-Seeding Databases For Integration Testing_simplified_abstract_(google llc)
Inventor(s): Srinath Badrinath of Bangalore (IN) for google llc, Derek Karl Hunter of Redmond WA (US) for google llc, Benson Margulies of Seattle WA (US) for google llc
IPC Code(s): G06F11/36, G06F7/08, G06F11/14, G06F16/23
CPC Code(s): G06F11/3664
Abstract: aspects of the disclosure are directed to pre-seeding test databases in a computing environment for software testing. a system manages a pool of pre-seeded databases to serve user devices with different database requirements for their integration testing needs. pre-seeded databases can be served more efficiently over empty databases that are populated client-side. from a user perspective, databases appear ready instantly, ready for use as part of testing software using the pre-seeded databases as a stand-in for production data. pre-seeding databases circumvents the issues of wasted time and potential error that are otherwise possible when databases are served and populated client-side. pre-seeding data mitigates the need to seed the database during test-time, reducing the integration test cycle for software being tested. aspects of the disclosure provide for real-time restoration of databases by fixing portions of the database in place instead of outright deletion and recreation of an entire database.
Inventor(s): Xi Chen of San Jose CA (US) for google llc, Chao Ni of Sunnyvale CA (US) for google llc, Jakob Raymond Jones of San Jose CA (US) for google llc
IPC Code(s): G06F12/06, G06F9/54, G06F13/40
CPC Code(s): G06F12/0692
Abstract: a data processing device incorporates a plurality of chiplets having working elements such as processing and memory elements. at least one of the working elements is operative to generate messages directed to working elements of the same chiplet or another one of the chiplets. each message includes a global address. an evaluation circuit determines whether the global address of a message is within a range of global addresses assigned to the chiplet. if so, the message passes to a translation circuit which translates the message to a local address for routing to a working element of the chiplet. if not, the message is dispatched to one or more other chiplets.
20240202150.DYNAMIC TIMING CALIBRATION SYSTEMS AND METHODS_simplified_abstract_(google llc)
Inventor(s): Jens Kristian Poulsen of Kitchener (CA) for google llc
IPC Code(s): G06F13/362, G06F1/12, G06F13/40, G06F13/42, H04L7/00
CPC Code(s): G06F13/3625
Abstract: provided herein are systems and methods for performing dynamic adaption and correction for internal delays in devices connected to a common time-multiplexed bus. the methods allow devices to operate reliably at a higher bus frequency by correcting for inherent and unknown delays within the components and in the system by measuring the actual delays using multiple readings with the bus. intrinsic noise and jitter are used to increase the precision of the measurements, thereby essentially using these uncertainties as self-dithering for increased measurement resolution. during adaption, delays may be adjusted in multiple step sizes to speed adaption time.
20240202224.PROVIDING KNOWLEDGE PANELS WITH SEARCH RESULTS_simplified_abstract_(google llc)
Inventor(s): Jeromy William Henry of Aptos CA (US) for google llc
IPC Code(s): G06F16/34, G06F16/2457, G06F16/248, G06F16/338, G06F16/951
CPC Code(s): G06F16/345
Abstract: a method may receive, from a client computing device, a query that references an entity. a method may generate, from a set of content items related to the entity that have been obtained from multiple electronic resources, a user interface element that provides a summary for the entity, wherein the set of content items include multiple types of content items. a method may in response to receiving the query, provide, to the client computing device, data that causes the client computing device to present the user interface element in a search results page, the user interface element being different from search results for the query.
20240202232.Methods and Systems for Processing Imagery_simplified_abstract_(google llc)
Inventor(s): David Karam of Los Gatos CA (US) for google llc, Li Zhang of Seattle WA (US) for google llc, Ariel Gilder of Fair Lawn NJ (US) for google llc, Yuzo Watanabe of Seattle WA (US) for google llc, Eric Penner of Redmond WA (US) for google llc, Farooq Ahmad of Shoreline WA (US) for google llc, Hartwig Adam of Marina del Rey CA (US) for google llc
IPC Code(s): G06F16/583, G06F16/535, G06F16/55, G06N20/00
CPC Code(s): G06F16/583
Abstract: the present disclosure is directed to processing imagery using one or more machine learning (ml) models. in particular, data describing imagery comprising a plurality of different and distinct frames can be received; and based at least in part on one or more ml models and the data describing the imagery, and for each frame of the plurality of different and distinct frames, one or more scores can be determined for the frame. each score of the score(s) can indicate a determined measure of suitability of the frame with respect to one or more of various different and distinct uses for which the ml model(s) are configured to determine suitability of imagery.
20240202235.COORDINATION OF OVERLAPPING PROCESSING OF AUDIO QUERIES_simplified_abstract_(google llc)
Inventor(s): Bo Wang of San Jose CA (US) for google llc, Smita Rai of Saratoga CA (US) for google llc, Max Ohlendorf of Mountain View CA (US) for google llc, Subbaiah Venkata of Cupertino CA (US) for google llc, Chad Yoshikawa of Menlo Park CA (US) for google llc, Abhinav Taneja of Cupertino CA (US) for google llc, Amit Agarwal of Sunnyvale CA (US) for google llc, Chris Ramsdale of Palo Alto CA (US) for google llc, Chris Turkstra of San Jose CA (US) for google llc
IPC Code(s): G06F16/632, G06F16/638, G06F21/62
CPC Code(s): G06F16/634
Abstract: coordinating processing of audio queries is provided. a system receives a query. the system provides the query to a first digital assistant component and a second digital assistant component for processing. the system receives a first response to the query from the first digital assistant component, and a second response to the query from the second digital assistant component. the first digital assistant component can be authorized to access a database the second digital assistant component is prohibited from accessing. the system determines, based on a ranking decision function, to select the second response to the query from the second digital assistant component. the system provides, responsive to the selection, the second response from the second digital assistant to a computing device.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G06F16/9536, G06F16/2455, G06F16/9535, G06F16/9538
CPC Code(s): G06F16/9536
Abstract: techniques are described herein for collaborative search sessions through an automated assistant. a method includes: receiving, from a first user of a first client device, a first query in a query session; providing, to the first user, a first set of search results; determining, based on at least one term in the first query, that the first query is relevant to a second user of the first client device; providing, to the second user, a selectable option to join the query session; in response to receiving, from the second user, an indication of acceptance of the selectable option, adding the second user to the query session; receiving, from the second user, additional input; generating, based on the additional input received from the second user, a modified set of search results; and providing, to the first user and the second user, the modified set of search results.
Inventor(s): Victor Carbune of Zurich (CH) for google llc, Matthew Sharifi of Kilchberg (CH) for google llc
IPC Code(s): G06F16/9537
CPC Code(s): G06F16/9537
Abstract: implementations described herein relate to pairing a location-based automated assistant with a user device. the user device can include, for example, a headphones apparatus and/or a device that is paired with the headphones apparatus. the user device provides an indication that it is present at a location that is associated with a location-based automated assistant. a trust measure is determined that is indicative of trust between the user device and the location-based automated assistant. user information is provided by the user device to the location-based automated assistant. the location-based automated assistant determines response data to provide, via one or more speakers associated with the user device, that is specific to the location and further based on the user information.
20240202360.PRIVACY PRESERVING CUSTOM EMBEDDINGS_simplified_abstract_(google llc)
Inventor(s): Gang Wang of Frederick MD (US) for google llc, Alexander E. Mayorov of Kirkland WA (US) for google llc
IPC Code(s): G06F21/62, G06F21/53
CPC Code(s): G06F21/6245
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting and distributing digital components to client devices in ways that protect user privacy and confidential data of content platforms and/or digital component providers are described. in one aspect, a method includes receiving, by a secure distribution system and from a client device of a user, a digital component request that includes, for each of multiple content platforms that distribute digital components to users, a corresponding user embedding comprising weights indicative of the relevance of multiple features to the user. the secure distribution system provides each user embedding as input to a respective isolated execution environment for the content platform corresponding to the user embedding, wherein the secure distribution system hosts each isolated execution environment. digital component selection data generated based on the user embedding is received from each isolated execution environment.
20240202469.AUTO-TRANSLATION OF CUSTOMIZED ASSISTANT_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): G06F40/58, G06F40/35, G06F40/51
CPC Code(s): G06F40/58
Abstract: implementations relate to automatically translating a customized automated assistant from a first language to a new language, so that the automated assistant can interpret spoken utterances in the new language and respond to such spoken utterances in the new language. for example, a customized automated assistant can be configured for use in a first language through the developer(s) providing input(s) that are in the first language, and thereafter automatically translated to a distinct second language for which no developer input is provided. the deployment of the customized automated assistant for utilization with the second language can be selective. for example, it can be selective in that it is only automatically deployed and/or is only suggested for deployment in response to determining that one or more objective criteria, that indicate accuracy and/or robustness of the second language translation of the customized automated assistant, are satisfied.
20240202490.Lane Selection Using Machine Learning_simplified_abstract_(google llc)
Inventor(s): Thomas Deselaers of Zurich (CH) for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G06N3/006, B60W30/18, G06F18/21, G06N20/00, G06V10/764, G06V10/82, G06V20/56, G06V20/58
CPC Code(s): G06N3/006
Abstract: to select a lane in a multi-lane road segment for a vehicle travelling on the road segment, a system identifies, in multiple lanes and in a region ahead of the vehicle, another vehicle defining a target; the system applies an optical flow technique to track the target during a period of time, to generate an estimate of how fast traffic moves; and the system applies the estimate to machine learning (ml) model to generate a recommendation which one of the plurality of lanes the vehicle is to choose
20240202519.GENERATING VECTOR REPRESENTATIONS OF DOCUMENTS_simplified_abstract_(google llc)
Inventor(s): Quoc V. Le of Sunnyvale CA (US) for google llc
IPC Code(s): G06N3/08, G06F16/583, G06F40/284, G06N3/04, G06N3/084
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating document vector representations. one of the methods includes obtaining a new document; and determining a vector representation for the new document using a trained neural network system, wherein the trained neural network system has been trained to receive an input document and a sequence of words from the input document and to generate a respective word score for each word in a set of words, wherein each of the respective word scores represents a predicted likelihood that the corresponding word follows a last word in the sequence in the input document, and wherein determining the vector representation for the new document using the trained neural network system comprises iteratively providing each of the plurality of sequences of words to the trained neural network system to determine the vector representation for the new document using gradient descent.
Inventor(s): Jibing Wang of San Jose CA (US) for google llc, Erik Richard Stauffer of Sunnyvale CA (US) for google llc
IPC Code(s): G06N3/082, G06N3/04
CPC Code(s): G06N3/082
Abstract: systems and techniques provide for the joint training and implementation of an end-to-end chain of neural networks along the nodes of an at least partially wireless transmission path used to transmit a data stream between a data source device and at least one data sink device. the source-side neural networks of the chain can implement one or both of data encoding and channel encoding of outgoing data blocks, and the sink-side neural networks of the chain conversely can implement one or both of channel decoding and data decoding to provide efficient end-to-end transmission of the data stream without necessitating individual design, test, and implementation of discrete processes for each coding and decoding stage, while also facilitating the adaptation of the end-to-end neural network chaining process to various operational parameters.
20240202553.INFERRED USER INTENTION NOTIFICATIONS_simplified_abstract_(google llc)
Inventor(s): Oren Naim of Cupertino CA (US) for google llc, Tomer Amarilio of Palo Alto CA (US) for google llc, Dennis Ai of Mountain View CA (US) for google llc
IPC Code(s): G06N5/04, G06Q30/02
CPC Code(s): G06N5/04
Abstract: in one example, a method includes receiving, by a computing system, context information associated with a computing device; inferring, by the computing system and based on the context information, an action of a user of the computing device, the action associated with at least one entity; determining, by the computing system and based on stored attribute information associated with the at least one entity, and based on a stored set of rules associated with the inferred action, that the inferred action is not advisable; and responsive to determining that the inferred action is not advisable, outputting, by the computing system and for display on the computing device, notification data indicating that the inferred action is not advisable.
20240202589.Transformation For Machine Learning Pre-Processing_simplified_abstract_(google llc)
Inventor(s): Jiaxun Wu of Sammamish WA (US) for google llc, Amir Hossein Hormati of Seattle WA (US) for google llc
IPC Code(s): G06N20/00, G06F16/242, G06F16/25, G06N5/04
CPC Code(s): G06N20/00
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for transformation for machine learning pre-processing. in some implementations, an instruction to create a model is obtained. a determination is made whether the instruction specifies a transform. in response to determining that the instruction specifies a transform, a determination is made as to whether the transform requires statistics on the training data. the training data is accessed. in response to determining that the transform requires statistics on the training data, transformed training data is generated from both the training data and the statistics. a model is generated with the transformed training data. a representation of the transform and the statistics is stored as metadata for the model.
20240202795.Search with Machine-Learned Model-generated Queries_simplified_abstract_(google llc)
Inventor(s): Harshit Kharbanda of Pleasanton CA (US) for google llc, Arash Sadr of Belmont CA (US) for google llc, Alice Au Quan of San Francisco CA (US) for google llc, Belinda Luna Zeng of Cupertino CA (US) for google llc, Christopher James Kelley of Orinda CA (US) for google llc, Jieming Yu of Jersey City NJ (US) for google llc, Minsang Choi of San Francisco CA (US) for google llc
IPC Code(s): G06Q30/0601
CPC Code(s): G06Q30/0627
Abstract: systems and methods for searching using machine-learned model-generated outputs can provide a user with a medium for generating a theoretical dataset that can then be matched to a real world example. the systems and methods can include selecting a plurality of terms, which can be utilized to generate a prompt input that can be processed by a dataset generation model to generate a plurality of model-generated datasets. a selection can then be received that selects a particular model-generated database to utilize to query a database.
20240202796.Search with Machine-Learned Model-Generated Queries_simplified_abstract_(google llc)
Inventor(s): Arash Sadr of Belmont CA (US) for google llc, Alice Au Quan of San Francisco CA (US) for google llc
IPC Code(s): G06Q30/0601
CPC Code(s): G06Q30/0627
Abstract: systems and methods for searching using machine-learned model-generated outputs can provide a user with a medium for generating a theoretical dataset that can then be matched to a real world example. the systems and methods can include selecting a plurality of terms, which can be utilized to generate a prompt input that can be processed by a dataset generation model to generate a plurality of model-generated datasets. a selection can then be received that selects a particular model-generated database to utilize to query a database.
Inventor(s): Diego Martin Arroyo of Zürich (CH) for google llc, Alessio Tonioni of Zürich (CH) for google llc, Federico Tombari of Zug (CH) for google llc
IPC Code(s): G06T5/50, G06N3/08
CPC Code(s): G06T5/50
Abstract: . a computer-implemented method to perform image-to-image translation. the method can include obtaining one or more machine-learned generator models. the one or more machine-learned generator models can be configured to receive an input image and a user-specified conditioning vector that parameterizes one or more desired values for one or more defined characteristics of an output image. the one or more machine-learned generator models can be configured to perform, based at least in part on the user-specified conditioning vector, one or more transformations on the input image to generate the output image with the one or more desired values for the one or more defined characteristics. the method can include receiving the input image and the user-specified conditioning vector. the method can include generating, using the machine-learned generator model, an output image having the one or more desired values for the one or more characteristics.
20240202969.Depth-Based 3D Human Pose Detection and Tracking_simplified_abstract_(google llc)
Inventor(s): Yixuan Wang of Urbana IL (US) for google llc, Ting Lu of Fremont CA (US) for google llc
IPC Code(s): G06T7/73, B25J11/00, G06T7/246, G06T7/50
CPC Code(s): G06T7/74
Abstract: a method includes determining, for each respective keypoint of a plurality of keypoints that represents a plurality of predetermined body locations of an actor, an initial three-dimensional (3d) position of the respective keypoint. the method also includes receiving image data and depth data representing the body of the actor, and determining, for each respective keypoint, a visibility value based on a visibility of the respective keypoint in the image data and a depth field value based on the initial 3d position and a reference 3d position that is based on at least one nearest neighbor of the initial 3d position in the depth data. the method further includes determining, based on the visibility value and the depth field value of each respective keypoint, a loss value, and determining, for each respective keypoint, an updated 3d position of the respective keypoint based on the loss value.
Inventor(s): Arash Sadr of Belmont CA (US) for google llc, Igor Bonaci of Wollerau (CH) for google llc
IPC Code(s): G06T11/00, G06T7/70
CPC Code(s): G06T11/00
Abstract: systems and methods for enabling users to generate and utilize neural radiance field models can include obtaining user image data and training one or more neural radiance field models based on the user image data. the systems and methods can include obtaining user images based on a determination that the user images depicted objects of a particular object type. the trained neural radiance field models can then be utilized for view synthesis image generation of the particular user objects.
20240203006.Techniques for Generating Dynamic Content_simplified_abstract_(google llc)
Inventor(s): Zebedee Pedersen of Hove East Sussex (GB) for google llc, Luis De Jorge Ladrero of London (GB) for google llc, Marta Soto Morras of London (GB) for google llc, Kathryn Jane Strudwick of London (GB) for google llc
IPC Code(s): G06T11/60, G06F16/53
CPC Code(s): G06T11/60
Abstract: a computer-implemented method for generating dynamic content. the method can include receiving, from an output of one or more machine-learned models, a first generated image. the first generated image can be generated based on a user query. additionally, the method can include processing the first generated image, using the one or more machine-learned models, to determine a plurality of objects in the first generated image. moreover, the method can include determining, using the one or more machine-learned models, a subset of actions associated with a first object in the plurality of objects. furthermore, the method can include receiving a user input selecting a first action from the subset of actions associated with the first object. subsequently, the method can include modifying the first object in the first generated image in response to the selection of the first action.
20240203042.User-Context Aware Rendering Dataset Selection_simplified_abstract_(google llc)
Inventor(s): Igor Bonaci of Wollerau (CH) for google llc
IPC Code(s): G06T15/20, G06F3/04815, G06T19/00, H04N13/117
CPC Code(s): G06T15/205
Abstract: systems and methods for generating and providing augmented virtual environments can include obtaining user data, processing the user data to determine a plurality of objects associated with the user data, and generating one or more renderings of the objects in an environment. the renderings can be generated based on a plurality of rendering datasets obtained based on the plurality of determined objects determined to available to a user. the plurality of rendering datasets can include a plurality of three-dimensional meshes and/or a plurality of neural radiance field datasets. the one or more renderings can be provided via an interactive user interface that can allow a user to view renderings of different views of the objects in the environment from different positions and view directions.
Inventor(s): Adam Michael Stooke of San Francisco CA (US) for google llc, Khe Chai Sim of Dublin CA (US) for google llc, Mason Vijay Chua of Mountain View CA (US) for google llc
IPC Code(s): G10L15/06, G10L15/16, G10L15/183
CPC Code(s): G10L15/063
Abstract: a method includes obtaining a training text sample, the training text sample not paired with corresponding audio data, and generating a sequence of pseudo-random encoder variables. the method also includes processing, using a decoder of a sequence transduction model, the sequence of pseudo-random encoder variables to predict a probability distribution over possible output labels. the method further includes determining a loss based metric based on the training text sample and the predicted probability distribution over possible output labels, and training the decoder based on the loss metric.
Inventor(s): Ignacio Lopez Moreno of New York NY (US) for google llc, Quan Wang of Hobokan NJ (US) for google llc, Jason Pelecanos of New York NY (US) for google llc, Li Wan of New York NY (US) for google llc, Alexander Gruenstein of Mountain View CA (US) for google llc, Hakan Erdogan of Belmont MA (US) for google llc
IPC Code(s): G10L15/06, G10L15/07, G10L15/08, G10L15/20, G10L17/04, G10L17/20, G10L21/0208
CPC Code(s): G10L15/063
Abstract: implementations relate to an automated assistant that can bypass invocation phrase detection when an estimation of device-to-device distance satisfies a distance threshold. the estimation of distance can be performed for a set of devices, such as a computerized watch and a cellular phone, and/or any other combination of devices. the devices can communicate ultrasonic signals between each other, and the estimated distance can be determined based on when the ultrasonic signals are sent and/or received by each respective device. when an estimated distance satisfies the distance threshold, the automated assistant can operate as if the user is holding onto their cellular phone while wearing their computerized watch. this scenario can indicate that the user may be intending to hold their device to interact with the automated assistant and, based on this indication, the automated assistant can temporarily bypass invocation phrase detection (e.g., invoke the automated assistant).
Inventor(s): Nir Shabat of Geva (IL) for google llc, Volodymyr Polosukhin of Ramat Gan (IL) for google llc, Shlomo Fruchter of Ness Ziona (IL) for google llc, Golan Pundak of New York NY (US) for google llc, Roy Atsmon of Tel-Aviv (IL) for google llc
IPC Code(s): G10L15/18, G10L13/027, G10L15/26
CPC Code(s): G10L15/1815
Abstract: in various implementations, a method implemented by one or more processors of a computing device can comprise receiving audio data that captures a spoken utterance of a user; processing the audio data using an automatic speech recognition (asr) model to generate textual data corresponding to the spoken utterance; generating a semantic representation corresponding to the spoken utterance of the user based on applying both the audio data and the textual data as input across a large language model (llm); and causing the semantic representation corresponding to the spoken utterance of the user to be utilized in fulfilling the spoken utterance.
20240203406.Semi-Supervised Training Scheme For Speech Recognition_simplified_abstract_(google llc)
Inventor(s): Soheil Khorram of Redwood City CA (US) for google llc, Anshuman Tripathi of Mountain View CA (US) for google llc, Kim Jaeyoung of Cupertino CA (US) for google llc, Han Lu of Redmond WA (US) for google llc, Qian Zhang of Mountain View CA (US) for google llc, Hasim Sak of Santa Clara CA (US) for google llc
IPC Code(s): G10L15/183, G10L15/06, G10L15/22
CPC Code(s): G10L15/183
Abstract: a method includes receiving a sequence of acoustic frames extracted from unlabeled audio samples that correspond to spoken utterances not paired with any corresponding transcriptions. the method also includes generating, using a supervised audio encoder, a target higher order feature representation for a corresponding acoustic frame. the method also includes augmenting the sequence of acoustic frames and generating, as output form an unsupervised audio encoder, a predicted higher order feature representation for a corresponding augmented acoustic frame in the sequence of augmented acoustic frames. the method also includes determining an unsupervised loss term based on the target higher order feature representation and the predicted higher order feature representation and updating parameters of the speech recognition model based on the unsupervised loss term.
Inventor(s): Neeraj Gaur of Mountain View CA (US) for google llc, Tongzhou Chen of Mountain View CA (US) for google llc, Ehsan Variani of Mountain View CA (US) for google llc, Bhuvana Ramabhadran of Mt. Kisco NY (US) for google llc, Parisa Haghani of Mountain View CA (US) for google llc, Pedro J. Moreno Mengibar of Jersey City NJ (US) for google llc
IPC Code(s): G10L15/197, G10L15/00, G10L15/16, G10L15/22
CPC Code(s): G10L15/197
Abstract: a method includes receiving a sequence of acoustic frames extracted from audio data corresponding to an utterance. during a first pass, the method includes processing the sequence of acoustic frames to generate n candidate hypotheses for the utterance. during a second pass, and for each candidate hypothesis, the method includes: generating a respective un-normalized likelihood score; generating a respective external language model score; generating a standalone score that models prior statistics of the corresponding candidate hypothesis; and generating a respective overall score for the candidate hypothesis based on the un-normalized likelihood score, the external language model score, and the standalone score. the method also includes selecting the candidate hypothesis having the highest respective overall score from among the n candidate hypotheses as a final transcription of the utterance.
Inventor(s): Victor Carbune of Zurich (CH) for google llc, Matthew Sharifi of Kilchberg (CH) for google llc
IPC Code(s): G10L15/22, G06F3/16, G06T17/00, G06V10/74
CPC Code(s): G10L15/22
Abstract: implementations set forth herein relate to an automated assistant application that can be accessible via a virtual environment and can streamline certain assistant interactions by rendering certain virtual features within the virtual environment. when the automated assistant determines that a user is accessing a portion of a virtual environment that includes a particular virtual object, the automated assistant can identify application operations that may be associated with the particular virtual object. based on these identified operations, the automated assistant can cause rendering of certain virtual features in the virtual environment for initializing and/or otherwise controlling the operations. in some instances, these operations can affect the virtual environment and/or devices in a physical environment, as well as any other users that may be accessing the virtual environment. virtual features can thereafter be adapted, by the automated assistant, to streamline interactions that a user may be repeatedly occurring.
Inventor(s): Dongeek Shin of San Jose CA (US) for google llc
IPC Code(s): G10L15/22, G10L15/08
CPC Code(s): G10L15/22
Abstract: techniques are described herein for arbitration between automated assistant devices based on interaction cues. a method includes: receiving, via one or more microphones of a first computing device, first audio data that captures a spoken utterance of a user; determining that each of one or more additional computing devices has detected the spoken utterance of the user; determining that hotword arbitration is to be initiated between the first computing device and the one or more additional computing devices; for each of the first computing device and the one or more additional computing devices, identifying a similarity score for the computing device; selecting a target computing device, from the first computing device and the one or more additional computing devices, based on the similarity scores; and causing the target computing device to respond to a query that is included in the spoken utterance of the user.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zurich (CH) for google llc
IPC Code(s): G10L15/22, G10L15/30
CPC Code(s): G10L15/22
Abstract: implementations related to selecting a primary automated assistant for a given automated assistant device that is connected to one or more other automated assistant devices in an ecosystem of connected devices. an affinity score is generated for each of a plurality of candidate automated assistants that are capable of executing on the automated assistant device. the affinity score of a given automated assistant for an automated assistant device is indicative of suitability of the automated assistant for the automated assistant device. one of the candidate automated assistants is selected as the primary automated assistant for the device. the primary automated assistant is prioritized when resources of the automated assistant device are allocated to automated assistants executing on the automated assistant device.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc, Victor Carbune of Zürich (CH) for google llc
IPC Code(s): G10L15/22, G10L15/08
CPC Code(s): G10L15/22
Abstract: a method for combining hotwords in a single utterance receives, at a first assistant-enabled device (aed), audio data corresponding to an utterance directed toward the first aed and a second aed among two or more aeds where the audio data includes a query specifying an operation to perform. the method also detects, using a hotword detector, a first hotword assigned to the first aed that is different than a second hotword assigned to the second aed. in response to detecting the first hotword, the method initiates processing on the audio data to determine that the audio data includes a term preceding the query that at least partially matches the second hotword assigned. based on the at least partial match, the method executes a collaboration routine to cause the first aed and the second aed to collaborate with one another to fulfill the query.
Inventor(s): Akshay Goel of Seattle WA (US) for google llc, Nitin Khandelwal of Sunnyvale CA (US) for google llc, Richard Park of Palo Alto CA (US) for google llc, Brian Chatham of Pleasanton CA (US) for google llc, Jonathan Eccles of San Francisco CA (US) for google llc, David Sanchez of Burlingame CA (US) for google llc, Dmytro Lapchuk of Mountain View CA (US) for google llc
IPC Code(s): G10L15/32, G10L15/18, G10L15/22, G10L15/30
CPC Code(s): G10L15/32
Abstract: implementations described herein are directed to enabling collaborative ranking of interpretations of spoken utterances based on data that is available to an automated assistant and third-party agent(s), respectively. the automated assistant can determine first-party interpretation(s) of a spoken utterance provided by a user, and can cause the third-party agent(s) to determine third-party interpretation(s) of the spoken utterance provided by the user. in some implementations, the automated assistant can select a given interpretation, from the first-party interpretation(s) and the third-party interpretation(s), of the spoken utterance, and can cause a given third-party agent to satisfy the spoken utterance based on the given interpretation. in additional or alternative implementations, an independent third-party agent can obtain the first-party interpretation(s) and the third-party interpretation(s), select the given interpretation, and then transmit the given interpretation to the automated assistant and/or the given third-party agent.
Inventor(s): Quan Wang of Hoboken NJ (US) for google llc, Prashant Sridhar of New York NY (US) for google llc, Ignacio Lopez Moreno of New York NY (US) for google llc, Hannah Muckenhim of Martigny (CH) for google llc
IPC Code(s): G10L17/04, G10L17/00, G10L17/02, G10L17/18, G10L17/22, G10L25/18
CPC Code(s): G10L17/04
Abstract: techniques are disclosed that enable processing of audio data to generate one or more refined versions of audio data, where each of the refined versions of audio data isolate one or more utterances of a single respective human speaker. various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by processing a spectrogram representation of the audio data (generated by processing the audio data with a frequency transformation) using a mask generated by processing the spectrogram of the audio data and a speaker embedding for the single human speaker using a trained voice filter model. output generated over the trained voice filter model is processed using an inverse of the frequency transformation to generate the refined audio data.
Inventor(s): Victor Carbune of Zurich (CH) for google llc, Matthew Sharifi of Kilchberg (CH) for google llc
IPC Code(s): G10L17/06, G06F3/16, G06V20/00, G10L17/00, H04L51/02
CPC Code(s): G10L17/06
Abstract: implementations set forth herein relate to an automated assistant that can be customized by a user to provide custom assistant responses to certain assistant queries, which may originate from other users. the user can establish certain custom assistant responses by providing an assistant response request to the automated assistant and/or responding to a request from the automated assistant to establish a particular custom assistant response. in some instances, a user can elect to establish a custom assistant response when the user determines or acknowledges that certain common queries are being submitted to the automated assistant—but the automated assistant is unable to resolve the common query. establishing such custom assistant responses can therefore condense interactions between other users and the automated assistant. furthermore, as such interactions are more immediately resolved, the automated assistant can avoid wasteful consumption of computational resources that may otherwise occur during prolonged assistant interactions.
Inventor(s): Chandan KARADAGUR ANANDA REDDY of Cupertino CA (US) for google llc, Navin CHATLANI of Palo Alto CA (US) for google llc
IPC Code(s): G10L21/0232, G10L21/0224, G10L25/60
CPC Code(s): G10L21/0232
Abstract: implementations described herein relate to providing noise suppression for speech data with reduced power consumption. in some implementations, a computer-implemented method includes receiving a current time frame of speech data, e.g., after receiving a previous time frame associated with a previous noise suppression mask. the current time frame is transformed to a current frequency frame in the frequency domain. a noise classifier is used to determine whether to create a current noise suppression mask for the current frame. if it is determined to create the mask, the mask is created and multiplied by the current frequency frame to obtain a noise-suppressed frequency frame. if it is determined to not create the current mask, the previous noise suppression mask is multiplied with the current frequency frame to obtain the noise-suppressed frequency frame, without creating a mask. the noise-suppressed frequency frame is transformed to a time frame and output.
20240203456.ENHANCING AUDIO USING MULTIPLE RECORDING DEVICES_simplified_abstract_(google llc)
Inventor(s): Dimitri Kanevsky of Ossining NY (US) for google llc, Golan Pundak of New York NY (US) for google llc
IPC Code(s): G11B20/10, G06F3/16, G10L17/00, G10L21/0208, G10L21/028, G10L21/0364, G10L25/51, G10L25/84, H04M3/56
CPC Code(s): G11B20/10527
Abstract: various arrangements for enhancing audio are detailed herein. an audio stream and a second audio stream can be received. from these audio streams, a first audio source and a second audio source are extracted. a conversation between the first audio source and a third audio source that occurs within the audio streams is identified. an updated audio stream is generated that enhances the first audio source and diminishes the second audio source extracted from the audio stream and the second audio stream.
20240203517.Logical Memory Repair with a Shared Physical Memory_simplified_abstract_(google llc)
Inventor(s): Wilson Pradeep of Bangalore (IN) for google llc, Nikhil Karkare of Bangalore (IN) for google llc
IPC Code(s): G11C29/44, G11C29/00, G11C29/18
CPC Code(s): G11C29/4401
Abstract: this document describes techniques, methods, and apparatuses for logical memory repair. in some aspects, a memory built-in self-test (mbist) controller can perform logical memory repair for a memory cluster including a shared bus interface that is coupled to the mbist controller and configured to provide access to multiple logical memories. the memory cluster includes multiple physical memories that are coupled to the shared bus interface. at least one physical memory is configured to have two or more logical memories overlaid thereon. in example aspects, the physical memory includes arbitration logic coupled to a first address register and a second address register that are respectively configured to store a first faulty memory address and a second faulty memory address. the arbitration logic includes circuitry configured to arbitrate access to at least one spare memory portion responsive to the first faulty memory address conflicting with the second faulty memory address.
Inventor(s): Houle Gan of Santa Clara CA (US) for google llc, Shuai Jiang of San Jose CA (US) for google llc, Gregory Sizikov of Sunnyvale CA (US) for google llc, Xin Li of San Jose CA (US) for google llc, Chee Yee Chung of Milpitas CA (US) for google llc
IPC Code(s): H01F17/00, H05K5/00
CPC Code(s): H01F17/0006
Abstract: the disclosure relates to power modules that include elevated inductors with capacitors disposed under the inductors. in one aspect, a power module includes a first circuit board having a first surface and a second surface opposite the first surface. one or more inductors are mounted on the first surface. each of the one or more inductors includes a top surface and a bottom surface opposite the top surface and that faces the first surface of the first circuit board. each inductor is elevated above the first surface of the first circuit board such that at least a portion of the bottom surface of the inductor does not contact the first surface of the first circuit board. the first circuit board includes capacitors arranged in an area below the portion of the bottom surface of the inductor that does not contact the first surface of the first circuit board.
20240204239.Low-Emission Cylindrical-Winding Battery Design_simplified_abstract_(google llc)
Inventor(s): Jianmin Zhang of Los Gatos CA (US) for google llc, Mingfeng Xue of Mountain View CA (US) for google llc, Chi Kin Benjamin Leung of Sunnyvale CA (US) for google llc, Ramesh C. Bhardwaj of Fremont CA (US) for google llc, Sheba Devan of Pleasanton CA (US) for google llc
IPC Code(s): H01M10/04, H01M50/497
CPC Code(s): H01M10/0431
Abstract: the present document describes a low-emission cylindrical-winding battery design. the battery design is a rolled and stacked battery, with two or more winding rolls of cathode and anode layers separated by insulation layers, the winding rolls also being separated by a distance with the distance, in some embodiments, filled with a dielectric material. a first winding roll of first stacked anode and cathode layers and a second winding roll of second stacked anode and cathode layers are wound in a direction around a central axis of the battery. the first winding roll of first stacked anode and cathode layers follows a first stacking order with the anode and cathode layers alternating. the second winding roll of second stacked anode and cathode layers follows a second stacking order with the anode and cathode layers alternating opposite to the first stacking order. the alternating stacking orders cause the battery to produce a reduced h-field when compared with a battery having non-alternating stacking orders.
20240204399.PHASED ARRAY ANTENNA MODULE WITH ROTATIONAL CONTROL_simplified_abstract_(google llc)
Inventor(s): Ming SUN of Mountain View CA (US) for google llc, Mohammad Reza GHAJAR of Redwood City CA (US) for google llc
IPC Code(s): H01Q3/04, H01Q1/24, H01Q3/30
CPC Code(s): H01Q3/04
Abstract: implementations described herein relate to a phased array antenna module with rotational control. in some implementations, a mobile device includes at least one processor, motion sensors configured to provide sensor data to the processor, and a phased array antenna module. the antenna module includes an antenna array that includes multiple antennas arranged linearly along a first axis. a rotary actuator is coupled to the antenna module and can rotate the phased array antenna module about a second axis that is parallel to the first axis. the processor performs operations including determining an orientation of the mobile device based at least on the sensor data from the motion sensors, and providing control signals based on the orientation of the mobile device to the rotary actuator to cause the rotary actuator to rotate the phased array antenna module about the second axis.
20240204461.UNIVERSAL SERIAL BUS RECEPTACLE_simplified_abstract_(google llc)
Inventor(s): Bernard ZHU of Mountain View CA (US) for google llc, Yongquan LI of Mountain View CA (US) for google llc, Billy LIU of Mountain View CA (US) for google llc, Enzo YEH of Mountain View CA (US) for google llc, Robin HUANG of Mountain View CA (US) for google llc, Burton WEI of Mountain View CA (US) for google llc, Beck QIN of Mountain View CA (US) for google llc
IPC Code(s): H01R13/6584, H01R13/52
CPC Code(s): H01R13/6584
Abstract: a universal serial bus (usb) receptacle includes: an enclosure, a metal connector body positioned adjacent to the enclosure, and a conductive o-ring that surrounds the metal connector body and connects the metal connector body to the enclosure.
20240204517.Controlling Feeder Units For Self-Restoration Of Power_simplified_abstract_(google llc)
Inventor(s): Hammad Ahmad Khan of Leesburg VA (US) for google llc, Kei Hao of Anaheim CA (US) for google llc
IPC Code(s): H02J3/00, G01R19/165, H02J3/38
CPC Code(s): H02J3/001
Abstract: generally disclosed herein is a power system architecture for controlling self-healing operations for n number of feeder units. the power system architecture may restore power automatically to all feeder units when a loss of power occurs by reconfiguring the status of feeder unit breakers. the power system architecture may also reconfigure and restore power automatically by opening and closing feeder unit breakers when a loss of source returns. the power system architecture may further reconfigure and restore power automatically for as many feeder units as possible under abnormal conditions such as fault scenarios, breaker failures, operation failures, and relay failures.
20240204576.Wireless Charging Coil In Wearable Devices_simplified_abstract_(google llc)
Inventor(s): Qi Tian of San Jose CA (US) for google llc, Liang Jia of Palo Alto CA (US) for google llc, Tressa Christie Scott of San Francisco CA (US) for google llc, Srikanth Lakshmikanthan of Milpitas CA (US) for google llc
IPC Code(s): H02J50/70, H02J7/02, H02J50/10
CPC Code(s): H02J50/70
Abstract: the present disclosure provides for a wearable device having a wireless power receiving system that may inductively receive or transmit power. the wireless power receiving system includes a receiver coil having a profile that follows a contour of a bottom cover of the wearable device. a transmitter coil from a wireless charging device has a complementary profile that mates with the profile defined by the receiver coil. in one example, the wireless power receiving system includes a shielding, and a receiver coil attached to the shielding. the receiver coil further includes an inner wall and an outer wall connected by a top surface of a coil body. the inner wall defines a center opening in the receiver coil, wherein the receiver coil is conical in shape.
Inventor(s): Ofer Naaman of Santa Barbara CA (US) for google llc
IPC Code(s): H03K17/92
CPC Code(s): H03K17/92
Abstract: a josephson parametric device (e.g., a circulator/isolator or directional amplifier) can include a plurality of resonant modes, a plurality of couplings, an input port and an output port. the plurality of resonant modes includes first, second, and third resonant modes, the first and third resonant modes both configured to operate at a first resonant frequency and the second resonant mode configured to operate at a second resonant frequency that is different than the first resonant frequency. the plurality of couplings includes a passive coupling between the first and third resonant modes, a first parametric coupling between the first and second resonant modes, and a second parametric coupling between the second and third resonant modes. the input port is coupled to the first resonant mode of the device, and the output port is coupled to the third resonant mode of the device.
20240204988.Secure Multi-Party Reach and Frequency Estimation_simplified_abstract_(google llc)
Inventor(s): Craig Wright of Louisville CO (US) for google llc, Benjamin R. Kreuter of Jersey City NJ (US) for google llc, James Robert Koehler of Boulder CO (US) for google llc, Evgeny Skvortsov of Kirkland WA (US) for google llc, Arthur Asuncion of Mountain View CA (US) for google llc, Laura Grace Book of Mountain View CA (US) for google llc, Sheng Ma of Belmont CA (US) for google llc, Jiayu Peng of Sunnyvale CA (US) for google llc, Xichen Huang of Sunnyvale CA (US) for google llc
IPC Code(s): H04L9/08, G06F16/22, G06F16/23, G06F21/62, G06N7/01, H04L9/00, H04L9/06
CPC Code(s): H04L9/0825
Abstract: systems and methods for generating min-increment counting bloom filters to determine count and frequency of device identifiers and attributes in a networking environment are disclosed. the system can maintain a set of data records including device identifiers and attributes associated with device in a network. the system can generate a vector comprising coordinates corresponding to counter registers. the system can identify hash functions to update a counting bloom filter. the system can hash the data records to extract index values pointing to a set of counter registers. the system can increment the positions in the min-increment counting bloom filter corresponding to the minimum values of the counter registers. the system can obtain an aggregated public key comprising a public key. the system can encrypt the counter registers using the aggregated shared key to generate an encrypted vector. the system can transmit the encrypted vector to a networked worker computing device.
20240204991.METHODS FOR PROTECTING PRIVACY_simplified_abstract_(google llc)
Inventor(s): Sarvar Patel of Montville NJ (US) for google llc, Marcel M.M. Yung of New York NY (US) for google llc, Gang Wang of Frederick MD (US) for google llc, Karn Seth of New York NY (US) for google llc, Mariana Raykova of New York NY (US) for google llc, Benjamin R. Kreuter of Jersey City NJ (US) for google llc, Ananth Raghunathan of Mountain View CA (US) for google llc
IPC Code(s): H04L9/08, H04L9/32
CPC Code(s): H04L9/085
Abstract: a method including at each of a number of client devices receiving a data item, receiving a public key from a second computing system, encrypting the data item using the public key to produce a singly encrypted data item, engaging in an oblivious pseudorandom function protocol with a first computing system using the singly encrypted data item to produce a seed, generating an encrypted secret share using a threshold secret sharing function under which the encrypted secret share cannot be decrypted until a threshold number of encrypted secret shares associated with the same singly encrypted data item are received, and transmitting the encrypted secret share to the first computing system and at the first computing system receiving a number of encrypted secret shares from the number of client devices, processing the number of encrypted secret shares to produce processed data, and transmitting the processed data to a second computing system.
Inventor(s): Rohit Vijay Jog of Milpitas CA (US) for google llc, Cristina Schmidt of Mountain View CA (US) for google llc
IPC Code(s): H04L9/08, G06F11/14, G06F16/2457
CPC Code(s): H04L9/0894
Abstract: aspects of the disclosure relate to a system for responding to transient errors temporarily preventing a computing platform hosting data from communicating with an external key manager hosting keys used to encrypt the platform data. the encryption key can be controlled external to the system in an external key manager (ekm). if an error occurs in which the system and the ekm are temporarily not in communication, the external key controlled by the ekm is temporarily not available. the system begins an observation period, during which the observation period the system polls the ekm to check if the external key continues to be unavailable. the system unloads the encrypted data if, after the expiration of the observation period, the ekm is still not available. if the ekm and the external key becomes accessible again during the observation period, the system cancels the observation period and resumes normal operation.
Inventor(s): Alexander Bailey of Wollerau (CH) for google llc
IPC Code(s): H04L51/02, G10L13/033, H04L51/06
CPC Code(s): H04L51/02
Abstract: implementations relate to processing, utilizing a large language model (“llm”), input that is based on sensor data, from sensor(s) of a client device, to generate llm output—and causing output, that is based on the generated llm output, to be rendered by an interactive chatbot. the input that is based on sensor data and that is processed by the llm in generating the llm output can be, or can include, non-acoustic input based on non-acoustic sensor data. for example, an instance of llm output can be generated based on processing of non-acoustic input using the llm and without any processing of acoustic input (that is based on acoustic sensor data) using the llm. as another example, an instance of llm output can be generated based on processing, using the llm, both non-acoustic input that is based on non-acoustic data and acoustic input that is based on acoustic sensor data.
Inventor(s): Matthew Sharifi of Kilchberg (CH) for google llc
IPC Code(s): H04L51/02, G10L15/06, G10L15/22
CPC Code(s): H04L51/02
Abstract: implementations set forth herein relate to an automated assistant that facilitates the creation of complex messages from user input(s) to the automated assistant. each message can be created according to a respective template that is selected based on user input that directs the automated assistant to communicate a message to a recipient. furthermore, sections of a template can be designated for certain content based on prior messages communicated by one or more users to one or more recipients. in this way, in response to a user requesting that the automated assistant send a message, the automated assistant can select a related template and fill out the template accordingly. in some instances, content that is assigned to certain sections of the selected template can come from a variety of different sources and/or may not be explicitly specified in the request from the user to the automated assistant.
20240205278.Safe and Privacy Preserving Video Representation_simplified_abstract_(google llc)
Inventor(s): Colvin Pitts of Snohomish WA (US) for google llc, Yukun Zu of Shoreline WA (US) for google llc, Xuhui Jia of Seattle WA (US) for google llc
IPC Code(s): H04L65/403, G06T11/00, G06V20/40, G06V40/20, H04L9/40, H04N5/272
CPC Code(s): H04L65/403
Abstract: a computing system and method that can be used for safe and privacy preserving video representations of participants in a videoconference. in particular, the present disclosure provides a general pipeline for generating reconstructions of videoconference participants based on semantic statuses and/or activity statuses of the participants. the systems and methods of the present disclosure allow for videoconferences that convey necessary or meaningful information of participants through presentation of generalized representations of participants while filtering unnecessary or unwanted information from the representations by leveraging machine-learning models.
20240205293.Distributed Ambient Computing within an Environment_simplified_abstract_(google llc)
Inventor(s): Kenneth Mixter of Los Altos Hills CA (US) for google llc, Ken MacKay of Sunnyvale CA (US) for google llc, Byungchul Kim of Los Altos CA (US) for google llc
IPC Code(s): H04L67/12, G06F8/71, G06F21/44, H04L67/51
CPC Code(s): H04L67/12
Abstract: systems and techniques are provided for distributed ambient computing within an environment. a first version of an ambient computing library running on a device may check a manifest in the storage of the device to identify a second device that provides a service. the first version of the ambient computing library may send data to be processed using the service to the second device through a second version of the ambient computing library running on the second device. the first device and the second device may include different computing hardware. the first version of the ambient computing library may receive data including results from the second device through the second version of the ambient computing library. the data including the results may be generated by the second device based on processing the data sent from the device by the first version of the ambient computing library.
20240205326.Hand-Grip Location Detection Using Ultrasound_simplified_abstract_(google llc)
Inventor(s): Patrick M. Amihood of Palo Alto CA (US) for google llc, Octavio Ponce Madrigal of Mountain View CA (US) for google llc, Anton Heistser of Munich (DE) for google llc
IPC Code(s): H04M1/72454, H04M1/60
CPC Code(s): H04M1/72454
Abstract: techniques and apparatuses are described that implement hand-grip location detection using ultrasound. in particular, an ultrasonic sensor determines a location that a user's hand grips a user device. while gripping the user device, the hand creates an additional aperture area, which amplifies ultrasonic signals that are received by one or more transducers of the ultrasonic sensor that are proximate to the user's hand. by analyzing the amplitude (or power) of received ultrasonic signals, the ultrasonic sensor can detect if the user's hand is proximate to a particular transducer. in some implementations, the ultrasonic sensor utilizes speakers and/or microphones that are present within the user device. in this way, the ultrasonic sensor can have a relatively small footprint and fit within space-constrained devices.
Inventor(s): Yoav Tzur of Tel Aviv (IL) for google llc, Yaniv Leviathan of New York NY (US) for google llc, Yossi Matias of Tel Aviv (IL) for google llc, Eyal Segalis of Tel Aviv (IL) for google llc
IPC Code(s): H04M3/493, G10L15/22, G10L15/30
CPC Code(s): H04M3/493
Abstract: implementations receive, via a client device, user input to initiate a telephone call with an entity, and, in response to receiving the user input to initiate the telephone call with the entity and prior to initiating the telephone call with the entity: obtain pre-call information that is stored in association with the entity, and cause the pre-call information that is stored in association with the entity to be provided for presentation to the user via the client device. the pre-call information may include any information that would be provided for presentation to a user subsequent to initiation of the telephone call with the entity. further, implementations determine, based on user consumption of the pre-call information, whether to (1) proceed with initiating the telephone call with the entity, or (2) refrain from initiating the telephone call with the entity, and cause the client device to implement the appropriate action.
Inventor(s): Yoav Tzur of Tel Aviv (IL) for google llc, Yaniv Leviathan of New York NY (US) for google llc, Yossi Matias of Tel Aviv (IL) for google llc, Jan Jedrzejowicz of San Francisco CA (US) for google llc
IPC Code(s): H04M3/493, G06F40/35, G10L13/02, G10L15/18, G10L15/22, H04M3/527
CPC Code(s): H04M3/4936
Abstract: processor(s) of a client device of a user can receive a telephone call that is initiated by an additional user, and, in response to receiving the telephone call, identify an entity that is associated with the additional user, and determine, based on the entity that is associated with the additional user, whether to (1) fully automate the telephone call, or (2) partially automate the telephone call. in fully automating the telephone call, the processor(s) can cause a chatbot to engage in a corresponding conversation with the additional user and without prompting the user for any input. in partially automating the telephone call, the processor(s) can cause the chatbot to engage in a corresponding conversation with the additional user but with prompting the user for input(s) via suggestion chip(s). in some implementations, the processor(s) can further determine whether to (3) refrain from automating the telephone call entirely.
20240205458.TRANSFORM PREDICTION WITH PARSING INDEPENDENT CODING_simplified_abstract_(google llc)
Inventor(s): Onur Guleryuz of San Francisco CA (US) for google llc, Zeyu Deng of Santa Barbara CA (US) for google llc, Debargha Mukherjee of Cupertino CA (US) for google llc, Lester Lu of Los Angeles CA (US) for google llc, Yue Chen of Kirkland WA (US) for google llc
IPC Code(s): H04N19/61, H04N19/105, H04N19/12, H04N19/124, H04N19/13, H04N19/172, H04N19/176, H04N19/42
CPC Code(s): H04N19/61
Abstract: transform prediction with parsing independent coding includes generating a reconstructed frame and outputting the reconstructed frame. generating the reconstructed frame includes entropy decoding transform blocks for the reconstructed frame, entropy decoding decoded transform identifiers for the transform blocks, obtaining transform-specific probability distributions for available transforms, and, for a current transform block from the transform blocks, identifying a current remapped transform identifier from the decoded transform identifiers, identifying a current transform identifier in accordance with the current remapped transform identifier, the transform coefficients from the current transform block, and the transform-specific probability distributions, identifying a current transform in accordance with the current transform identifier; inverse transforming, in accordance with the current transform, the current transform block to obtain a current residual block and obtaining a current reconstructed block using the current residual block. generating the reconstructed frame includes including the current reconstructed block in the reconstructed frame.
Inventor(s): Chunlei Zhu of Mountain View CA (US) for google llc, Zekan Qian of Mountain View CA (US) for google llc, Weiming Liu of Mountain View CA (US) for google llc
IPC Code(s): H04N21/4402, G06F1/16
CPC Code(s): H04N21/440272
Abstract: the present disclosure describes techniques for optimizing screen utilization of a content item displayed on a client device. the method can include receiving, from a client device, a request for content including one or more parameters corresponding to a content slot. the method can include determining that a first display orientation of the content item does not match a second display orientation of the content slot. the method can include transmitting, responsive to determining that the first display orientation of the content item does not match the second display orientation of the content slot, the content item and instructions that when executed, cause the client device to adjust an aspect ratio of the content slot based on the first display orientation of the content item.
Inventor(s): Kliulai CHOW-YEE of Mountain View CA (US) for google llc, Tiffany LIN of Mountain View CA (US) for google llc, Warren JONES of Mountain View CA (US) for google llc, Josh ALEXANDER of Mountain View CA (US) for google llc
IPC Code(s): H04R3/04, H04R1/04, H05K1/14, H05K1/18
CPC Code(s): H04R3/04
Abstract: a circuit board assembly includes a top circuit board forming a microphone aperture and carrying electrical conductors. the circuit board assembly further includes a back-firing microphone connected to the top circuit board, the circuit board assembly providing support for the microphone, and the microphone electrically connected to the electrical conductors. the circuit board assembly further includes at least one interposer connected to the circuit board assembly, the at least one interposer positioned to the side of the back-firing microphone and including vias for providing a pathway for electrical connection to the top circuit board conductors.
20240205603.SPEAKER ARRAY ADDRESSED BY ROW AND COLUMN SELECTION_simplified_abstract_(google llc)
Inventor(s): Jyrki Antero Alakuijala of Wollerau (CH) for google llc, Matthew Sharifi of Kilchberg (CH) for google llc, Martin Bruse of Tyreso (SE) for google llc, Zoltan Szabadka of Gyorujbarat (HU) for google llc, Thomas Fischbacher of Gattikon (CH) for google llc, Sami Boukortt of Zurich (CH) for google llc, Moritz Firsching of Basel (CH) for google llc, Evgenii Kliuchnikov of Thalwil (CH) for google llc
IPC Code(s): H04R3/12, H03F3/217, H04R1/40
CPC Code(s): H04R3/12
Abstract: spatial audio may be generated by a speaker array that is switched according to rows and/or columns to reduce its cost and complexity. the speaker array may include a row of speakers that are each coupled to a different column channel. the rows of speakers can receive portions of the spatial audio on a row-by-row basis as each row is activated to couple the speakers in a row to their respective column. this switched approach reduces a number of required audio sources. the audio sources may generate pwm signals for each column using an approach that is similar to that found in class-d amplification or sigma-delta modulation. analog signals may be recovered from the pwm signals using a low-pass filter positioned before each speaker in the array.
20240205628.Spatial Audio for Device Assistants_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): H04S7/00, G06F3/16, G10L15/22
CPC Code(s): H04S7/302
Abstract: a method includes, while a user is wearing stereo headphones in an environment, obtaining, from a target digital assistant, a response to a query issued by the user, and obtaining spatial audio preferences of the user. based on the spatial audio preferences of the user, the method also includes determining a spatially disposed location within a playback sound-field for the user to perceive as a sound-source of the response to the query. the method further includes rendering output audio signals characterizing the response to the query through the stereo headphones to produce the playback sound-field. here, the user perceives the response to the query as emanating from the sound-source at the spatially disposed location within the playback sound-field.
20240205682.SECURE COMMUNICATION IN MOBILE DIGITAL PAGES_simplified_abstract_(google llc)
Inventor(s): Jay Akkad of Palo Alto CA (US) for google llc, Nikhil Rao of Santa Clara CA (US) for google llc, Anshul Gupta of San Francisco CA (US) for google llc, David Wang of San Carlos CA (US) for google llc, Ian Baker of San Francisco CA (US) for google llc, Neil Dhillon of Mountain View CA (US) for google llc
IPC Code(s): H04W12/30, G06F9/54, G06F16/18, G06F16/22, G06F16/957, G06F16/958, G06F21/62, G06F21/64, G06F40/226, H04L9/40, H04L67/01, H04L67/02, H04L67/568, H04W12/03, H04W12/08
CPC Code(s): H04W12/35
Abstract: secure communication in mobile digital pages is provided. the system receives an electronic document and validates the electronic document for storage in a cache server. the system receives a request for the electronic document and provides it to a viewer component on a client computing device. the viewer component loads the electronic document in an iframe. the viewer component executes a runtime component to receive, via a secure communication channel, a tag from the electronic document. the system receives the tag and selects a data value for transmission to the viewer component. the viewer components provides the data value to cause the runtime component to execute an action with the data value.
- GOOGLE LLC
- A63F13/67
- A63F13/352
- A63F13/79
- G06N5/04
- CPC A63F13/67
- Google llc
- B25J17/02
- B25J19/00
- CPC B25J17/02
- F21V23/04
- F21S8/00
- F21V17/10
- F21V33/00
- F21W131/10
- G08B13/19
- CPC F21V23/0471
- G01C21/34
- CPC G01C21/3484
- G01K7/30
- A61B5/00
- A61B5/01
- G01K1/143
- G01K13/20
- CPC G01K7/30
- G05B15/02
- H04L12/28
- H04W4/80
- CPC G05B15/02
- G06F3/01
- A61B5/0536
- A61B5/263
- G06V10/12
- G06V10/764
- G06V40/20
- CPC G06F3/017
- G06F3/16
- G10L15/22
- CPC G06F3/165
- G06F11/10
- G06F11/07
- G06F12/02
- G06F12/0882
- CPC G06F11/1068
- G06F11/36
- G06F7/08
- G06F11/14
- G06F16/23
- CPC G06F11/3664
- G06F12/06
- G06F9/54
- G06F13/40
- CPC G06F12/0692
- G06F13/362
- G06F1/12
- G06F13/42
- H04L7/00
- CPC G06F13/3625
- G06F16/34
- G06F16/2457
- G06F16/248
- G06F16/338
- G06F16/951
- CPC G06F16/345
- G06F16/583
- G06F16/535
- G06F16/55
- G06N20/00
- CPC G06F16/583
- G06F16/632
- G06F16/638
- G06F21/62
- CPC G06F16/634
- G06F16/9536
- G06F16/2455
- G06F16/9535
- G06F16/9538
- CPC G06F16/9536
- G06F16/9537
- CPC G06F16/9537
- G06F21/53
- CPC G06F21/6245
- G06F40/58
- G06F40/35
- G06F40/51
- CPC G06F40/58
- G06N3/006
- B60W30/18
- G06F18/21
- G06V10/82
- G06V20/56
- G06V20/58
- CPC G06N3/006
- G06N3/08
- G06F40/284
- G06N3/04
- G06N3/084
- CPC G06N3/08
- G06N3/082
- CPC G06N3/082
- G06Q30/02
- CPC G06N5/04
- G06F16/242
- G06F16/25
- CPC G06N20/00
- G06Q30/0601
- CPC G06Q30/0627
- G06T5/50
- CPC G06T5/50
- G06T7/73
- B25J11/00
- G06T7/246
- G06T7/50
- CPC G06T7/74
- G06T11/00
- G06T7/70
- CPC G06T11/00
- G06T11/60
- G06F16/53
- CPC G06T11/60
- G06T15/20
- G06F3/04815
- G06T19/00
- H04N13/117
- CPC G06T15/205
- G10L15/06
- G10L15/16
- G10L15/183
- CPC G10L15/063
- G10L15/07
- G10L15/08
- G10L15/20
- G10L17/04
- G10L17/20
- G10L21/0208
- G10L15/18
- G10L13/027
- G10L15/26
- CPC G10L15/1815
- CPC G10L15/183
- G10L15/197
- G10L15/00
- CPC G10L15/197
- G06T17/00
- G06V10/74
- CPC G10L15/22
- G10L15/30
- G10L15/32
- CPC G10L15/32
- G10L17/00
- G10L17/02
- G10L17/18
- G10L17/22
- G10L25/18
- CPC G10L17/04
- G10L17/06
- G06V20/00
- H04L51/02
- CPC G10L17/06
- G10L21/0232
- G10L21/0224
- G10L25/60
- CPC G10L21/0232
- G11B20/10
- G10L21/028
- G10L21/0364
- G10L25/51
- G10L25/84
- H04M3/56
- CPC G11B20/10527
- G11C29/44
- G11C29/00
- G11C29/18
- CPC G11C29/4401
- H01F17/00
- H05K5/00
- CPC H01F17/0006
- H01M10/04
- H01M50/497
- CPC H01M10/0431
- H01Q3/04
- H01Q1/24
- H01Q3/30
- CPC H01Q3/04
- H01R13/6584
- H01R13/52
- CPC H01R13/6584
- H02J3/00
- G01R19/165
- H02J3/38
- CPC H02J3/001
- H02J50/70
- H02J7/02
- H02J50/10
- CPC H02J50/70
- H03K17/92
- CPC H03K17/92
- H04L9/08
- G06F16/22
- G06N7/01
- H04L9/00
- H04L9/06
- CPC H04L9/0825
- H04L9/32
- CPC H04L9/085
- CPC H04L9/0894
- G10L13/033
- H04L51/06
- CPC H04L51/02
- H04L65/403
- G06V20/40
- H04L9/40
- H04N5/272
- CPC H04L65/403
- H04L67/12
- G06F8/71
- G06F21/44
- H04L67/51
- CPC H04L67/12
- H04M1/72454
- H04M1/60
- CPC H04M1/72454
- H04M3/493
- CPC H04M3/493
- G10L13/02
- H04M3/527
- CPC H04M3/4936
- H04N19/61
- H04N19/105
- H04N19/12
- H04N19/124
- H04N19/13
- H04N19/172
- H04N19/176
- H04N19/42
- CPC H04N19/61
- H04N21/4402
- G06F1/16
- CPC H04N21/440272
- H04R3/04
- H04R1/04
- H05K1/14
- H05K1/18
- CPC H04R3/04
- H04R3/12
- H03F3/217
- H04R1/40
- CPC H04R3/12
- H04S7/00
- CPC H04S7/302
- H04W12/30
- G06F16/18
- G06F16/957
- G06F16/958
- G06F21/64
- G06F40/226
- H04L67/01
- H04L67/02
- H04L67/568
- H04W12/03
- H04W12/08
- CPC H04W12/35
