GOOGLE LLC patent applications on May 8th, 2025
Patent Applications by GOOGLE LLC on May 8th, 2025
GOOGLE LLC: 50 patent applications
GOOGLE LLC has applied for patents in the areas of G06N20/00 (5), G10L15/22 (4), G02B27/01 (4), G10L15/18 (3), G06F40/40 (3) G06N20/00 (3), G02B27/0172 (3), G06F16/951 (2), G10L15/22 (1), G06Q30/0277 (1)
With keywords such as: user, data, content, device, display, based, input, methods, computer, and systems in patent application abstracts.
Patent Applications by GOOGLE LLC
Inventor(s): Dov Zimring of Belmont CA US for google llc, Paul Leventis of Mountain View CA US for google llc, Benjamin Frenkel of Mountain View CA US for google llc, Matthew Rodgers of San Jose CA US for google llc, Clinton Smullen of Mountain View CA US for google llc, Robert McCool of Menlo Park CA US for google llc
IPC Code(s): A63F13/358, A63F13/323, A63F13/335, A63F13/40, G06F9/455
CPC Code(s): A63F13/358
Abstract: an electronic server receives a request from a client device to establish a real-time interactive session, determines a device capability of an output device associated with the client device, determines a connection capability of the network connection, determines one or more target quality parameters for the real-time interactive session based on the device capability and the connection capability, selects a first virtual machine of the plurality of virtual machines based on the one or more target quality parameters, establishes the real-time interactive session with the client device, and provides to the real-time interactive session, in accordance with the resource profile of the first virtual machine, resources for processing inputs from the client device and generating outputs in accordance with the processed inputs within the real-time interactive session.
20250144795. CONTROLLING ROBOTS USING MULTI-MODAL LANGUAGE MODELS_simplified_abstract_(google llc)
Inventor(s): Peter Raymond Florence of San Francisco CA US for google llc, Danny Michael Driess of Berlin DE for google llc, Igor Mordatch of Oakland CA US for google llc, Andy Zeng of Stanford CA US for google llc, Seyed Mohammad Mehdi Sajjadi of Berlin DE for google llc, Klaus Greff of Berlin DE for google llc
IPC Code(s): B25J9/16
CPC Code(s): B25J9/1658
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment. in one aspect, a method comprises: receiving one or more observations of an environment; receiving an input text sequence that describes a task to be performed by a robot in the environment; generating an encoded representation of the input text sequence in an embedding space; generating a corresponding encoded representation of each of the one or more observations in the embedding space; generating a sequence of input tokens that comprises the encoded representation of the input text sequence and the corresponding encoded representation of each observation; processing the sequence of input tokens using a language model neural network to generate an output text sequence that comprises high-level natural language instructions; and determining, from the high-level natural language instructions, one or more actions to be performed by the robot.
20250146890. A Squeeze Detection System_simplified_abstract_(google llc)
Inventor(s): Mathieu Simon Le Goc of San Francisco CA US for google llc, Daniel Husum Cornew of Daly City CA US for google llc, Christopher Alan Oberhauser of San Jose CA US for google llc
IPC Code(s): G01L1/14, G01L5/22
CPC Code(s): G01L1/14
Abstract: a squeeze detection system includes an elongated body extending along a longitudinal direction. the elongated body has a handle. a sensor assembly is positioned within the elongated body proximate the handle. the sensor assembly includes conductive target mounted to the elongated body. an inductive sensor is also mounted to the elongated body. a gap is defined between a coil of the inductive sensor and a target surface of the conductive target. the conductive target and the inductive sensor are mounted to the elongated body such that a size of the gap is changeable in order to detect a squeeze in either a first direction or a second direction within a plane that is perpendicular to the longitudinal direction at the handle of the elongated body. the first and second directions are perpendicular.
20250147254. Easily Accessible Fiber Optic Panel Assembly_simplified_abstract_(google llc)
Inventor(s): Charles Poe of Palo Alto CA US for google llc, Mathew William Berg of Goose Creek SC US for google llc
IPC Code(s): G02B6/44
CPC Code(s): G02B6/4452
Abstract: a fiber optic panel assembly that includes one or more sliding trays disposed therein is provided. the sliding trays may slide out certain selected adaptor modules outward from other non-selected fiber optic modules in a vertical fashion is provided. in one example, the fiber optic panel assembly includes a ceiling, a bottom cover, and two opposing side panels defining an interior opening therein, and a curved support plate disposed in the interior opening of the fiber optic panel assembly, wherein the curved support plate has a plate body having a plurality of apertures, each aperture is configured to receive a respective adaptor.
Inventor(s): Thomas Hoekman of Redwood City CA US for google llc
IPC Code(s): G02B27/01, G02B6/34
CPC Code(s): G02B27/0172
Abstract: one or more diffractive gratings of a waveguide introduce a phase perturbation to offset a lateral color misalignment due to surface deformations such as non-parallelism of the major surfaces of the waveguide. in some embodiments, a pitch and/or angle of the diffractive grating is tuned to change the k-vector of the grating in the direction of a change in total thickness variation (ttv) across the waveguide.
Inventor(s): Josh Moore of Elora CA for google llc, Kaveh Moussakhani of Toronto CA for google llc, Jaehong Choi of Waterloo CA for google llc, Daniel Adema of Kitchener CA for google llc
IPC Code(s): G02B27/01, G02B27/00, G02C11/00, G08B21/18, H01Q1/24, H01Q1/27
CPC Code(s): G02B27/0172
Abstract: lightguide integrity monitoring in a head mounted display is facilitated by monitoring an elongated conductor disposed proximal a lightguide in an optical combiner. when a sufficient change in one or more electrical characteristics of the elongated conductor is detected, a signal indicating that the lightguide has been damaged may be generated, which may alert the user to the damage or disable one or more light sources in the hmd to prevent eye discomfort. the monitored electrical characteristics of the elongated conductor may include connectivity, impedance, and gain, among others. a sufficient change in the one or more electrical characteristics may be detected based on a percentage change in an electrical characteristic, a change in more than one electrical characteristic, or a change in a ratio of two electrical characteristics, among others.
Inventor(s): Oleg Yaroshchuk of Mountain View CA US for google llc, Ravi Kumar Komanduri of Milpitas CA US for google llc, Shreyas Potnis of Kitchener CA for google llc, Michael Anthony Klug of Austin TX US for google llc, Christopher Charles Townsend of Elora CA for google llc, Zheng Qin of Mountain View CA US for google llc, Xinda Hu of Sunnyvale CA US for google llc, Scott Fullam of Palo Alto CA US for google llc
IPC Code(s): G02B27/01, G02B27/28, H04N9/31
CPC Code(s): G02B27/0172
Abstract: a time-division multiplexed projection display is pixel shifted to produce an increased perceived display resolution or to mitigate image defects, such as defects in a display, a waveguide, or a prism, in an augmented, mixed, or virtual reality device. a polarizing beam splitter (pbs) divides input unpolarized display light into two orthogonal linear polarizations and directs them to two pbs arms. the pbs arms act to shift the light in synchronization with the time-multiplexed display such that a single pixel of the light engine providing the display light is converted into two or four virtual pixels, effectively increasing the perceived display resolution relative to the native resolution of the light engine. the pbs combines the light from both pbs arms into a single, unpolarized output that may then be projected into a lens or a waveguide incoupler to enable the light to propagate through a waveguide for display.
Inventor(s): Ravi Kumar Komanduri of Milpitas CA US for google llc, Oleg Yaroshchuk of Mountain View CA US for google llc, Shreyas Potnis of Kitchener CA for google llc, Michael Anthony Klug of Austin TX US for google llc
IPC Code(s): G02B27/28
CPC Code(s): G02B27/283
Abstract: a time-division multiplexed projection display is pixel shifted to produce an increased perceived display resolution. a polarizing beam splitter (pbs) divides input unpolarized display light into two orthogonal linear polarizations and directs them to two pbs arms. the pbs arms act to shift the light in synchronization with the time-multiplexed display such that a single pixel of the light engine providing the display light is converted into two or four virtual pixels, effectively increasing the perceived display resolution relative to the native resolution of the light engine. the pbs combines the light from both pbs arms into a single, unpolarized output that may then be projected into a lens or a waveguide incoupler to enable the light to propagate through a waveguide for display at a user's eye.
20250147337. MULTI-MATERIAL EYEWEAR DEVICE_simplified_abstract_(google llc)
Inventor(s): Geoffrey Gudgeon of Waterdown CA for google llc, Joshua Moore of Elora CA for google llc
IPC Code(s): G02C5/00, G02B27/01, G02C11/00
CPC Code(s): G02C5/008
Abstract: a multi-material eyewear device that can be utilized in an augmented reality (ar) or mixed reality (mr) eyewear display system includes an upper portion composed of a different material from one or more lower portions. the upper portion has a higher stiffness or stiffness-to-mass ratio than the lower portions, is less rf-permeable than the lower portions, and/or has a higher thermal conductivity than the lower portions. one or more antennas bonded to, housed in, or coextensive with the lower portions operate with high performance and efficiency due to the lower portions having higher rf-permeability than the upper portions, while the multi-material eyewear device maintains a high overall stiffness or stiffness-to-mass ratio due to the stronger material of the upper portion.
20250147561. Vapor Chamber with an Extended Base Plate_simplified_abstract_(google llc)
Inventor(s): Tyler Jon Ewing of Menlo Park CA US for google llc, Joseph Allore of Mundelein IL US for google llc, Michael J. Lombardi of South Barrington IL US for google llc
IPC Code(s): G06F1/20, H05K7/20
CPC Code(s): G06F1/203
Abstract: this document describes an electronic device with a chassis and a vapor chamber positioned within the chassis. the vapor chamber includes a base plate and a cap portion attached to the base plate to form a sealed chamber. the base plate extends outward beyond the sealed chamber to form an extended portion with a first edge attached to a sidewall of the chassis and a second edge, in the form of a mechanical flange, connected to the chassis. the base plate with the extended portion forms the floor of a battery compartment within the chassis and provides a thermal path between the vapor chamber and the chassis. by integrating the vapor chamber into the structural components, the need for a separate mid-plate is eliminated, allowing for a thinner device that efficiently dissipates heat while maintaining structural rigidity.
Inventor(s): David McIntosh of San Francisco CA US for google llc, Peter Chi Hao Huang of Pacifica CA US for google llc, Erick Hachenburg of San Francisco CA US for google llc, David Lindsay Bowen of San Francisco CA US for google llc, Joseph Lieu of San Francisco CA US for google llc, Kira Lee Psomas of Berkeley CA US for google llc, Jason R. Krebs of New York NY US for google llc, Kumar Garapaty of San Francisco CA US for google llc, Samantha Janelle Jiwei Lau of San Francisco CA US for google llc
IPC Code(s): G06F3/04886, G06F3/0482, G06Q30/0241, G06T13/80
CPC Code(s): G06F3/04886
Abstract: the present disclosure is directed to positioning animated images within a dynamic keyboard interface. in particular, the methods and systems of the present disclosure can: receive, from a user device on which an application is executed, data indicating a context of: the application, and/or a dynamic keyboard interface provided in association with the application; identify, based at least in part on the data indicating the context, a plurality of different animated images, including an animated image comprising an advertisement, for presentation by the dynamic keyboard interface; communicate, to the user device, data indicating the plurality of different animated images; receive, from the user device, data indicating a selection of the animated image comprising the advertisement; and determine, based at least in part on the data indicating the selection and the data indicating the context, a position within the dynamic keyboard interface for presenting the animated image comprising the advertisement.
Inventor(s): Matthew Sharifi of Kilchberg CH for google llc, Victor Carbune of Zurich CH for google llc
IPC Code(s): G06F3/16, G06F3/0488, G06F18/214, G06F18/22, G06N20/00, G10L15/22
CPC Code(s): G06F3/167
Abstract: implementations relate to an automated assistant that can automate repeatedly performed procedures. the automation can involve communicating with different users, organizations, and/or other automated assistants. the automated assistant, with prior permission from respective user(s), can detect repeated performance of a particular series of manually initiated computational actions. based on this determination, the automated assistant can determine automated assistant computational action(s) that can be performed by the automated assistant in order to reduce latency in performing a procedure, reduce quantity and/or size of transmissions in performing the procedure, and/or reduce an amount of client device resources required for performing the procedure. such actions can include communicating with an additional automated assistant that may be associated with another user and/or organization. in these and other manners, manually initiated computational actions that include electronic communications amongst users can be converted to backend operations amongst instances of automated assistants to achieve technical benefits.
Inventor(s): Keun Soo Yim of San Jose CA US for google llc
IPC Code(s): G06F9/451, G06F16/901
CPC Code(s): G06F9/451
Abstract: implementations set forth herein relate to providing suggestions for application services using tree data structures provided by various application sources. a native data structure, created by an assistant application or other related application, can be present in a local memory and, depending on the status of this native data structure, can be utilized to generate deep links to be rendered within the search interface. selection of a particular deep link can initialize particular operations and/or routines at one or more client or remote applications. when the native structure is unavailable, or does not satisfy certain criteria, other actions can be initiated for fetching data from remote sources or utilizing other locally available application data structures. in some implementations, graphical user interface elements indicating operation statuses can be rendered based on the available data structure(s), thereby aiding in selecting certain services across multiple applications.
20250147786. FLEXIBLE MEMORY MANAGEMENT FOR VIRTUAL MACHINES_simplified_abstract_(google llc)
Inventor(s): Vaibhav Balwant Nagarnaik of Santa Clara CA US for google llc, Rahul Chaturvedi of Mountain View CA US for google llc, Steven Aaron Richman of San Francisco CA US for google llc
IPC Code(s): G06F9/455
CPC Code(s): G06F9/45558
Abstract: a virtual machine monitor (vmm) of a computing system may provide flexible memory management for guest virtual machines (guest vms). the vmm may allocate a flexible amount of memory that is accessible to a guest vm. a guest vm may be configured, such as by vmm, to utilize a larger fixed amount of guest memory. a memory access error may be generated when guest vm accesses a memory location outside of the flexible memory. the vmm may receive the memory access error and allocate additional memory including at least the memory location to the flexible memory. the memory location may then be accessed without triggering a failure.
Inventor(s): Gopala Suryanarayana of Cupertino CA US for google llc, Diwakar Gupta of Seattle WA US for google llc, Naoshad Mehta of Mountain View CA US for google llc, Zoltan Kalmanovich of Brooklyn NY US for google llc, James Michael Chacon of Duvall WA US for google llc, Benoit Lefebvre of Campbell CA US for google llc
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5072
Abstract: a method includes obtaining, for each service of a plurality of services of a public cloud environment, a criticality classification. each criticality classification includes one of a critical classification, a semi-critical classification, or a non-critical classification. the method includes obtaining a maintenance schedule for the public cloud environment. the maintenance schedule includes a plurality of maintenance windows and each maintenance window of the plurality of maintenance windows is associated with a respective criticality classification. the method includes receiving a maintenance request requesting maintenance of one of the plurality of services. the method also includes determining that each maintenance window associated with the respective criticality classification of the one of the plurality of services is currently closed. in response to determining that each maintenance window associated with the respective criticality classification of the one of the plurality of services is currently closed, the method includes denying the maintenance request.
20250147985. COMBINED ACTIVITIES HISTORY ON A DEVICE_simplified_abstract_(google llc)
Inventor(s): Pierre-Yves Laligand of Versailles FR for google llc, Stephen Shui Lam Leung of Cupertino CA US for google llc, Justin Koh of Mountain View CA US for google llc, Richard William Bragg of Los Altos CA US for google llc
IPC Code(s): G06F16/28, G06Q30/00, G06Q30/02, G06Q50/00
CPC Code(s): G06F16/285
Abstract: this application is directed to performing a plurality of activities each of which is performed in a respective application with content associated with a content type selected from a group consisting of television programming, online content, on-device application, information views, and other content types. each activity is associated with a timestamp, and described using a predefined format covering an action and content associated with the action. each of the plurality of activities is then logged into an activities log in accordance with the predefined format. a plurality of user selectable affordances are displayed concurrently in a home screen on a display of the client device. each of the affordances is associated with one of the plurality of activities performed with associated content, and the plurality of affordances includes at least two affordances associated with two distinct activities of the plurality of activities performed by two distinct applications.
20250148013. LABEL PROPAGATION IN A DISTRIBUTED SYSTEM_simplified_abstract_(google llc)
Inventor(s): Matthew H. Austern of Palo Alto CA US for google llc, James C. Dehnert of Palo Alto CA US for google llc, Aart J.c. Bik of Union City CA US for google llc, Grzegorz J. Czajkowski of Mountain View CA US for google llc, Grzegorz Malewicz of Menlo Park CA US for google llc
IPC Code(s): G06F16/901
CPC Code(s): G06F16/9024
Abstract: data are maintained in a distributed computing system that describe a graph. the graph represents relationships among items. the graph has a plurality of vertices that represent the items and a plurality of edges connecting the plurality of vertices. at least one vertex of the plurality of vertices includes a set of label values indicating the at least one vertex's strength of association with a label from a set of labels. the set of labels describe possible characteristics of an item represented by the at least one vertex. at least one edge of the plurality of edges includes a set of label weights for influencing label values that traverse the at least one edge. a label propagation algorithm is executed for a plurality of the vertices in the graph in parallel for a series of synchronized iterations to propagate labels through the graph.
20250148024. INDEPENDENT CONTENT HOSTING SYSTEM_simplified_abstract_(google llc)
Inventor(s): Tarik Ono of Vancouver CA for google llc, Xiguo Ma of Mountain View CA US for google llc, Yanling Zhang of Menlo Park CA US for google llc, Jiewen Wu of San Francisco CA US for google llc, Yuanyuan Yang of Jersey City NJ US for google llc, Yan Zhang of San Jose CA US for google llc, Negin Nejati of Mountain View CA US for google llc, Yi Liang of Jersey City NJ US for google llc, Alexander Fischer of Brooklyn NY US for google llc
IPC Code(s): G06F16/951, G06F16/9538
CPC Code(s): G06F16/951
Abstract: implementations relate to a system for hosting independent content items anchored to another online resource. the independent content items are themselves online resources. implementations also relate to enhancing search results by incorporating independent content items anchored to a resource identified in the search result page. an example method involves identifying resources to be included in search results for a query, determining that independent content items are associated with a resource, and adding an independent content item summary control to the search result for the resource. this control enables users to access an independent content feed interface for further exploration of the independent content items anchored to the resource. the search result page, enriched with these independent content item overview, is then delivered to the user's device.
Inventor(s): Qifan Wang of Sunnyvale CA US for google llc, Dongfang Liu of Rochester NY US for google llc
IPC Code(s): G06F16/951, G06F16/80
CPC Code(s): G06F16/951
Abstract: the technology provides a rich attention mechanism for structured information extraction of web pages and other electronic documents. an input layer of a model obtains system, information associated with the document, including field tokens representing respective fields to be extracted from the document, structured document type tokens associated, and text tokens from a text sequence in the document. an encoder connects the field tokens, the s type tokens and the text tokens according to a set of different attention patterns. the encoder generates an overall token representation based on the set of different attention patterns. an output layer of the model extracts a final text span for the each of the respective fields from the set of text tokens. the extracted final text span for each of the respective fields is stored in memory, and can be produced in response to a search query, analytics evaluation or other request.
20250148030. Generating Prompts for User Link Notes_simplified_abstract_(google llc)
Inventor(s): Kinton Cheung of Toronto CA for google llc, Rosemond Gerold Dorleans of San Francisco CA US for google llc, Vishu Goyal of Mountain View CA US for google llc, Bradley Charles Kellett of Los Altos CA US for google llc, Rohan Sarith Rogers of Sunnyvale CA US for google llc, Negin Nejati of Mountain View CA US for google llc, Gulhan Serhat of San Jose CA US for google llc, Pu Han of Mountain View CA US for google llc, Michiel Filip Kosters of Irvine CA US for google llc, Shekhar Agrawal Sharad of San Jose CA US for google llc
IPC Code(s): G06F16/9538, G06F16/9535
CPC Code(s): G06F16/9538
Abstract: systems and methods for generating prompts for user data entry can include obtaining context data. the context data can be processed to determine whether an input entry interface is to be provided. in response to determining an input entry interface is to be provided, the context data or other data associated with a content display instance can be processed with a generative model to generate a prompt that can be provided to the user. user input data can then be obtained and stored to be provided to other users.
Inventor(s): Esteban Alberto Real of Sunnyvale CA US for google llc, Mirko Rossini of Brooklyn NY US for google llc, Connal Joseph de Souza of New York NY US for google llc, Manav Garg of Milpitas CA US for google llc
IPC Code(s): G06F17/11
CPC Code(s): G06F17/11
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing a target function for execution on a target processor. in particular, the target function is optimized by searching through candidate computer programs that each represent an approximation of the target function.
20250148122. DATA COLLECTION ANALYSIS FOR PRIVACY RISK ASSESSMENT_simplified_abstract_(google llc)
Inventor(s): Radhika Ravindranath of South Plainfield NJ US for google llc, James Paul Black of Sunnyvale CA US for google llc, Dev Narendrabhai Patel of Gujarat IN for google llc
IPC Code(s): G06F21/62, G06F21/57
CPC Code(s): G06F21/6245
Abstract: a method includes identifying, by a processing device, a third-party service provider of a plurality of third-party service providers that is authorized by a user to access data associated with the user. a data privacy score is generated based on one or more privacy risk factors. the data privacy score is associated with the third-party service provider. the data privacy score is indicative of a level of protection and privacy the third-party service provider maintains with respect to the data. a user interface (ui) displaying at least the data privacy score associated with the third-party service provider is provided for presentation on a client device associated with the user.
Inventor(s): Gilman Edwin Tolle of San Francisco CA US for google llc
IPC Code(s): G06F40/20, H04L51/21, H04N21/4788
CPC Code(s): G06F40/20
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating natural language summaries of user messages using language model neural networks.
Inventor(s): Matthew Sharifi of Kilchberg CH for google llc, Victor Carbune of Zurich CH for google llc
IPC Code(s): G06F40/40, G06F40/166
CPC Code(s): G06F40/40
Abstract: implementations utilize a hybrid use of a smaller llm and a larger llm to generate and refine content responsive to a user query/request for content generation. in various implementations, the smaller llm is utilized to process the user query for content generation, to generate initial content responsive to the user query for content generation. the user query for content generation and the initial content can be utilized to generate a text prompt, where the text prompt can be configured to further include a request for focused edit(s). such a text prompt can be processed using the larger llm, to generate focused edit(s) to the initial content that refine the initiated content, so that revised content (with improved accuracy) responsive to the user query for content generation is acquired.
20250148224. Techniques and Models for Multilingual Text Rewriting_simplified_abstract_(google llc)
Inventor(s): Xavier Eduardo Garcia of New York NY US for google llc, Orhan Firat of New York NY US for google llc, Noah Constant of Cupertino CA US for google llc, Xiaoyue Guo of San Francisco CA US for google llc, Parker Riley of Mountain View CA US for google llc
IPC Code(s): G06F40/58, G06F40/166, G06F40/197, G06F40/253, G06F40/56, G06N3/045, G06N3/047, G06N3/08, G06N3/084
CPC Code(s): G06F40/58
Abstract: the technology provides a model-based approach for multilingual text rewriting that is applicable across many languages and across different styles including formality levels or other textual attributes. the model is configured to manipulate both language and textual attributes jointly. this approach supports zero-shot formality-sensitive translation, with no labeled data in the target language. an encoder-decoder architectural approach with attribute extraction is used to train rewriter models that can thus be used in âuniversalâ textual rewriting across many different languages. a cross-lingual learning signal can be incorporated into the training approach. certain training processes do not employ any exemplars. this approach enables not just straight translation, but also the ability to create new sentences with different attributes.
20250148257. AUTOMATED ASSISTANT INVOCATION OF APPROPRIATE AGENT_simplified_abstract_(google llc)
Inventor(s): Ilya Gennadyevich Gelfenbeyn of Sunnyvale CA US for google llc, Artem Goncharuk of Mountain View CA US for google llc, Pavel SIROTIN of Sunnyvale CA US for google llc
IPC Code(s): G06N3/004, G06F9/54, G06F16/3329, G06N3/006, G06N20/00, G10L15/18, G10L15/22, G10L15/30
CPC Code(s): G06N3/004
Abstract: invoking an agent during a dialog between a user and an automated assistant. some implementations are directed to receiving, during a human-to-automated assistant dialog, natural language input of the user that indicates a desire to engage an agent, but that fails to indicate a particular agent to be engaged. those implementations are further directed to selecting a particular agent from a plurality of available agents, and transmitting an invocation request to the selected particular agent. in some implementations an agent selection model can be utilized in selecting the particular agent, such as a machine learning model. the machine learning model can be trained to enable generation of output that indicates, for each of a plurality of available agents (and optionally intent(s) for those agents), a probability that the available agent (and optionally intent) will generate appropriate responsive content.
20250148331. PERFORMING UNITARY ITERATION AND INDEXED OPERATIONS_simplified_abstract_(google llc)
Inventor(s): Craig Gidney of Goleta CA US for google llc, Ryan Babbush of Venice CA US for google llc
IPC Code(s): G06F16/22, G06N10/00
CPC Code(s): G06N10/20
Abstract: methods, systems and apparatus for performing indexed operations using a unary iteration quantum circuit. in one aspect, a method includes encoding an index value in an index register comprising index qubits; encoding the index value in a control register comprising multiple control qubits; and repeatedly computing and uncomputing the control qubits to perform, conditioned on the state of the control qubits, the operation on one or more target qubits corresponding to the index value, wherein during the encoding, computing and uncomputing: the multiple control qubits are made available in sequence, and the multiple control qubits correspond to a one-hot encoding of the encoded index value.
Inventor(s): Benjamin Villalonga Correa of Santa Monica CA US for google llc, Sergio Boixo Castrillo of Rancho Palos Verdes CA US for google llc, Michael Gabriel Newman of Palo Alto CA US for google llc
IPC Code(s): G06N10/70, G06N10/40
CPC Code(s): G06N10/70
Abstract: an enhanced matrix product state-based decoder is generated and employed to almost optimally detect and correct errors within a quantum computing and information processing system. the decoder takes as input a detector level error model that describes physical error channels and a set of error detections. this error model is improved using experimental data.
20250148357. FLEXIBLE MACHINE LEARNING MODEL COMPRESSION_simplified_abstract_(google llc)
Inventor(s): Aditya Binodkumar Agrawal of Santa Clara CA US for google llc, Blake Alan Hechtman of Mountain View CA US for google llc, Matthew Leever Hedlund of Sun Prairie WI US for google llc, David Alexander Majnemer of Mountain View CA US for google llc, Marissa Karen Ikonomidis of Sunnyvale CA US for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compresses a machine learning model having a plurality of parameters. in one aspect, one of the methods includes obtaining trained values of a set of parameters for at least a portion of a machine learning model; identifying one or more dense ranges for the trained values; determining a least number of bits required to represent each trained value within the one or more dense ranges; identifying a second format having a range that is smaller than a range of the first format; and generating a compressed version of the at least a portion of the machine learning model.
Inventor(s): Joshua Brian Braverman of Oakland CA US for google llc, Camille Wormser of New York NY US for google llc, CĂŠsar Augusto Naranjo of San Diego CA US for google llc, Alexey Vaysburd of New York NY US for google llc, Dorothea Wiesmann Rothuizen of Oberrieden CH for google llc, Brian Michael Burdick of Newcastle WA US for google llc, Jason Sean Krueger of Seattle WA US for google llc, Xiaoxuan Zhang of Jersey City NJ US for google llc, Sergiu Ion Goschin of New York NY US for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enabling artificial intelligence to display responses in a conversational user interface that are tailored to a user of the interface, to predicted future states, and/or to predicted trajectories that include transitions between multiple states. in one aspect, a method includes initiating a user session with a conversational user interface of an artificial intelligence system that displays, within the conversational user interface, responses to user interactions received during the user session, the responses being generated using one or more machine learning models of the artificial intelligence system. during the user session, the system receives data indicating one or more user interactions within the conversational user interface by a user. the system updates a state record that represents a first state. the system processes the state record to determine potential trajectories for the user session.
Inventor(s): Dirk Ryan Padfield of Seattle WA US for google llc, Matthew Sharifi of Kilchberg CH for google llc
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: provided are systems and methods for continuous training of machine learning (ml) models on changing data. in particular, the present disclosure provides example approaches to model training that take advantage of constantly evolving data that may be available in various ancillary systems that contain large amounts of data, but which are not specific to or dedicated for model training.
Inventor(s): Amy Wu of Sunnyvale CA US for google llc, Brandon Murdock Pearcy of San Francisco CA US for google llc, Nathan Peter Lucash of Mountain View CA US for google llc, Jun Xu of Shanghai CN for google llc, Yi Zhang of Sunnyvale CA US for google llc, Zhen Yu of Shanghai CN for google llc
IPC Code(s): G06Q30/0241, G06F3/0482, G06F3/04842, G06F40/103, G06T3/40
CPC Code(s): G06Q30/0277
Abstract: one or more computer-readable media store instructions that cause one or more processors to transmit a request for content, receive a first content item and a second content item associated with the first content item, and display the first content item within a content slot in an information resource. the content slot has a first size occupying a first region of the information resource. the operations further include identifying a user interaction associated with the first content item and, responsive to the user interaction, expanding the content slot from the first size to a second size and displaying, in the expanded content slot, the first content item, the second content item, and an actionable object configured to reduce the content slot from the second size to the first size. the second size occupies the first region and an adjoining second region of the information resource.
Inventor(s): Keunhong Park of San Francisco CA US for google llc, Ricardo Martin-Brualla of Seattle WA US for google llc, Jonathan Tilton Barron of Alameda CA US for google llc, Philipp Henzler of San Francisco CA US for google llc, Benjamin Joseph Mildenhall of London GB for google llc
IPC Code(s): G06T3/00, G06T7/00
CPC Code(s): G06T3/06
Abstract: systems and methods for training a machine-learned model are disclosed herein. the method can include obtaining, by a processor, a plurality of images, each image having a set of parameter values comprising values for a plurality of camera parameters and determining a covariance matrix for the plurality of camera parameters with respect to a plurality of projected points generated via evaluation of a projection function. the method can also include performing a whitening algorithm to identify a preconditioning matrix that, when applied to the sets of parameter values, results in the covariance matrix being approximately equal to an identity matrix and performing an optimization algorithm on the plurality of sets of parameter values, performing the optimization algorithm can include applying an inverse of the preconditioning matrix to the plurality of sets of parameters in a forward prediction pass and applying the preconditioning matrix in a backward gradient pass.
20250148713. SELECTING BLOCKS TO REPRESENT SCENE_simplified_abstract_(google llc)
Inventor(s): Kathryn Heal of Los Angeles CA US for google llc, John Patrick Flynn of Los Angeles CA US for google llc, Ryan Styles Overbeck of Mountain View CA US for google llc, Michael Joseph Broxton of Los Gatos CA US for google llc, Stephen Anthony Lombardi of Seattle WA US for google llc, ClĂŠment Louis Jean-Claude Godard of San Francisco CA US for google llc
IPC Code(s): G06T17/20, G06T15/08
CPC Code(s): G06T17/20
Abstract: a non-transitory computer-readable storage medium comprises instructions stored thereon. when executed by at least one processor, the instructions are configured to cause a computing system to at least generate multiple mesh cells based on multiple mesh layers, the multiple mesh layers representing a volumetric scene, the multiple mesh cells including multiple mesh blocks; select, from the multiple mesh blocks, k selected blocks based on densities of the multiple mesh blocks, k being a predetermined number; and store the selected blocks and identifiers of locations of the selected blocks.
20250148759. OPEN-VOCABULARY OBJECT DETECTION IN IMAGES_simplified_abstract_(google llc)
Inventor(s): Matthias Johannes Lorenz Minderer of ZĂźrich CH for google llc, Alexey Alexeevich Gritsenko of Amsterdam NL for google llc, Austin Charles Stone of San Francisco CA US for google llc, Dirk Weissenborn of Berlin DE for google llc, Alexey Dosovitskiy of Berlin DE for google llc, Neil Matthew Tinmouth Houlsby of ZĂźrich CH for google llc
IPC Code(s): G06V10/764, G06F40/40, G06V10/22, G06V10/74, G06V10/774, G06V10/776, G06V10/82
CPC Code(s): G06V10/764
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection. in one aspect, a method comprises: obtaining: (i) an image, and (ii) a set of one or more query embeddings, wherein each query embedding represents a respective category of object; processing the image and the set of query embeddings using an object detection neural network to generate object detection data for the image, comprising: processing the image using an image encoding subnetwork of the object detection neural network to generate a set of object embeddings; processing each object embedding using a localization subnetwork to generate localization data defining a corresponding region of the image; and processing: (i) the set of object embeddings, and (ii) the set of query embeddings, using a classification subnetwork to generate, for each object embedding, a respective classification score distribution over the set of query embeddings.
Inventor(s): Jessica Lee of Brooklyn NY US for google llc, Christopher James Kelley of Orinda CA US for google llc, Alok Aggarwal of Foster City CA US for google llc, Harshit Kharbanda of Pleasanton CA US for google llc
IPC Code(s): G06V20/20, G06F16/9535, G06T11/00, G06V10/94
CPC Code(s): G06V20/20
Abstract: systems and methods for providing scene understanding can include obtaining a plurality of images, stitching images associated with the scene, detecting objects in the scene, and providing information associated with the objects in the scene. the systems and methods can include determining filter tags or query tags that can be selected to filter the plurality of objects, which can then be provided as information to the user to provide further insight on the scene. the information may be provided in an augmented-reality experience via text or other user-interface elements anchored to objects in the images.
20250149022. Text-Conditioned Speech Inpainting_simplified_abstract_(google llc)
Inventor(s): ZalĂĄn Borsos of Zurich CH for google llc, Marco Tagliasacchi of Kilchberg CH for google llc, Matthew Sharifi of Kilchberg CH for google llc
IPC Code(s): G10L13/08, G10L25/30
CPC Code(s): G10L13/08
Abstract: provided are systems, methods, and machine learning models for filling in gaps (e.g., of up to one second) in speech samples by leveraging an auxiliary textual input. example machine learning models described herein can perform speech inpainting with the appropriate content, while maintaining speaker identity, prosody and recording environment conditions, and generalizing to unseen speakers. this approach significantly outperforms baselines constructed using adaptive tts, as judged by human raters in side-by-side preference and mos tests.
Inventor(s): Lun Wang of Fremont CA US for google llc, Om Dipakbhai Thakkar of Sunnyvale CA US for google llc, Rajiv Mathews of Sunnyvale CA US for google llc
IPC Code(s): G10L15/065, G10L13/02
CPC Code(s): G10L15/065
Abstract: a method includes obtaining an automatic speech recognition (asr) model pre-trained on an initial training dataset, creating a set of canary speech utterances, and speeding up each canary speech utterance in the set of canary speech utterances. the operations also include fine-tuning the asr model on the set of sped-up canary speech utterances and measuring un-intended memorization of the fine-tuned asr model based on speech recognition results performed by the fine-tuned asr model on the sped-up canary speech utterances.
Inventor(s): Felix Weissenberger of Zurich CH for google llc, Alexander Froemmgen of Zurch CH for google llc, Bogdan Prisacari of Adliswil CH for google llc
IPC Code(s): G10L15/22, G10L13/08, G10L15/183
CPC Code(s): G10L15/22
Abstract: implementations described herein relate to causing certain reasoning with respect to why an automated assistant performed (or did not perform) certain fulfillment and/or alternate fulfillment of an assistant command. for example, implementations can receive user input that includes the assistant command, process the user input to determine data to be utilized in performance of the certain fulfillment or the alternate fulfillment of the assistant command, and cause the automated assistant to utilize the data to perform the certain fulfillment or the alternate fulfillment of the assistant command. in some implementations, output that includes the certain reasoning can be provided for presentation to a user in response to additional user input that requests the certain reasoning. in some implementations, a selectable element can be visually rendered and, when selected by the user, the output that includes the certain reasoning can be provided for presentation to the user.
Inventor(s): Efthymios Tzinis of Urbana IL US for google llc, Scott Wisdom of Boston MA US for google llc, Aren Jansen of Mountain View CA US for google llc, John R. Hershey of Winchester MA US for google llc
IPC Code(s): G10L25/57, G06F18/214, G06N3/088, G06V20/40, G10L25/30
CPC Code(s): G10L25/57
Abstract: apparatus and methods related to separation of audio sources are provided. the method includes receiving an audio waveform associated with a plurality of video frames. the method includes estimating, by a neural network, one or more audio sources associated with the plurality of video frames. the method includes generating, by the neural network, one or more audio embeddings corresponding to the one or more estimated audio sources. the method includes determining, based on the audio embeddings and a video embedding, whether one or more audio sources of the one or more estimated audio sources correspond to objects in the plurality of video frames. the method includes predicting, by the neural network and based on the one or more audio embeddings and the video embedding, a version of the audio waveform comprising audio sources that correspond to objects in the plurality of video frames.
Inventor(s): Jim Huibrecht Winkens of London GB for google llc, Alan Prasana Karthikesalingam of London GB for google llc, Krishnamurthy Dvijotham of Sunnyvale CA US for google llc, Ali Taylan Cemgil of London GB for google llc, Sumedh Kedar Ghaisas of London GB for google llc
IPC Code(s): G16H50/20, G06V10/764, G16H30/20
CPC Code(s): G16H50/20
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data points using a deferral model that determines whether to classify the data point using an output of one or more diagnostic machine learning models or to defer the data point for classification by one or more users.
20250150096. Secure Multi-Rail Control for Sparsely Encoded Signals_simplified_abstract_(google llc)
Inventor(s): Pirmin Robert Vogel of Zurich CH for google llc, Christopher Gori of San Francisco CA US for google llc
IPC Code(s): H03M13/19, H03M13/15
CPC Code(s): H03M13/19
Abstract: this document discloses techniques, apparatuses, and systems for secure multi-rail control for sparsely encoded signals. integrated circuits (ics) may transmit various signals to manage interactions between circuit components of the ic. these critical signals are common targets for malicious attacks because, when altered, they can cause the ic to perform differently than is intended, and in some cases, bypass security measures. while various strategies may be used to protect against these attacks, modern circuit synthesis tools may optimize away these security measures, leaving the ic vulnerable to manipulation. in contrast, the secure multi-rail control for sparsely encoded signals described herein utilizes multiple rails to transmit sparsely encoded critical signals. each rail may be controlled by a separate finite state machine (fsm) to reduce vulnerabilities that may arise due to circuit synthesis, provide an adjustable solution that may be leveraged differently based on implementation, and provide comportability to different ics.
20250150260. MULTI-KEY INFORMATION RETRIEVAL_simplified_abstract_(google llc)
Inventor(s): Eli Simon Fox-Epstein of Los Angeles CA US for google llc, Craig William Wright of Louisville CO US for google llc, Kevin Wei Li Yeo of New York NY US for google llc, Mariana Raykova of New York NY US for google llc, Karn Seth of New York NY US for google llc
IPC Code(s): H04L9/08
CPC Code(s): H04L9/0825
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium for retrieving information from a server. methods can include a server receiving a set of client-encrypted queries. the server identifies a set of server-encrypted decryption keys and transmits the set to the client device. the server receives a set of client-server-encrypted decryption keys that includes the set of server-encrypted decryption keys encrypted by the client device. the server also receives a set of client-encrypted/client-derived decryption keys that were derived by the client device. the server generates matching a map that specifies matches between the set of client-server-encrypted decryption keys and the set of client-encrypted/client-derived decryption keys. the server filters the set of client-encrypted queries using the map to create a set of filtered client-encrypted queries and generates a set of query results.
Inventor(s): Olivier Siohan of New York NY US for google llc, Takaki Makino of Ridgewood NJ US for google llc, Joshua Maynez of London GB for google llc, Ryan Mcdonald of London GB for google llc, Benyah Shaparenko of Rego Park NY US for google llc, Joseph Nelson of Chapel Hill NC US for google llc, Kishan Sachdeva of San Bruno CA US for google llc, Basilio Garcia of Secaucus NJ US for google llc
IPC Code(s): H04L12/18, G06F40/279, G10L15/18
CPC Code(s): H04L12/1818
Abstract: implementations relate to an application that can bias automatic speech recognition for meetings using data that may be associated with the meeting and/or meeting participants. a transcription of inputs provided during a meeting can additionally and/or alternatively be processed to determine whether the inputs should be incorporated into a meeting document, which can provide a summary for the meeting. in some instances, entries into a meeting document can be designated as action items, and those action items can optionally have conditions for reminding meeting participants about the action items and/or for determining whether an action item has been fulfilled. in this way, various tasks that may typically be manually performed by meeting participants, such as creating a meeting summary, can be automated in a more accurate manner. this can preserve resources that may otherwise be wasted during video conferences, in-person meetings, and/or other gatherings.
Inventor(s): Scott Eric Coull of Cary NC US for google llc, Jeffrey Thomas Johns of Leesburg VA US for google llc
IPC Code(s): H04L9/40, H04L41/16, H04L41/22
CPC Code(s): H04L63/1425
Abstract: a cyber-security analysis method uses machine learning (ml) technology to classify cyber-threat indicators, for example, as malicious or benign, by generating a threat score. the method includes receiving, at a compute device, a cyber-threat indicator (iue) and associated verdicts from a set of sources. augmenting the verdicts associated with the iue with verdicts associated with at least one related indicator having a defined relationship with the iue. the relationship between the iue and the at least one related indicator can be operational, e g., based on an administrative domain, or functional, e.g., based on a protocol specification. the cyber-threat score is generated for the iue based on the ml model and the combined verdicts of the iue and the at least one related indicator.
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.
Inventor(s): Bohan Li of Santa Clara CA US for google llc, Yaowu Xu of Saratoga CA US for google llc, Jingning Han of Santa Clara CA US for google llc
IPC Code(s): H04N19/105, H04N19/137, H04N19/172, H04N19/176
CPC Code(s): H04N19/105
Abstract: a motion vector for a current block of a current frame is decoded. the motion vector for the current block refers to a first reference block in a first reference frame. a first prediction block of two or more prediction blocks is identified in the first reference frame and using the first reference block. a first grid-aligned block is identified based on the first reference block. a second reference block is identified using a motion vector of the first grid-aligned block in a second reference frame. a second prediction block of the two or more prediction blocks is identified in the second reference frame and using the second reference block. the two or more prediction blocks are combined to obtain a prediction block for the current block.
Inventor(s): Jingning Han of Santa Clara CA US for google llc, Yaowu Xu of Saratoga CA US for google llc, Joseph Young of Mountain View CA US for google llc, In Suk Chong of Mountain View CA US for google llc, Debargha Mukherjee of Cupertino CA US for google llc
IPC Code(s): H04N19/91, H04N19/18, H04N19/70
CPC Code(s): H04N19/91
Abstract: entropy coding a sequence of syntax elements is described where an observation for a syntax element of the sequence is determined, and the observation is arithmetic coded using the probability model. thereafter, the probability model is updated using a time-variant update rate to produce an updated probability model. updating the probability model includes regularizing one or more probability values of the probability model so no probability of the updated probability model is below a defined minimum resolution. as a result, the use of a minimum probability value during the arithmetic coding, which can distort probability model, may be omitted.
20250150779. LOCATION-AWARE ASSISTANT_simplified_abstract_(google llc)
Inventor(s): Dongeek Shin of San Jose CA US for google llc
IPC Code(s): H04W4/021, G06F40/40
CPC Code(s): H04W4/021
Abstract: methods, systems, apparatus, including computer programs encoded on a computer storage medium, for spatialized audio feedback from automated assistants. in one aspect, the method includes actions of determining that a user input has been received at a client device, identifying, based on sensor data, one or more points of interest of an environment in which the client device is located and an orientation of a user of the client device relative to the one or more points of interest, identifying, based on processing the user input and the sensor data, a natural language response providing information relevant corresponds to a particular point of interest, determining, based on the orientation of the user of the client device relative to the particular point of interest, one or more spatial audio parameters to be used to provision the natural language response to the user, and causing the natural language response to be audibly rendered at the client device using one or more of the spatial audio parameters.
20250151481. SHAPE-ADAPTIVE DISPLAY ASSEMBLY_simplified_abstract_(google llc)
Inventor(s): JĂźrgen Burggraf of Schaerding AT for google llc
IPC Code(s): H01L33/54, G04G9/10, H01L25/075, H01L33/00, H01L33/62
CPC Code(s): H10H20/853
Abstract: shape-adaptive display assemblies are described herein, along with methods for their fabrication. one example method for fabricating a display assembly with a rigid segment and a flexible segment includes: depositing a pattern of conductive material onto a first substrate; coupling an integrated circuit to a first side of the pattern of conductive material, the integrated circuit disposed on the rigid segment without extending to the flexible segment; depositing a molding layer onto the first side of the pattern of conductive material, the molding layer configured to encapsulate the integrated circuit and to extend over the rigid segment and the flexible segment; bonding a second substrate to the molding layer and removing the first substrate to expose a second side of the pattern of conductive material; and coupling a plurality of pixel emitters to the second side of the pattern of conductive material and removing the second substrate.
- GOOGLE LLC
- A63F13/358
- A63F13/323
- A63F13/335
- A63F13/40
- G06F9/455
- CPC A63F13/358
- Google llc
- B25J9/16
- CPC B25J9/1658
- G01L1/14
- G01L5/22
- CPC G01L1/14
- G02B6/44
- CPC G02B6/4452
- G02B27/01
- G02B6/34
- CPC G02B27/0172
- G02B27/00
- G02C11/00
- G08B21/18
- H01Q1/24
- H01Q1/27
- G02B27/28
- H04N9/31
- CPC G02B27/283
- G02C5/00
- CPC G02C5/008
- G06F1/20
- H05K7/20
- CPC G06F1/203
- G06F3/04886
- G06F3/0482
- G06Q30/0241
- G06T13/80
- CPC G06F3/04886
- G06F3/16
- G06F3/0488
- G06F18/214
- G06F18/22
- G06N20/00
- G10L15/22
- CPC G06F3/167
- G06F9/451
- G06F16/901
- CPC G06F9/451
- CPC G06F9/45558
- G06F9/50
- CPC G06F9/5072
- G06F16/28
- G06Q30/00
- G06Q30/02
- G06Q50/00
- CPC G06F16/285
- CPC G06F16/9024
- G06F16/951
- G06F16/9538
- CPC G06F16/951
- G06F16/80
- G06F16/9535
- CPC G06F16/9538
- G06F17/11
- CPC G06F17/11
- G06F21/62
- G06F21/57
- CPC G06F21/6245
- G06F40/20
- H04L51/21
- H04N21/4788
- CPC G06F40/20
- G06F40/40
- G06F40/166
- CPC G06F40/40
- G06F40/58
- G06F40/197
- G06F40/253
- G06F40/56
- G06N3/045
- G06N3/047
- G06N3/08
- G06N3/084
- CPC G06F40/58
- G06N3/004
- G06F9/54
- G06F16/3329
- G06N3/006
- G10L15/18
- G10L15/30
- CPC G06N3/004
- G06F16/22
- G06N10/00
- CPC G06N10/20
- G06N10/70
- G06N10/40
- CPC G06N10/70
- CPC G06N20/00
- G06F3/04842
- G06F40/103
- G06T3/40
- CPC G06Q30/0277
- G06T3/00
- G06T7/00
- CPC G06T3/06
- G06T17/20
- G06T15/08
- CPC G06T17/20
- G06V10/764
- G06V10/22
- G06V10/74
- G06V10/774
- G06V10/776
- G06V10/82
- CPC G06V10/764
- G06V20/20
- G06T11/00
- G06V10/94
- CPC G06V20/20
- G10L13/08
- G10L25/30
- CPC G10L13/08
- G10L15/065
- G10L13/02
- CPC G10L15/065
- G10L15/183
- CPC G10L15/22
- G10L25/57
- G06N3/088
- G06V20/40
- CPC G10L25/57
- G16H50/20
- G16H30/20
- CPC G16H50/20
- H03M13/19
- H03M13/15
- CPC H03M13/19
- H04L9/08
- CPC H04L9/0825
- H04L12/18
- G06F40/279
- CPC H04L12/1818
- H04L9/40
- H04L41/16
- H04L41/22
- CPC H04L63/1425
- H04M3/493
- G06F40/35
- H04M3/527
- CPC H04M3/4936
- H04N19/105
- H04N19/137
- H04N19/172
- H04N19/176
- CPC H04N19/105
- H04N19/91
- H04N19/18
- H04N19/70
- CPC H04N19/91
- H04W4/021
- CPC H04W4/021
- H01L33/54
- G04G9/10
- H01L25/075
- H01L33/00
- H01L33/62
- CPC H10H20/853
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide
